diff --git "a/profile_trace/iteration_188416/rank0_trace.json" "b/profile_trace/iteration_188416/rank0_trace.json" new file mode 100644--- /dev/null +++ "b/profile_trace/iteration_188416/rank0_trace.json" @@ -0,0 +1,83427 @@ + +{ + "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": 0, "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": "3CB54859EDCD42BCAD985D1AFDBE8885", + "traceEvents": [ + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941917345.383, "dur": 146.273, + "args": { + "External id": 4551681,"Record function id": 0, "Sequence number": 45295814, "Fwd thread id": 1, "Ev Idx": 0 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941917365.013, "dur": 114.544, + "args": { + "External id": 4551682,"Sequence number": 45295814, "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": 1336753, "tid": 1381210, "ts": 1696941917365.013, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336753, "tid": 1381210, + "ts": 1696941917374.649, "dur": 102.042, + "args": { + "External id": 4551683,"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": 1336753, "tid": 1381210, + "ts": 1696941917506.312, "dur": 303.611, + "args": { + "External id": 4551684,"Record function id": 0, "Ev Idx": 3 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941917611.314, "dur": 110.537, + "args": { + "External id": 4551685,"Record function id": 0, "Ev Idx": 4 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.27", "pid": 1336753, "tid": 1381210, + "ts": 1696941917650.411, "dur": 59.153, + "args": { + "External id": 4551686,"Record function id": 0, "Ev Idx": 5 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941917727.397, "dur": 2.152, + "args": { + "External id": 4551687,"Sequence number": 45295813, "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": 1336753, "tid": 1381210, "ts": 1696941917727.397, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1696941917735.710, "dur": 67.526, + "args": { + "External id": 4551688,"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": 1336753, "tid": 1381210, + "ts": 1696941917746.704, "dur": 55.943, + "args": { + "External id": 4551689,"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": 1336753, "tid": 1381210, + "ts": 1696941917759.291, "dur": 3.980, + "args": { + "External id": 4551690,"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": 1336753, "tid": 1381210, + "ts": 1696941917821.780, "dur": 36364.263, + "args": { + "External id": 4551691,"Record function id": 0, "Sequence number": 45295811, "Fwd thread id": 1, "Ev Idx": 10 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941917823.448, "dur": 36348.509, + "args": { + "External id": 4551692,"Sequence number": 45295811, "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": 1336753, "tid": 1381210, "ts": 1696941917823.448, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696941917879.519, "dur": 4.260, + "args": { + "External id": 4551693,"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": 1336753, "tid": 1381210, + "ts": 1696941917887.212, "dur": 36162.774, + "args": { + "External id": 4551694,"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": 1336753, "tid": 1381210, + "ts": 1696941917891.981, "dur": 36157.589, + "args": { + "External id": 4551695,"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": 1336753, "tid": 1381210, + "ts": 1696941917897.676, "dur": 9.389, + "args": { + "External id": 4551696,"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": 1336753, "tid": 1381210, + "ts": 1696941917909.740, "dur": 36138.393, + "args": { + "External id": 4551697,"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": 1336753, "tid": 1381210, + "ts": 1696941954054.924, "dur": 0.559, + "args": { + "External id": 4551698,"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": 1336753, "tid": 1381210, + "ts": 1696941954057.997, "dur": 3.334, + "args": { + "External id": 4551699,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 18 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 1336753, "tid": 1381210, + "ts": 1696941954059.847, "dur": 1.322, + "args": { + "External id": 4551700,"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": 1336753, "tid": 1381210, + "ts": 1696941954068.287, "dur": 32.200, + "args": { + "External id": 4551701,"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": 1336753, "tid": 1381210, + "ts": 1696941954109.551, "dur": 52.571, + "args": { + "External id": 4551702,"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": 1336753, "tid": 1381210, + "ts": 1696941954111.727, "dur": 50.192, + "args": { + "External id": 4551703,"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": 1336753, "tid": 1381210, + "ts": 1696941954114.010, "dur": 47.435, + "args": { + "External id": 4551704,"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": 1336753, "tid": 1381210, + "ts": 1696941954196.444, "dur": 22.124, + "args": { + "External id": 4551705,"Record function id": 0, "Sequence number": 45295810, "Fwd thread id": 1, "Ev Idx": 24 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941954198.148, "dur": 16.595, + "args": { + "External id": 4551706,"Sequence number": 45295810, "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": 1336753, "tid": 1381210, "ts": 1696941954198.148, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941954202.837, "dur": 11.651, + "args": { + "External id": 4551707,"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": 1336753, "tid": 1381210, + "ts": 1696941954207.361, "dur": 6.923, + "args": { + "External id": 4551708,"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": 1336753, "tid": 1381210, + "ts": 1696941954224.660, "dur": 112.875, + "args": { + "External id": 4551709,"Record function id": 0, "Sequence number": 45295809, "Fwd thread id": 1, "Ev Idx": 28 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941954225.792, "dur": 100.164, + "args": { + "External id": 4551710,"Sequence number": 45295809, "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": 1336753, "tid": 1381210, "ts": 1696941954225.792, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941954229.900, "dur": 95.594, + "args": { + "External id": 4551711,"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": 1336753, "tid": 1381210, + "ts": 1696941954236.388, "dur": 40.430, + "args": { + "External id": 4551712,"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": 1336753, "tid": 1381210, + "ts": 1696941954241.187, "dur": 5.960, + "args": { + "External id": 4551713,"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": 1336753, "tid": 1381210, + "ts": 1696941954249.783, "dur": 26.728, + "args": { + "External id": 4551714,"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": 1336753, "tid": 1381210, + "ts": 1696941954256.033, "dur": 19.998, + "args": { + "External id": 4551715,"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": 1336753, "tid": 1381210, + "ts": 1696941954280.082, "dur": 4.583, + "args": { + "External id": 4551716,"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": 1336753, "tid": 1381210, + "ts": 1696941954282.715, "dur": 1.641, + "args": { + "External id": 4551717,"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": 1336753, "tid": 1381210, + "ts": 1696941954285.738, "dur": 38.916, + "args": { + "External id": 4551718,"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": 1336753, "tid": 1381210, + "ts": 1696941954341.780, "dur": 67.440, + "args": { + "External id": 4551719,"Record function id": 0, "Sequence number": 45295808, "Fwd thread id": 1, "Ev Idx": 38 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941954342.847, "dur": 62.458, + "args": { + "External id": 4551720,"Sequence number": 45295808, "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": 1336753, "tid": 1381210, "ts": 1696941954342.847, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941954346.205, "dur": 58.854, + "args": { + "External id": 4551721,"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": 1336753, "tid": 1381210, + "ts": 1696941954352.079, "dur": 20.780, + "args": { + "External id": 4551722,"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": 1336753, "tid": 1381210, + "ts": 1696941954353.574, "dur": 3.506, + "args": { + "External id": 4551723,"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": 1336753, "tid": 1381210, + "ts": 1696941954357.809, "dur": 14.764, + "args": { + "External id": 4551724,"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": 1336753, "tid": 1381210, + "ts": 1696941954360.831, "dur": 11.409, + "args": { + "External id": 4551725,"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": 1336753, "tid": 1381210, + "ts": 1696941954376.799, "dur": 6.540, + "args": { + "External id": 4551726,"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": 1336753, "tid": 1381210, + "ts": 1696941954381.272, "dur": 1.207, + "args": { + "External id": 4551727,"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": 1336753, "tid": 1381210, + "ts": 1696941954384.493, "dur": 20.059, + "args": { + "External id": 4551728,"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": 1336753, "tid": 1381210, + "ts": 1696941954413.104, "dur": 136.486, + "args": { + "External id": 4551729,"Record function id": 0, "Sequence number": 45295807, "Fwd thread id": 1, "Ev Idx": 48 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941954414.398, "dur": 129.274, + "args": { + "External id": 4551730,"Sequence number": 45295807, "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": 1336753, "tid": 1381210, "ts": 1696941954414.398, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941954418.657, "dur": 124.568, + "args": { + "External id": 4551731,"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": 1336753, "tid": 1381210, + "ts": 1696941954422.569, "dur": 15.881, + "args": { + "External id": 4551732,"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": 1336753, "tid": 1381210, + "ts": 1696941954423.095, "dur": 3.016, + "args": { + "External id": 4551733,"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": 1336753, "tid": 1381210, + "ts": 1696941954427.077, "dur": 11.126, + "args": { + "External id": 4551734,"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": 1336753, "tid": 1381210, + "ts": 1696941954428.099, "dur": 9.728, + "args": { + "External id": 4551735,"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": 1336753, "tid": 1381210, + "ts": 1696941954441.702, "dur": 2.204, + "args": { + "External id": 4551736,"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": 1336753, "tid": 1381210, + "ts": 1696941954443.150, "dur": 0.600, + "args": { + "External id": 4551737,"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": 1336753, "tid": 1381210, + "ts": 1696941954444.472, "dur": 97.558, + "args": { + "External id": 4551738,"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": 1336753, "tid": 1381210, + "ts": 1696941954556.094, "dur": 101.604, + "args": { + "External id": 4551739,"Record function id": 0, "Sequence number": 45295806, "Fwd thread id": 1, "Ev Idx": 58 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941954557.177, "dur": 96.852, + "args": { + "External id": 4551740,"Sequence number": 45295806, "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": 1336753, "tid": 1381210, "ts": 1696941954557.177, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941954559.253, "dur": 94.320, + "args": { + "External id": 4551741,"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": 1336753, "tid": 1381210, + "ts": 1696941954563.134, "dur": 19.655, + "args": { + "External id": 4551742,"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": 1336753, "tid": 1381210, + "ts": 1696941954564.126, "dur": 4.677, + "args": { + "External id": 4551743,"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": 1336753, "tid": 1381210, + "ts": 1696941954569.399, "dur": 13.146, + "args": { + "External id": 4551744,"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": 1336753, "tid": 1381210, + "ts": 1696941954570.166, "dur": 11.997, + "args": { + "External id": 4551745,"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": 1336753, "tid": 1381210, + "ts": 1696941954585.931, "dur": 4.406, + "args": { + "External id": 4551746,"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": 1336753, "tid": 1381210, + "ts": 1696941954589.241, "dur": 0.917, + "args": { + "External id": 4551747,"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": 1336753, "tid": 1381210, + "ts": 1696941954591.322, "dur": 61.710, + "args": { + "External id": 4551748,"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": 1336753, "tid": 1381210, + "ts": 1696941954661.956, "dur": 39.211, + "args": { + "External id": 4551749,"Record function id": 0, "Sequence number": 45295805, "Fwd thread id": 1, "Ev Idx": 68 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941954663.343, "dur": 1.557, + "args": { + "External id": 4551750,"Sequence number": 45295805, "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": 1336753, "tid": 1381210, "ts": 1696941954663.343, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1696941954667.799, "dur": 29.837, + "args": { + "External id": 4551751,"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": 1336753, "tid": 1381210, + "ts": 1696941954669.846, "dur": 27.319, + "args": { + "External id": 4551752,"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": 1336753, "tid": 1381210, + "ts": 1696941954679.233, "dur": 0.525, + "args": { + "External id": 4551753,"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": 1336753, "tid": 1381210, + "ts": 1696941954706.096, "dur": 2253.749, + "args": { + "External id": 4551754,"Record function id": 0, "Sequence number": 45295803, "Fwd thread id": 1, "Ev Idx": 73 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941954707.705, "dur": 2212.131, + "args": { + "External id": 4551755,"Sequence number": 45295803, "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": 1336753, "tid": 1381210, "ts": 1696941954707.705, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696941954748.588, "dur": 2.910, + "args": { + "External id": 4551756,"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": 1336753, "tid": 1381210, + "ts": 1696941954753.871, "dur": 2076.348, + "args": { + "External id": 4551757,"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": 1336753, "tid": 1381210, + "ts": 1696941954756.198, "dur": 2073.706, + "args": { + "External id": 4551758,"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": 1336753, "tid": 1381210, + "ts": 1696941954759.384, "dur": 4.057, + "args": { + "External id": 4551759,"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": 1336753, "tid": 1381210, + "ts": 1696941954766.386, "dur": 2062.313, + "args": { + "External id": 4551760,"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": 1336753, "tid": 1381210, + "ts": 1696941956833.248, "dur": 0.316, + "args": { + "External id": 4551761,"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": 1336753, "tid": 1381210, + "ts": 1696941956835.041, "dur": 2.483, + "args": { + "External id": 4551762,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 81 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 1336753, "tid": 1381210, + "ts": 1696941956836.516, "dur": 0.893, + "args": { + "External id": 4551763,"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": 1336753, "tid": 1381210, + "ts": 1696941956841.626, "dur": 22.009, + "args": { + "External id": 4551764,"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": 1336753, "tid": 1381210, + "ts": 1696941956869.259, "dur": 42.492, + "args": { + "External id": 4551765,"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": 1336753, "tid": 1381210, + "ts": 1696941956870.578, "dur": 40.974, + "args": { + "External id": 4551766,"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": 1336753, "tid": 1381210, + "ts": 1696941956871.877, "dur": 39.275, + "args": { + "External id": 4551767,"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": 1336753, "tid": 1381210, + "ts": 1696941956932.527, "dur": 22.555, + "args": { + "External id": 4551768,"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": 1336753, "tid": 1381210, + "ts": 1696941956968.191, "dur": 44.244, + "args": { + "External id": 4551769,"Record function id": 0, "Sequence number": 45295802, "Fwd thread id": 1, "Ev Idx": 88 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941956971.665, "dur": 35.491, + "args": { + "External id": 4551770,"Sequence number": 45295802, "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": 1336753, "tid": 1381210, "ts": 1696941956971.665, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941956975.860, "dur": 31.058, + "args": { + "External id": 4551771,"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": 1336753, "tid": 1381210, + "ts": 1696941956977.111, "dur": 29.196, + "args": { + "External id": 4551772,"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": 1336753, "tid": 1381210, + "ts": 1696941957017.878, "dur": 79.673, + "args": { + "External id": 4551773,"Record function id": 0, "Sequence number": 45295801, "Fwd thread id": 1, "Ev Idx": 92 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941957019.313, "dur": 71.533, + "args": { + "External id": 4551774,"Sequence number": 45295801, "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": 1336753, "tid": 1381210, "ts": 1696941957019.313, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941957022.079, "dur": 68.390, + "args": { + "External id": 4551775,"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": 1336753, "tid": 1381210, + "ts": 1696941957027.242, "dur": 22.665, + "args": { + "External id": 4551776,"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": 1336753, "tid": 1381210, + "ts": 1696941957028.900, "dur": 3.542, + "args": { + "External id": 4551777,"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": 1336753, "tid": 1381210, + "ts": 1696941957033.141, "dur": 16.500, + "args": { + "External id": 4551778,"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": 1336753, "tid": 1381210, + "ts": 1696941957034.561, "dur": 14.682, + "args": { + "External id": 4551779,"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": 1336753, "tid": 1381210, + "ts": 1696941957051.402, "dur": 5.318, + "args": { + "External id": 4551780,"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": 1336753, "tid": 1381210, + "ts": 1696941957053.160, "dur": 3.160, + "args": { + "External id": 4551781,"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": 1336753, "tid": 1381210, + "ts": 1696941957059.671, "dur": 30.072, + "args": { + "External id": 4551782,"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": 1336753, "tid": 1381210, + "ts": 1696941957101.568, "dur": 53.147, + "args": { + "External id": 4551783,"Record function id": 0, "Sequence number": 45295800, "Fwd thread id": 1, "Ev Idx": 102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941957102.779, "dur": 48.278, + "args": { + "External id": 4551784,"Sequence number": 45295800, "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": 1336753, "tid": 1381210, "ts": 1696941957102.779, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941957106.494, "dur": 44.346, + "args": { + "External id": 4551785,"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": 1336753, "tid": 1381210, + "ts": 1696941957108.223, "dur": 17.067, + "args": { + "External id": 4551786,"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": 1336753, "tid": 1381210, + "ts": 1696941957109.044, "dur": 1.968, + "args": { + "External id": 4551787,"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": 1336753, "tid": 1381210, + "ts": 1696941957111.498, "dur": 13.534, + "args": { + "External id": 4551788,"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": 1336753, "tid": 1381210, + "ts": 1696941957112.191, "dur": 12.435, + "args": { + "External id": 4551789,"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": 1336753, "tid": 1381210, + "ts": 1696941957126.523, "dur": 9.325, + "args": { + "External id": 4551790,"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": 1336753, "tid": 1381210, + "ts": 1696941957134.163, "dur": 1.079, + "args": { + "External id": 4551791,"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": 1336753, "tid": 1381210, + "ts": 1696941957136.651, "dur": 13.730, + "args": { + "External id": 4551792,"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": 1336753, "tid": 1381210, + "ts": 1696941957160.937, "dur": 90.752, + "args": { + "External id": 4551793,"Record function id": 0, "Sequence number": 45295799, "Fwd thread id": 1, "Ev Idx": 112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941957161.902, "dur": 86.590, + "args": { + "External id": 4551794,"Sequence number": 45295799, "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": 1336753, "tid": 1381210, "ts": 1696941957161.902, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941957163.600, "dur": 84.550, + "args": { + "External id": 4551795,"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": 1336753, "tid": 1381210, + "ts": 1696941957164.912, "dur": 15.928, + "args": { + "External id": 4551796,"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": 1336753, "tid": 1381210, + "ts": 1696941957165.868, "dur": 2.457, + "args": { + "External id": 4551797,"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": 1336753, "tid": 1381210, + "ts": 1696941957168.779, "dur": 11.815, + "args": { + "External id": 4551798,"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": 1336753, "tid": 1381210, + "ts": 1696941957169.579, "dur": 10.696, + "args": { + "External id": 4551799,"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": 1336753, "tid": 1381210, + "ts": 1696941957182.002, "dur": 3.757, + "args": { + "External id": 4551800,"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": 1336753, "tid": 1381210, + "ts": 1696941957184.840, "dur": 0.695, + "args": { + "External id": 4551801,"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": 1336753, "tid": 1381210, + "ts": 1696941957186.506, "dur": 61.039, + "args": { + "External id": 4551802,"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": 1336753, "tid": 1381210, + "ts": 1696941957257.566, "dur": 89.890, + "args": { + "External id": 4551803,"Record function id": 0, "Sequence number": 45295798, "Fwd thread id": 1, "Ev Idx": 122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941957258.811, "dur": 69.911, + "args": { + "External id": 4551804,"Sequence number": 45295798, "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": 1336753, "tid": 1381210, "ts": 1696941957258.811, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941957262.343, "dur": 66.139, + "args": { + "External id": 4551805,"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": 1336753, "tid": 1381210, + "ts": 1696941957263.113, "dur": 14.431, + "args": { + "External id": 4551806,"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": 1336753, "tid": 1381210, + "ts": 1696941957263.765, "dur": 1.884, + "args": { + "External id": 4551807,"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": 1336753, "tid": 1381210, + "ts": 1696941957266.242, "dur": 11.069, + "args": { + "External id": 4551808,"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": 1336753, "tid": 1381210, + "ts": 1696941957267.056, "dur": 9.911, + "args": { + "External id": 4551809,"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": 1336753, "tid": 1381210, + "ts": 1696941957278.257, "dur": 1.765, + "args": { + "External id": 4551810,"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": 1336753, "tid": 1381210, + "ts": 1696941957279.286, "dur": 0.599, + "args": { + "External id": 4551811,"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": 1336753, "tid": 1381210, + "ts": 1696941957280.804, "dur": 47.165, + "args": { + "External id": 4551812,"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": 1336753, "tid": 1381210, + "ts": 1696941957332.671, "dur": 13.382, + "args": { + "External id": 4551813,"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": 1336753, "tid": 1381210, + "ts": 1696941957353.642, "dur": 34.162, + "args": { + "External id": 4551814,"Record function id": 0, "Sequence number": 45295797, "Fwd thread id": 1, "Ev Idx": 133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941957354.891, "dur": 1.408, + "args": { + "External id": 4551815,"Sequence number": 45295797, "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": 1336753, "tid": 1381210, "ts": 1696941957354.891, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1696941957358.882, "dur": 24.929, + "args": { + "External id": 4551816,"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": 1336753, "tid": 1381210, + "ts": 1696941957360.533, "dur": 22.896, + "args": { + "External id": 4551817,"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": 1336753, "tid": 1381210, + "ts": 1696941957365.949, "dur": 2.795, + "args": { + "External id": 4551818,"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": 1336753, "tid": 1381210, + "ts": 1696941957392.297, "dur": 3087.086, + "args": { + "External id": 4551819,"Record function id": 0, "Sequence number": 45295795, "Fwd thread id": 1, "Ev Idx": 138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941957396.015, "dur": 3057.821, + "args": { + "External id": 4551820,"Sequence number": 45295795, "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": 1336753, "tid": 1381210, "ts": 1696941957396.015, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696941957427.233, "dur": 2.435, + "args": { + "External id": 4551821,"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": 1336753, "tid": 1381210, + "ts": 1696941957431.464, "dur": 2931.026, + "args": { + "External id": 4551822,"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": 1336753, "tid": 1381210, + "ts": 1696941957432.880, "dur": 2929.202, + "args": { + "External id": 4551823,"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": 1336753, "tid": 1381210, + "ts": 1696941957435.250, "dur": 4.920, + "args": { + "External id": 4551824,"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": 1336753, "tid": 1381210, + "ts": 1696941957441.038, "dur": 2919.527, + "args": { + "External id": 4551825,"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": 1336753, "tid": 1381210, + "ts": 1696941960365.892, "dur": 0.296, + "args": { + "External id": 4551826,"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": 1336753, "tid": 1381210, + "ts": 1696941960367.587, "dur": 4.228, + "args": { + "External id": 4551827,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 1336753, "tid": 1381210, + "ts": 1696941960370.572, "dur": 1.067, + "args": { + "External id": 4551828,"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": 1336753, "tid": 1381210, + "ts": 1696941960376.094, "dur": 21.619, + "args": { + "External id": 4551829,"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": 1336753, "tid": 1381210, + "ts": 1696941960405.033, "dur": 40.882, + "args": { + "External id": 4551830,"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": 1336753, "tid": 1381210, + "ts": 1696941960405.994, "dur": 39.699, + "args": { + "External id": 4551831,"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": 1336753, "tid": 1381210, + "ts": 1696941960406.859, "dur": 38.421, + "args": { + "External id": 4551832,"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": 1336753, "tid": 1381210, + "ts": 1696941960462.716, "dur": 13.138, + "args": { + "External id": 4551833,"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": 1336753, "tid": 1381210, + "ts": 1696941960486.848, "dur": 11.591, + "args": { + "External id": 4551834,"Record function id": 0, "Sequence number": 45295794, "Fwd thread id": 1, "Ev Idx": 153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941960488.348, "dur": 6.700, + "args": { + "External id": 4551835,"Sequence number": 45295794, "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": 1336753, "tid": 1381210, "ts": 1696941960488.348, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941960490.963, "dur": 3.886, + "args": { + "External id": 4551836,"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": 1336753, "tid": 1381210, + "ts": 1696941960491.969, "dur": 2.760, + "args": { + "External id": 4551837,"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": 1336753, "tid": 1381210, + "ts": 1696941960502.164, "dur": 81.541, + "args": { + "External id": 4551838,"Record function id": 0, "Sequence number": 45295793, "Fwd thread id": 1, "Ev Idx": 157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941960505.026, "dur": 71.691, + "args": { + "External id": 4551839,"Sequence number": 45295793, "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": 1336753, "tid": 1381210, "ts": 1696941960505.026, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941960508.814, "dur": 67.584, + "args": { + "External id": 4551840,"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": 1336753, "tid": 1381210, + "ts": 1696941960510.700, "dur": 30.249, + "args": { + "External id": 4551841,"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": 1336753, "tid": 1381210, + "ts": 1696941960511.862, "dur": 2.658, + "args": { + "External id": 4551842,"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": 1336753, "tid": 1381210, + "ts": 1696941960515.125, "dur": 25.564, + "args": { + "External id": 4551843,"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": 1336753, "tid": 1381210, + "ts": 1696941960516.792, "dur": 23.094, + "args": { + "External id": 4551844,"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": 1336753, "tid": 1381210, + "ts": 1696941960542.712, "dur": 5.773, + "args": { + "External id": 4551845,"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": 1336753, "tid": 1381210, + "ts": 1696941960547.031, "dur": 1.136, + "args": { + "External id": 4551846,"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": 1336753, "tid": 1381210, + "ts": 1696941960549.317, "dur": 26.174, + "args": { + "External id": 4551847,"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": 1336753, "tid": 1381210, + "ts": 1696941960589.166, "dur": 52.956, + "args": { + "External id": 4551848,"Record function id": 0, "Sequence number": 45295792, "Fwd thread id": 1, "Ev Idx": 167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941960590.433, "dur": 47.789, + "args": { + "External id": 4551849,"Sequence number": 45295792, "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": 1336753, "tid": 1381210, "ts": 1696941960590.433, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941960592.644, "dur": 45.367, + "args": { + "External id": 4551850,"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": 1336753, "tid": 1381210, + "ts": 1696941960596.195, "dur": 17.359, + "args": { + "External id": 4551851,"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": 1336753, "tid": 1381210, + "ts": 1696941960597.390, "dur": 2.939, + "args": { + "External id": 4551852,"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": 1336753, "tid": 1381210, + "ts": 1696941960601.047, "dur": 12.263, + "args": { + "External id": 4551853,"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": 1336753, "tid": 1381210, + "ts": 1696941960602.007, "dur": 10.886, + "args": { + "External id": 4551854,"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": 1336753, "tid": 1381210, + "ts": 1696941960614.648, "dur": 8.867, + "args": { + "External id": 4551855,"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": 1336753, "tid": 1381210, + "ts": 1696941960619.784, "dur": 3.202, + "args": { + "External id": 4551856,"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": 1336753, "tid": 1381210, + "ts": 1696941960624.138, "dur": 13.452, + "args": { + "External id": 4551857,"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": 1336753, "tid": 1381210, + "ts": 1696941960645.730, "dur": 89.418, + "args": { + "External id": 4551858,"Record function id": 0, "Sequence number": 45295791, "Fwd thread id": 1, "Ev Idx": 177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941960646.649, "dur": 85.446, + "args": { + "External id": 4551859,"Sequence number": 45295791, "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": 1336753, "tid": 1381210, "ts": 1696941960646.649, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941960648.711, "dur": 83.079, + "args": { + "External id": 4551860,"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": 1336753, "tid": 1381210, + "ts": 1696941960649.808, "dur": 19.226, + "args": { + "External id": 4551861,"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": 1336753, "tid": 1381210, + "ts": 1696941960652.735, "dur": 2.016, + "args": { + "External id": 4551862,"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": 1336753, "tid": 1381210, + "ts": 1696941960655.226, "dur": 13.560, + "args": { + "External id": 4551863,"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": 1336753, "tid": 1381210, + "ts": 1696941960656.119, "dur": 12.280, + "args": { + "External id": 4551864,"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": 1336753, "tid": 1381210, + "ts": 1696941960669.956, "dur": 3.912, + "args": { + "External id": 4551865,"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": 1336753, "tid": 1381210, + "ts": 1696941960673.091, "dur": 0.570, + "args": { + "External id": 4551866,"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": 1336753, "tid": 1381210, + "ts": 1696941960674.440, "dur": 56.642, + "args": { + "External id": 4551867,"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": 1336753, "tid": 1381210, + "ts": 1696941960738.995, "dur": 91.175, + "args": { + "External id": 4551868,"Record function id": 0, "Sequence number": 45295790, "Fwd thread id": 1, "Ev Idx": 187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941960740.083, "dur": 73.634, + "args": { + "External id": 4551869,"Sequence number": 45295790, "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": 1336753, "tid": 1381210, "ts": 1696941960740.083, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941960743.792, "dur": 69.599, + "args": { + "External id": 4551870,"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": 1336753, "tid": 1381210, + "ts": 1696941960744.628, "dur": 15.857, + "args": { + "External id": 4551871,"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": 1336753, "tid": 1381210, + "ts": 1696941960747.431, "dur": 1.755, + "args": { + "External id": 4551872,"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": 1336753, "tid": 1381210, + "ts": 1696941960749.617, "dur": 10.626, + "args": { + "External id": 4551873,"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": 1336753, "tid": 1381210, + "ts": 1696941960750.445, "dur": 9.427, + "args": { + "External id": 4551874,"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": 1336753, "tid": 1381210, + "ts": 1696941960761.263, "dur": 3.632, + "args": { + "External id": 4551875,"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": 1336753, "tid": 1381210, + "ts": 1696941960764.287, "dur": 0.435, + "args": { + "External id": 4551876,"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": 1336753, "tid": 1381210, + "ts": 1696941960765.314, "dur": 47.460, + "args": { + "External id": 4551877,"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": 1336753, "tid": 1381210, + "ts": 1696941960817.003, "dur": 12.011, + "args": { + "External id": 4551878,"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": 1336753, "tid": 1381210, + "ts": 1696941960835.958, "dur": 31.176, + "args": { + "External id": 4551879,"Record function id": 0, "Sequence number": 45295789, "Fwd thread id": 1, "Ev Idx": 198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941960837.183, "dur": 0.997, + "args": { + "External id": 4551880,"Sequence number": 45295789, "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": 1336753, "tid": 1381210, "ts": 1696941960837.183, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1696941960840.359, "dur": 21.093, + "args": { + "External id": 4551881,"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": 1336753, "tid": 1381210, + "ts": 1696941960841.998, "dur": 19.128, + "args": { + "External id": 4551882,"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": 1336753, "tid": 1381210, + "ts": 1696941960846.167, "dur": 0.996, + "args": { + "External id": 4551883,"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": 1336753, "tid": 1381210, + "ts": 1696941960871.437, "dur": 3140.242, + "args": { + "External id": 4551884,"Record function id": 0, "Sequence number": 45295788, "Fwd thread id": 1, "Ev Idx": 203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941960883.401, "dur": 3072.340, + "args": { + "External id": 4551885,"Sequence number": 45295788, "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": 1336753, "tid": 1381210, "ts": 1696941960883.401, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696941960912.453, "dur": 1.845, + "args": { + "External id": 4551886,"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": 1336753, "tid": 1381210, + "ts": 1696941960916.196, "dur": 2960.002, + "args": { + "External id": 4551887,"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": 1336753, "tid": 1381210, + "ts": 1696941960917.615, "dur": 2958.237, + "args": { + "External id": 4551888,"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": 1336753, "tid": 1381210, + "ts": 1696941960921.682, "dur": 2.890, + "args": { + "External id": 4551889,"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": 1336753, "tid": 1381210, + "ts": 1696941960925.327, "dur": 2949.568, + "args": { + "External id": 4551890,"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": 1336753, "tid": 1381210, + "ts": 1696941963878.873, "dur": 0.344, + "args": { + "External id": 4551891,"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": 1336753, "tid": 1381210, + "ts": 1696941963880.324, "dur": 2.138, + "args": { + "External id": 4551892,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 1336753, "tid": 1381210, + "ts": 1696941963881.330, "dur": 0.978, + "args": { + "External id": 4551893,"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": 1336753, "tid": 1381210, + "ts": 1696941963886.022, "dur": 20.851, + "args": { + "External id": 4551894,"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": 1336753, "tid": 1381210, + "ts": 1696941963911.249, "dur": 38.451, + "args": { + "External id": 4551895,"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": 1336753, "tid": 1381210, + "ts": 1696941963912.570, "dur": 36.922, + "args": { + "External id": 4551896,"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": 1336753, "tid": 1381210, + "ts": 1696941963913.539, "dur": 35.571, + "args": { + "External id": 4551897,"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": 1336753, "tid": 1381210, + "ts": 1696941963966.798, "dur": 37.182, + "args": { + "External id": 4551898,"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": 1336753, "tid": 1381210, + "ts": 1696941964023.390, "dur": 14.339, + "args": { + "External id": 4551899,"Record function id": 0, "Ev Idx": 218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941964026.027, "dur": 9.769, + "args": { + "External id": 4551900,"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": 1336753, "tid": 1381210, + "ts": 1696941964029.904, "dur": 4.791, + "args": { + "External id": 4551901,"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": 1336753, "tid": 1381210, + "ts": 1696941964030.816, "dur": 3.785, + "args": { + "External id": 4551902,"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": 1336753, "tid": 1381210, + "ts": 1696941964041.668, "dur": 12.425, + "args": { + "External id": 4551903,"Record function id": 0, "Sequence number": 45295787, "Fwd thread id": 1, "Ev Idx": 222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941964043.032, "dur": 8.057, + "args": { + "External id": 4551904,"Sequence number": 45295787, "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": 1336753, "tid": 1381210, "ts": 1696941964043.032, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941964045.500, "dur": 5.408, + "args": { + "External id": 4551905,"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": 1336753, "tid": 1381210, + "ts": 1696941964048.275, "dur": 2.515, + "args": { + "External id": 4551906,"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": 1336753, "tid": 1381210, + "ts": 1696941964057.265, "dur": 71.680, + "args": { + "External id": 4551907,"Record function id": 0, "Sequence number": 45295786, "Fwd thread id": 1, "Ev Idx": 226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941964060.595, "dur": 62.791, + "args": { + "External id": 4551908,"Sequence number": 45295786, "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": 1336753, "tid": 1381210, "ts": 1696941964060.595, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941964062.502, "dur": 60.533, + "args": { + "External id": 4551909,"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": 1336753, "tid": 1381210, + "ts": 1696941964064.531, "dur": 22.681, + "args": { + "External id": 4551910,"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": 1336753, "tid": 1381210, + "ts": 1696941964065.700, "dur": 3.049, + "args": { + "External id": 4551911,"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": 1336753, "tid": 1381210, + "ts": 1696941964069.755, "dur": 17.186, + "args": { + "External id": 4551912,"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": 1336753, "tid": 1381210, + "ts": 1696941964071.183, "dur": 15.306, + "args": { + "External id": 4551913,"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": 1336753, "tid": 1381210, + "ts": 1696941964088.670, "dur": 4.886, + "args": { + "External id": 4551914,"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": 1336753, "tid": 1381210, + "ts": 1696941964092.331, "dur": 0.964, + "args": { + "External id": 4551915,"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": 1336753, "tid": 1381210, + "ts": 1696941964094.552, "dur": 27.753, + "args": { + "External id": 4551916,"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": 1336753, "tid": 1381210, + "ts": 1696941964132.936, "dur": 49.516, + "args": { + "External id": 4551917,"Record function id": 0, "Sequence number": 45295785, "Fwd thread id": 1, "Ev Idx": 236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941964134.220, "dur": 44.620, + "args": { + "External id": 4551918,"Sequence number": 45295785, "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": 1336753, "tid": 1381210, "ts": 1696941964134.220, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941964136.340, "dur": 42.200, + "args": { + "External id": 4551919,"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": 1336753, "tid": 1381210, + "ts": 1696941964139.463, "dur": 19.163, + "args": { + "External id": 4551920,"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": 1336753, "tid": 1381210, + "ts": 1696941964143.813, "dur": 2.085, + "args": { + "External id": 4551921,"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": 1336753, "tid": 1381210, + "ts": 1696941964146.589, "dur": 11.802, + "args": { + "External id": 4551922,"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": 1336753, "tid": 1381210, + "ts": 1696941964147.491, "dur": 10.551, + "args": { + "External id": 4551923,"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": 1336753, "tid": 1381210, + "ts": 1696941964159.663, "dur": 4.162, + "args": { + "External id": 4551924,"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": 1336753, "tid": 1381210, + "ts": 1696941964162.542, "dur": 0.835, + "args": { + "External id": 4551925,"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": 1336753, "tid": 1381210, + "ts": 1696941964164.620, "dur": 13.420, + "args": { + "External id": 4551926,"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": 1336753, "tid": 1381210, + "ts": 1696941964186.095, "dur": 90.680, + "args": { + "External id": 4551927,"Record function id": 0, "Sequence number": 45295784, "Fwd thread id": 1, "Ev Idx": 246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941964187.277, "dur": 85.677, + "args": { + "External id": 4551928,"Sequence number": 45295784, "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": 1336753, "tid": 1381210, "ts": 1696941964187.277, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941964188.901, "dur": 83.813, + "args": { + "External id": 4551929,"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": 1336753, "tid": 1381210, + "ts": 1696941964191.962, "dur": 17.161, + "args": { + "External id": 4551930,"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": 1336753, "tid": 1381210, + "ts": 1696941964194.594, "dur": 1.865, + "args": { + "External id": 4551931,"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": 1336753, "tid": 1381210, + "ts": 1696941964197.064, "dur": 11.824, + "args": { + "External id": 4551932,"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": 1336753, "tid": 1381210, + "ts": 1696941964198.018, "dur": 10.506, + "args": { + "External id": 4551933,"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": 1336753, "tid": 1381210, + "ts": 1696941964209.986, "dur": 4.274, + "args": { + "External id": 4551934,"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": 1336753, "tid": 1381210, + "ts": 1696941964211.263, "dur": 2.835, + "args": { + "External id": 4551935,"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": 1336753, "tid": 1381210, + "ts": 1696941964215.080, "dur": 56.868, + "args": { + "External id": 4551936,"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": 1336753, "tid": 1381210, + "ts": 1696941964280.555, "dur": 97.523, + "args": { + "External id": 4551937,"Record function id": 0, "Sequence number": 45295783, "Fwd thread id": 1, "Ev Idx": 256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941964281.393, "dur": 80.062, + "args": { + "External id": 4551938,"Sequence number": 45295783, "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": 1336753, "tid": 1381210, "ts": 1696941964281.393, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1696941964283.284, "dur": 77.812, + "args": { + "External id": 4551939,"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": 1336753, "tid": 1381210, + "ts": 1696941964284.204, "dur": 25.927, + "args": { + "External id": 4551940,"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": 1336753, "tid": 1381210, + "ts": 1696941964290.090, "dur": 2.020, + "args": { + "External id": 4551941,"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": 1336753, "tid": 1381210, + "ts": 1696941964297.023, "dur": 12.847, + "args": { + "External id": 4551942,"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": 1336753, "tid": 1381210, + "ts": 1696941964299.526, "dur": 10.008, + "args": { + "External id": 4551943,"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": 1336753, "tid": 1381210, + "ts": 1696941964311.117, "dur": 1.849, + "args": { + "External id": 4551944,"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": 1336753, "tid": 1381210, + "ts": 1696941964312.490, "dur": 0.330, + "args": { + "External id": 4551945,"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": 1336753, "tid": 1381210, + "ts": 1696941964313.816, "dur": 46.710, + "args": { + "External id": 4551946,"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": 1336753, "tid": 1381210, + "ts": 1696941964365.063, "dur": 11.307, + "args": { + "External id": 4551947,"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": 1336753, "tid": 1381210, + "ts": 1696941964383.752, "dur": 414.044, + "args": { + "External id": 4551948,"Record function id": 0, "Sequence number": 45295782, "Fwd thread id": 1, "Ev Idx": 267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941964385.124, "dur": 401.492, + "args": { + "External id": 4551949,"Sequence number": 45295782, "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": 1336753, "tid": 1381210, "ts": 1696941964385.124, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1696941964604.586, "dur": 48.395, + "args": { + "External id": 4551950,"kernel_hash": "c2likoimxa3yi6j6dwntng3kzuvmiu64h4ync66w4mrx4v7x6wto", "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/2l/c2likoimxa3yi6j6dwntng3kzuvmiu64h4ync66w4mrx4v7x6wto.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": 1336753, "tid": 1381210, + "ts": 1696941964690.085, "dur": 27.379, + "args": { + "External id": 4551951,"kernel_hash": "c2mqya6ilpprpgchmqenn6k5mpg3mienn3ill2mhoh2uq42xagjg", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2m/c2mqya6ilpprpgchmqenn6k5mpg3mienn3ill2mhoh2uq42xagjg.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": 1336753, "tid": 1381210, + "ts": 1696941964738.139, "dur": 19.014, + "args": { + "External id": 4551952,"kernel_hash": "cstbyq2jrfkh2pvulirtdouqrjc47q3sh3z3auux63nbg6d6xj43", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/st/cstbyq2jrfkh2pvulirtdouqrjc47q3sh3z3auux63nbg6d6xj43.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": 1336753, "tid": 1381210, + "ts": 1696941964808.890, "dur": 11.075, + "args": { + "External id": 4551953,"Record function id": 0, "Ev Idx": 272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941964810.955, "dur": 8.200, + "args": { + "External id": 4551954,"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": 1336753, "tid": 1381210, + "ts": 1696941964814.004, "dur": 4.351, + "args": { + "External id": 4551955,"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": 1336753, "tid": 1381210, + "ts": 1696941964815.296, "dur": 2.978, + "args": { + "External id": 4551956,"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": 1336753, "tid": 1381210, + "ts": 1696941964824.294, "dur": 36.577, + "args": { + "External id": 4551957,"Record function id": 0, "Sequence number": 45295781, "Fwd thread id": 1, "Ev Idx": 276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941964825.399, "dur": 23.914, + "args": { + "External id": 4551958,"Sequence number": 45295781, "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": 1336753, "tid": 1381210, "ts": 1696941964825.399, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1381210, + "ts": 1696941964827.980, "dur": 8.208, + "args": { + "External id": 4551959,"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": 1336753, "tid": 1381210, + "ts": 1696941964833.282, "dur": 1.067, + "args": { + "External id": 4551960,"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": 1336753, "tid": 1381210, + "ts": 1696941964836.905, "dur": 4.370, + "args": { + "External id": 4551961,"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": 1336753, "tid": 1381210, + "ts": 1696941964840.114, "dur": 0.476, + "args": { + "External id": 4551962,"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": 1336753, "tid": 1381210, + "ts": 1696941964841.902, "dur": 2.546, + "args": { + "External id": 4551963,"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": 1336753, "tid": 1381210, + "ts": 1696941964842.980, "dur": 0.710, + "args": { + "External id": 4551964,"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": 1336753, "tid": 1381210, + "ts": 1696941964844.824, "dur": 3.946, + "args": { + "External id": 4551965,"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": 1336753, "tid": 1381210, + "ts": 1696941964847.727, "dur": 0.414, + "args": { + "External id": 4551966,"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": 1336753, "tid": 1381210, + "ts": 1696941964864.668, "dur": 8.623, + "args": { + "External id": 4551967,"Record function id": 0, "Sequence number": 45295780, "Fwd thread id": 1, "Ev Idx": 286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941964865.791, "dur": 1.178, + "args": { + "External id": 4551968,"Sequence number": 45295780, "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": 1336753, "tid": 1381210, "ts": 1696941964865.791, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941964878.066, "dur": 627.468, + "args": { + "External id": 4551969,"Record function id": 0, "Sequence number": 45295779, "Fwd thread id": 1, "Ev Idx": 288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941964879.101, "dur": 608.888, + "args": { + "External id": 4551970,"Sequence number": 45295779, "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": 1336753, "tid": 1381210, "ts": 1696941964879.101, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941964928.807, "dur": 14.012, + "args": { + "External id": 4551971,"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": 1336753, "tid": 1381210, + "ts": 1696941964937.786, "dur": 4.677, + "args": { + "External id": 4551972,"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": 1336753, "tid": 1381210, + "ts": 1696941964949.983, "dur": 10.639, + "args": { + "External id": 4551973,"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": 1336753, "tid": 1381210, + "ts": 1696941964954.273, "dur": 5.194, + "args": { + "External id": 4551974,"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": 1336753, "tid": 1381210, + "ts": 1696941964958.268, "dur": 0.966, + "args": { + "External id": 4551975,"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": 1336753, "tid": 1381210, + "ts": 1696941964966.330, "dur": 192.559, + "args": { + "External id": 4551976,"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": 1336753, "tid": 1381210, + "ts": 1696941964967.490, "dur": 7.705, + "args": { + "External id": 4551977,"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": 1336753, "tid": 1381210, + "ts": 1696941964967.993, "dur": 6.377, + "args": { + "External id": 4551978,"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": 1336753, "tid": 1381210, + "ts": 1696941964971.290, "dur": 2.953, + "args": { + "External id": 4551979,"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": 1336753, "tid": 1381210, + "ts": 1696941964977.671, "dur": 180.271, + "args": { + "External id": 4551980,"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": 1336753, "tid": 1381210, + "ts": 1696941965027.852, "dur": 128.584, + "args": { + "External id": 4551981,"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": 1336753, "tid": 1381210, + "ts": 1696941965167.859, "dur": 5.218, + "args": { + "External id": 4551982,"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": 1336753, "tid": 1381210, + "ts": 1696941965169.985, "dur": 2.927, + "args": { + "External id": 4551983,"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": 1336753, "tid": 1381210, + "ts": 1696941965218.580, "dur": 4.818, + "args": { + "External id": 4551984,"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": 1336753, "tid": 1381210, + "ts": 1696941965224.394, "dur": 3.799, + "args": { + "External id": 4551985,"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": 1336753, "tid": 1381210, + "ts": 1696941965231.557, "dur": 1.917, + "args": { + "External id": 4551986,"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": 1336753, "tid": 1381210, + "ts": 1696941965275.342, "dur": 2.402, + "args": { + "External id": 4551987,"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": 1336753, "tid": 1381210, + "ts": 1696941965276.126, "dur": 1.433, + "args": { + "External id": 4551988,"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": 1336753, "tid": 1381210, + "ts": 1696941965309.814, "dur": 156.686, + "args": { + "External id": 4551989,"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": 1336753, "tid": 1381210, + "ts": 1696941965318.870, "dur": 10.576, + "args": { + "External id": 4551990,"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": 1336753, "tid": 1381210, + "ts": 1696941965324.826, "dur": 1.119, + "args": { + "External id": 4551991,"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": 1336753, "tid": 1381210, + "ts": 1696941965331.716, "dur": 7.780, + "args": { + "External id": 4551992,"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": 1336753, "tid": 1381210, + "ts": 1696941965336.670, "dur": 2.150, + "args": { + "External id": 4551993,"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": 1336753, "tid": 1381210, + "ts": 1696941965341.522, "dur": 3.173, + "args": { + "External id": 4551994,"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": 1336753, "tid": 1381210, + "ts": 1696941965343.963, "dur": 0.398, + "args": { + "External id": 4551995,"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": 1336753, "tid": 1381210, + "ts": 1696941965345.328, "dur": 4.547, + "args": { + "External id": 4551996,"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": 1336753, "tid": 1381210, + "ts": 1696941965348.646, "dur": 0.547, + "args": { + "External id": 4551997,"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": 1336753, "tid": 1381210, + "ts": 1696941965356.886, "dur": 4.272, + "args": { + "External id": 4551998,"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": 1336753, "tid": 1381210, + "ts": 1696941965360.220, "dur": 0.632, + "args": { + "External id": 4551999,"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": 1336753, "tid": 1381210, + "ts": 1696941965362.096, "dur": 7.678, + "args": { + "External id": 4552000,"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": 1336753, "tid": 1381210, + "ts": 1696941965367.802, "dur": 1.775, + "args": { + "External id": 4552001,"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": 1336753, "tid": 1381210, + "ts": 1696941965370.506, "dur": 3.875, + "args": { + "External id": 4552002,"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": 1336753, "tid": 1381210, + "ts": 1696941965373.558, "dur": 0.528, + "args": { + "External id": 4552003,"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": 1336753, "tid": 1381210, + "ts": 1696941965375.246, "dur": 1.937, + "args": { + "External id": 4552004,"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": 1336753, "tid": 1381210, + "ts": 1696941965375.753, "dur": 1.350, + "args": { + "External id": 4552005,"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": 1336753, "tid": 1381210, + "ts": 1696941965379.425, "dur": 71.267, + "args": { + "External id": 4552006,"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": 1336753, "tid": 1381210, + "ts": 1696941965454.126, "dur": 3.076, + "args": { + "External id": 4552007,"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": 1336753, "tid": 1381210, + "ts": 1696941965459.814, "dur": 2.375, + "args": { + "External id": 4552008,"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": 1336753, "tid": 1381210, + "ts": 1696941965460.950, "dur": 0.424, + "args": { + "External id": 4552009,"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": 1336753, "tid": 1381210, + "ts": 1696941965464.281, "dur": 0.781, + "args": { + "External id": 4552010,"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": 1336753, "tid": 1381210, + "ts": 1696941965518.298, "dur": 27.102, + "args": { + "External id": 4552011,"Record function id": 0, "Ev Idx": 330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941965520.317, "dur": 23.657, + "args": { + "External id": 4552012,"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": 1336753, "tid": 1381210, + "ts": 1696941965522.804, "dur": 19.737, + "args": { + "External id": 4552013,"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": 1336753, "tid": 1381210, + "ts": 1696941965523.950, "dur": 18.150, + "args": { + "External id": 4552014,"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": 1336753, "tid": 1381210, + "ts": 1696941965551.558, "dur": 15.274, + "args": { + "External id": 4552015,"Record function id": 0, "Sequence number": 45295778, "Fwd thread id": 1, "Ev Idx": 334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941965552.917, "dur": 9.607, + "args": { + "External id": 4552016,"Sequence number": 45295778, "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": 1336753, "tid": 1381210, "ts": 1696941965552.917, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941965557.724, "dur": 4.591, + "args": { + "External id": 4552017,"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": 1336753, "tid": 1381210, + "ts": 1696941965560.652, "dur": 1.497, + "args": { + "External id": 4552018,"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": 1336753, "tid": 1381210, + "ts": 1696941965570.850, "dur": 183.198, + "args": { + "External id": 4552019,"Record function id": 0, "Sequence number": 45295777, "Fwd thread id": 1, "Ev Idx": 338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941965572.050, "dur": 172.985, + "args": { + "External id": 4552020,"Sequence number": 45295777, "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": 1336753, "tid": 1381210, "ts": 1696941965572.050, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941965577.545, "dur": 4.022, + "args": { + "External id": 4552021,"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": 1336753, "tid": 1381210, + "ts": 1696941965579.070, "dur": 1.890, + "args": { + "External id": 4552022,"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": 1336753, "tid": 1381210, + "ts": 1696941965580.177, "dur": 0.625, + "args": { + "External id": 4552023,"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": 1336753, "tid": 1381210, + "ts": 1696941965583.284, "dur": 65.140, + "args": { + "External id": 4552024,"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": 1336753, "tid": 1381210, + "ts": 1696941965651.466, "dur": 3.673, + "args": { + "External id": 4552025,"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": 1336753, "tid": 1381210, + "ts": 1696941965652.101, "dur": 2.386, + "args": { + "External id": 4552026,"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": 1336753, "tid": 1381210, + "ts": 1696941965652.998, "dur": 1.297, + "args": { + "External id": 4552027,"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": 1336753, "tid": 1381210, + "ts": 1696941965657.334, "dur": 5.122, + "args": { + "External id": 4552028,"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": 1336753, "tid": 1381210, + "ts": 1696941965658.279, "dur": 3.602, + "args": { + "External id": 4552029,"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": 1336753, "tid": 1381210, + "ts": 1696941965661.170, "dur": 0.595, + "args": { + "External id": 4552030,"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": 1336753, "tid": 1381210, + "ts": 1696941965664.939, "dur": 79.204, + "args": { + "External id": 4552031,"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": 1336753, "tid": 1381210, + "ts": 1696941965758.545, "dur": 7.185, + "args": { + "External id": 4552032,"Record function id": 0, "Sequence number": 45295776, "Fwd thread id": 1, "Ev Idx": 351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941965759.697, "dur": 3.716, + "args": { + "External id": 4552033,"Sequence number": 45295776, "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": 1336753, "tid": 1381210, "ts": 1696941965759.697, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941965761.407, "dur": 1.877, + "args": { + "External id": 4552034,"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": 1336753, "tid": 1381210, + "ts": 1696941965762.126, "dur": 1.014, + "args": { + "External id": 4552035,"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": 1336753, "tid": 1381210, + "ts": 1696941965769.254, "dur": 12.557, + "args": { + "External id": 4552036,"Record function id": 0, "Sequence number": 45295775, "Fwd thread id": 1, "Ev Idx": 355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941965770.497, "dur": 8.529, + "args": { + "External id": 4552037,"Sequence number": 45295775, "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": 1336753, "tid": 1381210, "ts": 1696941965770.497, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941965771.745, "dur": 7.095, + "args": { + "External id": 4552038,"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": 1336753, "tid": 1381210, + "ts": 1696941965772.529, "dur": 5.817, + "args": { + "External id": 4552039,"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": 1336753, "tid": 1381210, + "ts": 1696941965777.805, "dur": 0.376, + "args": { + "External id": 4552040,"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": 1336753, "tid": 1381210, + "ts": 1696941965785.985, "dur": 5.976, + "args": { + "External id": 4552041,"Record function id": 0, "Ev Idx": 360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941965787.202, "dur": 4.257, + "args": { + "External id": 4552042,"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": 1336753, "tid": 1381210, + "ts": 1696941965788.628, "dur": 2.561, + "args": { + "External id": 4552043,"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": 1336753, "tid": 1381210, + "ts": 1696941965789.379, "dur": 1.701, + "args": { + "External id": 4552044,"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": 1336753, "tid": 1381210, + "ts": 1696941965797.201, "dur": 7.412, + "args": { + "External id": 4552045,"Record function id": 0, "Sequence number": 45295774, "Fwd thread id": 1, "Ev Idx": 364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941965798.373, "dur": 2.925, + "args": { + "External id": 4552046,"Sequence number": 45295774, "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": 1336753, "tid": 1381210, "ts": 1696941965798.373, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941965799.717, "dur": 1.450, + "args": { + "External id": 4552047,"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": 1336753, "tid": 1381210, + "ts": 1696941965800.234, "dur": 0.778, + "args": { + "External id": 4552048,"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": 1336753, "tid": 1381210, + "ts": 1696941965807.605, "dur": 122.514, + "args": { + "External id": 4552049,"Record function id": 0, "Sequence number": 45295773, "Fwd thread id": 1, "Ev Idx": 368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941965808.299, "dur": 110.839, + "args": { + "External id": 4552050,"Sequence number": 45295773, "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": 1336753, "tid": 1381210, "ts": 1696941965808.299, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941965812.758, "dur": 2.666, + "args": { + "External id": 4552051,"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": 1336753, "tid": 1381210, + "ts": 1696941965813.300, "dur": 1.743, + "args": { + "External id": 4552052,"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": 1336753, "tid": 1381210, + "ts": 1696941965814.550, "dur": 0.368, + "args": { + "External id": 4552053,"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": 1336753, "tid": 1381210, + "ts": 1696941965816.233, "dur": 36.996, + "args": { + "External id": 4552054,"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": 1336753, "tid": 1381210, + "ts": 1696941965854.093, "dur": 8.500, + "args": { + "External id": 4552055,"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": 1336753, "tid": 1381210, + "ts": 1696941965854.871, "dur": 7.190, + "args": { + "External id": 4552056,"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": 1336753, "tid": 1381210, + "ts": 1696941965860.893, "dur": 1.044, + "args": { + "External id": 4552057,"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": 1336753, "tid": 1381210, + "ts": 1696941965863.698, "dur": 5.337, + "args": { + "External id": 4552058,"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": 1336753, "tid": 1381210, + "ts": 1696941965865.058, "dur": 3.437, + "args": { + "External id": 4552059,"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": 1336753, "tid": 1381210, + "ts": 1696941965865.868, "dur": 2.552, + "args": { + "External id": 4552060,"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": 1336753, "tid": 1381210, + "ts": 1696941965869.697, "dur": 48.838, + "args": { + "External id": 4552061,"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": 1336753, "tid": 1381210, + "ts": 1696941965934.482, "dur": 35.775, + "args": { + "External id": 4552062,"Record function id": 0, "Sequence number": 45295772, "Fwd thread id": 1, "Ev Idx": 381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941965935.803, "dur": 5.918, + "args": { + "External id": 4552063,"Sequence number": 45295772, "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": 1336753, "tid": 1381210, "ts": 1696941965935.803, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941965937.528, "dur": 4.039, + "args": { + "External id": 4552064,"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": 1336753, "tid": 1381210, + "ts": 1696941965940.337, "dur": 1.082, + "args": { + "External id": 4552065,"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": 1336753, "tid": 1381210, + "ts": 1696941965945.962, "dur": 21.501, + "args": { + "External id": 4552066,"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": 1336753, "tid": 1381210, + "ts": 1696941965975.832, "dur": 56.164, + "args": { + "External id": 4552067,"Record function id": 0, "Sequence number": 45295771, "Fwd thread id": 1, "Ev Idx": 386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941965977.142, "dur": 51.167, + "args": { + "External id": 4552068,"Sequence number": 45295771, "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": 1336753, "tid": 1381210, "ts": 1696941965977.142, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941965978.516, "dur": 49.559, + "args": { + "External id": 4552069,"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": 1336753, "tid": 1381210, + "ts": 1696941965979.646, "dur": 47.473, + "args": { + "External id": 4552070,"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": 1336753, "tid": 1381210, + "ts": 1696941966025.515, "dur": 1.145, + "args": { + "External id": 4552071,"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": 1336753, "tid": 1381210, + "ts": 1696941966038.234, "dur": 7.674, + "args": { + "External id": 4552072,"Record function id": 0, "Ev Idx": 391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941966040.061, "dur": 5.218, + "args": { + "External id": 4552073,"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": 1336753, "tid": 1381210, + "ts": 1696941966041.763, "dur": 2.940, + "args": { + "External id": 4552074,"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": 1336753, "tid": 1381210, + "ts": 1696941966042.979, "dur": 1.652, + "args": { + "External id": 4552075,"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": 1336753, "tid": 1381210, + "ts": 1696941966050.769, "dur": 542.840, + "args": { + "External id": 4552076,"Record function id": 0, "Sequence number": 45295770, "Fwd thread id": 1, "Ev Idx": 395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941966052.126, "dur": 520.407, + "args": { + "External id": 4552077,"Sequence number": 45295770, "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": 1336753, "tid": 1381210, "ts": 1696941966052.126, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1381210, + "ts": 1696941966083.263, "dur": 41.169, + "args": { + "External id": 4552078,"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": 1336753, "tid": 1381210, + "ts": 1696941966085.700, "dur": 38.458, + "args": { + "External id": 4552079,"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": 1336753, "tid": 1381210, + "ts": 1696941966089.396, "dur": 8.972, + "args": { + "External id": 4552080,"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": 1336753, "tid": 1381210, + "ts": 1696941966094.267, "dur": 3.530, + "args": { + "External id": 4552081,"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": 1336753, "tid": 1381210, + "ts": 1696941966099.596, "dur": 24.052, + "args": { + "External id": 4552082,"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": 1336753, "tid": 1381210, + "ts": 1696941966138.235, "dur": 2.349, + "args": { + "External id": 4552083,"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": 1336753, "tid": 1381210, + "ts": 1696941966138.981, "dur": 1.473, + "args": { + "External id": 4552084,"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": 1336753, "tid": 1381210, + "ts": 1696941966144.445, "dur": 5.695, + "args": { + "External id": 4552085,"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": 1336753, "tid": 1381210, + "ts": 1696941966147.073, "dur": 2.982, + "args": { + "External id": 4552086,"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": 1336753, "tid": 1381210, + "ts": 1696941966167.775, "dur": 2.505, + "args": { + "External id": 4552087,"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": 1336753, "tid": 1381210, + "ts": 1696941966184.436, "dur": 4.045, + "args": { + "External id": 4552088,"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": 1336753, "tid": 1381210, + "ts": 1696941966428.185, "dur": 3.307, + "args": { + "External id": 4552089,"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": 1336753, "tid": 1381210, + "ts": 1696941966437.091, "dur": 36.487, + "args": { + "External id": 4552090,"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": 1336753, "tid": 1381210, + "ts": 1696941966448.394, "dur": 1.137, + "args": { + "External id": 4552091,"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": 1336753, "tid": 1381210, + "ts": 1696941966480.692, "dur": 31.603, + "args": { + "External id": 4552092,"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": 1336753, "tid": 1381210, + "ts": 1696941966483.043, "dur": 29.016, + "args": { + "External id": 4552093,"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": 1336753, "tid": 1381210, + "ts": 1696941966489.229, "dur": 4.187, + "args": { + "External id": 4552094,"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": 1336753, "tid": 1381210, + "ts": 1696941966494.478, "dur": 17.123, + "args": { + "External id": 4552095,"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": 1336753, "tid": 1381210, + "ts": 1696941966517.012, "dur": 2.410, + "args": { + "External id": 4552096,"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": 1336753, "tid": 1381210, + "ts": 1696941966518.052, "dur": 1.238, + "args": { + "External id": 4552097,"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": 1336753, "tid": 1381210, + "ts": 1696941966546.996, "dur": 5.597, + "args": { + "External id": 4552098,"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": 1336753, "tid": 1381210, + "ts": 1696941966550.237, "dur": 2.130, + "args": { + "External id": 4552099,"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": 1336753, "tid": 1381210, + "ts": 1696941966557.760, "dur": 3.728, + "args": { + "External id": 4552100,"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": 1336753, "tid": 1381210, + "ts": 1696941966558.529, "dur": 2.864, + "args": { + "External id": 4552101,"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": 1336753, "tid": 1381210, + "ts": 1696941966608.328, "dur": 9.214, + "args": { + "External id": 4552102,"Record function id": 0, "Ev Idx": 421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941966610.650, "dur": 6.172, + "args": { + "External id": 4552103,"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": 1336753, "tid": 1381210, + "ts": 1696941966612.876, "dur": 2.980, + "args": { + "External id": 4552104,"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": 1336753, "tid": 1381210, + "ts": 1696941966613.815, "dur": 1.942, + "args": { + "External id": 4552105,"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": 1336753, "tid": 1381210, + "ts": 1696941966621.342, "dur": 12.302, + "args": { + "External id": 4552106,"Record function id": 0, "Sequence number": 45295769, "Fwd thread id": 1, "Ev Idx": 425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941966622.433, "dur": 7.689, + "args": { + "External id": 4552107,"Sequence number": 45295769, "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": 1336753, "tid": 1381210, "ts": 1696941966622.433, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941966627.642, "dur": 2.292, + "args": { + "External id": 4552108,"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": 1336753, "tid": 1381210, + "ts": 1696941966628.252, "dur": 1.554, + "args": { + "External id": 4552109,"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": 1336753, "tid": 1381210, + "ts": 1696941966637.113, "dur": 153.527, + "args": { + "External id": 4552110,"Record function id": 0, "Sequence number": 45295768, "Fwd thread id": 1, "Ev Idx": 429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941966638.674, "dur": 146.026, + "args": { + "External id": 4552111,"Sequence number": 45295768, "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": 1336753, "tid": 1381210, "ts": 1696941966638.674, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941966643.020, "dur": 6.716, + "args": { + "External id": 4552112,"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": 1336753, "tid": 1381210, + "ts": 1696941966644.622, "dur": 4.462, + "args": { + "External id": 4552113,"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": 1336753, "tid": 1381210, + "ts": 1696941966647.852, "dur": 0.955, + "args": { + "External id": 4552114,"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": 1336753, "tid": 1381210, + "ts": 1696941966651.123, "dur": 67.369, + "args": { + "External id": 4552115,"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": 1336753, "tid": 1381210, + "ts": 1696941966720.007, "dur": 5.185, + "args": { + "External id": 4552116,"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": 1336753, "tid": 1381210, + "ts": 1696941966720.777, "dur": 3.850, + "args": { + "External id": 4552117,"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": 1336753, "tid": 1381210, + "ts": 1696941966721.983, "dur": 2.473, + "args": { + "External id": 4552118,"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": 1336753, "tid": 1381210, + "ts": 1696941966727.381, "dur": 7.874, + "args": { + "External id": 4552119,"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": 1336753, "tid": 1381210, + "ts": 1696941966728.581, "dur": 6.130, + "args": { + "External id": 4552120,"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": 1336753, "tid": 1381210, + "ts": 1696941966734.105, "dur": 0.482, + "args": { + "External id": 4552121,"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": 1336753, "tid": 1381210, + "ts": 1696941966736.011, "dur": 47.854, + "args": { + "External id": 4552122,"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": 1336753, "tid": 1381210, + "ts": 1696941966795.356, "dur": 9.723, + "args": { + "External id": 4552123,"Record function id": 0, "Sequence number": 45295767, "Fwd thread id": 1, "Ev Idx": 442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941966796.259, "dur": 5.181, + "args": { + "External id": 4552124,"Sequence number": 45295767, "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": 1336753, "tid": 1381210, "ts": 1696941966796.259, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941966797.618, "dur": 3.662, + "args": { + "External id": 4552125,"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": 1336753, "tid": 1381210, + "ts": 1696941966798.476, "dur": 2.677, + "args": { + "External id": 4552126,"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": 1336753, "tid": 1381210, + "ts": 1696941966808.625, "dur": 12.140, + "args": { + "External id": 4552127,"Record function id": 0, "Sequence number": 45295766, "Fwd thread id": 1, "Ev Idx": 446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941966809.732, "dur": 8.137, + "args": { + "External id": 4552128,"Sequence number": 45295766, "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": 1336753, "tid": 1381210, "ts": 1696941966809.732, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941966810.831, "dur": 6.829, + "args": { + "External id": 4552129,"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": 1336753, "tid": 1381210, + "ts": 1696941966811.543, "dur": 5.621, + "args": { + "External id": 4552130,"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": 1336753, "tid": 1381210, + "ts": 1696941966816.527, "dur": 0.498, + "args": { + "External id": 4552131,"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": 1336753, "tid": 1381210, + "ts": 1696941966824.799, "dur": 6.212, + "args": { + "External id": 4552132,"Record function id": 0, "Ev Idx": 451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941966826.106, "dur": 4.372, + "args": { + "External id": 4552133,"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": 1336753, "tid": 1381210, + "ts": 1696941966827.761, "dur": 2.435, + "args": { + "External id": 4552134,"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": 1336753, "tid": 1381210, + "ts": 1696941966828.488, "dur": 1.634, + "args": { + "External id": 4552135,"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": 1336753, "tid": 1381210, + "ts": 1696941966834.382, "dur": 7.954, + "args": { + "External id": 4552136,"Record function id": 0, "Sequence number": 45295765, "Fwd thread id": 1, "Ev Idx": 455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941966835.604, "dur": 4.134, + "args": { + "External id": 4552137,"Sequence number": 45295765, "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": 1336753, "tid": 1381210, "ts": 1696941966835.604, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941966837.211, "dur": 2.379, + "args": { + "External id": 4552138,"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": 1336753, "tid": 1381210, + "ts": 1696941966838.322, "dur": 1.134, + "args": { + "External id": 4552139,"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": 1336753, "tid": 1381210, + "ts": 1696941966848.926, "dur": 404.063, + "args": { + "External id": 4552140,"Record function id": 0, "Sequence number": 45295764, "Fwd thread id": 1, "Ev Idx": 459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941966850.016, "dur": 376.692, + "args": { + "External id": 4552141,"Sequence number": 45295764, "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": 1336753, "tid": 1381210, "ts": 1696941966850.016, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1696941966871.204, "dur": 10.391, + "args": { + "External id": 4552142,"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": 1336753, "tid": 1381210, + "ts": 1696941966877.002, "dur": 4.083, + "args": { + "External id": 4552143,"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": 1336753, "tid": 1381210, + "ts": 1696941966883.645, "dur": 3.245, + "args": { + "External id": 4552144,"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": 1336753, "tid": 1381210, + "ts": 1696941966884.902, "dur": 1.738, + "args": { + "External id": 4552145,"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": 1336753, "tid": 1381210, + "ts": 1696941966888.669, "dur": 5.831, + "args": { + "External id": 4552146,"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": 1336753, "tid": 1381210, + "ts": 1696941966891.250, "dur": 3.050, + "args": { + "External id": 4552147,"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": 1336753, "tid": 1381210, + "ts": 1696941966927.655, "dur": 269.349, + "args": { + "External id": 4552148,"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": 1336753, "tid": 1381210, + "ts": 1696941967086.605, "dur": 5.257, + "args": { + "External id": 4552149,"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": 1336753, "tid": 1381210, + "ts": 1696941967094.016, "dur": 3.677, + "args": { + "External id": 4552150,"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": 1336753, "tid": 1381210, + "ts": 1696941967212.815, "dur": 4.636, + "args": { + "External id": 4552151,"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": 1336753, "tid": 1381210, + "ts": 1696941967220.415, "dur": 0.750, + "args": { + "External id": 4552152,"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": 1336753, "tid": 1381210, + "ts": 1696941967223.133, "dur": 0.593, + "args": { + "External id": 4552153,"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": 1336753, "tid": 1381210, + "ts": 1696941967263.489, "dur": 259.073, + "args": { + "External id": 4552154,"Record function id": 0, "Sequence number": 45295763, "Fwd thread id": 1, "Ev Idx": 473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941967265.040, "dur": 248.209, + "args": { + "External id": 4552155,"Sequence number": 45295763, "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": 1336753, "tid": 1381210, "ts": 1696941967265.040, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1696941967289.728, "dur": 50.867, + "args": { + "External id": 4552156,"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": 1336753, "tid": 1381210, + "ts": 1696941967297.426, "dur": 3.220, + "args": { + "External id": 4552157,"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": 1336753, "tid": 1381210, + "ts": 1696941967301.812, "dur": 38.093, + "args": { + "External id": 4552158,"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": 1336753, "tid": 1381210, + "ts": 1696941967351.930, "dur": 4.112, + "args": { + "External id": 4552159,"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": 1336753, "tid": 1381210, + "ts": 1696941967353.347, "dur": 2.344, + "args": { + "External id": 4552160,"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": 1336753, "tid": 1381210, + "ts": 1696941967550.271, "dur": 169.303, + "args": { + "External id": 4552161,"Record function id": 0, "Sequence number": 45295762, "Fwd thread id": 1, "Ev Idx": 480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941967552.828, "dur": 159.543, + "args": { + "External id": 4552162,"Sequence number": 45295762, "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": 1336753, "tid": 1381210, "ts": 1696941967552.828, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1696941967568.656, "dur": 36.887, + "args": { + "External id": 4552163,"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": 1336753, "tid": 1381210, + "ts": 1696941967573.494, "dur": 3.404, + "args": { + "External id": 4552164,"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": 1336753, "tid": 1381210, + "ts": 1696941967577.941, "dur": 27.063, + "args": { + "External id": 4552165,"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": 1336753, "tid": 1381210, + "ts": 1696941967612.930, "dur": 4.681, + "args": { + "External id": 4552166,"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": 1336753, "tid": 1381210, + "ts": 1696941967614.591, "dur": 2.642, + "args": { + "External id": 4552167,"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": 1336753, "tid": 1381210, + "ts": 1696941967726.627, "dur": 16.515, + "args": { + "External id": 4552168,"Record function id": 0, "Sequence number": 45295761, "Fwd thread id": 1, "Ev Idx": 487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941967728.287, "dur": 11.156, + "args": { + "External id": 4552169,"Sequence number": 45295761, "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": 1336753, "tid": 1381210, "ts": 1696941967728.287, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941967730.831, "dur": 8.354, + "args": { + "External id": 4552170,"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": 1336753, "tid": 1381210, + "ts": 1696941967732.041, "dur": 6.928, + "args": { + "External id": 4552171,"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": 1336753, "tid": 1381210, + "ts": 1696941967746.747, "dur": 11.244, + "args": { + "External id": 4552172,"Record function id": 0, "Sequence number": 45295760, "Fwd thread id": 1, "Ev Idx": 491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941967747.883, "dur": 7.337, + "args": { + "External id": 4552173,"Sequence number": 45295760, "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": 1336753, "tid": 1381210, "ts": 1696941967747.883, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941967751.294, "dur": 3.776, + "args": { + "External id": 4552174,"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": 1336753, "tid": 1381210, + "ts": 1696941967753.990, "dur": 0.901, + "args": { + "External id": 4552175,"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": 1336753, "tid": 1381210, + "ts": 1696941967761.144, "dur": 6.629, + "args": { + "External id": 4552176,"Record function id": 0, "Sequence number": 45295759, "Fwd thread id": 1, "Ev Idx": 495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941967762.204, "dur": 3.127, + "args": { + "External id": 4552177,"Sequence number": 45295759, "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": 1336753, "tid": 1381210, "ts": 1696941967762.204, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941967763.486, "dur": 1.703, + "args": { + "External id": 4552178,"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": 1336753, "tid": 1381210, + "ts": 1696941967764.179, "dur": 0.877, + "args": { + "External id": 4552179,"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": 1336753, "tid": 1381210, + "ts": 1696941967773.140, "dur": 8.022, + "args": { + "External id": 4552180,"Record function id": 0, "Sequence number": 45295758, "Fwd thread id": 1, "Ev Idx": 499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941967774.125, "dur": 3.665, + "args": { + "External id": 4552181,"Sequence number": 45295758, "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": 1336753, "tid": 1381210, "ts": 1696941967774.125, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941967775.612, "dur": 2.016, + "args": { + "External id": 4552182,"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": 1336753, "tid": 1381210, + "ts": 1696941967776.335, "dur": 1.140, + "args": { + "External id": 4552183,"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": 1336753, "tid": 1381210, + "ts": 1696941967784.635, "dur": 185.059, + "args": { + "External id": 4552184,"Record function id": 0, "Sequence number": 45295757, "Fwd thread id": 1, "Ev Idx": 503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941967787.744, "dur": 173.872, + "args": { + "External id": 4552185,"Sequence number": 45295757, "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": 1336753, "tid": 1381210, "ts": 1696941967787.744, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941967793.318, "dur": 6.949, + "args": { + "External id": 4552186,"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": 1336753, "tid": 1381210, + "ts": 1696941967795.616, "dur": 4.039, + "args": { + "External id": 4552187,"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": 1336753, "tid": 1381210, + "ts": 1696941967797.623, "dur": 1.721, + "args": { + "External id": 4552188,"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": 1336753, "tid": 1381210, + "ts": 1696941967802.111, "dur": 67.678, + "args": { + "External id": 4552189,"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": 1336753, "tid": 1381210, + "ts": 1696941967871.102, "dur": 8.027, + "args": { + "External id": 4552190,"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": 1336753, "tid": 1381210, + "ts": 1696941967871.887, "dur": 6.577, + "args": { + "External id": 4552191,"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": 1336753, "tid": 1381210, + "ts": 1696941967877.041, "dur": 1.269, + "args": { + "External id": 4552192,"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": 1336753, "tid": 1381210, + "ts": 1696941967909.520, "dur": 2.899, + "args": { + "External id": 4552193,"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": 1336753, "tid": 1381210, + "ts": 1696941967910.622, "dur": 1.261, + "args": { + "External id": 4552194,"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": 1336753, "tid": 1381210, + "ts": 1696941967911.417, "dur": 0.354, + "args": { + "External id": 4552195,"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": 1336753, "tid": 1381210, + "ts": 1696941967913.075, "dur": 47.635, + "args": { + "External id": 4552196,"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": 1336753, "tid": 1381210, + "ts": 1696941967974.485, "dur": 60.953, + "args": { + "External id": 4552197,"Record function id": 0, "Sequence number": 45295756, "Fwd thread id": 1, "Ev Idx": 516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941967975.683, "dur": 56.315, + "args": { + "External id": 4552198,"Sequence number": 45295756, "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": 1336753, "tid": 1381210, "ts": 1696941967975.683, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941967976.903, "dur": 54.895, + "args": { + "External id": 4552199,"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": 1336753, "tid": 1381210, + "ts": 1696941967979.474, "dur": 51.800, + "args": { + "External id": 4552200,"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": 1336753, "tid": 1381210, + "ts": 1696941968041.118, "dur": 11.704, + "args": { + "External id": 4552201,"Record function id": 0, "Sequence number": 45295755, "Fwd thread id": 1, "Ev Idx": 520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941968042.168, "dur": 7.565, + "args": { + "External id": 4552202,"Sequence number": 45295755, "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": 1336753, "tid": 1381210, "ts": 1696941968042.168, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941968043.365, "dur": 6.164, + "args": { + "External id": 4552203,"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": 1336753, "tid": 1381210, + "ts": 1696941968044.522, "dur": 4.396, + "args": { + "External id": 4552204,"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": 1336753, "tid": 1381210, + "ts": 1696941968048.235, "dur": 0.581, + "args": { + "External id": 4552205,"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": 1336753, "tid": 1381210, + "ts": 1696941968059.247, "dur": 11.715, + "args": { + "External id": 4552206,"Record function id": 0, "Ev Idx": 525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941968060.868, "dur": 9.354, + "args": { + "External id": 4552207,"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": 1336753, "tid": 1381210, + "ts": 1696941968063.439, "dur": 6.402, + "args": { + "External id": 4552208,"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": 1336753, "tid": 1381210, + "ts": 1696941968067.045, "dur": 2.696, + "args": { + "External id": 4552209,"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": 1336753, "tid": 1381210, + "ts": 1696941968076.670, "dur": 6.185, + "args": { + "External id": 4552210,"Record function id": 0, "Sequence number": 45295754, "Fwd thread id": 1, "Ev Idx": 529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941968077.879, "dur": 2.768, + "args": { + "External id": 4552211,"Sequence number": 45295754, "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": 1336753, "tid": 1381210, "ts": 1696941968077.879, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941968079.049, "dur": 1.452, + "args": { + "External id": 4552212,"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": 1336753, "tid": 1381210, + "ts": 1696941968079.436, "dur": 0.945, + "args": { + "External id": 4552213,"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": 1336753, "tid": 1381210, + "ts": 1696941968086.153, "dur": 103.307, + "args": { + "External id": 4552214,"Record function id": 0, "Sequence number": 45295753, "Fwd thread id": 1, "Ev Idx": 533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941968087.005, "dur": 94.956, + "args": { + "External id": 4552215,"Sequence number": 45295753, "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": 1336753, "tid": 1381210, "ts": 1696941968087.005, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941968091.176, "dur": 6.255, + "args": { + "External id": 4552216,"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": 1336753, "tid": 1381210, + "ts": 1696941968091.831, "dur": 5.182, + "args": { + "External id": 4552217,"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": 1336753, "tid": 1381210, + "ts": 1696941968096.576, "dur": 0.334, + "args": { + "External id": 4552218,"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": 1336753, "tid": 1381210, + "ts": 1696941968098.334, "dur": 35.584, + "args": { + "External id": 4552219,"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": 1336753, "tid": 1381210, + "ts": 1696941968135.127, "dur": 3.085, + "args": { + "External id": 4552220,"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": 1336753, "tid": 1381210, + "ts": 1696941968135.884, "dur": 1.733, + "args": { + "External id": 4552221,"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": 1336753, "tid": 1381210, + "ts": 1696941968136.705, "dur": 0.811, + "args": { + "External id": 4552222,"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": 1336753, "tid": 1381210, + "ts": 1696941968139.433, "dur": 6.549, + "args": { + "External id": 4552223,"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": 1336753, "tid": 1381210, + "ts": 1696941968142.389, "dur": 3.181, + "args": { + "External id": 4552224,"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": 1336753, "tid": 1381210, + "ts": 1696941968143.178, "dur": 2.277, + "args": { + "External id": 4552225,"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": 1336753, "tid": 1381210, + "ts": 1696941968146.516, "dur": 34.659, + "args": { + "External id": 4552226,"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": 1336753, "tid": 1381210, + "ts": 1696941968193.672, "dur": 35.092, + "args": { + "External id": 4552227,"Record function id": 0, "Sequence number": 45295752, "Fwd thread id": 1, "Ev Idx": 546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941968194.668, "dur": 5.629, + "args": { + "External id": 4552228,"Sequence number": 45295752, "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": 1336753, "tid": 1381210, "ts": 1696941968194.668, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941968198.297, "dur": 1.860, + "args": { + "External id": 4552229,"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": 1336753, "tid": 1381210, + "ts": 1696941968199.067, "dur": 0.966, + "args": { + "External id": 4552230,"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": 1336753, "tid": 1381210, + "ts": 1696941968203.393, "dur": 22.433, + "args": { + "External id": 4552231,"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": 1336753, "tid": 1381210, + "ts": 1696941968232.429, "dur": 8.925, + "args": { + "External id": 4552232,"Record function id": 0, "Sequence number": 45295751, "Fwd thread id": 1, "Ev Idx": 551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941968233.577, "dur": 5.908, + "args": { + "External id": 4552233,"Sequence number": 45295751, "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": 1336753, "tid": 1381210, "ts": 1696941968233.577, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941968236.346, "dur": 2.942, + "args": { + "External id": 4552234,"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": 1336753, "tid": 1381210, + "ts": 1696941968236.994, "dur": 1.822, + "args": { + "External id": 4552235,"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": 1336753, "tid": 1381210, + "ts": 1696941968238.160, "dur": 0.531, + "args": { + "External id": 4552236,"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": 1336753, "tid": 1381210, + "ts": 1696941968245.204, "dur": 6.907, + "args": { + "External id": 4552237,"Record function id": 0, "Ev Idx": 556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941968248.227, "dur": 3.404, + "args": { + "External id": 4552238,"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": 1336753, "tid": 1381210, + "ts": 1696941968249.321, "dur": 1.865, + "args": { + "External id": 4552239,"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": 1336753, "tid": 1381210, + "ts": 1696941968250.072, "dur": 0.996, + "args": { + "External id": 4552240,"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": 1336753, "tid": 1381210, + "ts": 1696941968255.215, "dur": 8.025, + "args": { + "External id": 4552241,"Record function id": 0, "Sequence number": 45295750, "Fwd thread id": 1, "Ev Idx": 560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941968256.025, "dur": 5.103, + "args": { + "External id": 4552242,"Sequence number": 45295750, "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": 1336753, "tid": 1381210, "ts": 1696941968256.025, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941968257.354, "dur": 3.623, + "args": { + "External id": 4552243,"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": 1336753, "tid": 1381210, + "ts": 1696941968259.924, "dur": 0.895, + "args": { + "External id": 4552244,"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": 1336753, "tid": 1381210, + "ts": 1696941968266.307, "dur": 90.938, + "args": { + "External id": 4552245,"Record function id": 0, "Sequence number": 45295749, "Fwd thread id": 1, "Ev Idx": 564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941968267.050, "dur": 79.683, + "args": { + "External id": 4552246,"Sequence number": 45295749, "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": 1336753, "tid": 1381210, "ts": 1696941968267.050, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941968269.901, "dur": 2.069, + "args": { + "External id": 4552247,"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": 1336753, "tid": 1381210, + "ts": 1696941968270.527, "dur": 1.034, + "args": { + "External id": 4552248,"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": 1336753, "tid": 1381210, + "ts": 1696941968271.106, "dur": 0.336, + "args": { + "External id": 4552249,"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": 1336753, "tid": 1381210, + "ts": 1696941968272.854, "dur": 26.939, + "args": { + "External id": 4552250,"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": 1336753, "tid": 1381210, + "ts": 1696941968302.655, "dur": 4.601, + "args": { + "External id": 4552251,"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": 1336753, "tid": 1381210, + "ts": 1696941968303.326, "dur": 3.476, + "args": { + "External id": 4552252,"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": 1336753, "tid": 1381210, + "ts": 1696941968306.061, "dur": 0.622, + "args": { + "External id": 4552253,"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": 1336753, "tid": 1381210, + "ts": 1696941968308.448, "dur": 2.602, + "args": { + "External id": 4552254,"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": 1336753, "tid": 1381210, + "ts": 1696941968309.408, "dur": 1.189, + "args": { + "External id": 4552255,"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": 1336753, "tid": 1381210, + "ts": 1696941968310.132, "dur": 0.396, + "args": { + "External id": 4552256,"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": 1336753, "tid": 1381210, + "ts": 1696941968313.656, "dur": 32.483, + "args": { + "External id": 4552257,"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": 1336753, "tid": 1381210, + "ts": 1696941968361.730, "dur": 23.337, + "args": { + "External id": 4552258,"Record function id": 0, "Sequence number": 45295748, "Fwd thread id": 1, "Ev Idx": 577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941968362.669, "dur": 3.289, + "args": { + "External id": 4552259,"Sequence number": 45295748, "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": 1336753, "tid": 1381210, "ts": 1696941968362.669, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941968364.284, "dur": 1.511, + "args": { + "External id": 4552260,"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": 1336753, "tid": 1381210, + "ts": 1696941968364.754, "dur": 0.902, + "args": { + "External id": 4552261,"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": 1336753, "tid": 1381210, + "ts": 1696941968368.365, "dur": 14.476, + "args": { + "External id": 4552262,"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": 1336753, "tid": 1381210, + "ts": 1696941968388.716, "dur": 12.144, + "args": { + "External id": 4552263,"Record function id": 0, "Sequence number": 45295747, "Fwd thread id": 1, "Ev Idx": 582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941968389.658, "dur": 9.416, + "args": { + "External id": 4552264,"Sequence number": 45295747, "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": 1336753, "tid": 1381210, "ts": 1696941968389.658, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941968390.446, "dur": 8.414, + "args": { + "External id": 4552265,"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": 1336753, "tid": 1381210, + "ts": 1696941968393.251, "dur": 5.107, + "args": { + "External id": 4552266,"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": 1336753, "tid": 1381210, + "ts": 1696941968397.632, "dur": 0.611, + "args": { + "External id": 4552267,"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": 1336753, "tid": 1381210, + "ts": 1696941968404.643, "dur": 4.806, + "args": { + "External id": 4552268,"Record function id": 0, "Ev Idx": 587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941968405.840, "dur": 3.136, + "args": { + "External id": 4552269,"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": 1336753, "tid": 1381210, + "ts": 1696941968406.641, "dur": 2.065, + "args": { + "External id": 4552270,"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": 1336753, "tid": 1381210, + "ts": 1696941968407.263, "dur": 1.349, + "args": { + "External id": 4552271,"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": 1336753, "tid": 1381210, + "ts": 1696941968414.189, "dur": 398.722, + "args": { + "External id": 4552272,"Record function id": 0, "Sequence number": 45295746, "Fwd thread id": 1, "Ev Idx": 591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941968415.230, "dur": 364.694, + "args": { + "External id": 4552273,"Sequence number": 45295746, "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": 1336753, "tid": 1381210, "ts": 1696941968415.230, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941968451.171, "dur": 1.833, + "args": { + "External id": 4552274,"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": 1336753, "tid": 1381210, + "ts": 1696941968451.793, "dur": 1.052, + "args": { + "External id": 4552275,"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": 1336753, "tid": 1381210, + "ts": 1696941968471.395, "dur": 5.932, + "args": { + "External id": 4552276,"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": 1336753, "tid": 1381210, + "ts": 1696941968486.799, "dur": 1.895, + "args": { + "External id": 4552277,"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": 1336753, "tid": 1381210, + "ts": 1696941968671.223, "dur": 2.858, + "args": { + "External id": 4552278,"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": 1336753, "tid": 1381210, + "ts": 1696941968678.083, "dur": 38.745, + "args": { + "External id": 4552279,"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": 1336753, "tid": 1381210, + "ts": 1696941968691.873, "dur": 1.328, + "args": { + "External id": 4552280,"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": 1336753, "tid": 1381210, + "ts": 1696941968722.462, "dur": 30.384, + "args": { + "External id": 4552281,"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": 1336753, "tid": 1381210, + "ts": 1696941968724.785, "dur": 27.716, + "args": { + "External id": 4552282,"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": 1336753, "tid": 1381210, + "ts": 1696941968728.689, "dur": 5.426, + "args": { + "External id": 4552283,"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": 1336753, "tid": 1381210, + "ts": 1696941968735.439, "dur": 16.588, + "args": { + "External id": 4552284,"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": 1336753, "tid": 1381210, + "ts": 1696941968759.739, "dur": 2.270, + "args": { + "External id": 4552285,"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": 1336753, "tid": 1381210, + "ts": 1696941968760.810, "dur": 1.105, + "args": { + "External id": 4552286,"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": 1336753, "tid": 1381210, + "ts": 1696941968768.907, "dur": 3.766, + "args": { + "External id": 4552287,"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": 1336753, "tid": 1381210, + "ts": 1696941968771.647, "dur": 0.897, + "args": { + "External id": 4552288,"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": 1336753, "tid": 1381210, + "ts": 1696941968791.420, "dur": 16.078, + "args": { + "External id": 4552289,"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": 1336753, "tid": 1381210, + "ts": 1696941968824.502, "dur": 10.415, + "args": { + "External id": 4552290,"Record function id": 0, "Ev Idx": 609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941968826.614, "dur": 7.449, + "args": { + "External id": 4552291,"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": 1336753, "tid": 1381210, + "ts": 1696941968828.282, "dur": 4.862, + "args": { + "External id": 4552292,"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": 1336753, "tid": 1381210, + "ts": 1696941968831.162, "dur": 1.840, + "args": { + "External id": 4552293,"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": 1336753, "tid": 1381210, + "ts": 1696941968840.773, "dur": 7.899, + "args": { + "External id": 4552294,"Record function id": 0, "Sequence number": 45295745, "Fwd thread id": 1, "Ev Idx": 613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941968842.378, "dur": 1.571, + "args": { + "External id": 4552295,"Sequence number": 45295745, "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": 1336753, "tid": 1381210, "ts": 1696941968842.378, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941968852.597, "dur": 455.311, + "args": { + "External id": 4552296,"Record function id": 0, "Sequence number": 45295744, "Fwd thread id": 1, "Ev Idx": 615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941968853.760, "dur": 439.410, + "args": { + "External id": 4552297,"Sequence number": 45295744, "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": 1336753, "tid": 1381210, "ts": 1696941968853.760, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941968883.569, "dur": 8.017, + "args": { + "External id": 4552298,"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": 1336753, "tid": 1381210, + "ts": 1696941968888.703, "dur": 2.592, + "args": { + "External id": 4552299,"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": 1336753, "tid": 1381210, + "ts": 1696941968895.029, "dur": 10.141, + "args": { + "External id": 4552300,"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": 1336753, "tid": 1381210, + "ts": 1696941968896.229, "dur": 8.010, + "args": { + "External id": 4552301,"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": 1336753, "tid": 1381210, + "ts": 1696941968901.070, "dur": 2.991, + "args": { + "External id": 4552302,"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": 1336753, "tid": 1381210, + "ts": 1696941968908.482, "dur": 120.108, + "args": { + "External id": 4552303,"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": 1336753, "tid": 1381210, + "ts": 1696941968909.415, "dur": 2.144, + "args": { + "External id": 4552304,"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": 1336753, "tid": 1381210, + "ts": 1696941968909.927, "dur": 1.190, + "args": { + "External id": 4552305,"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": 1336753, "tid": 1381210, + "ts": 1696941968910.707, "dur": 0.328, + "args": { + "External id": 4552306,"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": 1336753, "tid": 1381210, + "ts": 1696941968912.630, "dur": 115.164, + "args": { + "External id": 4552307,"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": 1336753, "tid": 1381210, + "ts": 1696941968915.790, "dur": 110.453, + "args": { + "External id": 4552308,"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": 1336753, "tid": 1381210, + "ts": 1696941969034.233, "dur": 3.669, + "args": { + "External id": 4552309,"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": 1336753, "tid": 1381210, + "ts": 1696941969035.930, "dur": 1.879, + "args": { + "External id": 4552310,"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": 1336753, "tid": 1381210, + "ts": 1696941969072.826, "dur": 5.725, + "args": { + "External id": 4552311,"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": 1336753, "tid": 1381210, + "ts": 1696941969079.502, "dur": 2.047, + "args": { + "External id": 4552312,"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": 1336753, "tid": 1381210, + "ts": 1696941969082.213, "dur": 1.800, + "args": { + "External id": 4552313,"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": 1336753, "tid": 1381210, + "ts": 1696941969120.437, "dur": 2.041, + "args": { + "External id": 4552314,"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": 1336753, "tid": 1381210, + "ts": 1696941969121.255, "dur": 1.063, + "args": { + "External id": 4552315,"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": 1336753, "tid": 1381210, + "ts": 1696941969148.681, "dur": 125.933, + "args": { + "External id": 4552316,"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": 1336753, "tid": 1381210, + "ts": 1696941969154.350, "dur": 6.460, + "args": { + "External id": 4552317,"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": 1336753, "tid": 1381210, + "ts": 1696941969157.337, "dur": 2.726, + "args": { + "External id": 4552318,"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": 1336753, "tid": 1381210, + "ts": 1696941969161.949, "dur": 8.111, + "args": { + "External id": 4552319,"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": 1336753, "tid": 1381210, + "ts": 1696941969168.577, "dur": 0.653, + "args": { + "External id": 4552320,"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": 1336753, "tid": 1381210, + "ts": 1696941969171.656, "dur": 3.384, + "args": { + "External id": 4552321,"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": 1336753, "tid": 1381210, + "ts": 1696941969174.309, "dur": 0.398, + "args": { + "External id": 4552322,"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": 1336753, "tid": 1381210, + "ts": 1696941969175.597, "dur": 3.481, + "args": { + "External id": 4552323,"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": 1336753, "tid": 1381210, + "ts": 1696941969178.044, "dur": 0.555, + "args": { + "External id": 4552324,"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": 1336753, "tid": 1381210, + "ts": 1696941969183.990, "dur": 1.832, + "args": { + "External id": 4552325,"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": 1336753, "tid": 1381210, + "ts": 1696941969185.125, "dur": 0.390, + "args": { + "External id": 4552326,"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": 1336753, "tid": 1381210, + "ts": 1696941969188.890, "dur": 5.020, + "args": { + "External id": 4552327,"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": 1336753, "tid": 1381210, + "ts": 1696941969191.696, "dur": 2.039, + "args": { + "External id": 4552328,"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": 1336753, "tid": 1381210, + "ts": 1696941969196.528, "dur": 1.258, + "args": { + "External id": 4552329,"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": 1336753, "tid": 1381210, + "ts": 1696941969197.216, "dur": 0.269, + "args": { + "External id": 4552330,"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": 1336753, "tid": 1381210, + "ts": 1696941969198.223, "dur": 5.794, + "args": { + "External id": 4552331,"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": 1336753, "tid": 1381210, + "ts": 1696941969200.890, "dur": 3.037, + "args": { + "External id": 4552332,"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": 1336753, "tid": 1381210, + "ts": 1696941969205.181, "dur": 55.689, + "args": { + "External id": 4552333,"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": 1336753, "tid": 1381210, + "ts": 1696941969264.642, "dur": 1.357, + "args": { + "External id": 4552334,"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": 1336753, "tid": 1381210, + "ts": 1696941969266.520, "dur": 4.035, + "args": { + "External id": 4552335,"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": 1336753, "tid": 1381210, + "ts": 1696941969269.330, "dur": 0.462, + "args": { + "External id": 4552336,"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": 1336753, "tid": 1381210, + "ts": 1696941969272.712, "dur": 0.744, + "args": { + "External id": 4552337,"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": 1336753, "tid": 1381210, + "ts": 1696941969319.439, "dur": 8.312, + "args": { + "External id": 4552338,"Record function id": 0, "Ev Idx": 657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941969321.665, "dur": 5.460, + "args": { + "External id": 4552339,"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": 1336753, "tid": 1381210, + "ts": 1696941969323.495, "dur": 2.800, + "args": { + "External id": 4552340,"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": 1336753, "tid": 1381210, + "ts": 1696941969324.372, "dur": 1.839, + "args": { + "External id": 4552341,"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": 1336753, "tid": 1381210, + "ts": 1696941969331.981, "dur": 9.655, + "args": { + "External id": 4552342,"Record function id": 0, "Sequence number": 45295743, "Fwd thread id": 1, "Ev Idx": 661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941969332.979, "dur": 5.597, + "args": { + "External id": 4552343,"Sequence number": 45295743, "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": 1336753, "tid": 1381210, "ts": 1696941969332.979, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941969334.784, "dur": 3.578, + "args": { + "External id": 4552344,"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": 1336753, "tid": 1381210, + "ts": 1696941969337.479, "dur": 0.746, + "args": { + "External id": 4552345,"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": 1336753, "tid": 1381210, + "ts": 1696941969345.223, "dur": 122.306, + "args": { + "External id": 4552346,"Record function id": 0, "Sequence number": 45295742, "Fwd thread id": 1, "Ev Idx": 665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941969345.965, "dur": 115.216, + "args": { + "External id": 4552347,"Sequence number": 45295742, "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": 1336753, "tid": 1381210, "ts": 1696941969345.965, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941969349.300, "dur": 5.587, + "args": { + "External id": 4552348,"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": 1336753, "tid": 1381210, + "ts": 1696941969350.608, "dur": 3.741, + "args": { + "External id": 4552349,"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": 1336753, "tid": 1381210, + "ts": 1696941969353.557, "dur": 0.628, + "args": { + "External id": 4552350,"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": 1336753, "tid": 1381210, + "ts": 1696941969356.223, "dur": 40.396, + "args": { + "External id": 4552351,"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": 1336753, "tid": 1381210, + "ts": 1696941969399.903, "dur": 4.000, + "args": { + "External id": 4552352,"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": 1336753, "tid": 1381210, + "ts": 1696941969400.778, "dur": 2.145, + "args": { + "External id": 4552353,"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": 1336753, "tid": 1381210, + "ts": 1696941969401.860, "dur": 0.892, + "args": { + "External id": 4552354,"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": 1336753, "tid": 1381210, + "ts": 1696941969405.686, "dur": 5.155, + "args": { + "External id": 4552355,"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": 1336753, "tid": 1381210, + "ts": 1696941969406.735, "dur": 3.449, + "args": { + "External id": 4552356,"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": 1336753, "tid": 1381210, + "ts": 1696941969407.424, "dur": 2.659, + "args": { + "External id": 4552357,"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": 1336753, "tid": 1381210, + "ts": 1696941969413.044, "dur": 47.374, + "args": { + "External id": 4552358,"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": 1336753, "tid": 1381210, + "ts": 1696941969472.268, "dur": 7.647, + "args": { + "External id": 4552359,"Record function id": 0, "Sequence number": 45295741, "Fwd thread id": 1, "Ev Idx": 678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941969473.140, "dur": 5.215, + "args": { + "External id": 4552360,"Sequence number": 45295741, "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": 1336753, "tid": 1381210, "ts": 1696941969473.140, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941969476.400, "dur": 1.820, + "args": { + "External id": 4552361,"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": 1336753, "tid": 1381210, + "ts": 1696941969477.040, "dur": 1.019, + "args": { + "External id": 4552362,"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": 1336753, "tid": 1381210, + "ts": 1696941969483.527, "dur": 8.167, + "args": { + "External id": 4552363,"Record function id": 0, "Sequence number": 45295740, "Fwd thread id": 1, "Ev Idx": 682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941969484.435, "dur": 4.309, + "args": { + "External id": 4552364,"Sequence number": 45295740, "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": 1336753, "tid": 1381210, "ts": 1696941969484.435, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941969485.793, "dur": 2.765, + "args": { + "External id": 4552365,"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": 1336753, "tid": 1381210, + "ts": 1696941969486.425, "dur": 1.686, + "args": { + "External id": 4552366,"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": 1336753, "tid": 1381210, + "ts": 1696941969487.458, "dur": 0.535, + "args": { + "External id": 4552367,"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": 1336753, "tid": 1381210, + "ts": 1696941969495.539, "dur": 6.225, + "args": { + "External id": 4552368,"Record function id": 0, "Ev Idx": 687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941969496.564, "dur": 4.740, + "args": { + "External id": 4552369,"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": 1336753, "tid": 1381210, + "ts": 1696941969497.439, "dur": 3.633, + "args": { + "External id": 4552370,"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": 1336753, "tid": 1381210, + "ts": 1696941969499.872, "dur": 1.100, + "args": { + "External id": 4552371,"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": 1336753, "tid": 1381210, + "ts": 1696941969505.152, "dur": 7.511, + "args": { + "External id": 4552372,"Record function id": 0, "Sequence number": 45295739, "Fwd thread id": 1, "Ev Idx": 691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941969508.015, "dur": 2.371, + "args": { + "External id": 4552373,"Sequence number": 45295739, "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": 1336753, "tid": 1381210, "ts": 1696941969508.015, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941969508.983, "dur": 1.261, + "args": { + "External id": 4552374,"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": 1336753, "tid": 1381210, + "ts": 1696941969509.555, "dur": 0.577, + "args": { + "External id": 4552375,"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": 1336753, "tid": 1381210, + "ts": 1696941969515.828, "dur": 144.697, + "args": { + "External id": 4552376,"Record function id": 0, "Sequence number": 45295738, "Fwd thread id": 1, "Ev Idx": 695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941969516.659, "dur": 133.278, + "args": { + "External id": 4552377,"Sequence number": 45295738, "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": 1336753, "tid": 1381210, "ts": 1696941969516.659, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941969520.498, "dur": 23.551, + "args": { + "External id": 4552378,"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": 1336753, "tid": 1381210, + "ts": 1696941969522.997, "dur": 20.287, + "args": { + "External id": 4552379,"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": 1336753, "tid": 1381210, + "ts": 1696941969541.903, "dur": 0.992, + "args": { + "External id": 4552380,"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": 1336753, "tid": 1381210, + "ts": 1696941969545.189, "dur": 42.276, + "args": { + "External id": 4552381,"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": 1336753, "tid": 1381210, + "ts": 1696941969588.883, "dur": 6.771, + "args": { + "External id": 4552382,"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": 1336753, "tid": 1381210, + "ts": 1696941969589.708, "dur": 5.431, + "args": { + "External id": 4552383,"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": 1336753, "tid": 1381210, + "ts": 1696941969590.814, "dur": 4.163, + "args": { + "External id": 4552384,"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": 1336753, "tid": 1381210, + "ts": 1696941969598.837, "dur": 4.610, + "args": { + "External id": 4552385,"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": 1336753, "tid": 1381210, + "ts": 1696941969599.663, "dur": 3.133, + "args": { + "External id": 4552386,"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": 1336753, "tid": 1381210, + "ts": 1696941969602.069, "dur": 0.660, + "args": { + "External id": 4552387,"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": 1336753, "tid": 1381210, + "ts": 1696941969603.927, "dur": 45.298, + "args": { + "External id": 4552388,"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": 1336753, "tid": 1381210, + "ts": 1696941969666.590, "dur": 30.212, + "args": { + "External id": 4552389,"Record function id": 0, "Sequence number": 45295737, "Fwd thread id": 1, "Ev Idx": 708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941969667.737, "dur": 3.773, + "args": { + "External id": 4552390,"Sequence number": 45295737, "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": 1336753, "tid": 1381210, "ts": 1696941969667.737, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941969669.197, "dur": 2.187, + "args": { + "External id": 4552391,"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": 1336753, "tid": 1381210, + "ts": 1696941969669.808, "dur": 1.422, + "args": { + "External id": 4552392,"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": 1336753, "tid": 1381210, + "ts": 1696941969674.427, "dur": 19.694, + "args": { + "External id": 4552393,"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": 1336753, "tid": 1381210, + "ts": 1696941969700.528, "dur": 12.889, + "args": { + "External id": 4552394,"Record function id": 0, "Sequence number": 45295736, "Fwd thread id": 1, "Ev Idx": 713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941969703.510, "dur": 6.938, + "args": { + "External id": 4552395,"Sequence number": 45295736, "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": 1336753, "tid": 1381210, "ts": 1696941969703.510, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941969704.778, "dur": 5.452, + "args": { + "External id": 4552396,"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": 1336753, "tid": 1381210, + "ts": 1696941969705.468, "dur": 4.288, + "args": { + "External id": 4552397,"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": 1336753, "tid": 1381210, + "ts": 1696941969709.088, "dur": 0.553, + "args": { + "External id": 4552398,"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": 1336753, "tid": 1381210, + "ts": 1696941969717.768, "dur": 5.363, + "args": { + "External id": 4552399,"Record function id": 0, "Ev Idx": 718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941969719.104, "dur": 3.488, + "args": { + "External id": 4552400,"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": 1336753, "tid": 1381210, + "ts": 1696941969720.454, "dur": 1.691, + "args": { + "External id": 4552401,"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": 1336753, "tid": 1381210, + "ts": 1696941969720.987, "dur": 1.027, + "args": { + "External id": 4552402,"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": 1336753, "tid": 1381210, + "ts": 1696941969729.283, "dur": 463.473, + "args": { + "External id": 4552403,"Record function id": 0, "Sequence number": 45295735, "Fwd thread id": 1, "Ev Idx": 722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941969730.560, "dur": 426.113, + "args": { + "External id": 4552404,"Sequence number": 45295735, "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": 1336753, "tid": 1381210, "ts": 1696941969730.560, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1381210, + "ts": 1696941969752.906, "dur": 32.487, + "args": { + "External id": 4552405,"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": 1336753, "tid": 1381210, + "ts": 1696941969754.440, "dur": 30.756, + "args": { + "External id": 4552406,"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": 1336753, "tid": 1381210, + "ts": 1696941969757.072, "dur": 7.040, + "args": { + "External id": 4552407,"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": 1336753, "tid": 1381210, + "ts": 1696941969760.957, "dur": 2.706, + "args": { + "External id": 4552408,"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": 1336753, "tid": 1381210, + "ts": 1696941969765.268, "dur": 19.502, + "args": { + "External id": 4552409,"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": 1336753, "tid": 1381210, + "ts": 1696941969797.925, "dur": 4.093, + "args": { + "External id": 4552410,"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": 1336753, "tid": 1381210, + "ts": 1696941969798.737, "dur": 3.132, + "args": { + "External id": 4552411,"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": 1336753, "tid": 1381210, + "ts": 1696941969805.485, "dur": 1.467, + "args": { + "External id": 4552412,"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": 1336753, "tid": 1381210, + "ts": 1696941969806.164, "dur": 0.698, + "args": { + "External id": 4552413,"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": 1336753, "tid": 1381210, + "ts": 1696941969820.505, "dur": 2.189, + "args": { + "External id": 4552414,"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": 1336753, "tid": 1381210, + "ts": 1696941969832.939, "dur": 2.463, + "args": { + "External id": 4552415,"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": 1336753, "tid": 1381210, + "ts": 1696941970042.643, "dur": 3.673, + "args": { + "External id": 4552416,"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": 1336753, "tid": 1381210, + "ts": 1696941970050.628, "dur": 32.379, + "args": { + "External id": 4552417,"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": 1336753, "tid": 1381210, + "ts": 1696941970059.945, "dur": 1.073, + "args": { + "External id": 4552418,"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": 1336753, "tid": 1381210, + "ts": 1696941970088.735, "dur": 31.320, + "args": { + "External id": 4552419,"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": 1336753, "tid": 1381210, + "ts": 1696941970090.495, "dur": 29.296, + "args": { + "External id": 4552420,"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": 1336753, "tid": 1381210, + "ts": 1696941970096.287, "dur": 4.709, + "args": { + "External id": 4552421,"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": 1336753, "tid": 1381210, + "ts": 1696941970103.977, "dur": 15.303, + "args": { + "External id": 4552422,"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": 1336753, "tid": 1381210, + "ts": 1696941970124.336, "dur": 2.178, + "args": { + "External id": 4552423,"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": 1336753, "tid": 1381210, + "ts": 1696941970125.385, "dur": 1.015, + "args": { + "External id": 4552424,"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": 1336753, "tid": 1381210, + "ts": 1696941970134.096, "dur": 4.630, + "args": { + "External id": 4552425,"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": 1336753, "tid": 1381210, + "ts": 1696941970134.819, "dur": 3.769, + "args": { + "External id": 4552426,"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": 1336753, "tid": 1381210, + "ts": 1696941970142.143, "dur": 1.981, + "args": { + "External id": 4552427,"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": 1336753, "tid": 1381210, + "ts": 1696941970142.752, "dur": 1.287, + "args": { + "External id": 4552428,"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": 1336753, "tid": 1381210, + "ts": 1696941970174.024, "dur": 17.179, + "args": { + "External id": 4552429,"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": 1336753, "tid": 1381210, + "ts": 1696941970206.035, "dur": 8.494, + "args": { + "External id": 4552430,"Record function id": 0, "Ev Idx": 749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941970208.017, "dur": 5.827, + "args": { + "External id": 4552431,"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": 1336753, "tid": 1381210, + "ts": 1696941970209.870, "dur": 2.972, + "args": { + "External id": 4552432,"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": 1336753, "tid": 1381210, + "ts": 1696941970210.878, "dur": 1.857, + "args": { + "External id": 4552433,"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": 1336753, "tid": 1381210, + "ts": 1696941970218.100, "dur": 7.541, + "args": { + "External id": 4552434,"Record function id": 0, "Sequence number": 45295734, "Fwd thread id": 1, "Ev Idx": 753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941970219.368, "dur": 3.733, + "args": { + "External id": 4552435,"Sequence number": 45295734, "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": 1336753, "tid": 1381210, "ts": 1696941970219.368, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941970221.028, "dur": 1.880, + "args": { + "External id": 4552436,"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": 1336753, "tid": 1381210, + "ts": 1696941970221.715, "dur": 1.072, + "args": { + "External id": 4552437,"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": 1336753, "tid": 1381210, + "ts": 1696941970231.123, "dur": 127.169, + "args": { + "External id": 4552438,"Record function id": 0, "Sequence number": 45295733, "Fwd thread id": 1, "Ev Idx": 757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941970231.958, "dur": 119.512, + "args": { + "External id": 4552439,"Sequence number": 45295733, "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": 1336753, "tid": 1381210, "ts": 1696941970231.958, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941970236.411, "dur": 6.259, + "args": { + "External id": 4552440,"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": 1336753, "tid": 1381210, + "ts": 1696941970237.747, "dur": 4.294, + "args": { + "External id": 4552441,"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": 1336753, "tid": 1381210, + "ts": 1696941970240.921, "dur": 0.908, + "args": { + "External id": 4552442,"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": 1336753, "tid": 1381210, + "ts": 1696941970244.175, "dur": 53.653, + "args": { + "External id": 4552443,"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": 1336753, "tid": 1381210, + "ts": 1696941970298.962, "dur": 7.328, + "args": { + "External id": 4552444,"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": 1336753, "tid": 1381210, + "ts": 1696941970302.240, "dur": 3.537, + "args": { + "External id": 4552445,"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": 1336753, "tid": 1381210, + "ts": 1696941970303.017, "dur": 2.617, + "args": { + "External id": 4552446,"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": 1336753, "tid": 1381210, + "ts": 1696941970308.200, "dur": 3.254, + "args": { + "External id": 4552447,"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": 1336753, "tid": 1381210, + "ts": 1696941970309.807, "dur": 1.079, + "args": { + "External id": 4552448,"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": 1336753, "tid": 1381210, + "ts": 1696941970310.400, "dur": 0.393, + "args": { + "External id": 4552449,"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": 1336753, "tid": 1381210, + "ts": 1696941970311.970, "dur": 38.751, + "args": { + "External id": 4552450,"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": 1336753, "tid": 1381210, + "ts": 1696941970362.988, "dur": 12.267, + "args": { + "External id": 4552451,"Record function id": 0, "Sequence number": 45295732, "Fwd thread id": 1, "Ev Idx": 770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941970365.874, "dur": 7.009, + "args": { + "External id": 4552452,"Sequence number": 45295732, "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": 1336753, "tid": 1381210, "ts": 1696941970365.874, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941970369.034, "dur": 3.702, + "args": { + "External id": 4552453,"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": 1336753, "tid": 1381210, + "ts": 1696941970369.594, "dur": 3.018, + "args": { + "External id": 4552454,"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": 1336753, "tid": 1381210, + "ts": 1696941970380.573, "dur": 6.823, + "args": { + "External id": 4552455,"Record function id": 0, "Sequence number": 45295731, "Fwd thread id": 1, "Ev Idx": 774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941970381.380, "dur": 3.832, + "args": { + "External id": 4552456,"Sequence number": 45295731, "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": 1336753, "tid": 1381210, "ts": 1696941970381.380, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941970382.370, "dur": 2.632, + "args": { + "External id": 4552457,"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": 1336753, "tid": 1381210, + "ts": 1696941970383.092, "dur": 1.421, + "args": { + "External id": 4552458,"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": 1336753, "tid": 1381210, + "ts": 1696941970383.720, "dur": 0.692, + "args": { + "External id": 4552459,"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": 1336753, "tid": 1381210, + "ts": 1696941970391.469, "dur": 7.850, + "args": { + "External id": 4552460,"Record function id": 0, "Ev Idx": 779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941970392.800, "dur": 6.020, + "args": { + "External id": 4552461,"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": 1336753, "tid": 1381210, + "ts": 1696941970393.826, "dur": 4.733, + "args": { + "External id": 4552462,"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": 1336753, "tid": 1381210, + "ts": 1696941970396.986, "dur": 1.414, + "args": { + "External id": 4552463,"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": 1336753, "tid": 1381210, + "ts": 1696941970402.742, "dur": 9.043, + "args": { + "External id": 4552464,"Record function id": 0, "Sequence number": 45295730, "Fwd thread id": 1, "Ev Idx": 783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941970403.636, "dur": 5.392, + "args": { + "External id": 4552465,"Sequence number": 45295730, "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": 1336753, "tid": 1381210, "ts": 1696941970403.636, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941970405.080, "dur": 3.812, + "args": { + "External id": 4552466,"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": 1336753, "tid": 1381210, + "ts": 1696941970407.661, "dur": 1.103, + "args": { + "External id": 4552467,"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": 1336753, "tid": 1381210, + "ts": 1696941970415.966, "dur": 317.503, + "args": { + "External id": 4552468,"Record function id": 0, "Sequence number": 45295729, "Fwd thread id": 1, "Ev Idx": 787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941970417.132, "dur": 291.381, + "args": { + "External id": 4552469,"Sequence number": 45295729, "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": 1336753, "tid": 1381210, "ts": 1696941970417.132, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1696941970433.842, "dur": 5.300, + "args": { + "External id": 4552470,"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": 1336753, "tid": 1381210, + "ts": 1696941970436.129, "dur": 2.651, + "args": { + "External id": 4552471,"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": 1336753, "tid": 1381210, + "ts": 1696941970441.350, "dur": 4.555, + "args": { + "External id": 4552472,"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": 1336753, "tid": 1381210, + "ts": 1696941970443.876, "dur": 1.861, + "args": { + "External id": 4552473,"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": 1336753, "tid": 1381210, + "ts": 1696941970447.364, "dur": 4.327, + "args": { + "External id": 4552474,"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": 1336753, "tid": 1381210, + "ts": 1696941970448.283, "dur": 3.170, + "args": { + "External id": 4552475,"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": 1336753, "tid": 1381210, + "ts": 1696941970477.027, "dur": 205.948, + "args": { + "External id": 4552476,"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": 1336753, "tid": 1381210, + "ts": 1696941970587.475, "dur": 4.381, + "args": { + "External id": 4552477,"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": 1336753, "tid": 1381210, + "ts": 1696941970593.670, "dur": 4.159, + "args": { + "External id": 4552478,"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": 1336753, "tid": 1381210, + "ts": 1696941970695.572, "dur": 3.850, + "args": { + "External id": 4552479,"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": 1336753, "tid": 1381210, + "ts": 1696941970702.294, "dur": 0.779, + "args": { + "External id": 4552480,"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": 1336753, "tid": 1381210, + "ts": 1696941970705.130, "dur": 0.604, + "args": { + "External id": 4552481,"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": 1336753, "tid": 1381210, + "ts": 1696941970742.907, "dur": 219.258, + "args": { + "External id": 4552482,"Record function id": 0, "Sequence number": 45295728, "Fwd thread id": 1, "Ev Idx": 801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941970744.416, "dur": 210.862, + "args": { + "External id": 4552483,"Sequence number": 45295728, "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": 1336753, "tid": 1381210, "ts": 1696941970744.416, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1696941970763.202, "dur": 43.174, + "args": { + "External id": 4552484,"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": 1336753, "tid": 1381210, + "ts": 1696941970765.720, "dur": 2.831, + "args": { + "External id": 4552485,"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": 1336753, "tid": 1381210, + "ts": 1696941970769.968, "dur": 35.767, + "args": { + "External id": 4552486,"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": 1336753, "tid": 1381210, + "ts": 1696941970815.308, "dur": 6.087, + "args": { + "External id": 4552487,"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": 1336753, "tid": 1381210, + "ts": 1696941970818.921, "dur": 2.128, + "args": { + "External id": 4552488,"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": 1336753, "tid": 1381210, + "ts": 1696941970969.062, "dur": 202.232, + "args": { + "External id": 4552489,"Record function id": 0, "Sequence number": 45295727, "Fwd thread id": 1, "Ev Idx": 808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941970970.901, "dur": 192.375, + "args": { + "External id": 4552490,"Sequence number": 45295727, "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": 1336753, "tid": 1381210, "ts": 1696941970970.901, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1696941970982.505, "dur": 75.406, + "args": { + "External id": 4552491,"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": 1336753, "tid": 1381210, + "ts": 1696941971022.677, "dur": 4.608, + "args": { + "External id": 4552492,"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": 1336753, "tid": 1381210, + "ts": 1696941971029.198, "dur": 28.229, + "args": { + "External id": 4552493,"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": 1336753, "tid": 1381210, + "ts": 1696941971065.822, "dur": 7.982, + "args": { + "External id": 4552494,"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": 1336753, "tid": 1381210, + "ts": 1696941971071.259, "dur": 2.250, + "args": { + "External id": 4552495,"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": 1336753, "tid": 1381210, + "ts": 1696941971179.396, "dur": 17.887, + "args": { + "External id": 4552496,"Record function id": 0, "Sequence number": 45295726, "Fwd thread id": 1, "Ev Idx": 815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971183.382, "dur": 10.816, + "args": { + "External id": 4552497,"Sequence number": 45295726, "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": 1336753, "tid": 1381210, "ts": 1696941971183.382, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941971185.672, "dur": 8.206, + "args": { + "External id": 4552498,"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": 1336753, "tid": 1381210, + "ts": 1696941971187.112, "dur": 6.602, + "args": { + "External id": 4552499,"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": 1336753, "tid": 1381210, + "ts": 1696941971200.764, "dur": 9.575, + "args": { + "External id": 4552500,"Record function id": 0, "Sequence number": 45295725, "Fwd thread id": 1, "Ev Idx": 819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971201.891, "dur": 5.722, + "args": { + "External id": 4552501,"Sequence number": 45295725, "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": 1336753, "tid": 1381210, "ts": 1696941971201.891, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941971203.470, "dur": 3.980, + "args": { + "External id": 4552502,"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": 1336753, "tid": 1381210, + "ts": 1696941971206.441, "dur": 0.907, + "args": { + "External id": 4552503,"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": 1336753, "tid": 1381210, + "ts": 1696941971215.397, "dur": 8.014, + "args": { + "External id": 4552504,"Record function id": 0, "Sequence number": 45295724, "Fwd thread id": 1, "Ev Idx": 823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971216.153, "dur": 5.299, + "args": { + "External id": 4552505,"Sequence number": 45295724, "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": 1336753, "tid": 1381210, "ts": 1696941971216.153, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941971217.486, "dur": 3.826, + "args": { + "External id": 4552506,"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": 1336753, "tid": 1381210, + "ts": 1696941971219.984, "dur": 1.246, + "args": { + "External id": 4552507,"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": 1336753, "tid": 1381210, + "ts": 1696941971226.742, "dur": 7.684, + "args": { + "External id": 4552508,"Record function id": 0, "Sequence number": 45295723, "Fwd thread id": 1, "Ev Idx": 827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971227.688, "dur": 4.693, + "args": { + "External id": 4552509,"Sequence number": 45295723, "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": 1336753, "tid": 1381210, "ts": 1696941971227.688, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941971228.633, "dur": 3.616, + "args": { + "External id": 4552510,"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": 1336753, "tid": 1381210, + "ts": 1696941971231.245, "dur": 0.882, + "args": { + "External id": 4552511,"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": 1336753, "tid": 1381210, + "ts": 1696941971237.975, "dur": 148.637, + "args": { + "External id": 4552512,"Record function id": 0, "Sequence number": 45295722, "Fwd thread id": 1, "Ev Idx": 831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971238.700, "dur": 139.189, + "args": { + "External id": 4552513,"Sequence number": 45295722, "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": 1336753, "tid": 1381210, "ts": 1696941971238.700, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941971244.485, "dur": 8.256, + "args": { + "External id": 4552514,"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": 1336753, "tid": 1381210, + "ts": 1696941971246.382, "dur": 5.639, + "args": { + "External id": 4552515,"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": 1336753, "tid": 1381210, + "ts": 1696941971250.261, "dur": 1.417, + "args": { + "External id": 4552516,"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": 1336753, "tid": 1381210, + "ts": 1696941971254.406, "dur": 64.057, + "args": { + "External id": 4552517,"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": 1336753, "tid": 1381210, + "ts": 1696941971319.627, "dur": 4.077, + "args": { + "External id": 4552518,"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": 1336753, "tid": 1381210, + "ts": 1696941971320.228, "dur": 2.502, + "args": { + "External id": 4552519,"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": 1336753, "tid": 1381210, + "ts": 1696941971321.350, "dur": 1.241, + "args": { + "External id": 4552520,"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": 1336753, "tid": 1381210, + "ts": 1696941971325.891, "dur": 7.409, + "args": { + "External id": 4552521,"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": 1336753, "tid": 1381210, + "ts": 1696941971327.504, "dur": 5.155, + "args": { + "External id": 4552522,"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": 1336753, "tid": 1381210, + "ts": 1696941971332.187, "dur": 0.399, + "args": { + "External id": 4552523,"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": 1336753, "tid": 1381210, + "ts": 1696941971334.183, "dur": 42.904, + "args": { + "External id": 4552524,"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": 1336753, "tid": 1381210, + "ts": 1696941971391.286, "dur": 6.972, + "args": { + "External id": 4552525,"Record function id": 0, "Sequence number": 45295721, "Fwd thread id": 1, "Ev Idx": 844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971392.265, "dur": 3.694, + "args": { + "External id": 4552526,"Sequence number": 45295721, "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": 1336753, "tid": 1381210, "ts": 1696941971392.265, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941971393.844, "dur": 1.987, + "args": { + "External id": 4552527,"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": 1336753, "tid": 1381210, + "ts": 1696941971394.627, "dur": 1.122, + "args": { + "External id": 4552528,"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": 1336753, "tid": 1381210, + "ts": 1696941971401.593, "dur": 9.158, + "args": { + "External id": 4552529,"Record function id": 0, "Sequence number": 45295720, "Fwd thread id": 1, "Ev Idx": 848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971402.673, "dur": 6.120, + "args": { + "External id": 4552530,"Sequence number": 45295720, "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": 1336753, "tid": 1381210, "ts": 1696941971402.673, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941971403.893, "dur": 4.703, + "args": { + "External id": 4552531,"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": 1336753, "tid": 1381210, + "ts": 1696941971406.688, "dur": 1.425, + "args": { + "External id": 4552532,"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": 1336753, "tid": 1381210, + "ts": 1696941971407.445, "dur": 0.564, + "args": { + "External id": 4552533,"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": 1336753, "tid": 1381210, + "ts": 1696941971418.653, "dur": 8.785, + "args": { + "External id": 4552534,"Record function id": 0, "Ev Idx": 853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941971420.258, "dur": 6.428, + "args": { + "External id": 4552535,"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": 1336753, "tid": 1381210, + "ts": 1696941971422.665, "dur": 3.624, + "args": { + "External id": 4552536,"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": 1336753, "tid": 1381210, + "ts": 1696941971423.652, "dur": 2.490, + "args": { + "External id": 4552537,"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": 1336753, "tid": 1381210, + "ts": 1696941971430.844, "dur": 6.688, + "args": { + "External id": 4552538,"Record function id": 0, "Sequence number": 45295719, "Fwd thread id": 1, "Ev Idx": 857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971431.669, "dur": 3.269, + "args": { + "External id": 4552539,"Sequence number": 45295719, "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": 1336753, "tid": 1381210, "ts": 1696941971431.669, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941971433.340, "dur": 1.451, + "args": { + "External id": 4552540,"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": 1336753, "tid": 1381210, + "ts": 1696941971433.955, "dur": 0.704, + "args": { + "External id": 4552541,"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": 1336753, "tid": 1381210, + "ts": 1696941971442.704, "dur": 107.641, + "args": { + "External id": 4552542,"Record function id": 0, "Sequence number": 45295718, "Fwd thread id": 1, "Ev Idx": 861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971443.625, "dur": 80.069, + "args": { + "External id": 4552543,"Sequence number": 45295718, "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": 1336753, "tid": 1381210, "ts": 1696941971443.625, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941971446.926, "dur": 2.372, + "args": { + "External id": 4552544,"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": 1336753, "tid": 1381210, + "ts": 1696941971447.485, "dur": 1.410, + "args": { + "External id": 4552545,"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": 1336753, "tid": 1381210, + "ts": 1696941971448.293, "dur": 0.492, + "args": { + "External id": 4552546,"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": 1336753, "tid": 1381210, + "ts": 1696941971450.009, "dur": 24.874, + "args": { + "External id": 4552547,"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": 1336753, "tid": 1381210, + "ts": 1696941971475.783, "dur": 7.214, + "args": { + "External id": 4552548,"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": 1336753, "tid": 1381210, + "ts": 1696941971478.457, "dur": 3.963, + "args": { + "External id": 4552549,"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": 1336753, "tid": 1381210, + "ts": 1696941971481.415, "dur": 0.871, + "args": { + "External id": 4552550,"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": 1336753, "tid": 1381210, + "ts": 1696941971484.130, "dur": 5.665, + "args": { + "External id": 4552551,"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": 1336753, "tid": 1381210, + "ts": 1696941971485.303, "dur": 4.021, + "args": { + "External id": 4552552,"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": 1336753, "tid": 1381210, + "ts": 1696941971486.246, "dur": 2.969, + "args": { + "External id": 4552553,"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": 1336753, "tid": 1381210, + "ts": 1696941971490.544, "dur": 32.551, + "args": { + "External id": 4552554,"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": 1336753, "tid": 1381210, + "ts": 1696941971557.338, "dur": 40.583, + "args": { + "External id": 4552555,"Record function id": 0, "Sequence number": 45295717, "Fwd thread id": 1, "Ev Idx": 874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971560.265, "dur": 6.646, + "args": { + "External id": 4552556,"Sequence number": 45295717, "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": 1336753, "tid": 1381210, "ts": 1696941971560.265, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941971561.902, "dur": 4.823, + "args": { + "External id": 4552557,"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": 1336753, "tid": 1381210, + "ts": 1696941971564.978, "dur": 1.648, + "args": { + "External id": 4552558,"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": 1336753, "tid": 1381210, + "ts": 1696941971570.134, "dur": 25.731, + "args": { + "External id": 4552559,"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": 1336753, "tid": 1381210, + "ts": 1696941971601.740, "dur": 9.916, + "args": { + "External id": 4552560,"Record function id": 0, "Sequence number": 45295716, "Fwd thread id": 1, "Ev Idx": 879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971602.946, "dur": 6.821, + "args": { + "External id": 4552561,"Sequence number": 45295716, "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": 1336753, "tid": 1381210, "ts": 1696941971602.946, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941971604.040, "dur": 5.532, + "args": { + "External id": 4552562,"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": 1336753, "tid": 1381210, + "ts": 1696941971605.176, "dur": 3.883, + "args": { + "External id": 4552563,"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": 1336753, "tid": 1381210, + "ts": 1696941971608.019, "dur": 0.921, + "args": { + "External id": 4552564,"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": 1336753, "tid": 1381210, + "ts": 1696941971616.010, "dur": 5.947, + "args": { + "External id": 4552565,"Record function id": 0, "Ev Idx": 884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941971617.149, "dur": 4.288, + "args": { + "External id": 4552566,"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": 1336753, "tid": 1381210, + "ts": 1696941971618.412, "dur": 2.693, + "args": { + "External id": 4552567,"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": 1336753, "tid": 1381210, + "ts": 1696941971619.175, "dur": 1.840, + "args": { + "External id": 4552568,"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": 1336753, "tid": 1381210, + "ts": 1696941971625.186, "dur": 8.996, + "args": { + "External id": 4552569,"Record function id": 0, "Sequence number": 45295715, "Fwd thread id": 1, "Ev Idx": 888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971626.113, "dur": 5.406, + "args": { + "External id": 4552570,"Sequence number": 45295715, "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": 1336753, "tid": 1381210, "ts": 1696941971626.113, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941971627.708, "dur": 3.630, + "args": { + "External id": 4552571,"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": 1336753, "tid": 1381210, + "ts": 1696941971630.467, "dur": 0.764, + "args": { + "External id": 4552572,"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": 1336753, "tid": 1381210, + "ts": 1696941971639.561, "dur": 116.872, + "args": { + "External id": 4552573,"Record function id": 0, "Sequence number": 45295714, "Fwd thread id": 1, "Ev Idx": 892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971642.189, "dur": 105.136, + "args": { + "External id": 4552574,"Sequence number": 45295714, "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": 1336753, "tid": 1381210, "ts": 1696941971642.189, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941971645.415, "dur": 2.012, + "args": { + "External id": 4552575,"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": 1336753, "tid": 1381210, + "ts": 1696941971645.857, "dur": 1.140, + "args": { + "External id": 4552576,"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": 1336753, "tid": 1381210, + "ts": 1696941971646.509, "dur": 0.390, + "args": { + "External id": 4552577,"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": 1336753, "tid": 1381210, + "ts": 1696941971648.355, "dur": 30.912, + "args": { + "External id": 4552578,"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": 1336753, "tid": 1381210, + "ts": 1696941971680.085, "dur": 5.007, + "args": { + "External id": 4552579,"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": 1336753, "tid": 1381210, + "ts": 1696941971680.626, "dur": 4.006, + "args": { + "External id": 4552580,"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": 1336753, "tid": 1381210, + "ts": 1696941971683.409, "dur": 1.111, + "args": { + "External id": 4552581,"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": 1336753, "tid": 1381210, + "ts": 1696941971686.638, "dur": 6.782, + "args": { + "External id": 4552582,"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": 1336753, "tid": 1381210, + "ts": 1696941971689.716, "dur": 3.242, + "args": { + "External id": 4552583,"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": 1336753, "tid": 1381210, + "ts": 1696941971692.493, "dur": 0.395, + "args": { + "External id": 4552584,"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": 1336753, "tid": 1381210, + "ts": 1696941971693.806, "dur": 52.750, + "args": { + "External id": 4552585,"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": 1336753, "tid": 1381210, + "ts": 1696941971760.780, "dur": 25.711, + "args": { + "External id": 4552586,"Record function id": 0, "Sequence number": 45295713, "Fwd thread id": 1, "Ev Idx": 905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971761.761, "dur": 5.065, + "args": { + "External id": 4552587,"Sequence number": 45295713, "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": 1336753, "tid": 1381210, "ts": 1696941971761.761, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941971764.902, "dur": 1.783, + "args": { + "External id": 4552588,"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": 1336753, "tid": 1381210, + "ts": 1696941971765.577, "dur": 1.000, + "args": { + "External id": 4552589,"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": 1336753, "tid": 1381210, + "ts": 1696941971768.956, "dur": 15.290, + "args": { + "External id": 4552590,"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": 1336753, "tid": 1381210, + "ts": 1696941971790.171, "dur": 9.635, + "args": { + "External id": 4552591,"Record function id": 0, "Sequence number": 45295712, "Fwd thread id": 1, "Ev Idx": 910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941971791.320, "dur": 5.953, + "args": { + "External id": 4552592,"Sequence number": 45295712, "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": 1336753, "tid": 1381210, "ts": 1696941971791.320, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941971792.033, "dur": 5.038, + "args": { + "External id": 4552593,"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": 1336753, "tid": 1381210, + "ts": 1696941971792.786, "dur": 3.773, + "args": { + "External id": 4552594,"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": 1336753, "tid": 1381210, + "ts": 1696941971795.598, "dur": 0.856, + "args": { + "External id": 4552595,"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": 1336753, "tid": 1381210, + "ts": 1696941971803.605, "dur": 7.081, + "args": { + "External id": 4552596,"Record function id": 0, "Ev Idx": 915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941971804.722, "dur": 5.464, + "args": { + "External id": 4552597,"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": 1336753, "tid": 1381210, + "ts": 1696941971805.848, "dur": 4.084, + "args": { + "External id": 4552598,"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": 1336753, "tid": 1381210, + "ts": 1696941971808.518, "dur": 1.350, + "args": { + "External id": 4552599,"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": 1336753, "tid": 1381210, + "ts": 1696941971815.131, "dur": 412.186, + "args": { + "External id": 4552600,"Record function id": 0, "Sequence number": 45295711, "Fwd thread id": 1, "Ev Idx": 919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941971816.238, "dur": 379.999, + "args": { + "External id": 4552601,"Sequence number": 45295711, "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": 1336753, "tid": 1381210, "ts": 1696941971816.238, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941971850.976, "dur": 2.054, + "args": { + "External id": 4552602,"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": 1336753, "tid": 1381210, + "ts": 1696941971851.654, "dur": 1.276, + "args": { + "External id": 4552603,"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": 1336753, "tid": 1381210, + "ts": 1696941971866.684, "dur": 6.221, + "args": { + "External id": 4552604,"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": 1336753, "tid": 1381210, + "ts": 1696941971883.179, "dur": 1.893, + "args": { + "External id": 4552605,"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": 1336753, "tid": 1381210, + "ts": 1696941972083.838, "dur": 3.765, + "args": { + "External id": 4552606,"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": 1336753, "tid": 1381210, + "ts": 1696941972091.898, "dur": 37.521, + "args": { + "External id": 4552607,"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": 1336753, "tid": 1381210, + "ts": 1696941972104.389, "dur": 1.086, + "args": { + "External id": 4552608,"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": 1336753, "tid": 1381210, + "ts": 1696941972138.589, "dur": 32.298, + "args": { + "External id": 4552609,"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": 1336753, "tid": 1381210, + "ts": 1696941972140.742, "dur": 29.898, + "args": { + "External id": 4552610,"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": 1336753, "tid": 1381210, + "ts": 1696941972146.975, "dur": 6.018, + "args": { + "External id": 4552611,"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": 1336753, "tid": 1381210, + "ts": 1696941972154.369, "dur": 15.758, + "args": { + "External id": 4552612,"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": 1336753, "tid": 1381210, + "ts": 1696941972176.939, "dur": 2.611, + "args": { + "External id": 4552613,"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": 1336753, "tid": 1381210, + "ts": 1696941972178.302, "dur": 1.118, + "args": { + "External id": 4552614,"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": 1336753, "tid": 1381210, + "ts": 1696941972186.539, "dur": 2.487, + "args": { + "External id": 4552615,"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": 1336753, "tid": 1381210, + "ts": 1696941972187.751, "dur": 1.189, + "args": { + "External id": 4552616,"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": 1336753, "tid": 1381210, + "ts": 1696941972208.129, "dur": 15.459, + "args": { + "External id": 4552617,"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": 1336753, "tid": 1381210, + "ts": 1696941972239.825, "dur": 12.449, + "args": { + "External id": 4552618,"Record function id": 0, "Ev Idx": 937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941972243.848, "dur": 7.705, + "args": { + "External id": 4552619,"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": 1336753, "tid": 1381210, + "ts": 1696941972246.230, "dur": 4.279, + "args": { + "External id": 4552620,"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": 1336753, "tid": 1381210, + "ts": 1696941972248.707, "dur": 1.705, + "args": { + "External id": 4552621,"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": 1336753, "tid": 1381210, + "ts": 1696941972255.907, "dur": 7.488, + "args": { + "External id": 4552622,"Record function id": 0, "Sequence number": 45295710, "Fwd thread id": 1, "Ev Idx": 941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941972257.635, "dur": 1.870, + "args": { + "External id": 4552623,"Sequence number": 45295710, "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": 1336753, "tid": 1381210, "ts": 1696941972257.635, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941972267.504, "dur": 450.808, + "args": { + "External id": 4552624,"Record function id": 0, "Sequence number": 45295709, "Fwd thread id": 1, "Ev Idx": 943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941972268.565, "dur": 434.427, + "args": { + "External id": 4552625,"Sequence number": 45295709, "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": 1336753, "tid": 1381210, "ts": 1696941972268.565, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941972298.325, "dur": 8.025, + "args": { + "External id": 4552626,"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": 1336753, "tid": 1381210, + "ts": 1696941972303.330, "dur": 2.795, + "args": { + "External id": 4552627,"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": 1336753, "tid": 1381210, + "ts": 1696941972309.948, "dur": 10.352, + "args": { + "External id": 4552628,"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": 1336753, "tid": 1381210, + "ts": 1696941972313.367, "dur": 6.326, + "args": { + "External id": 4552629,"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": 1336753, "tid": 1381210, + "ts": 1696941972316.663, "dur": 2.809, + "args": { + "External id": 4552630,"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": 1336753, "tid": 1381210, + "ts": 1696941972323.745, "dur": 98.288, + "args": { + "External id": 4552631,"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": 1336753, "tid": 1381210, + "ts": 1696941972324.515, "dur": 2.075, + "args": { + "External id": 4552632,"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": 1336753, "tid": 1381210, + "ts": 1696941972325.139, "dur": 1.033, + "args": { + "External id": 4552633,"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": 1336753, "tid": 1381210, + "ts": 1696941972325.743, "dur": 0.337, + "args": { + "External id": 4552634,"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": 1336753, "tid": 1381210, + "ts": 1696941972329.858, "dur": 91.666, + "args": { + "External id": 4552635,"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": 1336753, "tid": 1381210, + "ts": 1696941972330.962, "dur": 89.730, + "args": { + "External id": 4552636,"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": 1336753, "tid": 1381210, + "ts": 1696941972425.814, "dur": 2.126, + "args": { + "External id": 4552637,"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": 1336753, "tid": 1381210, + "ts": 1696941972426.575, "dur": 1.218, + "args": { + "External id": 4552638,"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": 1336753, "tid": 1381210, + "ts": 1696941972457.805, "dur": 4.888, + "args": { + "External id": 4552639,"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": 1336753, "tid": 1381210, + "ts": 1696941972465.575, "dur": 2.201, + "args": { + "External id": 4552640,"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": 1336753, "tid": 1381210, + "ts": 1696941972468.385, "dur": 2.521, + "args": { + "External id": 4552641,"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": 1336753, "tid": 1381210, + "ts": 1696941972502.986, "dur": 2.491, + "args": { + "External id": 4552642,"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": 1336753, "tid": 1381210, + "ts": 1696941972503.719, "dur": 1.630, + "args": { + "External id": 4552643,"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": 1336753, "tid": 1381210, + "ts": 1696941972546.812, "dur": 136.999, + "args": { + "External id": 4552644,"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": 1336753, "tid": 1381210, + "ts": 1696941972552.070, "dur": 9.510, + "args": { + "External id": 4552645,"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": 1336753, "tid": 1381210, + "ts": 1696941972557.250, "dur": 3.370, + "args": { + "External id": 4552646,"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": 1336753, "tid": 1381210, + "ts": 1696941972563.246, "dur": 7.590, + "args": { + "External id": 4552647,"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": 1336753, "tid": 1381210, + "ts": 1696941972569.413, "dur": 0.486, + "args": { + "External id": 4552648,"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": 1336753, "tid": 1381210, + "ts": 1696941972572.575, "dur": 1.608, + "args": { + "External id": 4552649,"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": 1336753, "tid": 1381210, + "ts": 1696941972573.479, "dur": 0.373, + "args": { + "External id": 4552650,"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": 1336753, "tid": 1381210, + "ts": 1696941972576.903, "dur": 2.228, + "args": { + "External id": 4552651,"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": 1336753, "tid": 1381210, + "ts": 1696941972578.160, "dur": 0.439, + "args": { + "External id": 4552652,"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": 1336753, "tid": 1381210, + "ts": 1696941972586.708, "dur": 1.759, + "args": { + "External id": 4552653,"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": 1336753, "tid": 1381210, + "ts": 1696941972587.747, "dur": 0.420, + "args": { + "External id": 4552654,"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": 1336753, "tid": 1381210, + "ts": 1696941972589.197, "dur": 7.579, + "args": { + "External id": 4552655,"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": 1336753, "tid": 1381210, + "ts": 1696941972594.651, "dur": 1.937, + "args": { + "External id": 4552656,"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": 1336753, "tid": 1381210, + "ts": 1696941972597.341, "dur": 3.726, + "args": { + "External id": 4552657,"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": 1336753, "tid": 1381210, + "ts": 1696941972600.344, "dur": 0.476, + "args": { + "External id": 4552658,"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": 1336753, "tid": 1381210, + "ts": 1696941972601.447, "dur": 4.052, + "args": { + "External id": 4552659,"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": 1336753, "tid": 1381210, + "ts": 1696941972602.005, "dur": 3.379, + "args": { + "External id": 4552660,"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": 1336753, "tid": 1381210, + "ts": 1696941972606.771, "dur": 61.801, + "args": { + "External id": 4552661,"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": 1336753, "tid": 1381210, + "ts": 1696941972674.076, "dur": 1.394, + "args": { + "External id": 4552662,"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": 1336753, "tid": 1381210, + "ts": 1696941972675.981, "dur": 3.752, + "args": { + "External id": 4552663,"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": 1336753, "tid": 1381210, + "ts": 1696941972678.648, "dur": 0.481, + "args": { + "External id": 4552664,"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": 1336753, "tid": 1381210, + "ts": 1696941972681.771, "dur": 0.925, + "args": { + "External id": 4552665,"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": 1336753, "tid": 1381210, + "ts": 1696941972729.591, "dur": 8.084, + "args": { + "External id": 4552666,"Record function id": 0, "Ev Idx": 985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941972731.770, "dur": 5.294, + "args": { + "External id": 4552667,"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": 1336753, "tid": 1381210, + "ts": 1696941972733.504, "dur": 2.633, + "args": { + "External id": 4552668,"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": 1336753, "tid": 1381210, + "ts": 1696941972734.391, "dur": 1.663, + "args": { + "External id": 4552669,"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": 1336753, "tid": 1381210, + "ts": 1696941972741.287, "dur": 6.748, + "args": { + "External id": 4552670,"Record function id": 0, "Sequence number": 45295708, "Fwd thread id": 1, "Ev Idx": 989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941972742.276, "dur": 3.310, + "args": { + "External id": 4552671,"Sequence number": 45295708, "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": 1336753, "tid": 1381210, "ts": 1696941972742.276, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941972743.943, "dur": 1.430, + "args": { + "External id": 4552672,"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": 1336753, "tid": 1381210, + "ts": 1696941972744.458, "dur": 0.790, + "args": { + "External id": 4552673,"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": 1336753, "tid": 1381210, + "ts": 1696941972753.702, "dur": 122.660, + "args": { + "External id": 4552674,"Record function id": 0, "Sequence number": 45295707, "Fwd thread id": 1, "Ev Idx": 993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941972754.590, "dur": 113.508, + "args": { + "External id": 4552675,"Sequence number": 45295707, "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": 1336753, "tid": 1381210, "ts": 1696941972754.590, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941972759.456, "dur": 3.154, + "args": { + "External id": 4552676,"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": 1336753, "tid": 1381210, + "ts": 1696941972760.483, "dur": 1.624, + "args": { + "External id": 4552677,"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": 1336753, "tid": 1381210, + "ts": 1696941972761.484, "dur": 0.497, + "args": { + "External id": 4552678,"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": 1336753, "tid": 1381210, + "ts": 1696941972763.560, "dur": 39.899, + "args": { + "External id": 4552679,"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": 1336753, "tid": 1381210, + "ts": 1696941972804.789, "dur": 6.763, + "args": { + "External id": 4552680,"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": 1336753, "tid": 1381210, + "ts": 1696941972805.504, "dur": 5.249, + "args": { + "External id": 4552681,"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": 1336753, "tid": 1381210, + "ts": 1696941972809.484, "dur": 1.133, + "args": { + "External id": 4552682,"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": 1336753, "tid": 1381210, + "ts": 1696941972813.273, "dur": 5.860, + "args": { + "External id": 4552683,"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": 1336753, "tid": 1381210, + "ts": 1696941972815.353, "dur": 3.135, + "args": { + "External id": 4552684,"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": 1336753, "tid": 1381210, + "ts": 1696941972815.912, "dur": 2.512, + "args": { + "External id": 4552685,"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": 1336753, "tid": 1381210, + "ts": 1696941972819.720, "dur": 47.802, + "args": { + "External id": 4552686,"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": 1336753, "tid": 1381210, + "ts": 1696941972881.185, "dur": 9.396, + "args": { + "External id": 4552687,"Record function id": 0, "Sequence number": 45295706, "Fwd thread id": 1, "Ev Idx": 1006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941972882.095, "dur": 7.257, + "args": { + "External id": 4552688,"Sequence number": 45295706, "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": 1336753, "tid": 1381210, "ts": 1696941972882.095, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941972883.568, "dur": 5.625, + "args": { + "External id": 4552689,"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": 1336753, "tid": 1381210, + "ts": 1696941972888.016, "dur": 1.038, + "args": { + "External id": 4552690,"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": 1336753, "tid": 1381210, + "ts": 1696941972894.033, "dur": 7.017, + "args": { + "External id": 4552691,"Record function id": 0, "Sequence number": 45295705, "Fwd thread id": 1, "Ev Idx": 1010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941972895.008, "dur": 3.709, + "args": { + "External id": 4552692,"Sequence number": 45295705, "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": 1336753, "tid": 1381210, "ts": 1696941972895.008, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941972896.246, "dur": 2.264, + "args": { + "External id": 4552693,"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": 1336753, "tid": 1381210, + "ts": 1696941972896.796, "dur": 1.287, + "args": { + "External id": 4552694,"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": 1336753, "tid": 1381210, + "ts": 1696941972897.582, "dur": 0.383, + "args": { + "External id": 4552695,"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": 1336753, "tid": 1381210, + "ts": 1696941972904.676, "dur": 4.438, + "args": { + "External id": 4552696,"Record function id": 0, "Ev Idx": 1015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941972905.789, "dur": 2.819, + "args": { + "External id": 4552697,"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": 1336753, "tid": 1381210, + "ts": 1696941972906.725, "dur": 1.657, + "args": { + "External id": 4552698,"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": 1336753, "tid": 1381210, + "ts": 1696941972907.314, "dur": 1.002, + "args": { + "External id": 4552699,"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": 1336753, "tid": 1381210, + "ts": 1696941972915.410, "dur": 9.858, + "args": { + "External id": 4552700,"Record function id": 0, "Sequence number": 45295704, "Fwd thread id": 1, "Ev Idx": 1019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941972916.468, "dur": 5.596, + "args": { + "External id": 4552701,"Sequence number": 45295704, "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": 1336753, "tid": 1381210, "ts": 1696941972916.468, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941972918.940, "dur": 2.974, + "args": { + "External id": 4552702,"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": 1336753, "tid": 1381210, + "ts": 1696941972921.161, "dur": 0.632, + "args": { + "External id": 4552703,"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": 1336753, "tid": 1381210, + "ts": 1696941972928.465, "dur": 195.231, + "args": { + "External id": 4552704,"Record function id": 0, "Sequence number": 45295703, "Fwd thread id": 1, "Ev Idx": 1023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941972957.399, "dur": 154.619, + "args": { + "External id": 4552705,"Sequence number": 45295703, "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": 1336753, "tid": 1381210, "ts": 1696941972957.399, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941972961.559, "dur": 3.817, + "args": { + "External id": 4552706,"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": 1336753, "tid": 1381210, + "ts": 1696941972961.957, "dur": 3.009, + "args": { + "External id": 4552707,"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": 1336753, "tid": 1381210, + "ts": 1696941972964.425, "dur": 0.435, + "args": { + "External id": 4552708,"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": 1336753, "tid": 1381210, + "ts": 1696941972965.960, "dur": 73.933, + "args": { + "External id": 4552709,"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": 1336753, "tid": 1381210, + "ts": 1696941973042.262, "dur": 7.356, + "args": { + "External id": 4552710,"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": 1336753, "tid": 1381210, + "ts": 1696941973043.154, "dur": 5.615, + "args": { + "External id": 4552711,"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": 1336753, "tid": 1381210, + "ts": 1696941973044.271, "dur": 4.349, + "args": { + "External id": 4552712,"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": 1336753, "tid": 1381210, + "ts": 1696941973051.194, "dur": 7.059, + "args": { + "External id": 4552713,"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": 1336753, "tid": 1381210, + "ts": 1696941973052.598, "dur": 5.246, + "args": { + "External id": 4552714,"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": 1336753, "tid": 1381210, + "ts": 1696941973057.478, "dur": 0.296, + "args": { + "External id": 4552715,"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": 1336753, "tid": 1381210, + "ts": 1696941973058.881, "dur": 52.327, + "args": { + "External id": 4552716,"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": 1336753, "tid": 1381210, + "ts": 1696941973130.350, "dur": 31.007, + "args": { + "External id": 4552717,"Record function id": 0, "Sequence number": 45295702, "Fwd thread id": 1, "Ev Idx": 1036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941973131.379, "dur": 3.462, + "args": { + "External id": 4552718,"Sequence number": 45295702, "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": 1336753, "tid": 1381210, "ts": 1696941973131.379, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941973132.743, "dur": 1.934, + "args": { + "External id": 4552719,"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": 1336753, "tid": 1381210, + "ts": 1696941973133.319, "dur": 1.242, + "args": { + "External id": 4552720,"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": 1336753, "tid": 1381210, + "ts": 1696941973138.095, "dur": 20.211, + "args": { + "External id": 4552721,"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": 1336753, "tid": 1381210, + "ts": 1696941973165.009, "dur": 11.313, + "args": { + "External id": 4552722,"Record function id": 0, "Sequence number": 45295701, "Fwd thread id": 1, "Ev Idx": 1041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941973166.043, "dur": 7.952, + "args": { + "External id": 4552723,"Sequence number": 45295701, "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": 1336753, "tid": 1381210, "ts": 1696941973166.043, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941973169.179, "dur": 4.589, + "args": { + "External id": 4552724,"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": 1336753, "tid": 1381210, + "ts": 1696941973169.790, "dur": 3.498, + "args": { + "External id": 4552725,"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": 1336753, "tid": 1381210, + "ts": 1696941973172.505, "dur": 0.640, + "args": { + "External id": 4552726,"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": 1336753, "tid": 1381210, + "ts": 1696941973180.596, "dur": 5.891, + "args": { + "External id": 4552727,"Record function id": 0, "Ev Idx": 1046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941973181.897, "dur": 4.066, + "args": { + "External id": 4552728,"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": 1336753, "tid": 1381210, + "ts": 1696941973183.327, "dur": 2.132, + "args": { + "External id": 4552729,"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": 1336753, "tid": 1381210, + "ts": 1696941973183.906, "dur": 1.473, + "args": { + "External id": 4552730,"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": 1336753, "tid": 1381210, + "ts": 1696941973190.565, "dur": 439.165, + "args": { + "External id": 4552731,"Record function id": 0, "Sequence number": 45295700, "Fwd thread id": 1, "Ev Idx": 1050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941973191.871, "dur": 400.410, + "args": { + "External id": 4552732,"Sequence number": 45295700, "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": 1336753, "tid": 1381210, "ts": 1696941973191.871, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1381210, + "ts": 1696941973215.452, "dur": 30.720, + "args": { + "External id": 4552733,"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": 1336753, "tid": 1381210, + "ts": 1696941973216.687, "dur": 29.294, + "args": { + "External id": 4552734,"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": 1336753, "tid": 1381210, + "ts": 1696941973219.290, "dur": 5.484, + "args": { + "External id": 4552735,"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": 1336753, "tid": 1381210, + "ts": 1696941973221.433, "dur": 2.866, + "args": { + "External id": 4552736,"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": 1336753, "tid": 1381210, + "ts": 1696941973225.865, "dur": 19.578, + "args": { + "External id": 4552737,"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": 1336753, "tid": 1381210, + "ts": 1696941973261.836, "dur": 3.834, + "args": { + "External id": 4552738,"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": 1336753, "tid": 1381210, + "ts": 1696941973262.508, "dur": 3.020, + "args": { + "External id": 4552739,"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": 1336753, "tid": 1381210, + "ts": 1696941973269.282, "dur": 1.241, + "args": { + "External id": 4552740,"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": 1336753, "tid": 1381210, + "ts": 1696941973269.765, "dur": 0.653, + "args": { + "External id": 4552741,"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": 1336753, "tid": 1381210, + "ts": 1696941973283.576, "dur": 2.631, + "args": { + "External id": 4552742,"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": 1336753, "tid": 1381210, + "ts": 1696941973296.676, "dur": 2.192, + "args": { + "External id": 4552743,"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": 1336753, "tid": 1381210, + "ts": 1696941973458.027, "dur": 2.401, + "args": { + "External id": 4552744,"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": 1336753, "tid": 1381210, + "ts": 1696941973466.797, "dur": 30.574, + "args": { + "External id": 4552745,"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": 1336753, "tid": 1381210, + "ts": 1696941973475.737, "dur": 0.905, + "args": { + "External id": 4552746,"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": 1336753, "tid": 1381210, + "ts": 1696941973503.269, "dur": 49.245, + "args": { + "External id": 4552747,"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": 1336753, "tid": 1381210, + "ts": 1696941973505.044, "dur": 47.266, + "args": { + "External id": 4552748,"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": 1336753, "tid": 1381210, + "ts": 1696941973510.626, "dur": 3.812, + "args": { + "External id": 4552749,"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": 1336753, "tid": 1381210, + "ts": 1696941973517.468, "dur": 34.097, + "args": { + "External id": 4552750,"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": 1336753, "tid": 1381210, + "ts": 1696941973558.747, "dur": 3.087, + "args": { + "External id": 4552751,"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": 1336753, "tid": 1381210, + "ts": 1696941973559.987, "dur": 1.716, + "args": { + "External id": 4552752,"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": 1336753, "tid": 1381210, + "ts": 1696941973570.063, "dur": 4.600, + "args": { + "External id": 4552753,"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": 1336753, "tid": 1381210, + "ts": 1696941973571.020, "dur": 3.511, + "args": { + "External id": 4552754,"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": 1336753, "tid": 1381210, + "ts": 1696941973576.798, "dur": 3.770, + "args": { + "External id": 4552755,"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": 1336753, "tid": 1381210, + "ts": 1696941973579.248, "dur": 1.231, + "args": { + "External id": 4552756,"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": 1336753, "tid": 1381210, + "ts": 1696941973609.219, "dur": 18.816, + "args": { + "External id": 4552757,"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": 1336753, "tid": 1381210, + "ts": 1696941973641.602, "dur": 8.276, + "args": { + "External id": 4552758,"Record function id": 0, "Ev Idx": 1077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941973643.454, "dur": 5.749, + "args": { + "External id": 4552759,"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": 1336753, "tid": 1381210, + "ts": 1696941973645.315, "dur": 3.048, + "args": { + "External id": 4552760,"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": 1336753, "tid": 1381210, + "ts": 1696941973646.197, "dur": 2.067, + "args": { + "External id": 4552761,"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": 1336753, "tid": 1381210, + "ts": 1696941973653.578, "dur": 7.441, + "args": { + "External id": 4552762,"Record function id": 0, "Sequence number": 45295699, "Fwd thread id": 1, "Ev Idx": 1081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941973654.503, "dur": 3.494, + "args": { + "External id": 4552763,"Sequence number": 45295699, "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": 1336753, "tid": 1381210, "ts": 1696941973654.503, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941973656.001, "dur": 1.798, + "args": { + "External id": 4552764,"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": 1336753, "tid": 1381210, + "ts": 1696941973656.633, "dur": 1.030, + "args": { + "External id": 4552765,"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": 1336753, "tid": 1381210, + "ts": 1696941973666.488, "dur": 126.991, + "args": { + "External id": 4552766,"Record function id": 0, "Sequence number": 45295698, "Fwd thread id": 1, "Ev Idx": 1085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941973667.661, "dur": 118.854, + "args": { + "External id": 4552767,"Sequence number": 45295698, "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": 1336753, "tid": 1381210, "ts": 1696941973667.661, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941973672.631, "dur": 4.364, + "args": { + "External id": 4552768,"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": 1336753, "tid": 1381210, + "ts": 1696941973673.986, "dur": 2.370, + "args": { + "External id": 4552769,"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": 1336753, "tid": 1381210, + "ts": 1696941973675.247, "dur": 0.936, + "args": { + "External id": 4552770,"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": 1336753, "tid": 1381210, + "ts": 1696941973678.256, "dur": 52.184, + "args": { + "External id": 4552771,"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": 1336753, "tid": 1381210, + "ts": 1696941973731.752, "dur": 9.167, + "args": { + "External id": 4552772,"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": 1336753, "tid": 1381210, + "ts": 1696941973734.855, "dur": 5.578, + "args": { + "External id": 4552773,"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": 1336753, "tid": 1381210, + "ts": 1696941973737.549, "dur": 2.726, + "args": { + "External id": 4552774,"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": 1336753, "tid": 1381210, + "ts": 1696941973742.481, "dur": 3.856, + "args": { + "External id": 4552775,"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": 1336753, "tid": 1381210, + "ts": 1696941973744.397, "dur": 1.528, + "args": { + "External id": 4552776,"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": 1336753, "tid": 1381210, + "ts": 1696941973745.466, "dur": 0.373, + "args": { + "External id": 4552777,"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": 1336753, "tid": 1381210, + "ts": 1696941973747.051, "dur": 38.557, + "args": { + "External id": 4552778,"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": 1336753, "tid": 1381210, + "ts": 1696941973798.003, "dur": 14.041, + "args": { + "External id": 4552779,"Record function id": 0, "Sequence number": 45295697, "Fwd thread id": 1, "Ev Idx": 1098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941973799.268, "dur": 9.876, + "args": { + "External id": 4552780,"Sequence number": 45295697, "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": 1336753, "tid": 1381210, "ts": 1696941973799.268, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941973803.068, "dur": 5.933, + "args": { + "External id": 4552781,"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": 1336753, "tid": 1381210, + "ts": 1696941973805.462, "dur": 3.426, + "args": { + "External id": 4552782,"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": 1336753, "tid": 1381210, + "ts": 1696941973817.499, "dur": 7.290, + "args": { + "External id": 4552783,"Record function id": 0, "Sequence number": 45295696, "Fwd thread id": 1, "Ev Idx": 1102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941973818.622, "dur": 4.003, + "args": { + "External id": 4552784,"Sequence number": 45295696, "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": 1336753, "tid": 1381210, "ts": 1696941973818.622, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941973819.683, "dur": 2.736, + "args": { + "External id": 4552785,"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": 1336753, "tid": 1381210, + "ts": 1696941973820.475, "dur": 1.489, + "args": { + "External id": 4552786,"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": 1336753, "tid": 1381210, + "ts": 1696941973821.348, "dur": 0.462, + "args": { + "External id": 4552787,"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": 1336753, "tid": 1381210, + "ts": 1696941973828.534, "dur": 7.853, + "args": { + "External id": 4552788,"Record function id": 0, "Ev Idx": 1107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941973830.023, "dur": 5.873, + "args": { + "External id": 4552789,"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": 1336753, "tid": 1381210, + "ts": 1696941973831.069, "dur": 4.593, + "args": { + "External id": 4552790,"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": 1336753, "tid": 1381210, + "ts": 1696941973833.987, "dur": 1.548, + "args": { + "External id": 4552791,"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": 1336753, "tid": 1381210, + "ts": 1696941973841.543, "dur": 7.131, + "args": { + "External id": 4552792,"Record function id": 0, "Sequence number": 45295695, "Fwd thread id": 1, "Ev Idx": 1111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941973842.447, "dur": 3.264, + "args": { + "External id": 4552793,"Sequence number": 45295695, "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": 1336753, "tid": 1381210, "ts": 1696941973842.447, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941973843.587, "dur": 1.979, + "args": { + "External id": 4552794,"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": 1336753, "tid": 1381210, + "ts": 1696941973844.168, "dur": 1.265, + "args": { + "External id": 4552795,"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": 1336753, "tid": 1381210, + "ts": 1696941973855.058, "dur": 351.244, + "args": { + "External id": 4552796,"Record function id": 0, "Sequence number": 45295694, "Fwd thread id": 1, "Ev Idx": 1115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941973856.463, "dur": 324.153, + "args": { + "External id": 4552797,"Sequence number": 45295694, "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": 1336753, "tid": 1381210, "ts": 1696941973856.463, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1696941973872.457, "dur": 6.502, + "args": { + "External id": 4552798,"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": 1336753, "tid": 1381210, + "ts": 1696941973874.650, "dur": 3.894, + "args": { + "External id": 4552799,"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": 1336753, "tid": 1381210, + "ts": 1696941973880.763, "dur": 7.200, + "args": { + "External id": 4552800,"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": 1336753, "tid": 1381210, + "ts": 1696941973883.820, "dur": 3.933, + "args": { + "External id": 4552801,"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": 1336753, "tid": 1381210, + "ts": 1696941973896.668, "dur": 5.182, + "args": { + "External id": 4552802,"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": 1336753, "tid": 1381210, + "ts": 1696941973899.754, "dur": 1.919, + "args": { + "External id": 4552803,"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": 1336753, "tid": 1381210, + "ts": 1696941973927.449, "dur": 225.848, + "args": { + "External id": 4552804,"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": 1336753, "tid": 1381210, + "ts": 1696941974052.367, "dur": 6.379, + "args": { + "External id": 4552805,"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": 1336753, "tid": 1381210, + "ts": 1696941974060.785, "dur": 4.108, + "args": { + "External id": 4552806,"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": 1336753, "tid": 1381210, + "ts": 1696941974167.216, "dur": 3.719, + "args": { + "External id": 4552807,"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": 1336753, "tid": 1381210, + "ts": 1696941974173.899, "dur": 0.697, + "args": { + "External id": 4552808,"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": 1336753, "tid": 1381210, + "ts": 1696941974176.846, "dur": 0.786, + "args": { + "External id": 4552809,"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": 1336753, "tid": 1381210, + "ts": 1696941974216.210, "dur": 220.649, + "args": { + "External id": 4552810,"Record function id": 0, "Sequence number": 45295693, "Fwd thread id": 1, "Ev Idx": 1129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941974218.074, "dur": 211.591, + "args": { + "External id": 4552811,"Sequence number": 45295693, "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": 1336753, "tid": 1381210, "ts": 1696941974218.074, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1696941974237.331, "dur": 43.618, + "args": { + "External id": 4552812,"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": 1336753, "tid": 1381210, + "ts": 1696941974240.179, "dur": 3.371, + "args": { + "External id": 4552813,"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": 1336753, "tid": 1381210, + "ts": 1696941974245.019, "dur": 35.336, + "args": { + "External id": 4552814,"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": 1336753, "tid": 1381210, + "ts": 1696941974289.572, "dur": 6.284, + "args": { + "External id": 4552815,"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": 1336753, "tid": 1381210, + "ts": 1696941974292.965, "dur": 2.524, + "args": { + "External id": 4552816,"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": 1336753, "tid": 1381210, + "ts": 1696941974443.843, "dur": 180.240, + "args": { + "External id": 4552817,"Record function id": 0, "Sequence number": 45295692, "Fwd thread id": 1, "Ev Idx": 1136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941974445.220, "dur": 170.275, + "args": { + "External id": 4552818,"Sequence number": 45295692, "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": 1336753, "tid": 1381210, "ts": 1696941974445.220, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1696941974457.173, "dur": 39.533, + "args": { + "External id": 4552819,"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": 1336753, "tid": 1381210, + "ts": 1696941974458.873, "dur": 2.626, + "args": { + "External id": 4552820,"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": 1336753, "tid": 1381210, + "ts": 1696941974467.762, "dur": 28.483, + "args": { + "External id": 4552821,"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": 1336753, "tid": 1381210, + "ts": 1696941974503.319, "dur": 5.853, + "args": { + "External id": 4552822,"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": 1336753, "tid": 1381210, + "ts": 1696941974506.770, "dur": 2.062, + "args": { + "External id": 4552823,"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": 1336753, "tid": 1381210, + "ts": 1696941974635.217, "dur": 18.850, + "args": { + "External id": 4552824,"Record function id": 0, "Sequence number": 45295691, "Fwd thread id": 1, "Ev Idx": 1143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941974636.812, "dur": 13.553, + "args": { + "External id": 4552825,"Sequence number": 45295691, "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": 1336753, "tid": 1381210, "ts": 1696941974636.812, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941974639.925, "dur": 10.115, + "args": { + "External id": 4552826,"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": 1336753, "tid": 1381210, + "ts": 1696941974641.209, "dur": 8.638, + "args": { + "External id": 4552827,"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": 1336753, "tid": 1381210, + "ts": 1696941974658.025, "dur": 8.896, + "args": { + "External id": 4552828,"Record function id": 0, "Sequence number": 45295690, "Fwd thread id": 1, "Ev Idx": 1147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941974659.102, "dur": 4.957, + "args": { + "External id": 4552829,"Sequence number": 45295690, "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": 1336753, "tid": 1381210, "ts": 1696941974659.102, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941974660.251, "dur": 3.666, + "args": { + "External id": 4552830,"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": 1336753, "tid": 1381210, + "ts": 1696941974662.837, "dur": 0.949, + "args": { + "External id": 4552831,"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": 1336753, "tid": 1381210, + "ts": 1696941974670.146, "dur": 10.003, + "args": { + "External id": 4552832,"Record function id": 0, "Sequence number": 45295689, "Fwd thread id": 1, "Ev Idx": 1151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941974670.843, "dur": 6.117, + "args": { + "External id": 4552833,"Sequence number": 45295689, "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": 1336753, "tid": 1381210, "ts": 1696941974670.843, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941974674.803, "dur": 2.032, + "args": { + "External id": 4552834,"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": 1336753, "tid": 1381210, + "ts": 1696941974675.604, "dur": 1.102, + "args": { + "External id": 4552835,"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": 1336753, "tid": 1381210, + "ts": 1696941974683.769, "dur": 9.262, + "args": { + "External id": 4552836,"Record function id": 0, "Sequence number": 45295688, "Fwd thread id": 1, "Ev Idx": 1155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941974684.778, "dur": 5.331, + "args": { + "External id": 4552837,"Sequence number": 45295688, "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": 1336753, "tid": 1381210, "ts": 1696941974684.778, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941974686.168, "dur": 3.797, + "args": { + "External id": 4552838,"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": 1336753, "tid": 1381210, + "ts": 1696941974688.824, "dur": 1.060, + "args": { + "External id": 4552839,"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": 1336753, "tid": 1381210, + "ts": 1696941974696.668, "dur": 149.073, + "args": { + "External id": 4552840,"Record function id": 0, "Sequence number": 45295687, "Fwd thread id": 1, "Ev Idx": 1159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941974697.797, "dur": 140.396, + "args": { + "External id": 4552841,"Sequence number": 45295687, "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": 1336753, "tid": 1381210, "ts": 1696941974697.797, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941974702.984, "dur": 8.846, + "args": { + "External id": 4552842,"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": 1336753, "tid": 1381210, + "ts": 1696941974707.254, "dur": 3.940, + "args": { + "External id": 4552843,"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": 1336753, "tid": 1381210, + "ts": 1696941974709.344, "dur": 1.611, + "args": { + "External id": 4552844,"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": 1336753, "tid": 1381210, + "ts": 1696941974713.617, "dur": 66.149, + "args": { + "External id": 4552845,"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": 1336753, "tid": 1381210, + "ts": 1696941974781.059, "dur": 4.092, + "args": { + "External id": 4552846,"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": 1336753, "tid": 1381210, + "ts": 1696941974781.867, "dur": 2.499, + "args": { + "External id": 4552847,"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": 1336753, "tid": 1381210, + "ts": 1696941974783.228, "dur": 1.013, + "args": { + "External id": 4552848,"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": 1336753, "tid": 1381210, + "ts": 1696941974787.069, "dur": 7.287, + "args": { + "External id": 4552849,"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": 1336753, "tid": 1381210, + "ts": 1696941974790.868, "dur": 2.935, + "args": { + "External id": 4552850,"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": 1336753, "tid": 1381210, + "ts": 1696941974793.315, "dur": 0.384, + "args": { + "External id": 4552851,"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": 1336753, "tid": 1381210, + "ts": 1696941974795.157, "dur": 42.293, + "args": { + "External id": 4552852,"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": 1336753, "tid": 1381210, + "ts": 1696941974852.447, "dur": 7.583, + "args": { + "External id": 4552853,"Record function id": 0, "Sequence number": 45295686, "Fwd thread id": 1, "Ev Idx": 1172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941974853.666, "dur": 4.083, + "args": { + "External id": 4552854,"Sequence number": 45295686, "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": 1336753, "tid": 1381210, "ts": 1696941974853.666, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941974855.247, "dur": 2.347, + "args": { + "External id": 4552855,"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": 1336753, "tid": 1381210, + "ts": 1696941974856.016, "dur": 1.485, + "args": { + "External id": 4552856,"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": 1336753, "tid": 1381210, + "ts": 1696941974863.392, "dur": 9.819, + "args": { + "External id": 4552857,"Record function id": 0, "Sequence number": 45295685, "Fwd thread id": 1, "Ev Idx": 1176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941974864.319, "dur": 6.596, + "args": { + "External id": 4552858,"Sequence number": 45295685, "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": 1336753, "tid": 1381210, "ts": 1696941974864.319, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941974867.371, "dur": 3.336, + "args": { + "External id": 4552859,"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": 1336753, "tid": 1381210, + "ts": 1696941974868.323, "dur": 1.897, + "args": { + "External id": 4552860,"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": 1336753, "tid": 1381210, + "ts": 1696941974869.641, "dur": 0.477, + "args": { + "External id": 4552861,"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": 1336753, "tid": 1381210, + "ts": 1696941974880.939, "dur": 10.040, + "args": { + "External id": 4552862,"Record function id": 0, "Ev Idx": 1181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941974882.705, "dur": 7.454, + "args": { + "External id": 4552863,"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": 1336753, "tid": 1381210, + "ts": 1696941974885.728, "dur": 4.046, + "args": { + "External id": 4552864,"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": 1336753, "tid": 1381210, + "ts": 1696941974887.069, "dur": 2.618, + "args": { + "External id": 4552865,"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": 1336753, "tid": 1381210, + "ts": 1696941974894.296, "dur": 7.788, + "args": { + "External id": 4552866,"Record function id": 0, "Sequence number": 45295684, "Fwd thread id": 1, "Ev Idx": 1185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941974895.490, "dur": 4.624, + "args": { + "External id": 4552867,"Sequence number": 45295684, "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": 1336753, "tid": 1381210, "ts": 1696941974895.490, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941974896.607, "dur": 3.364, + "args": { + "External id": 4552868,"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": 1336753, "tid": 1381210, + "ts": 1696941974899.145, "dur": 0.730, + "args": { + "External id": 4552869,"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": 1336753, "tid": 1381210, + "ts": 1696941974905.234, "dur": 132.884, + "args": { + "External id": 4552870,"Record function id": 0, "Sequence number": 45295683, "Fwd thread id": 1, "Ev Idx": 1189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941974906.236, "dur": 122.519, + "args": { + "External id": 4552871,"Sequence number": 45295683, "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": 1336753, "tid": 1381210, "ts": 1696941974906.236, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941974910.437, "dur": 2.460, + "args": { + "External id": 4552872,"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": 1336753, "tid": 1381210, + "ts": 1696941974911.031, "dur": 1.396, + "args": { + "External id": 4552873,"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": 1336753, "tid": 1381210, + "ts": 1696941974911.801, "dur": 0.519, + "args": { + "External id": 4552874,"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": 1336753, "tid": 1381210, + "ts": 1696941974913.688, "dur": 24.495, + "args": { + "External id": 4552875,"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": 1336753, "tid": 1381210, + "ts": 1696941974941.109, "dur": 5.142, + "args": { + "External id": 4552876,"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": 1336753, "tid": 1381210, + "ts": 1696941974941.769, "dur": 3.936, + "args": { + "External id": 4552877,"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": 1336753, "tid": 1381210, + "ts": 1696941974944.802, "dur": 0.799, + "args": { + "External id": 4552878,"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": 1336753, "tid": 1381210, + "ts": 1696941974947.278, "dur": 6.284, + "args": { + "External id": 4552879,"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": 1336753, "tid": 1381210, + "ts": 1696941974949.242, "dur": 3.853, + "args": { + "External id": 4552880,"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": 1336753, "tid": 1381210, + "ts": 1696941974949.998, "dur": 2.960, + "args": { + "External id": 4552881,"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": 1336753, "tid": 1381210, + "ts": 1696941974955.586, "dur": 71.940, + "args": { + "External id": 4552882,"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": 1336753, "tid": 1381210, + "ts": 1696941975044.848, "dur": 36.361, + "args": { + "External id": 4552883,"Record function id": 0, "Sequence number": 45295682, "Fwd thread id": 1, "Ev Idx": 1202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941975046.535, "dur": 6.571, + "args": { + "External id": 4552884,"Sequence number": 45295682, "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": 1336753, "tid": 1381210, "ts": 1696941975046.535, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941975048.906, "dur": 4.058, + "args": { + "External id": 4552885,"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": 1336753, "tid": 1381210, + "ts": 1696941975051.156, "dur": 1.715, + "args": { + "External id": 4552886,"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": 1336753, "tid": 1381210, + "ts": 1696941975056.213, "dur": 22.642, + "args": { + "External id": 4552887,"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": 1336753, "tid": 1381210, + "ts": 1696941975086.975, "dur": 10.429, + "args": { + "External id": 4552888,"Record function id": 0, "Sequence number": 45295681, "Fwd thread id": 1, "Ev Idx": 1207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941975088.397, "dur": 7.200, + "args": { + "External id": 4552889,"Sequence number": 45295681, "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": 1336753, "tid": 1381210, "ts": 1696941975088.397, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941975089.571, "dur": 5.820, + "args": { + "External id": 4552890,"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": 1336753, "tid": 1381210, + "ts": 1696941975092.875, "dur": 1.991, + "args": { + "External id": 4552891,"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": 1336753, "tid": 1381210, + "ts": 1696941975094.140, "dur": 0.621, + "args": { + "External id": 4552892,"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": 1336753, "tid": 1381210, + "ts": 1696941975101.670, "dur": 6.254, + "args": { + "External id": 4552893,"Record function id": 0, "Ev Idx": 1212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941975102.816, "dur": 4.567, + "args": { + "External id": 4552894,"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": 1336753, "tid": 1381210, + "ts": 1696941975104.361, "dur": 2.605, + "args": { + "External id": 4552895,"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": 1336753, "tid": 1381210, + "ts": 1696941975104.957, "dur": 1.900, + "args": { + "External id": 4552896,"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": 1336753, "tid": 1381210, + "ts": 1696941975110.891, "dur": 12.002, + "args": { + "External id": 4552897,"Record function id": 0, "Sequence number": 45295680, "Fwd thread id": 1, "Ev Idx": 1216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941975111.806, "dur": 7.978, + "args": { + "External id": 4552898,"Sequence number": 45295680, "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": 1336753, "tid": 1381210, "ts": 1696941975111.806, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941975113.028, "dur": 6.597, + "args": { + "External id": 4552899,"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": 1336753, "tid": 1381210, + "ts": 1696941975118.523, "dur": 1.008, + "args": { + "External id": 4552900,"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": 1336753, "tid": 1381210, + "ts": 1696941975127.516, "dur": 96.705, + "args": { + "External id": 4552901,"Record function id": 0, "Sequence number": 45295679, "Fwd thread id": 1, "Ev Idx": 1220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941975128.548, "dur": 85.560, + "args": { + "External id": 4552902,"Sequence number": 45295679, "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": 1336753, "tid": 1381210, "ts": 1696941975128.548, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941975131.855, "dur": 2.759, + "args": { + "External id": 4552903,"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": 1336753, "tid": 1381210, + "ts": 1696941975132.585, "dur": 1.614, + "args": { + "External id": 4552904,"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": 1336753, "tid": 1381210, + "ts": 1696941975133.659, "dur": 0.438, + "args": { + "External id": 4552905,"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": 1336753, "tid": 1381210, + "ts": 1696941975135.392, "dur": 30.708, + "args": { + "External id": 4552906,"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": 1336753, "tid": 1381210, + "ts": 1696941975166.981, "dur": 6.771, + "args": { + "External id": 4552907,"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": 1336753, "tid": 1381210, + "ts": 1696941975169.942, "dur": 3.251, + "args": { + "External id": 4552908,"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": 1336753, "tid": 1381210, + "ts": 1696941975170.845, "dur": 2.205, + "args": { + "External id": 4552909,"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": 1336753, "tid": 1381210, + "ts": 1696941975175.044, "dur": 5.136, + "args": { + "External id": 4552910,"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": 1336753, "tid": 1381210, + "ts": 1696941975176.870, "dur": 2.887, + "args": { + "External id": 4552911,"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": 1336753, "tid": 1381210, + "ts": 1696941975179.339, "dur": 0.351, + "args": { + "External id": 4552912,"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": 1336753, "tid": 1381210, + "ts": 1696941975180.710, "dur": 32.651, + "args": { + "External id": 4552913,"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": 1336753, "tid": 1381210, + "ts": 1696941975228.596, "dur": 24.913, + "args": { + "External id": 4552914,"Record function id": 0, "Sequence number": 45295678, "Fwd thread id": 1, "Ev Idx": 1233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941975229.514, "dur": 4.911, + "args": { + "External id": 4552915,"Sequence number": 45295678, "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": 1336753, "tid": 1381210, "ts": 1696941975229.514, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941975232.505, "dur": 1.792, + "args": { + "External id": 4552916,"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": 1336753, "tid": 1381210, + "ts": 1696941975233.177, "dur": 0.998, + "args": { + "External id": 4552917,"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": 1336753, "tid": 1381210, + "ts": 1696941975236.938, "dur": 14.590, + "args": { + "External id": 4552918,"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": 1336753, "tid": 1381210, + "ts": 1696941975256.849, "dur": 8.291, + "args": { + "External id": 4552919,"Record function id": 0, "Sequence number": 45295677, "Fwd thread id": 1, "Ev Idx": 1238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941975257.933, "dur": 4.146, + "args": { + "External id": 4552920,"Sequence number": 45295677, "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": 1336753, "tid": 1381210, "ts": 1696941975257.933, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941975259.182, "dur": 2.694, + "args": { + "External id": 4552921,"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": 1336753, "tid": 1381210, + "ts": 1696941975259.937, "dur": 1.419, + "args": { + "External id": 4552922,"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": 1336753, "tid": 1381210, + "ts": 1696941975260.739, "dur": 0.512, + "args": { + "External id": 4552923,"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": 1336753, "tid": 1381210, + "ts": 1696941975271.132, "dur": 7.034, + "args": { + "External id": 4552924,"Record function id": 0, "Ev Idx": 1243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941975272.580, "dur": 5.149, + "args": { + "External id": 4552925,"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": 1336753, "tid": 1381210, + "ts": 1696941975273.405, "dur": 3.915, + "args": { + "External id": 4552926,"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": 1336753, "tid": 1381210, + "ts": 1696941975276.119, "dur": 1.131, + "args": { + "External id": 4552927,"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": 1336753, "tid": 1381210, + "ts": 1696941975284.647, "dur": 353.729, + "args": { + "External id": 4552928,"Record function id": 0, "Sequence number": 45295676, "Fwd thread id": 1, "Ev Idx": 1247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941975285.671, "dur": 322.732, + "args": { + "External id": 4552929,"Sequence number": 45295676, "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": 1336753, "tid": 1381210, "ts": 1696941975285.671, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941975317.785, "dur": 1.558, + "args": { + "External id": 4552930,"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": 1336753, "tid": 1381210, + "ts": 1696941975318.243, "dur": 0.973, + "args": { + "External id": 4552931,"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": 1336753, "tid": 1381210, + "ts": 1696941975332.689, "dur": 6.118, + "args": { + "External id": 4552932,"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": 1336753, "tid": 1381210, + "ts": 1696941975347.213, "dur": 1.595, + "args": { + "External id": 4552933,"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": 1336753, "tid": 1381210, + "ts": 1696941975488.866, "dur": 1.677, + "args": { + "External id": 4552934,"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": 1336753, "tid": 1381210, + "ts": 1696941975494.491, "dur": 47.954, + "args": { + "External id": 4552935,"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": 1336753, "tid": 1381210, + "ts": 1696941975503.303, "dur": 0.789, + "args": { + "External id": 4552936,"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": 1336753, "tid": 1381210, + "ts": 1696941975549.902, "dur": 33.640, + "args": { + "External id": 4552937,"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": 1336753, "tid": 1381210, + "ts": 1696941975551.892, "dur": 31.448, + "args": { + "External id": 4552938,"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": 1336753, "tid": 1381210, + "ts": 1696941975557.756, "dur": 6.403, + "args": { + "External id": 4552939,"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": 1336753, "tid": 1381210, + "ts": 1696941975565.623, "dur": 17.200, + "args": { + "External id": 4552940,"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": 1336753, "tid": 1381210, + "ts": 1696941975588.074, "dur": 4.944, + "args": { + "External id": 4552941,"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": 1336753, "tid": 1381210, + "ts": 1696941975591.336, "dur": 1.590, + "args": { + "External id": 4552942,"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": 1336753, "tid": 1381210, + "ts": 1696941975600.385, "dur": 1.891, + "args": { + "External id": 4552943,"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": 1336753, "tid": 1381210, + "ts": 1696941975601.155, "dur": 1.027, + "args": { + "External id": 4552944,"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": 1336753, "tid": 1381210, + "ts": 1696941975619.221, "dur": 14.839, + "args": { + "External id": 4552945,"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": 1336753, "tid": 1381210, + "ts": 1696941975649.491, "dur": 7.917, + "args": { + "External id": 4552946,"Record function id": 0, "Ev Idx": 1265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941975651.271, "dur": 5.451, + "args": { + "External id": 4552947,"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": 1336753, "tid": 1381210, + "ts": 1696941975653.041, "dur": 2.705, + "args": { + "External id": 4552948,"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": 1336753, "tid": 1381210, + "ts": 1696941975653.842, "dur": 1.831, + "args": { + "External id": 4552949,"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": 1336753, "tid": 1381210, + "ts": 1696941975661.485, "dur": 22.619, + "args": { + "External id": 4552950,"Record function id": 0, "Sequence number": 45295675, "Fwd thread id": 1, "Ev Idx": 1269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941975664.838, "dur": 1.524, + "args": { + "External id": 4552951,"Sequence number": 45295675, "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": 1336753, "tid": 1381210, "ts": 1696941975664.838, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941975707.822, "dur": 474.331, + "args": { + "External id": 4552952,"Record function id": 0, "Sequence number": 45295674, "Fwd thread id": 1, "Ev Idx": 1271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941975712.790, "dur": 455.381, + "args": { + "External id": 4552953,"Sequence number": 45295674, "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": 1336753, "tid": 1381210, "ts": 1696941975712.790, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941975748.131, "dur": 9.869, + "args": { + "External id": 4552954,"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": 1336753, "tid": 1381210, + "ts": 1696941975753.400, "dur": 4.208, + "args": { + "External id": 4552955,"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": 1336753, "tid": 1381210, + "ts": 1696941975762.075, "dur": 9.289, + "args": { + "External id": 4552956,"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": 1336753, "tid": 1381210, + "ts": 1696941975763.801, "dur": 7.007, + "args": { + "External id": 4552957,"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": 1336753, "tid": 1381210, + "ts": 1696941975767.267, "dur": 3.403, + "args": { + "External id": 4552958,"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": 1336753, "tid": 1381210, + "ts": 1696941975774.969, "dur": 87.538, + "args": { + "External id": 4552959,"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": 1336753, "tid": 1381210, + "ts": 1696941975775.989, "dur": 4.905, + "args": { + "External id": 4552960,"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": 1336753, "tid": 1381210, + "ts": 1696941975776.870, "dur": 3.570, + "args": { + "External id": 4552961,"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": 1336753, "tid": 1381210, + "ts": 1696941975779.699, "dur": 0.600, + "args": { + "External id": 4552962,"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": 1336753, "tid": 1381210, + "ts": 1696941975782.324, "dur": 79.573, + "args": { + "External id": 4552963,"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": 1336753, "tid": 1381210, + "ts": 1696941975783.938, "dur": 77.074, + "args": { + "External id": 4552964,"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": 1336753, "tid": 1381210, + "ts": 1696941975868.191, "dur": 2.663, + "args": { + "External id": 4552965,"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": 1336753, "tid": 1381210, + "ts": 1696941975869.386, "dur": 1.311, + "args": { + "External id": 4552966,"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": 1336753, "tid": 1381210, + "ts": 1696941975901.358, "dur": 6.381, + "args": { + "External id": 4552967,"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": 1336753, "tid": 1381210, + "ts": 1696941975911.443, "dur": 2.489, + "args": { + "External id": 4552968,"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": 1336753, "tid": 1381210, + "ts": 1696941975914.580, "dur": 1.925, + "args": { + "External id": 4552969,"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": 1336753, "tid": 1381210, + "ts": 1696941975949.676, "dur": 1.964, + "args": { + "External id": 4552970,"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": 1336753, "tid": 1381210, + "ts": 1696941975950.458, "dur": 1.017, + "args": { + "External id": 4552971,"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": 1336753, "tid": 1381210, + "ts": 1696941975974.575, "dur": 172.569, + "args": { + "External id": 4552972,"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": 1336753, "tid": 1381210, + "ts": 1696941975979.855, "dur": 48.656, + "args": { + "External id": 4552973,"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": 1336753, "tid": 1381210, + "ts": 1696941976021.595, "dur": 5.392, + "args": { + "External id": 4552974,"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": 1336753, "tid": 1381210, + "ts": 1696941976030.176, "dur": 6.226, + "args": { + "External id": 4552975,"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": 1336753, "tid": 1381210, + "ts": 1696941976035.006, "dur": 0.740, + "args": { + "External id": 4552976,"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": 1336753, "tid": 1381210, + "ts": 1696941976038.353, "dur": 1.954, + "args": { + "External id": 4552977,"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": 1336753, "tid": 1381210, + "ts": 1696941976039.604, "dur": 0.358, + "args": { + "External id": 4552978,"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": 1336753, "tid": 1381210, + "ts": 1696941976042.946, "dur": 2.154, + "args": { + "External id": 4552979,"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": 1336753, "tid": 1381210, + "ts": 1696941976043.978, "dur": 0.648, + "args": { + "External id": 4552980,"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": 1336753, "tid": 1381210, + "ts": 1696941976051.105, "dur": 4.133, + "args": { + "External id": 4552981,"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": 1336753, "tid": 1381210, + "ts": 1696941976054.429, "dur": 0.539, + "args": { + "External id": 4552982,"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": 1336753, "tid": 1381210, + "ts": 1696941976056.108, "dur": 8.063, + "args": { + "External id": 4552983,"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": 1336753, "tid": 1381210, + "ts": 1696941976061.954, "dur": 2.045, + "args": { + "External id": 4552984,"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": 1336753, "tid": 1381210, + "ts": 1696941976064.837, "dur": 3.829, + "args": { + "External id": 4552985,"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": 1336753, "tid": 1381210, + "ts": 1696941976068.028, "dur": 0.388, + "args": { + "External id": 4552986,"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": 1336753, "tid": 1381210, + "ts": 1696941976069.258, "dur": 4.639, + "args": { + "External id": 4552987,"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": 1336753, "tid": 1381210, + "ts": 1696941976069.937, "dur": 3.867, + "args": { + "External id": 4552988,"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": 1336753, "tid": 1381210, + "ts": 1696941976075.088, "dur": 57.788, + "args": { + "External id": 4552989,"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": 1336753, "tid": 1381210, + "ts": 1696941976136.735, "dur": 1.173, + "args": { + "External id": 4552990,"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": 1336753, "tid": 1381210, + "ts": 1696941976138.625, "dur": 2.824, + "args": { + "External id": 4552991,"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": 1336753, "tid": 1381210, + "ts": 1696941976140.070, "dur": 0.690, + "args": { + "External id": 4552992,"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": 1336753, "tid": 1381210, + "ts": 1696941976145.073, "dur": 0.939, + "args": { + "External id": 4552993,"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": 1336753, "tid": 1381210, + "ts": 1696941976194.317, "dur": 9.554, + "args": { + "External id": 4552994,"Record function id": 0, "Ev Idx": 1313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941976196.343, "dur": 6.794, + "args": { + "External id": 4552995,"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": 1336753, "tid": 1381210, + "ts": 1696941976198.756, "dur": 3.513, + "args": { + "External id": 4552996,"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": 1336753, "tid": 1381210, + "ts": 1696941976199.903, "dur": 2.226, + "args": { + "External id": 4552997,"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": 1336753, "tid": 1381210, + "ts": 1696941976207.760, "dur": 7.232, + "args": { + "External id": 4552998,"Record function id": 0, "Sequence number": 45295673, "Fwd thread id": 1, "Ev Idx": 1317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941976208.670, "dur": 3.820, + "args": { + "External id": 4552999,"Sequence number": 45295673, "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": 1336753, "tid": 1381210, "ts": 1696941976208.670, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941976210.439, "dur": 1.851, + "args": { + "External id": 4553000,"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": 1336753, "tid": 1381210, + "ts": 1696941976211.156, "dur": 1.005, + "args": { + "External id": 4553001,"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": 1336753, "tid": 1381210, + "ts": 1696941976218.576, "dur": 122.370, + "args": { + "External id": 4553002,"Record function id": 0, "Sequence number": 45295672, "Fwd thread id": 1, "Ev Idx": 1321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941976219.789, "dur": 114.815, + "args": { + "External id": 4553003,"Sequence number": 45295672, "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": 1336753, "tid": 1381210, "ts": 1696941976219.789, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941976227.060, "dur": 3.518, + "args": { + "External id": 4553004,"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": 1336753, "tid": 1381210, + "ts": 1696941976228.196, "dur": 1.786, + "args": { + "External id": 4553005,"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": 1336753, "tid": 1381210, + "ts": 1696941976229.151, "dur": 0.637, + "args": { + "External id": 4553006,"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": 1336753, "tid": 1381210, + "ts": 1696941976231.782, "dur": 38.599, + "args": { + "External id": 4553007,"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": 1336753, "tid": 1381210, + "ts": 1696941976271.551, "dur": 7.375, + "args": { + "External id": 4553008,"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": 1336753, "tid": 1381210, + "ts": 1696941976272.134, "dur": 6.026, + "args": { + "External id": 4553009,"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": 1336753, "tid": 1381210, + "ts": 1696941976277.124, "dur": 0.896, + "args": { + "External id": 4553010,"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": 1336753, "tid": 1381210, + "ts": 1696941976280.639, "dur": 5.794, + "args": { + "External id": 4553011,"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": 1336753, "tid": 1381210, + "ts": 1696941976282.647, "dur": 3.339, + "args": { + "External id": 4553012,"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": 1336753, "tid": 1381210, + "ts": 1696941976283.360, "dur": 2.538, + "args": { + "External id": 4553013,"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": 1336753, "tid": 1381210, + "ts": 1696941976286.962, "dur": 46.856, + "args": { + "External id": 4553014,"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": 1336753, "tid": 1381210, + "ts": 1696941976345.541, "dur": 8.417, + "args": { + "External id": 4553015,"Record function id": 0, "Sequence number": 45295671, "Fwd thread id": 1, "Ev Idx": 1334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941976346.654, "dur": 5.514, + "args": { + "External id": 4553016,"Sequence number": 45295671, "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": 1336753, "tid": 1381210, "ts": 1696941976346.654, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941976347.986, "dur": 4.046, + "args": { + "External id": 4553017,"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": 1336753, "tid": 1381210, + "ts": 1696941976350.706, "dur": 1.200, + "args": { + "External id": 4553018,"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": 1336753, "tid": 1381210, + "ts": 1696941976357.449, "dur": 10.299, + "args": { + "External id": 4553019,"Record function id": 0, "Sequence number": 45295670, "Fwd thread id": 1, "Ev Idx": 1338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941976358.753, "dur": 6.355, + "args": { + "External id": 4553020,"Sequence number": 45295670, "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": 1336753, "tid": 1381210, "ts": 1696941976358.753, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941976359.659, "dur": 5.222, + "args": { + "External id": 4553021,"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": 1336753, "tid": 1381210, + "ts": 1696941976360.415, "dur": 3.974, + "args": { + "External id": 4553022,"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": 1336753, "tid": 1381210, + "ts": 1696941976363.680, "dur": 0.608, + "args": { + "External id": 4553023,"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": 1336753, "tid": 1381210, + "ts": 1696941976371.536, "dur": 5.478, + "args": { + "External id": 4553024,"Record function id": 0, "Ev Idx": 1343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941976373.108, "dur": 3.443, + "args": { + "External id": 4553025,"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": 1336753, "tid": 1381210, + "ts": 1696941976374.261, "dur": 2.066, + "args": { + "External id": 4553026,"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": 1336753, "tid": 1381210, + "ts": 1696941976374.981, "dur": 1.268, + "args": { + "External id": 4553027,"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": 1336753, "tid": 1381210, + "ts": 1696941976380.121, "dur": 7.841, + "args": { + "External id": 4553028,"Record function id": 0, "Sequence number": 45295669, "Fwd thread id": 1, "Ev Idx": 1347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941976381.168, "dur": 4.769, + "args": { + "External id": 4553029,"Sequence number": 45295669, "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": 1336753, "tid": 1381210, "ts": 1696941976381.168, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941976384.248, "dur": 1.551, + "args": { + "External id": 4553030,"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": 1336753, "tid": 1381210, + "ts": 1696941976385.078, "dur": 0.583, + "args": { + "External id": 4553031,"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": 1336753, "tid": 1381210, + "ts": 1696941976391.040, "dur": 114.748, + "args": { + "External id": 4553032,"Record function id": 0, "Sequence number": 45295668, "Fwd thread id": 1, "Ev Idx": 1351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941976391.870, "dur": 105.671, + "args": { + "External id": 4553033,"Sequence number": 45295668, "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": 1336753, "tid": 1381210, "ts": 1696941976391.870, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941976395.095, "dur": 5.753, + "args": { + "External id": 4553034,"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": 1336753, "tid": 1381210, + "ts": 1696941976395.510, "dur": 4.856, + "args": { + "External id": 4553035,"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": 1336753, "tid": 1381210, + "ts": 1696941976399.595, "dur": 0.671, + "args": { + "External id": 4553036,"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": 1336753, "tid": 1381210, + "ts": 1696941976401.495, "dur": 32.639, + "args": { + "External id": 4553037,"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": 1336753, "tid": 1381210, + "ts": 1696941976435.358, "dur": 5.173, + "args": { + "External id": 4553038,"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": 1336753, "tid": 1381210, + "ts": 1696941976436.042, "dur": 3.915, + "args": { + "External id": 4553039,"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": 1336753, "tid": 1381210, + "ts": 1696941976437.092, "dur": 2.726, + "args": { + "External id": 4553040,"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": 1336753, "tid": 1381210, + "ts": 1696941976441.991, "dur": 5.103, + "args": { + "External id": 4553041,"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": 1336753, "tid": 1381210, + "ts": 1696941976443.721, "dur": 2.907, + "args": { + "External id": 4553042,"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": 1336753, "tid": 1381210, + "ts": 1696941976446.151, "dur": 0.411, + "args": { + "External id": 4553043,"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": 1336753, "tid": 1381210, + "ts": 1696941976447.721, "dur": 49.027, + "args": { + "External id": 4553044,"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": 1336753, "tid": 1381210, + "ts": 1696941976511.877, "dur": 54.318, + "args": { + "External id": 4553045,"Record function id": 0, "Sequence number": 45295667, "Fwd thread id": 1, "Ev Idx": 1364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941976512.768, "dur": 5.362, + "args": { + "External id": 4553046,"Sequence number": 45295667, "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": 1336753, "tid": 1381210, "ts": 1696941976512.768, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941976516.123, "dur": 1.869, + "args": { + "External id": 4553047,"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": 1336753, "tid": 1381210, + "ts": 1696941976516.884, "dur": 0.991, + "args": { + "External id": 4553048,"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": 1336753, "tid": 1381210, + "ts": 1696941976521.133, "dur": 41.265, + "args": { + "External id": 4553049,"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": 1336753, "tid": 1381210, + "ts": 1696941976572.107, "dur": 11.792, + "args": { + "External id": 4553050,"Record function id": 0, "Sequence number": 45295666, "Fwd thread id": 1, "Ev Idx": 1369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941976573.507, "dur": 7.892, + "args": { + "External id": 4553051,"Sequence number": 45295666, "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": 1336753, "tid": 1381210, "ts": 1696941976573.507, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941976574.911, "dur": 6.258, + "args": { + "External id": 4553052,"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": 1336753, "tid": 1381210, + "ts": 1696941976578.206, "dur": 2.321, + "args": { + "External id": 4553053,"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": 1336753, "tid": 1381210, + "ts": 1696941976579.558, "dur": 0.860, + "args": { + "External id": 4553054,"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": 1336753, "tid": 1381210, + "ts": 1696941976587.851, "dur": 8.018, + "args": { + "External id": 4553055,"Record function id": 0, "Ev Idx": 1374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941976591.197, "dur": 4.110, + "args": { + "External id": 4553056,"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": 1336753, "tid": 1381210, + "ts": 1696941976592.718, "dur": 2.150, + "args": { + "External id": 4553057,"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": 1336753, "tid": 1381210, + "ts": 1696941976593.530, "dur": 1.247, + "args": { + "External id": 4553058,"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": 1336753, "tid": 1381210, + "ts": 1696941976600.601, "dur": 474.019, + "args": { + "External id": 4553059,"Record function id": 0, "Sequence number": 45295665, "Fwd thread id": 1, "Ev Idx": 1378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941976605.489, "dur": 426.882, + "args": { + "External id": 4553060,"Sequence number": 45295665, "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": 1336753, "tid": 1381210, "ts": 1696941976605.489, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1381210, + "ts": 1696941976630.314, "dur": 32.423, + "args": { + "External id": 4553061,"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": 1336753, "tid": 1381210, + "ts": 1696941976631.635, "dur": 30.871, + "args": { + "External id": 4553062,"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": 1336753, "tid": 1381210, + "ts": 1696941976634.304, "dur": 6.060, + "args": { + "External id": 4553063,"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": 1336753, "tid": 1381210, + "ts": 1696941976636.562, "dur": 3.428, + "args": { + "External id": 4553064,"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": 1336753, "tid": 1381210, + "ts": 1696941976641.582, "dur": 20.548, + "args": { + "External id": 4553065,"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": 1336753, "tid": 1381210, + "ts": 1696941976675.850, "dur": 6.289, + "args": { + "External id": 4553066,"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": 1336753, "tid": 1381210, + "ts": 1696941976678.698, "dur": 3.265, + "args": { + "External id": 4553067,"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": 1336753, "tid": 1381210, + "ts": 1696941976685.849, "dur": 1.437, + "args": { + "External id": 4553068,"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": 1336753, "tid": 1381210, + "ts": 1696941976686.512, "dur": 0.669, + "args": { + "External id": 4553069,"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": 1336753, "tid": 1381210, + "ts": 1696941976700.728, "dur": 2.644, + "args": { + "External id": 4553070,"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": 1336753, "tid": 1381210, + "ts": 1696941976713.439, "dur": 4.024, + "args": { + "External id": 4553071,"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": 1336753, "tid": 1381210, + "ts": 1696941976878.088, "dur": 3.986, + "args": { + "External id": 4553072,"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": 1336753, "tid": 1381210, + "ts": 1696941976886.009, "dur": 31.030, + "args": { + "External id": 4553073,"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": 1336753, "tid": 1381210, + "ts": 1696941976895.857, "dur": 0.894, + "args": { + "External id": 4553074,"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": 1336753, "tid": 1381210, + "ts": 1696941976922.579, "dur": 27.652, + "args": { + "External id": 4553075,"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": 1336753, "tid": 1381210, + "ts": 1696941976924.659, "dur": 25.366, + "args": { + "External id": 4553076,"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": 1336753, "tid": 1381210, + "ts": 1696941976928.815, "dur": 4.131, + "args": { + "External id": 4553077,"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": 1336753, "tid": 1381210, + "ts": 1696941976936.109, "dur": 13.412, + "args": { + "External id": 4553078,"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": 1336753, "tid": 1381210, + "ts": 1696941976954.509, "dur": 4.883, + "args": { + "External id": 4553079,"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": 1336753, "tid": 1381210, + "ts": 1696941976958.151, "dur": 1.113, + "args": { + "External id": 4553080,"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": 1336753, "tid": 1381210, + "ts": 1696941976966.163, "dur": 3.832, + "args": { + "External id": 4553081,"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": 1336753, "tid": 1381210, + "ts": 1696941976967.002, "dur": 2.895, + "args": { + "External id": 4553082,"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": 1336753, "tid": 1381210, + "ts": 1696941976972.165, "dur": 3.925, + "args": { + "External id": 4553083,"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": 1336753, "tid": 1381210, + "ts": 1696941976974.741, "dur": 1.263, + "args": { + "External id": 4553084,"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": 1336753, "tid": 1381210, + "ts": 1696941977053.666, "dur": 19.547, + "args": { + "External id": 4553085,"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": 1336753, "tid": 1381210, + "ts": 1696941977087.813, "dur": 9.511, + "args": { + "External id": 4553086,"Record function id": 0, "Ev Idx": 1405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941977090.467, "dur": 6.317, + "args": { + "External id": 4553087,"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": 1336753, "tid": 1381210, + "ts": 1696941977092.963, "dur": 2.945, + "args": { + "External id": 4553088,"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": 1336753, "tid": 1381210, + "ts": 1696941977094.008, "dur": 1.774, + "args": { + "External id": 4553089,"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": 1336753, "tid": 1381210, + "ts": 1696941977100.861, "dur": 10.767, + "args": { + "External id": 4553090,"Record function id": 0, "Sequence number": 45295664, "Fwd thread id": 1, "Ev Idx": 1409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941977102.239, "dur": 6.830, + "args": { + "External id": 4553091,"Sequence number": 45295664, "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": 1336753, "tid": 1381210, "ts": 1696941977102.239, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941977104.296, "dur": 4.579, + "args": { + "External id": 4553092,"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": 1336753, "tid": 1381210, + "ts": 1696941977106.983, "dur": 1.778, + "args": { + "External id": 4553093,"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": 1336753, "tid": 1381210, + "ts": 1696941977115.278, "dur": 130.269, + "args": { + "External id": 4553094,"Record function id": 0, "Sequence number": 45295663, "Fwd thread id": 1, "Ev Idx": 1413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941977116.276, "dur": 122.451, + "args": { + "External id": 4553095,"Sequence number": 45295663, "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": 1336753, "tid": 1381210, "ts": 1696941977116.276, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941977119.921, "dur": 4.883, + "args": { + "External id": 4553096,"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": 1336753, "tid": 1381210, + "ts": 1696941977121.723, "dur": 2.432, + "args": { + "External id": 4553097,"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": 1336753, "tid": 1381210, + "ts": 1696941977123.007, "dur": 0.932, + "args": { + "External id": 4553098,"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": 1336753, "tid": 1381210, + "ts": 1696941977126.256, "dur": 53.910, + "args": { + "External id": 4553099,"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": 1336753, "tid": 1381210, + "ts": 1696941977183.574, "dur": 7.391, + "args": { + "External id": 4553100,"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": 1336753, "tid": 1381210, + "ts": 1696941977184.540, "dur": 5.927, + "args": { + "External id": 4553101,"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": 1336753, "tid": 1381210, + "ts": 1696941977187.712, "dur": 2.609, + "args": { + "External id": 4553102,"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": 1336753, "tid": 1381210, + "ts": 1696941977192.732, "dur": 3.593, + "args": { + "External id": 4553103,"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": 1336753, "tid": 1381210, + "ts": 1696941977194.444, "dur": 1.270, + "args": { + "External id": 4553104,"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": 1336753, "tid": 1381210, + "ts": 1696941977195.210, "dur": 0.435, + "args": { + "External id": 4553105,"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": 1336753, "tid": 1381210, + "ts": 1696941977198.923, "dur": 39.122, + "args": { + "External id": 4553106,"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": 1336753, "tid": 1381210, + "ts": 1696941977250.347, "dur": 11.855, + "args": { + "External id": 4553107,"Record function id": 0, "Sequence number": 45295662, "Fwd thread id": 1, "Ev Idx": 1426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941977251.529, "dur": 7.773, + "args": { + "External id": 4553108,"Sequence number": 45295662, "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": 1336753, "tid": 1381210, "ts": 1696941977251.529, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941977253.437, "dur": 5.720, + "args": { + "External id": 4553109,"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": 1336753, "tid": 1381210, + "ts": 1696941977256.354, "dur": 2.695, + "args": { + "External id": 4553110,"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": 1336753, "tid": 1381210, + "ts": 1696941977265.512, "dur": 9.666, + "args": { + "External id": 4553111,"Record function id": 0, "Sequence number": 45295661, "Fwd thread id": 1, "Ev Idx": 1430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941977266.623, "dur": 6.752, + "args": { + "External id": 4553112,"Sequence number": 45295661, "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": 1336753, "tid": 1381210, "ts": 1696941977266.623, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941977267.931, "dur": 5.231, + "args": { + "External id": 4553113,"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": 1336753, "tid": 1381210, + "ts": 1696941977268.909, "dur": 3.734, + "args": { + "External id": 4553114,"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": 1336753, "tid": 1381210, + "ts": 1696941977271.752, "dur": 0.737, + "args": { + "External id": 4553115,"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": 1336753, "tid": 1381210, + "ts": 1696941977278.995, "dur": 5.259, + "args": { + "External id": 4553116,"Record function id": 0, "Ev Idx": 1435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941977280.166, "dur": 3.586, + "args": { + "External id": 4553117,"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": 1336753, "tid": 1381210, + "ts": 1696941977281.629, "dur": 1.888, + "args": { + "External id": 4553118,"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": 1336753, "tid": 1381210, + "ts": 1696941977282.174, "dur": 1.253, + "args": { + "External id": 4553119,"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": 1336753, "tid": 1381210, + "ts": 1696941977287.362, "dur": 6.111, + "args": { + "External id": 4553120,"Record function id": 0, "Sequence number": 45295660, "Fwd thread id": 1, "Ev Idx": 1439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941977288.494, "dur": 2.928, + "args": { + "External id": 4553121,"Sequence number": 45295660, "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": 1336753, "tid": 1381210, "ts": 1696941977288.494, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941977289.568, "dur": 1.711, + "args": { + "External id": 4553122,"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": 1336753, "tid": 1381210, + "ts": 1696941977290.010, "dur": 1.157, + "args": { + "External id": 4553123,"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": 1336753, "tid": 1381210, + "ts": 1696941977297.720, "dur": 311.754, + "args": { + "External id": 4553124,"Record function id": 0, "Sequence number": 45295659, "Fwd thread id": 1, "Ev Idx": 1443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941977300.922, "dur": 285.461, + "args": { + "External id": 4553125,"Sequence number": 45295659, "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": 1336753, "tid": 1381210, "ts": 1696941977300.922, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1696941977317.197, "dur": 8.606, + "args": { + "External id": 4553126,"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": 1336753, "tid": 1381210, + "ts": 1696941977321.308, "dur": 4.103, + "args": { + "External id": 4553127,"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": 1336753, "tid": 1381210, + "ts": 1696941977328.042, "dur": 5.052, + "args": { + "External id": 4553128,"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": 1336753, "tid": 1381210, + "ts": 1696941977331.014, "dur": 1.891, + "args": { + "External id": 4553129,"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": 1336753, "tid": 1381210, + "ts": 1696941977334.651, "dur": 2.861, + "args": { + "External id": 4553130,"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": 1336753, "tid": 1381210, + "ts": 1696941977335.506, "dur": 1.836, + "args": { + "External id": 4553131,"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": 1336753, "tid": 1381210, + "ts": 1696941977362.509, "dur": 195.008, + "args": { + "External id": 4553132,"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": 1336753, "tid": 1381210, + "ts": 1696941977440.579, "dur": 5.167, + "args": { + "External id": 4553133,"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": 1336753, "tid": 1381210, + "ts": 1696941977449.307, "dur": 4.137, + "args": { + "External id": 4553134,"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": 1336753, "tid": 1381210, + "ts": 1696941977572.892, "dur": 3.871, + "args": { + "External id": 4553135,"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": 1336753, "tid": 1381210, + "ts": 1696941977580.113, "dur": 0.788, + "args": { + "External id": 4553136,"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": 1336753, "tid": 1381210, + "ts": 1696941977582.863, "dur": 0.783, + "args": { + "External id": 4553137,"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": 1336753, "tid": 1381210, + "ts": 1696941977618.920, "dur": 237.181, + "args": { + "External id": 4553138,"Record function id": 0, "Sequence number": 45295658, "Fwd thread id": 1, "Ev Idx": 1457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941977620.699, "dur": 228.143, + "args": { + "External id": 4553139,"Sequence number": 45295658, "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": 1336753, "tid": 1381210, "ts": 1696941977620.699, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1696941977641.158, "dur": 58.696, + "args": { + "External id": 4553140,"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": 1336753, "tid": 1381210, + "ts": 1696941977646.491, "dur": 3.820, + "args": { + "External id": 4553141,"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": 1336753, "tid": 1381210, + "ts": 1696941977651.722, "dur": 47.461, + "args": { + "External id": 4553142,"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": 1336753, "tid": 1381210, + "ts": 1696941977709.144, "dur": 4.515, + "args": { + "External id": 4553143,"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": 1336753, "tid": 1381210, + "ts": 1696941977710.817, "dur": 2.507, + "args": { + "External id": 4553144,"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": 1336753, "tid": 1381210, + "ts": 1696941977862.764, "dur": 194.192, + "args": { + "External id": 4553145,"Record function id": 0, "Sequence number": 45295657, "Fwd thread id": 1, "Ev Idx": 1464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941977866.420, "dur": 181.601, + "args": { + "External id": 4553146,"Sequence number": 45295657, "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": 1336753, "tid": 1381210, "ts": 1696941977866.420, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1696941977878.769, "dur": 29.959, + "args": { + "External id": 4553147,"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": 1336753, "tid": 1381210, + "ts": 1696941977880.873, "dur": 2.387, + "args": { + "External id": 4553148,"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": 1336753, "tid": 1381210, + "ts": 1696941977884.153, "dur": 23.774, + "args": { + "External id": 4553149,"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": 1336753, "tid": 1381210, + "ts": 1696941977915.108, "dur": 4.277, + "args": { + "External id": 4553150,"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": 1336753, "tid": 1381210, + "ts": 1696941977916.278, "dur": 2.763, + "args": { + "External id": 4553151,"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": 1336753, "tid": 1381210, + "ts": 1696941978066.272, "dur": 16.357, + "args": { + "External id": 4553152,"Record function id": 0, "Sequence number": 45295656, "Fwd thread id": 1, "Ev Idx": 1471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978067.708, "dur": 11.949, + "args": { + "External id": 4553153,"Sequence number": 45295656, "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": 1336753, "tid": 1381210, "ts": 1696941978067.708, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941978071.622, "dur": 7.732, + "args": { + "External id": 4553154,"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": 1336753, "tid": 1381210, + "ts": 1696941978072.820, "dur": 6.366, + "args": { + "External id": 4553155,"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": 1336753, "tid": 1381210, + "ts": 1696941978086.032, "dur": 5.979, + "args": { + "External id": 4553156,"Record function id": 0, "Sequence number": 45295655, "Fwd thread id": 1, "Ev Idx": 1475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978086.795, "dur": 2.940, + "args": { + "External id": 4553157,"Sequence number": 45295655, "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": 1336753, "tid": 1381210, "ts": 1696941978086.795, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941978088.014, "dur": 1.593, + "args": { + "External id": 4553158,"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": 1336753, "tid": 1381210, + "ts": 1696941978088.664, "dur": 0.853, + "args": { + "External id": 4553159,"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": 1336753, "tid": 1381210, + "ts": 1696941978094.974, "dur": 10.231, + "args": { + "External id": 4553160,"Record function id": 0, "Sequence number": 45295654, "Fwd thread id": 1, "Ev Idx": 1479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978096.112, "dur": 6.615, + "args": { + "External id": 4553161,"Sequence number": 45295654, "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": 1336753, "tid": 1381210, "ts": 1696941978096.112, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941978100.488, "dur": 2.100, + "args": { + "External id": 4553162,"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": 1336753, "tid": 1381210, + "ts": 1696941978101.242, "dur": 1.228, + "args": { + "External id": 4553163,"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": 1336753, "tid": 1381210, + "ts": 1696941978108.433, "dur": 6.466, + "args": { + "External id": 4553164,"Record function id": 0, "Sequence number": 45295653, "Fwd thread id": 1, "Ev Idx": 1483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978109.539, "dur": 3.242, + "args": { + "External id": 4553165,"Sequence number": 45295653, "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": 1336753, "tid": 1381210, "ts": 1696941978109.539, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941978110.699, "dur": 1.925, + "args": { + "External id": 4553166,"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": 1336753, "tid": 1381210, + "ts": 1696941978111.348, "dur": 1.185, + "args": { + "External id": 4553167,"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": 1336753, "tid": 1381210, + "ts": 1696941978118.332, "dur": 142.635, + "args": { + "External id": 4553168,"Record function id": 0, "Sequence number": 45295652, "Fwd thread id": 1, "Ev Idx": 1487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978119.249, "dur": 134.051, + "args": { + "External id": 4553169,"Sequence number": 45295652, "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": 1336753, "tid": 1381210, "ts": 1696941978119.249, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941978124.010, "dur": 9.573, + "args": { + "External id": 4553170,"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": 1336753, "tid": 1381210, + "ts": 1696941978128.090, "dur": 4.873, + "args": { + "External id": 4553171,"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": 1336753, "tid": 1381210, + "ts": 1696941978131.313, "dur": 1.418, + "args": { + "External id": 4553172,"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": 1336753, "tid": 1381210, + "ts": 1696941978135.330, "dur": 60.836, + "args": { + "External id": 4553173,"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": 1336753, "tid": 1381210, + "ts": 1696941978197.497, "dur": 3.851, + "args": { + "External id": 4553174,"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": 1336753, "tid": 1381210, + "ts": 1696941978198.139, "dur": 2.595, + "args": { + "External id": 4553175,"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": 1336753, "tid": 1381210, + "ts": 1696941978199.459, "dur": 1.130, + "args": { + "External id": 4553176,"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": 1336753, "tid": 1381210, + "ts": 1696941978203.246, "dur": 5.432, + "args": { + "External id": 4553177,"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": 1336753, "tid": 1381210, + "ts": 1696941978206.863, "dur": 1.278, + "args": { + "External id": 4553178,"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": 1336753, "tid": 1381210, + "ts": 1696941978207.484, "dur": 0.589, + "args": { + "External id": 4553179,"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": 1336753, "tid": 1381210, + "ts": 1696941978209.553, "dur": 42.984, + "args": { + "External id": 4553180,"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": 1336753, "tid": 1381210, + "ts": 1696941978265.455, "dur": 8.714, + "args": { + "External id": 4553181,"Record function id": 0, "Sequence number": 45295651, "Fwd thread id": 1, "Ev Idx": 1500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978266.427, "dur": 5.910, + "args": { + "External id": 4553182,"Sequence number": 45295651, "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": 1336753, "tid": 1381210, "ts": 1696941978266.427, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941978270.009, "dur": 2.184, + "args": { + "External id": 4553183,"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": 1336753, "tid": 1381210, + "ts": 1696941978270.869, "dur": 1.187, + "args": { + "External id": 4553184,"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": 1336753, "tid": 1381210, + "ts": 1696941978277.221, "dur": 10.418, + "args": { + "External id": 4553185,"Record function id": 0, "Sequence number": 45295650, "Fwd thread id": 1, "Ev Idx": 1504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978278.287, "dur": 6.242, + "args": { + "External id": 4553186,"Sequence number": 45295650, "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": 1336753, "tid": 1381210, "ts": 1696941978278.287, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941978281.872, "dur": 2.440, + "args": { + "External id": 4553187,"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": 1336753, "tid": 1381210, + "ts": 1696941978282.628, "dur": 1.247, + "args": { + "External id": 4553188,"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": 1336753, "tid": 1381210, + "ts": 1696941978283.394, "dur": 0.382, + "args": { + "External id": 4553189,"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": 1336753, "tid": 1381210, + "ts": 1696941978293.395, "dur": 8.724, + "args": { + "External id": 4553190,"Record function id": 0, "Ev Idx": 1509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941978295.020, "dur": 6.253, + "args": { + "External id": 4553191,"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": 1336753, "tid": 1381210, + "ts": 1696941978297.385, "dur": 3.399, + "args": { + "External id": 4553192,"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": 1336753, "tid": 1381210, + "ts": 1696941978298.361, "dur": 2.331, + "args": { + "External id": 4553193,"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": 1336753, "tid": 1381210, + "ts": 1696941978308.188, "dur": 10.901, + "args": { + "External id": 4553194,"Record function id": 0, "Sequence number": 45295649, "Fwd thread id": 1, "Ev Idx": 1513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978311.117, "dur": 5.247, + "args": { + "External id": 4553195,"Sequence number": 45295649, "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": 1336753, "tid": 1381210, "ts": 1696941978311.117, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941978312.558, "dur": 3.660, + "args": { + "External id": 4553196,"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": 1336753, "tid": 1381210, + "ts": 1696941978315.167, "dur": 0.964, + "args": { + "External id": 4553197,"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": 1336753, "tid": 1381210, + "ts": 1696941978322.113, "dur": 90.762, + "args": { + "External id": 4553198,"Record function id": 0, "Sequence number": 45295648, "Fwd thread id": 1, "Ev Idx": 1517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978323.253, "dur": 83.232, + "args": { + "External id": 4553199,"Sequence number": 45295648, "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": 1336753, "tid": 1381210, "ts": 1696941978323.253, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941978326.486, "dur": 2.640, + "args": { + "External id": 4553200,"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": 1336753, "tid": 1381210, + "ts": 1696941978327.412, "dur": 1.279, + "args": { + "External id": 4553201,"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": 1336753, "tid": 1381210, + "ts": 1696941978328.020, "dur": 0.565, + "args": { + "External id": 4553202,"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": 1336753, "tid": 1381210, + "ts": 1696941978330.002, "dur": 24.632, + "args": { + "External id": 4553203,"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": 1336753, "tid": 1381210, + "ts": 1696941978357.872, "dur": 3.474, + "args": { + "External id": 4553204,"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": 1336753, "tid": 1381210, + "ts": 1696941978358.916, "dur": 1.916, + "args": { + "External id": 4553205,"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": 1336753, "tid": 1381210, + "ts": 1696941978359.703, "dur": 1.012, + "args": { + "External id": 4553206,"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": 1336753, "tid": 1381210, + "ts": 1696941978363.166, "dur": 7.374, + "args": { + "External id": 4553207,"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": 1336753, "tid": 1381210, + "ts": 1696941978364.500, "dur": 5.403, + "args": { + "External id": 4553208,"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": 1336753, "tid": 1381210, + "ts": 1696941978367.353, "dur": 2.471, + "args": { + "External id": 4553209,"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": 1336753, "tid": 1381210, + "ts": 1696941978372.725, "dur": 33.034, + "args": { + "External id": 4553210,"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": 1336753, "tid": 1381210, + "ts": 1696941978419.383, "dur": 34.792, + "args": { + "External id": 4553211,"Record function id": 0, "Sequence number": 45295647, "Fwd thread id": 1, "Ev Idx": 1530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978420.276, "dur": 8.079, + "args": { + "External id": 4553212,"Sequence number": 45295647, "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": 1336753, "tid": 1381210, "ts": 1696941978420.276, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941978421.922, "dur": 6.287, + "args": { + "External id": 4553213,"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": 1336753, "tid": 1381210, + "ts": 1696941978426.861, "dur": 1.253, + "args": { + "External id": 4553214,"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": 1336753, "tid": 1381210, + "ts": 1696941978431.661, "dur": 20.311, + "args": { + "External id": 4553215,"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": 1336753, "tid": 1381210, + "ts": 1696941978457.969, "dur": 38.256, + "args": { + "External id": 4553216,"Record function id": 0, "Sequence number": 45295646, "Fwd thread id": 1, "Ev Idx": 1535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978486.053, "dur": 7.950, + "args": { + "External id": 4553217,"Sequence number": 45295646, "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": 1336753, "tid": 1381210, "ts": 1696941978486.053, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941978488.935, "dur": 4.872, + "args": { + "External id": 4553218,"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": 1336753, "tid": 1381210, + "ts": 1696941978489.578, "dur": 3.700, + "args": { + "External id": 4553219,"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": 1336753, "tid": 1381210, + "ts": 1696941978492.655, "dur": 0.472, + "args": { + "External id": 4553220,"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": 1336753, "tid": 1381210, + "ts": 1696941978500.170, "dur": 4.547, + "args": { + "External id": 4553221,"Record function id": 0, "Ev Idx": 1540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941978501.260, "dur": 2.930, + "args": { + "External id": 4553222,"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": 1336753, "tid": 1381210, + "ts": 1696941978502.277, "dur": 1.588, + "args": { + "External id": 4553223,"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": 1336753, "tid": 1381210, + "ts": 1696941978502.810, "dur": 0.962, + "args": { + "External id": 4553224,"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": 1336753, "tid": 1381210, + "ts": 1696941978507.970, "dur": 7.928, + "args": { + "External id": 4553225,"Record function id": 0, "Sequence number": 45295645, "Fwd thread id": 1, "Ev Idx": 1544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978508.957, "dur": 4.481, + "args": { + "External id": 4553226,"Sequence number": 45295645, "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": 1336753, "tid": 1381210, "ts": 1696941978508.957, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941978510.010, "dur": 3.299, + "args": { + "External id": 4553227,"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": 1336753, "tid": 1381210, + "ts": 1696941978512.416, "dur": 0.787, + "args": { + "External id": 4553228,"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": 1336753, "tid": 1381210, + "ts": 1696941978518.876, "dur": 128.283, + "args": { + "External id": 4553229,"Record function id": 0, "Sequence number": 45295644, "Fwd thread id": 1, "Ev Idx": 1548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978519.723, "dur": 116.934, + "args": { + "External id": 4553230,"Sequence number": 45295644, "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": 1336753, "tid": 1381210, "ts": 1696941978519.723, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941978523.305, "dur": 27.756, + "args": { + "External id": 4553231,"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": 1336753, "tid": 1381210, + "ts": 1696941978523.664, "dur": 26.641, + "args": { + "External id": 4553232,"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": 1336753, "tid": 1381210, + "ts": 1696941978548.876, "dur": 0.998, + "args": { + "External id": 4553233,"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": 1336753, "tid": 1381210, + "ts": 1696941978552.122, "dur": 34.018, + "args": { + "External id": 4553234,"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": 1336753, "tid": 1381210, + "ts": 1696941978589.085, "dur": 2.914, + "args": { + "External id": 4553235,"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": 1336753, "tid": 1381210, + "ts": 1696941978589.726, "dur": 1.788, + "args": { + "External id": 4553236,"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": 1336753, "tid": 1381210, + "ts": 1696941978590.616, "dur": 0.780, + "args": { + "External id": 4553237,"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": 1336753, "tid": 1381210, + "ts": 1696941978593.160, "dur": 2.596, + "args": { + "External id": 4553238,"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": 1336753, "tid": 1381210, + "ts": 1696941978594.393, "dur": 1.000, + "args": { + "External id": 4553239,"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": 1336753, "tid": 1381210, + "ts": 1696941978594.915, "dur": 0.412, + "args": { + "External id": 4553240,"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": 1336753, "tid": 1381210, + "ts": 1696941978601.011, "dur": 35.011, + "args": { + "External id": 4553241,"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": 1336753, "tid": 1381210, + "ts": 1696941978653.024, "dur": 29.619, + "args": { + "External id": 4553242,"Record function id": 0, "Sequence number": 45295643, "Fwd thread id": 1, "Ev Idx": 1561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978654.148, "dur": 7.976, + "args": { + "External id": 4553243,"Sequence number": 45295643, "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": 1336753, "tid": 1381210, "ts": 1696941978654.148, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941978660.074, "dur": 1.868, + "args": { + "External id": 4553244,"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": 1336753, "tid": 1381210, + "ts": 1696941978660.658, "dur": 1.171, + "args": { + "External id": 4553245,"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": 1336753, "tid": 1381210, + "ts": 1696941978664.686, "dur": 15.762, + "args": { + "External id": 4553246,"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": 1336753, "tid": 1381210, + "ts": 1696941978686.164, "dur": 7.765, + "args": { + "External id": 4553247,"Record function id": 0, "Sequence number": 45295642, "Fwd thread id": 1, "Ev Idx": 1566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1696941978687.088, "dur": 5.301, + "args": { + "External id": 4553248,"Sequence number": 45295642, "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": 1336753, "tid": 1381210, "ts": 1696941978687.088, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1696941978688.080, "dur": 4.109, + "args": { + "External id": 4553249,"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": 1336753, "tid": 1381210, + "ts": 1696941978688.604, "dur": 3.127, + "args": { + "External id": 4553250,"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": 1336753, "tid": 1381210, + "ts": 1696941978691.184, "dur": 0.393, + "args": { + "External id": 4553251,"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": 1336753, "tid": 1381210, + "ts": 1696941978697.920, "dur": 5.479, + "args": { + "External id": 4553252,"Record function id": 0, "Ev Idx": 1571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941978699.293, "dur": 3.504, + "args": { + "External id": 4553253,"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": 1336753, "tid": 1381210, + "ts": 1696941978700.499, "dur": 1.905, + "args": { + "External id": 4553254,"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": 1336753, "tid": 1381210, + "ts": 1696941978701.005, "dur": 1.284, + "args": { + "External id": 4553255,"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": 1336753, "tid": 1381210, + "ts": 1696941978707.427, "dur": 401.200, + "args": { + "External id": 4553256,"Record function id": 0, "Sequence number": 45295641, "Fwd thread id": 1, "Ev Idx": 1575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941978710.478, "dur": 361.914, + "args": { + "External id": 4553257,"Sequence number": 45295641, "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": 1336753, "tid": 1381210, "ts": 1696941978710.478, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1696941978742.847, "dur": 1.692, + "args": { + "External id": 4553258,"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": 1336753, "tid": 1381210, + "ts": 1696941978743.251, "dur": 1.168, + "args": { + "External id": 4553259,"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": 1336753, "tid": 1381210, + "ts": 1696941978760.580, "dur": 5.768, + "args": { + "External id": 4553260,"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": 1336753, "tid": 1381210, + "ts": 1696941978775.183, "dur": 1.921, + "args": { + "External id": 4553261,"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": 1336753, "tid": 1381210, + "ts": 1696941978923.862, "dur": 1.796, + "args": { + "External id": 4553262,"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": 1336753, "tid": 1381210, + "ts": 1696941978929.368, "dur": 35.486, + "args": { + "External id": 4553263,"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": 1336753, "tid": 1381210, + "ts": 1696941978941.430, "dur": 0.705, + "args": { + "External id": 4553264,"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": 1336753, "tid": 1381210, + "ts": 1696941978970.348, "dur": 72.414, + "args": { + "External id": 4553265,"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": 1336753, "tid": 1381210, + "ts": 1696941978972.287, "dur": 70.144, + "args": { + "External id": 4553266,"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": 1336753, "tid": 1381210, + "ts": 1696941978975.870, "dur": 4.534, + "args": { + "External id": 4553267,"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": 1336753, "tid": 1381210, + "ts": 1696941978983.692, "dur": 57.804, + "args": { + "External id": 4553268,"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": 1336753, "tid": 1381210, + "ts": 1696941979049.299, "dur": 5.103, + "args": { + "External id": 4553269,"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": 1336753, "tid": 1381210, + "ts": 1696941979052.657, "dur": 1.633, + "args": { + "External id": 4553270,"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": 1336753, "tid": 1381210, + "ts": 1696941979062.501, "dur": 2.049, + "args": { + "External id": 4553271,"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": 1336753, "tid": 1381210, + "ts": 1696941979063.308, "dur": 1.131, + "args": { + "External id": 4553272,"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": 1336753, "tid": 1381210, + "ts": 1696941979088.462, "dur": 15.092, + "args": { + "External id": 4553273,"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": 1336753, "tid": 1381210, + "ts": 1696941979122.489, "dur": 11.468, + "args": { + "External id": 4553274,"Record function id": 0, "Ev Idx": 1593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941979124.681, "dur": 8.529, + "args": { + "External id": 4553275,"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": 1336753, "tid": 1381210, + "ts": 1696941979126.714, "dur": 5.346, + "args": { + "External id": 4553276,"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": 1336753, "tid": 1381210, + "ts": 1696941979129.783, "dur": 2.178, + "args": { + "External id": 4553277,"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": 1336753, "tid": 1381210, + "ts": 1696941979138.889, "dur": 2771.171, + "args": { + "External id": 4553278,"Record function id": 0, "Ev Idx": 1597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.27)", "pid": 1336753, "tid": 1381210, + "ts": 1696941979173.518, "dur": 1006.757, + "args": { + "External id": 4553279,"Record function id": 0, "Ev Idx": 1598 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.26", "pid": 1336753, "tid": 1381210, + "ts": 1696941979201.743, "dur": 970.182, + "args": { + "External id": 4553280,"Record function id": 0, "Ev Idx": 1599 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1696941979214.040, "dur": 942.243, + "args": { + "External id": 4553281,"Record function id": 0, "Ev Idx": 1600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696941979310.097, "dur": 6.618, + "args": { + "External id": 4553282,"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": 1336753, "tid": 1381210, + "ts": 1696941979336.381, "dur": 40.275, + "args": { + "External id": 4553283,"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": 1336753, "tid": 1381210, + "ts": 1696941979342.877, "dur": 3.272, + "args": { + "External id": 4553284,"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": 1336753, "tid": 1381210, + "ts": 1696941979347.406, "dur": 0.885, + "args": { + "External id": 4553285,"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": 1336753, "tid": 1381210, + "ts": 1696941979353.186, "dur": 0.538, + "args": { + "External id": 4553286,"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": 1336753, "tid": 1381210, + "ts": 1696941979354.673, "dur": 0.585, + "args": { + "External id": 4553287,"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": 1336753, "tid": 1381210, + "ts": 1696941979356.129, "dur": 0.354, + "args": { + "External id": 4553288,"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": 1336753, "tid": 1381210, + "ts": 1696941979360.795, "dur": 0.827, + "args": { + "External id": 4553289,"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": 1336753, "tid": 1381210, + "ts": 1696941979362.232, "dur": 0.642, + "args": { + "External id": 4553290,"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": 1336753, "tid": 1381210, + "ts": 1696941979363.315, "dur": 2.208, + "args": { + "External id": 4553291,"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": 1336753, "tid": 1381210, + "ts": 1696941979368.082, "dur": 2.181, + "args": { + "External id": 4553292,"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": 1336753, "tid": 1381210, + "ts": 1696941979394.291, "dur": 33.905, + "args": { + "External id": 4553293,"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": 1336753, "tid": 1381210, + "ts": 1696941979474.014, "dur": 148.354, + "args": { + "External id": 4553294,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696941979487.979, "dur": 6.931, + "args": { + "External id": 4553295,"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": 1336753, "tid": 1381210, + "ts": 1696941979501.943, "dur": 10.062, + "args": { + "External id": 4553296,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696941979506.469, "dur": 5.181, + "args": { + "External id": 4553297,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696941979509.805, "dur": 0.533, + "args": { + "External id": 4553298,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696941979521.464, "dur": 50.893, + "args": { + "External id": 4553299,"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": 1336753, "tid": 1381210, + "ts": 1696941979524.699, "dur": 0.535, + "args": { + "External id": 4553300,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696941979544.097, "dur": 2.746, + "args": { + "External id": 4553301,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696941979548.107, "dur": 0.541, + "args": { + "External id": 4553302,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696941979551.458, "dur": 0.318, + "args": { + "External id": 4553303,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696941979554.187, "dur": 0.292, + "args": { + "External id": 4553304,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696941979555.369, "dur": 2.422, + "args": { + "External id": 4553305,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696941979560.350, "dur": 0.401, + "args": { + "External id": 4553306,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696941979563.196, "dur": 0.430, + "args": { + "External id": 4553307,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696941979565.767, "dur": 0.323, + "args": { + "External id": 4553308,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696941979587.724, "dur": 25.646, + "args": { + "External id": 4553309,"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": 1336753, "tid": 1381210, + "ts": 1696941979694.146, "dur": 352.029, + "args": { + "External id": 4553310,"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": 1336753, "tid": 1381210, + "ts": 1696941979730.953, "dur": 309.540, + "args": { + "External id": 4553311,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696941979742.717, "dur": 291.551, + "args": { + "External id": 4553312,"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": 1336753, "tid": 1381210, + "ts": 1696941980071.625, "dur": 2.898, + "args": { + "External id": 4553313,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941980188.747, "dur": 1697.111, + "args": { + "External id": 4553314,"Sequence number": 45295640, "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": 1336753, "tid": 1381210, "ts": 1696941980188.747, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696941980321.583, "dur": 109.198, + "args": { + "External id": 4553315,"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": 1336753, "tid": 1381210, + "ts": 1696941980476.421, "dur": 42.112, + "args": { + "External id": 4553316,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696941980556.745, "dur": 53.211, + "args": { + "External id": 4553317,"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": 1336753, "tid": 1381210, + "ts": 1696941980619.926, "dur": 31.830, + "args": { + "External id": 4553318,"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": 1336753, "tid": 1381210, + "ts": 1696941980658.059, "dur": 45.159, + "args": { + "External id": 4553319,"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": 1336753, "tid": 1381210, + "ts": 1696941980711.346, "dur": 27.646, + "args": { + "External id": 4553320,"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": 1336753, "tid": 1381210, + "ts": 1696941980746.707, "dur": 43.028, + "args": { + "External id": 4553321,"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": 1336753, "tid": 1381210, + "ts": 1696941980817.986, "dur": 26.579, + "args": { + "External id": 4553322,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696941980863.727, "dur": 32.839, + "args": { + "External id": 4553323,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696941980921.427, "dur": 19.877, + "args": { + "External id": 4553324,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696941980956.955, "dur": 16.705, + "args": { + "External id": 4553325,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696941980983.991, "dur": 69.519, + "args": { + "External id": 4553326,"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": 1336753, "tid": 1381210, + "ts": 1696941981059.135, "dur": 31.974, + "args": { + "External id": 4553327,"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": 1336753, "tid": 1381210, + "ts": 1696941981124.110, "dur": 172.137, + "args": { + "External id": 4553328,"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": 1336753, "tid": 1381210, + "ts": 1696941981204.186, "dur": 7.947, + "args": { + "External id": 4553329,"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": 1336753, "tid": 1381210, + "ts": 1696941981214.061, "dur": 2.375, + "args": { + "External id": 4553330,"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": 1336753, "tid": 1381210, + "ts": 1696941981333.855, "dur": 27.771, + "args": { + "External id": 4553331,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696941981379.601, "dur": 14.988, + "args": { + "External id": 4553332,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696941981402.473, "dur": 31.985, + "args": { + "External id": 4553333,"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": 1336753, "tid": 1381210, + "ts": 1696941981439.864, "dur": 32.583, + "args": { + "External id": 4553334,"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": 1336753, "tid": 1381210, + "ts": 1696941981479.054, "dur": 19.272, + "args": { + "External id": 4553335,"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": 1336753, "tid": 1381210, + "ts": 1696941981505.283, "dur": 43.977, + "args": { + "External id": 4553336,"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": 1336753, "tid": 1381210, + "ts": 1696941981557.959, "dur": 35.545, + "args": { + "External id": 4553337,"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": 1336753, "tid": 1381210, + "ts": 1696941981606.418, "dur": 39.470, + "args": { + "External id": 4553338,"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": 1336753, "tid": 1381210, + "ts": 1696941981672.551, "dur": 27.222, + "args": { + "External id": 4553339,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696941981719.072, "dur": 29.089, + "args": { + "External id": 4553340,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696941981769.119, "dur": 16.934, + "args": { + "External id": 4553341,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696941981800.312, "dur": 13.571, + "args": { + "External id": 4553342,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696941981836.653, "dur": 18.129, + "args": { + "External id": 4553343,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696941981932.511, "dur": 18.272, + "args": { + "External id": 4553344,"Record function id": 0, "Ev Idx": 1663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941981935.650, "dur": 14.276, + "args": { + "External id": 4553345,"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": 1336753, "tid": 1381210, + "ts": 1696941981939.912, "dur": 9.059, + "args": { + "External id": 4553346,"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": 1336753, "tid": 1381210, + "ts": 1696941981944.904, "dur": 3.955, + "args": { + "External id": 4553347,"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": 1336753, "tid": 1381210, + "ts": 1696941981954.655, "dur": 6.549, + "args": { + "External id": 4553348,"Record function id": 0, "Ev Idx": 1667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941981957.779, "dur": 2.992, + "args": { + "External id": 4553349,"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": 1336753, "tid": 1381210, + "ts": 1696941981958.684, "dur": 1.630, + "args": { + "External id": 4553350,"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": 1336753, "tid": 1381210, + "ts": 1696941981959.445, "dur": 0.806, + "args": { + "External id": 4553351,"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": 1336753, "tid": 1381210, + "ts": 1696941981964.530, "dur": 5.275, + "args": { + "External id": 4553352,"Record function id": 0, "Ev Idx": 1671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941981966.279, "dur": 3.087, + "args": { + "External id": 4553353,"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": 1336753, "tid": 1381210, + "ts": 1696941981967.160, "dur": 1.726, + "args": { + "External id": 4553354,"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": 1336753, "tid": 1381210, + "ts": 1696941981967.992, "dur": 0.794, + "args": { + "External id": 4553355,"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": 1336753, "tid": 1381210, + "ts": 1696941981973.190, "dur": 6.603, + "args": { + "External id": 4553356,"Record function id": 0, "Ev Idx": 1675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941981974.094, "dur": 5.276, + "args": { + "External id": 4553357,"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": 1336753, "tid": 1381210, + "ts": 1696941981974.958, "dur": 3.980, + "args": { + "External id": 4553358,"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": 1336753, "tid": 1381210, + "ts": 1696941981975.348, "dur": 3.479, + "args": { + "External id": 4553359,"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": 1336753, "tid": 1381210, + "ts": 1696941981982.823, "dur": 41.980, + "args": { + "External id": 4553360,"Record function id": 0, "Ev Idx": 1679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941981983.874, "dur": 39.600, + "args": { + "External id": 4553361,"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": 1336753, "tid": 1381210, + "ts": 1696941982019.227, "dur": 3.106, + "args": { + "External id": 4553362,"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": 1336753, "tid": 1381210, + "ts": 1696941982020.224, "dur": 1.863, + "args": { + "External id": 4553363,"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": 1336753, "tid": 1381210, + "ts": 1696941982029.910, "dur": 5.566, + "args": { + "External id": 4553364,"Record function id": 0, "Ev Idx": 1683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941982031.633, "dur": 3.441, + "args": { + "External id": 4553365,"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": 1336753, "tid": 1381210, + "ts": 1696941982032.843, "dur": 1.737, + "args": { + "External id": 4553366,"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": 1336753, "tid": 1381210, + "ts": 1696941982033.684, "dur": 0.829, + "args": { + "External id": 4553367,"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": 1336753, "tid": 1381210, + "ts": 1696941982038.939, "dur": 4.202, + "args": { + "External id": 4553368,"Record function id": 0, "Ev Idx": 1687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941982040.296, "dur": 2.394, + "args": { + "External id": 4553369,"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": 1336753, "tid": 1381210, + "ts": 1696941982040.880, "dur": 1.410, + "args": { + "External id": 4553370,"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": 1336753, "tid": 1381210, + "ts": 1696941982041.523, "dur": 0.697, + "args": { + "External id": 4553371,"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": 1336753, "tid": 1381210, + "ts": 1696941982046.317, "dur": 6.114, + "args": { + "External id": 4553372,"Record function id": 0, "Ev Idx": 1691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941982047.757, "dur": 4.251, + "args": { + "External id": 4553373,"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": 1336753, "tid": 1381210, + "ts": 1696941982048.227, "dur": 3.203, + "args": { + "External id": 4553374,"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": 1336753, "tid": 1381210, + "ts": 1696941982050.692, "dur": 0.639, + "args": { + "External id": 4553375,"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": 1336753, "tid": 1381210, + "ts": 1696941982055.524, "dur": 3.993, + "args": { + "External id": 4553376,"Record function id": 0, "Ev Idx": 1695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696941982056.853, "dur": 2.245, + "args": { + "External id": 4553377,"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": 1336753, "tid": 1381210, + "ts": 1696941982057.313, "dur": 1.354, + "args": { + "External id": 4553378,"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": 1336753, "tid": 1381210, + "ts": 1696941982057.835, "dur": 0.739, + "args": { + "External id": 4553379,"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": 1336753, "tid": 1381210, + "ts": 1696941982065.881, "dur": 168352.981, + "args": { + "External id": 4553380,"Record function id": 0, "Sequence number": 45295639, "Fwd thread id": 1, "Ev Idx": 1699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696941982067.237, "dur": 168343.421, + "args": { + "External id": 4553381,"Sequence number": 45295639, "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": 1336753, "tid": 1381210, "ts": 1696941982067.237, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.27)", "pid": 1336753, "tid": 1381210, + "ts": 1696941982104.845, "dur": 46.589, + "args": { + "External id": 4553382,"Record function id": 0, "Ev Idx": 1701 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.27)", "pid": 1336753, "tid": 1381210, + "ts": 1696941982162.956, "dur": 91.677, + "args": { + "External id": 4553383,"Record function id": 0, "Ev Idx": 1702 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.27)", "pid": 1336753, "tid": 1381210, + "ts": 1696941982262.078, "dur": 168140.262, + "args": { + "External id": 4553384,"Record function id": 0, "Ev Idx": 1703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696941982327.375, "dur": 7.424, + "args": { + "External id": 4553385,"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": 1336753, "tid": 1381210, + "ts": 1696941982347.976, "dur": 4.739, + "args": { + "External id": 4553386,"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": 1336753, "tid": 1381210, + "ts": 1696941982368.523, "dur": 167143.343, + "args": { + "External id": 4553387,"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": 1336753, "tid": 1381210, + "ts": 1696941982383.048, "dur": 167118.448, + "args": { + "External id": 4553388,"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": 1336753, "tid": 1381210, + "ts": 1696941982446.481, "dur": 5.686, + "args": { + "External id": 4553389,"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": 1336753, "tid": 1381210, + "ts": 1696941982461.892, "dur": 166996.939, + "args": { + "External id": 4553390,"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": 1336753, "tid": 1381210, + "ts": 1696941982464.741, "dur": 166993.206, + "args": { + "External id": 4553391,"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": 1336753, "tid": 1381210, + "ts": 1696941982468.180, "dur": 6.310, + "args": { + "External id": 4553392,"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": 1336753, "tid": 1381210, + "ts": 1696941982476.150, "dur": 166977.686, + "args": { + "External id": 4553393,"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": 1336753, "tid": 1381210, + "ts": 1696942149625.589, "dur": 9.683, + "args": { + "External id": 4553394,"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": 1336753, "tid": 1381210, + "ts": 1696942149628.839, "dur": 5.904, + "args": { + "External id": 4553395,"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": 1336753, "tid": 1381210, + "ts": 1696942149672.962, "dur": 410.766, + "args": { + "External id": 4553396,"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": 1336753, "tid": 1381210, + "ts": 1696942149707.992, "dur": 370.689, + "args": { + "External id": 4553397,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942149726.045, "dur": 346.561, + "args": { + "External id": 4553398,"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": 1336753, "tid": 1381210, + "ts": 1696942150109.423, "dur": 2.175, + "args": { + "External id": 4553399,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942150175.556, "dur": 7.037, + "args": { + "External id": 4553400,"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": 1336753, "tid": 1381210, + "ts": 1696942150236.000, "dur": 1.339, + "args": { + "External id": 4553401,"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": 1336753, "tid": 1381210, + "ts": 1696942150254.004, "dur": 1.500, + "args": { + "External id": 4553402,"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": 1336753, "tid": 1381210, + "ts": 1696942150271.937, "dur": 1.262, + "args": { + "External id": 4553403,"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": 1336753, "tid": 1381210, + "ts": 1696942150285.074, "dur": 1.065, + "args": { + "External id": 4553404,"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": 1336753, "tid": 1381210, + "ts": 1696942150295.915, "dur": 0.926, + "args": { + "External id": 4553405,"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": 1336753, "tid": 1381210, + "ts": 1696942150308.374, "dur": 1.498, + "args": { + "External id": 4553406,"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": 1336753, "tid": 1381210, + "ts": 1696942150323.703, "dur": 2.929, + "args": { + "External id": 4553407,"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": 1336753, "tid": 1381210, + "ts": 1696942150337.782, "dur": 1.054, + "args": { + "External id": 4553408,"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": 1336753, "tid": 1381210, + "ts": 1696942150433.554, "dur": 2867.407, + "args": { + "External id": 4553409,"Record function id": 0, "Ev Idx": 1728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1696942150452.696, "dur": 1142.343, + "args": { + "External id": 4553410,"Record function id": 0, "Ev Idx": 1729 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1696942150467.913, "dur": 372.225, + "args": { + "External id": 4553411,"Record function id": 0, "Ev Idx": 1730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942150572.914, "dur": 4.343, + "args": { + "External id": 4553412,"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": 1336753, "tid": 1381210, + "ts": 1696942150581.404, "dur": 1.008, + "args": { + "External id": 4553413,"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": 1336753, "tid": 1381210, + "ts": 1696942150584.061, "dur": 1.142, + "args": { + "External id": 4553414,"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": 1336753, "tid": 1381210, + "ts": 1696942150586.780, "dur": 2.647, + "args": { + "External id": 4553415,"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": 1336753, "tid": 1381210, + "ts": 1696942150592.712, "dur": 1.041, + "args": { + "External id": 4553416,"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": 1336753, "tid": 1381210, + "ts": 1696942150595.136, "dur": 1.105, + "args": { + "External id": 4553417,"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": 1336753, "tid": 1381210, + "ts": 1696942150597.634, "dur": 2.683, + "args": { + "External id": 4553418,"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": 1336753, "tid": 1381210, + "ts": 1696942150601.611, "dur": 0.892, + "args": { + "External id": 4553419,"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": 1336753, "tid": 1381210, + "ts": 1696942150606.986, "dur": 1.017, + "args": { + "External id": 4553420,"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": 1336753, "tid": 1381210, + "ts": 1696942150609.443, "dur": 1.069, + "args": { + "External id": 4553421,"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": 1336753, "tid": 1381210, + "ts": 1696942150631.897, "dur": 178.804, + "args": { + "External id": 4553422,"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": 1336753, "tid": 1381210, + "ts": 1696942150656.930, "dur": 149.135, + "args": { + "External id": 4553423,"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": 1336753, "tid": 1381210, + "ts": 1696942150682.548, "dur": 13.325, + "args": { + "External id": 4553424,"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": 1336753, "tid": 1381210, + "ts": 1696942150700.046, "dur": 76.702, + "args": { + "External id": 4553425,"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": 1336753, "tid": 1381210, + "ts": 1696942150702.674, "dur": 73.704, + "args": { + "External id": 4553426,"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": 1336753, "tid": 1381210, + "ts": 1696942150706.326, "dur": 12.946, + "args": { + "External id": 4553427,"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": 1336753, "tid": 1381210, + "ts": 1696942150723.112, "dur": 52.530, + "args": { + "External id": 4553428,"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": 1336753, "tid": 1381210, + "ts": 1696942150934.709, "dur": 652.128, + "args": { + "External id": 4553429,"Record function id": 0, "Ev Idx": 1748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1696942150950.184, "dur": 623.478, + "args": { + "External id": 4553430,"Record function id": 0, "Ev Idx": 1749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942151051.230, "dur": 7.013, + "args": { + "External id": 4553431,"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": 1336753, "tid": 1381210, + "ts": 1696942151074.863, "dur": 39.901, + "args": { + "External id": 4553432,"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": 1336753, "tid": 1381210, + "ts": 1696942151081.551, "dur": 3.316, + "args": { + "External id": 4553433,"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": 1336753, "tid": 1381210, + "ts": 1696942151086.213, "dur": 0.549, + "args": { + "External id": 4553434,"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": 1336753, "tid": 1381210, + "ts": 1696942151087.550, "dur": 0.588, + "args": { + "External id": 4553435,"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": 1336753, "tid": 1381210, + "ts": 1696942151092.942, "dur": 0.499, + "args": { + "External id": 4553436,"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": 1336753, "tid": 1381210, + "ts": 1696942151094.116, "dur": 0.699, + "args": { + "External id": 4553437,"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": 1336753, "tid": 1381210, + "ts": 1696942151095.434, "dur": 0.279, + "args": { + "External id": 4553438,"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": 1336753, "tid": 1381210, + "ts": 1696942151100.062, "dur": 2.284, + "args": { + "External id": 4553439,"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": 1336753, "tid": 1381210, + "ts": 1696942151102.839, "dur": 0.619, + "args": { + "External id": 4553440,"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": 1336753, "tid": 1381210, + "ts": 1696942151105.534, "dur": 2.518, + "args": { + "External id": 4553441,"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": 1336753, "tid": 1381210, + "ts": 1696942151135.828, "dur": 33.789, + "args": { + "External id": 4553442,"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": 1336753, "tid": 1381210, + "ts": 1696942151202.537, "dur": 108.491, + "args": { + "External id": 4553443,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942151212.698, "dur": 4.896, + "args": { + "External id": 4553444,"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": 1336753, "tid": 1381210, + "ts": 1696942151223.073, "dur": 12.087, + "args": { + "External id": 4553445,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942151227.249, "dur": 7.512, + "args": { + "External id": 4553446,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942151232.913, "dur": 0.743, + "args": { + "External id": 4553447,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942151242.326, "dur": 28.895, + "args": { + "External id": 4553448,"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": 1336753, "tid": 1381210, + "ts": 1696942151243.726, "dur": 0.668, + "args": { + "External id": 4553449,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942151247.281, "dur": 1.977, + "args": { + "External id": 4553450,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942151250.163, "dur": 0.227, + "args": { + "External id": 4553451,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942151250.859, "dur": 2.363, + "args": { + "External id": 4553452,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942151257.564, "dur": 0.285, + "args": { + "External id": 4553453,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942151258.472, "dur": 0.342, + "args": { + "External id": 4553454,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942151261.126, "dur": 0.562, + "args": { + "External id": 4553455,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942151264.046, "dur": 0.239, + "args": { + "External id": 4553456,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942151264.930, "dur": 0.557, + "args": { + "External id": 4553457,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942151284.073, "dur": 19.032, + "args": { + "External id": 4553458,"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": 1336753, "tid": 1381210, + "ts": 1696942151358.913, "dur": 124.118, + "args": { + "External id": 4553459,"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": 1336753, "tid": 1381210, + "ts": 1696942151389.654, "dur": 90.142, + "args": { + "External id": 4553460,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942151401.406, "dur": 74.034, + "args": { + "External id": 4553461,"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": 1336753, "tid": 1381210, + "ts": 1696942151501.736, "dur": 1.833, + "args": { + "External id": 4553462,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942151602.856, "dur": 1674.598, + "args": { + "External id": 4553463,"Sequence number": 45295638, "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": 1336753, "tid": 1381210, "ts": 1696942151602.856, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942151717.157, "dur": 104.231, + "args": { + "External id": 4553464,"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": 1336753, "tid": 1381210, + "ts": 1696942151866.080, "dur": 38.811, + "args": { + "External id": 4553465,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942151922.544, "dur": 46.264, + "args": { + "External id": 4553466,"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": 1336753, "tid": 1381210, + "ts": 1696942151978.565, "dur": 75.011, + "args": { + "External id": 4553467,"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": 1336753, "tid": 1381210, + "ts": 1696942152069.796, "dur": 46.437, + "args": { + "External id": 4553468,"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": 1336753, "tid": 1381210, + "ts": 1696942152123.378, "dur": 26.822, + "args": { + "External id": 4553469,"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": 1336753, "tid": 1381210, + "ts": 1696942152157.831, "dur": 41.376, + "args": { + "External id": 4553470,"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": 1336753, "tid": 1381210, + "ts": 1696942152225.283, "dur": 25.451, + "args": { + "External id": 4553471,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942152274.648, "dur": 28.444, + "args": { + "External id": 4553472,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942152326.193, "dur": 19.221, + "args": { + "External id": 4553473,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942152364.242, "dur": 14.871, + "args": { + "External id": 4553474,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942152386.915, "dur": 27.256, + "args": { + "External id": 4553475,"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": 1336753, "tid": 1381210, + "ts": 1696942152417.178, "dur": 31.851, + "args": { + "External id": 4553476,"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": 1336753, "tid": 1381210, + "ts": 1696942152479.826, "dur": 192.025, + "args": { + "External id": 4553477,"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": 1336753, "tid": 1381210, + "ts": 1696942152579.392, "dur": 6.583, + "args": { + "External id": 4553478,"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": 1336753, "tid": 1381210, + "ts": 1696942152587.975, "dur": 2.694, + "args": { + "External id": 4553479,"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": 1336753, "tid": 1381210, + "ts": 1696942152716.647, "dur": 27.884, + "args": { + "External id": 4553480,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942152757.076, "dur": 14.020, + "args": { + "External id": 4553481,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942152778.328, "dur": 37.517, + "args": { + "External id": 4553482,"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": 1336753, "tid": 1381210, + "ts": 1696942152821.328, "dur": 34.187, + "args": { + "External id": 4553483,"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": 1336753, "tid": 1381210, + "ts": 1696942152867.294, "dur": 34.803, + "args": { + "External id": 4553484,"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": 1336753, "tid": 1381210, + "ts": 1696942152912.001, "dur": 35.069, + "args": { + "External id": 4553485,"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": 1336753, "tid": 1381210, + "ts": 1696942152954.123, "dur": 19.496, + "args": { + "External id": 4553486,"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": 1336753, "tid": 1381210, + "ts": 1696942153014.515, "dur": 36.483, + "args": { + "External id": 4553487,"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": 1336753, "tid": 1381210, + "ts": 1696942153080.222, "dur": 22.487, + "args": { + "External id": 4553488,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942153123.568, "dur": 28.520, + "args": { + "External id": 4553489,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942153168.492, "dur": 16.447, + "args": { + "External id": 4553490,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942153204.256, "dur": 14.245, + "args": { + "External id": 4553491,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942153232.783, "dur": 16.669, + "args": { + "External id": 4553492,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942153323.897, "dur": 14.473, + "args": { + "External id": 4553493,"Record function id": 0, "Ev Idx": 1812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942153327.046, "dur": 10.488, + "args": { + "External id": 4553494,"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": 1336753, "tid": 1381210, + "ts": 1696942153331.268, "dur": 5.423, + "args": { + "External id": 4553495,"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": 1336753, "tid": 1381210, + "ts": 1696942153332.635, "dur": 3.954, + "args": { + "External id": 4553496,"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": 1336753, "tid": 1381210, + "ts": 1696942153342.274, "dur": 5.061, + "args": { + "External id": 4553497,"Record function id": 0, "Ev Idx": 1816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942153343.625, "dur": 3.304, + "args": { + "External id": 4553498,"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": 1336753, "tid": 1381210, + "ts": 1696942153344.938, "dur": 1.503, + "args": { + "External id": 4553499,"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": 1336753, "tid": 1381210, + "ts": 1696942153345.484, "dur": 0.888, + "args": { + "External id": 4553500,"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": 1336753, "tid": 1381210, + "ts": 1696942153350.824, "dur": 5.701, + "args": { + "External id": 4553501,"Record function id": 0, "Ev Idx": 1820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942153352.051, "dur": 4.072, + "args": { + "External id": 4553502,"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": 1336753, "tid": 1381210, + "ts": 1696942153352.591, "dur": 3.065, + "args": { + "External id": 4553503,"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": 1336753, "tid": 1381210, + "ts": 1696942153353.080, "dur": 2.482, + "args": { + "External id": 4553504,"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": 1336753, "tid": 1381210, + "ts": 1696942153359.794, "dur": 4.416, + "args": { + "External id": 4553505,"Record function id": 0, "Ev Idx": 1824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942153361.000, "dur": 2.829, + "args": { + "External id": 4553506,"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": 1336753, "tid": 1381210, + "ts": 1696942153361.697, "dur": 1.698, + "args": { + "External id": 4553507,"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": 1336753, "tid": 1381210, + "ts": 1696942153362.278, "dur": 1.053, + "args": { + "External id": 4553508,"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": 1336753, "tid": 1381210, + "ts": 1696942153367.435, "dur": 3.945, + "args": { + "External id": 4553509,"Record function id": 0, "Ev Idx": 1828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942153368.664, "dur": 2.338, + "args": { + "External id": 4553510,"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": 1336753, "tid": 1381210, + "ts": 1696942153369.264, "dur": 1.274, + "args": { + "External id": 4553511,"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": 1336753, "tid": 1381210, + "ts": 1696942153369.738, "dur": 0.733, + "args": { + "External id": 4553512,"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": 1336753, "tid": 1381210, + "ts": 1696942153374.509, "dur": 6.427, + "args": { + "External id": 4553513,"Record function id": 0, "Ev Idx": 1832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942153377.420, "dur": 3.085, + "args": { + "External id": 4553514,"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": 1336753, "tid": 1381210, + "ts": 1696942153378.275, "dur": 1.784, + "args": { + "External id": 4553515,"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": 1336753, "tid": 1381210, + "ts": 1696942153378.869, "dur": 1.124, + "args": { + "External id": 4553516,"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": 1336753, "tid": 1381210, + "ts": 1696942153384.201, "dur": 3.577, + "args": { + "External id": 4553517,"Record function id": 0, "Ev Idx": 1836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942153385.184, "dur": 2.173, + "args": { + "External id": 4553518,"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": 1336753, "tid": 1381210, + "ts": 1696942153385.867, "dur": 1.028, + "args": { + "External id": 4553519,"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": 1336753, "tid": 1381210, + "ts": 1696942153386.191, "dur": 0.639, + "args": { + "External id": 4553520,"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": 1336753, "tid": 1381210, + "ts": 1696942153390.814, "dur": 5.438, + "args": { + "External id": 4553521,"Record function id": 0, "Ev Idx": 1840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942153391.826, "dur": 4.028, + "args": { + "External id": 4553522,"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": 1336753, "tid": 1381210, + "ts": 1696942153392.640, "dur": 2.775, + "args": { + "External id": 4553523,"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": 1336753, "tid": 1381210, + "ts": 1696942153394.787, "dur": 0.560, + "args": { + "External id": 4553524,"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": 1336753, "tid": 1381210, + "ts": 1696942153399.331, "dur": 3.353, + "args": { + "External id": 4553525,"Record function id": 0, "Ev Idx": 1844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942153400.326, "dur": 1.960, + "args": { + "External id": 4553526,"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": 1336753, "tid": 1381210, + "ts": 1696942153400.911, "dur": 0.945, + "args": { + "External id": 4553527,"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": 1336753, "tid": 1381210, + "ts": 1696942153401.189, "dur": 0.599, + "args": { + "External id": 4553528,"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": 1336753, "tid": 1381210, + "ts": 1696942153406.875, "dur": 38323.843, + "args": { + "External id": 4553529,"Record function id": 0, "Sequence number": 45295637, "Fwd thread id": 1, "Ev Idx": 1848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942153408.169, "dur": 38313.641, + "args": { + "External id": 4553530,"Sequence number": 45295637, "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": 1336753, "tid": 1381210, "ts": 1696942153408.169, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1696942153436.370, "dur": 36.419, + "args": { + "External id": 4553531,"Record function id": 0, "Ev Idx": 1850 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1696942153480.308, "dur": 80.326, + "args": { + "External id": 4553532,"Record function id": 0, "Ev Idx": 1851 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1696942153570.548, "dur": 38141.879, + "args": { + "External id": 4553533,"Record function id": 0, "Ev Idx": 1852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942153661.226, "dur": 7.160, + "args": { + "External id": 4553534,"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": 1336753, "tid": 1381210, + "ts": 1696942153678.067, "dur": 7.096, + "args": { + "External id": 4553535,"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": 1336753, "tid": 1381210, + "ts": 1696942153704.466, "dur": 37132.481, + "args": { + "External id": 4553536,"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": 1336753, "tid": 1381210, + "ts": 1696942153718.990, "dur": 37108.780, + "args": { + "External id": 4553537,"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": 1336753, "tid": 1381210, + "ts": 1696942153772.921, "dur": 13.947, + "args": { + "External id": 4553538,"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": 1336753, "tid": 1381210, + "ts": 1696942153794.686, "dur": 36994.678, + "args": { + "External id": 4553539,"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": 1336753, "tid": 1381210, + "ts": 1696942153797.031, "dur": 36991.607, + "args": { + "External id": 4553540,"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": 1336753, "tid": 1381210, + "ts": 1696942153802.119, "dur": 4.826, + "args": { + "External id": 4553541,"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": 1336753, "tid": 1381210, + "ts": 1696942153808.704, "dur": 36975.849, + "args": { + "External id": 4553542,"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": 1336753, "tid": 1381210, + "ts": 1696942190928.499, "dur": 11.270, + "args": { + "External id": 4553543,"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": 1336753, "tid": 1381210, + "ts": 1696942190931.332, "dur": 8.084, + "args": { + "External id": 4553544,"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": 1336753, "tid": 1381210, + "ts": 1696942190972.471, "dur": 419.380, + "args": { + "External id": 4553545,"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": 1336753, "tid": 1381210, + "ts": 1696942191031.371, "dur": 355.433, + "args": { + "External id": 4553546,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942191044.140, "dur": 337.596, + "args": { + "External id": 4553547,"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": 1336753, "tid": 1381210, + "ts": 1696942191412.979, "dur": 2.668, + "args": { + "External id": 4553548,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942191476.105, "dur": 7.051, + "args": { + "External id": 4553549,"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": 1336753, "tid": 1381210, + "ts": 1696942191545.306, "dur": 2.010, + "args": { + "External id": 4553550,"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": 1336753, "tid": 1381210, + "ts": 1696942191567.447, "dur": 3.672, + "args": { + "External id": 4553551,"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": 1336753, "tid": 1381210, + "ts": 1696942191584.862, "dur": 0.983, + "args": { + "External id": 4553552,"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": 1336753, "tid": 1381210, + "ts": 1696942191597.144, "dur": 0.964, + "args": { + "External id": 4553553,"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": 1336753, "tid": 1381210, + "ts": 1696942191609.220, "dur": 1.218, + "args": { + "External id": 4553554,"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": 1336753, "tid": 1381210, + "ts": 1696942191620.253, "dur": 3.332, + "args": { + "External id": 4553555,"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": 1336753, "tid": 1381210, + "ts": 1696942191636.006, "dur": 2.739, + "args": { + "External id": 4553556,"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": 1336753, "tid": 1381210, + "ts": 1696942191649.692, "dur": 0.844, + "args": { + "External id": 4553557,"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": 1336753, "tid": 1381210, + "ts": 1696942191747.834, "dur": 2809.071, + "args": { + "External id": 4553558,"Record function id": 0, "Ev Idx": 1877 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1696942191767.951, "dur": 1089.405, + "args": { + "External id": 4553559,"Record function id": 0, "Ev Idx": 1878 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1696942191782.653, "dur": 381.626, + "args": { + "External id": 4553560,"Record function id": 0, "Ev Idx": 1879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942191867.084, "dur": 4.333, + "args": { + "External id": 4553561,"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": 1336753, "tid": 1381210, + "ts": 1696942191874.392, "dur": 1.347, + "args": { + "External id": 4553562,"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": 1336753, "tid": 1381210, + "ts": 1696942191877.530, "dur": 3.184, + "args": { + "External id": 4553563,"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": 1336753, "tid": 1381210, + "ts": 1696942191882.164, "dur": 1.129, + "args": { + "External id": 4553564,"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": 1336753, "tid": 1381210, + "ts": 1696942191886.438, "dur": 0.792, + "args": { + "External id": 4553565,"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": 1336753, "tid": 1381210, + "ts": 1696942191888.559, "dur": 1.211, + "args": { + "External id": 4553566,"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": 1336753, "tid": 1381210, + "ts": 1696942191893.271, "dur": 3.073, + "args": { + "External id": 4553567,"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": 1336753, "tid": 1381210, + "ts": 1696942191897.892, "dur": 1.064, + "args": { + "External id": 4553568,"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": 1336753, "tid": 1381210, + "ts": 1696942191902.136, "dur": 1.102, + "args": { + "External id": 4553569,"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": 1336753, "tid": 1381210, + "ts": 1696942191904.579, "dur": 0.946, + "args": { + "External id": 4553570,"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": 1336753, "tid": 1381210, + "ts": 1696942191925.113, "dur": 205.915, + "args": { + "External id": 4553571,"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": 1336753, "tid": 1381210, + "ts": 1696942191942.527, "dur": 183.421, + "args": { + "External id": 4553572,"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": 1336753, "tid": 1381210, + "ts": 1696942191961.772, "dur": 14.484, + "args": { + "External id": 4553573,"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": 1336753, "tid": 1381210, + "ts": 1696942191979.736, "dur": 118.713, + "args": { + "External id": 4553574,"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": 1336753, "tid": 1381210, + "ts": 1696942192020.730, "dur": 77.388, + "args": { + "External id": 4553575,"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": 1336753, "tid": 1381210, + "ts": 1696942192024.656, "dur": 13.631, + "args": { + "External id": 4553576,"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": 1336753, "tid": 1381210, + "ts": 1696942192040.342, "dur": 57.185, + "args": { + "External id": 4553577,"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": 1336753, "tid": 1381210, + "ts": 1696942192258.280, "dur": 590.847, + "args": { + "External id": 4553578,"Record function id": 0, "Ev Idx": 1897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1696942192276.576, "dur": 558.497, + "args": { + "External id": 4553579,"Record function id": 0, "Ev Idx": 1898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942192338.697, "dur": 4.705, + "args": { + "External id": 4553580,"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": 1336753, "tid": 1381210, + "ts": 1696942192359.343, "dur": 35.503, + "args": { + "External id": 4553581,"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": 1336753, "tid": 1381210, + "ts": 1696942192365.382, "dur": 1.629, + "args": { + "External id": 4553582,"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": 1336753, "tid": 1381210, + "ts": 1696942192370.425, "dur": 0.546, + "args": { + "External id": 4553583,"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": 1336753, "tid": 1381210, + "ts": 1696942192371.555, "dur": 0.372, + "args": { + "External id": 4553584,"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": 1336753, "tid": 1381210, + "ts": 1696942192374.253, "dur": 2.320, + "args": { + "External id": 4553585,"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": 1336753, "tid": 1381210, + "ts": 1696942192377.143, "dur": 0.326, + "args": { + "External id": 4553586,"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": 1336753, "tid": 1381210, + "ts": 1696942192379.802, "dur": 2.156, + "args": { + "External id": 4553587,"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": 1336753, "tid": 1381210, + "ts": 1696942192384.535, "dur": 0.334, + "args": { + "External id": 4553588,"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": 1336753, "tid": 1381210, + "ts": 1696942192385.441, "dur": 0.403, + "args": { + "External id": 4553589,"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": 1336753, "tid": 1381210, + "ts": 1696942192387.989, "dur": 0.293, + "args": { + "External id": 4553590,"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": 1336753, "tid": 1381210, + "ts": 1696942192404.299, "dur": 29.318, + "args": { + "External id": 4553591,"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": 1336753, "tid": 1381210, + "ts": 1696942192464.357, "dur": 139.466, + "args": { + "External id": 4553592,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942192474.221, "dur": 3.458, + "args": { + "External id": 4553593,"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": 1336753, "tid": 1381210, + "ts": 1696942192482.606, "dur": 12.420, + "args": { + "External id": 4553594,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942192486.654, "dur": 7.956, + "args": { + "External id": 4553595,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942192491.374, "dur": 2.038, + "args": { + "External id": 4553596,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942192501.357, "dur": 56.232, + "args": { + "External id": 4553597,"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": 1336753, "tid": 1381210, + "ts": 1696942192502.834, "dur": 0.385, + "args": { + "External id": 4553598,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942192506.090, "dur": 0.330, + "args": { + "External id": 4553599,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942192518.760, "dur": 2.294, + "args": { + "External id": 4553600,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942192524.928, "dur": 0.584, + "args": { + "External id": 4553601,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942192540.942, "dur": 0.485, + "args": { + "External id": 4553602,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942192542.662, "dur": 1.912, + "args": { + "External id": 4553603,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942192546.532, "dur": 0.385, + "args": { + "External id": 4553604,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942192547.524, "dur": 0.361, + "args": { + "External id": 4553605,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942192550.707, "dur": 0.395, + "args": { + "External id": 4553606,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942192570.353, "dur": 25.244, + "args": { + "External id": 4553607,"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": 1336753, "tid": 1381210, + "ts": 1696942192649.719, "dur": 119.177, + "args": { + "External id": 4553608,"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": 1336753, "tid": 1381210, + "ts": 1696942192679.404, "dur": 86.133, + "args": { + "External id": 4553609,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942192687.985, "dur": 72.766, + "args": { + "External id": 4553610,"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": 1336753, "tid": 1381210, + "ts": 1696942192783.637, "dur": 1.745, + "args": { + "External id": 4553611,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942192864.511, "dur": 1653.521, + "args": { + "External id": 4553612,"Sequence number": 45295636, "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": 1336753, "tid": 1381210, "ts": 1696942192864.511, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942192975.160, "dur": 141.222, + "args": { + "External id": 4553613,"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": 1336753, "tid": 1381210, + "ts": 1696942193166.100, "dur": 39.321, + "args": { + "External id": 4553614,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942193223.263, "dur": 47.735, + "args": { + "External id": 4553615,"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": 1336753, "tid": 1381210, + "ts": 1696942193282.660, "dur": 32.111, + "args": { + "External id": 4553616,"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": 1336753, "tid": 1381210, + "ts": 1696942193320.952, "dur": 44.823, + "args": { + "External id": 4553617,"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": 1336753, "tid": 1381210, + "ts": 1696942193372.235, "dur": 27.615, + "args": { + "External id": 4553618,"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": 1336753, "tid": 1381210, + "ts": 1696942193415.706, "dur": 42.986, + "args": { + "External id": 4553619,"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": 1336753, "tid": 1381210, + "ts": 1696942193488.564, "dur": 25.673, + "args": { + "External id": 4553620,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942193553.563, "dur": 29.268, + "args": { + "External id": 4553621,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942193607.689, "dur": 18.757, + "args": { + "External id": 4553622,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942193645.146, "dur": 13.996, + "args": { + "External id": 4553623,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942193669.103, "dur": 31.230, + "args": { + "External id": 4553624,"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": 1336753, "tid": 1381210, + "ts": 1696942193704.049, "dur": 32.272, + "args": { + "External id": 4553625,"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": 1336753, "tid": 1381210, + "ts": 1696942193765.284, "dur": 173.811, + "args": { + "External id": 4553626,"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": 1336753, "tid": 1381210, + "ts": 1696942193846.667, "dur": 9.081, + "args": { + "External id": 4553627,"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": 1336753, "tid": 1381210, + "ts": 1696942193857.448, "dur": 2.580, + "args": { + "External id": 4553628,"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": 1336753, "tid": 1381210, + "ts": 1696942193975.000, "dur": 62.598, + "args": { + "External id": 4553629,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942194054.435, "dur": 14.397, + "args": { + "External id": 4553630,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942194078.598, "dur": 37.304, + "args": { + "External id": 4553631,"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": 1336753, "tid": 1381210, + "ts": 1696942194122.077, "dur": 33.373, + "args": { + "External id": 4553632,"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": 1336753, "tid": 1381210, + "ts": 1696942194163.468, "dur": 19.219, + "args": { + "External id": 4553633,"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": 1336753, "tid": 1381210, + "ts": 1696942194187.001, "dur": 41.466, + "args": { + "External id": 4553634,"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": 1336753, "tid": 1381210, + "ts": 1696942194240.364, "dur": 23.211, + "args": { + "External id": 4553635,"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": 1336753, "tid": 1381210, + "ts": 1696942194270.416, "dur": 30.875, + "args": { + "External id": 4553636,"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": 1336753, "tid": 1381210, + "ts": 1696942194328.770, "dur": 23.810, + "args": { + "External id": 4553637,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942194371.207, "dur": 26.898, + "args": { + "External id": 4553638,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942194414.144, "dur": 18.380, + "args": { + "External id": 4553639,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942194448.330, "dur": 14.031, + "args": { + "External id": 4553640,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942194476.008, "dur": 15.053, + "args": { + "External id": 4553641,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942194580.423, "dur": 15.516, + "args": { + "External id": 4553642,"Record function id": 0, "Ev Idx": 1961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942194583.848, "dur": 11.082, + "args": { + "External id": 4553643,"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": 1336753, "tid": 1381210, + "ts": 1696942194587.794, "dur": 6.185, + "args": { + "External id": 4553644,"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": 1336753, "tid": 1381210, + "ts": 1696942194589.503, "dur": 4.392, + "args": { + "External id": 4553645,"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": 1336753, "tid": 1381210, + "ts": 1696942194599.833, "dur": 7.864, + "args": { + "External id": 4553646,"Record function id": 0, "Ev Idx": 1965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942194602.402, "dur": 4.785, + "args": { + "External id": 4553647,"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": 1336753, "tid": 1381210, + "ts": 1696942194603.369, "dur": 3.400, + "args": { + "External id": 4553648,"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": 1336753, "tid": 1381210, + "ts": 1696942194603.916, "dur": 2.782, + "args": { + "External id": 4553649,"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": 1336753, "tid": 1381210, + "ts": 1696942194611.162, "dur": 4.320, + "args": { + "External id": 4553650,"Record function id": 0, "Ev Idx": 1969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942194612.549, "dur": 2.532, + "args": { + "External id": 4553651,"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": 1336753, "tid": 1381210, + "ts": 1696942194613.053, "dur": 1.530, + "args": { + "External id": 4553652,"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": 1336753, "tid": 1381210, + "ts": 1696942194613.774, "dur": 0.722, + "args": { + "External id": 4553653,"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": 1336753, "tid": 1381210, + "ts": 1696942194618.614, "dur": 3.528, + "args": { + "External id": 4553654,"Record function id": 0, "Ev Idx": 1973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942194619.674, "dur": 1.993, + "args": { + "External id": 4553655,"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": 1336753, "tid": 1381210, + "ts": 1696942194620.164, "dur": 0.933, + "args": { + "External id": 4553656,"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": 1336753, "tid": 1381210, + "ts": 1696942194620.445, "dur": 0.579, + "args": { + "External id": 4553657,"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": 1336753, "tid": 1381210, + "ts": 1696942194625.413, "dur": 3.630, + "args": { + "External id": 4553658,"Record function id": 0, "Ev Idx": 1977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942194626.584, "dur": 2.072, + "args": { + "External id": 4553659,"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": 1336753, "tid": 1381210, + "ts": 1696942194627.064, "dur": 1.192, + "args": { + "External id": 4553660,"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": 1336753, "tid": 1381210, + "ts": 1696942194627.559, "dur": 0.630, + "args": { + "External id": 4553661,"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": 1336753, "tid": 1381210, + "ts": 1696942194632.041, "dur": 3.688, + "args": { + "External id": 4553662,"Record function id": 0, "Ev Idx": 1981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942194633.118, "dur": 2.213, + "args": { + "External id": 4553663,"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": 1336753, "tid": 1381210, + "ts": 1696942194633.728, "dur": 1.087, + "args": { + "External id": 4553664,"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": 1336753, "tid": 1381210, + "ts": 1696942194634.149, "dur": 0.598, + "args": { + "External id": 4553665,"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": 1336753, "tid": 1381210, + "ts": 1696942194639.013, "dur": 5.387, + "args": { + "External id": 4553666,"Record function id": 0, "Ev Idx": 1985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942194640.027, "dur": 3.978, + "args": { + "External id": 4553667,"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": 1336753, "tid": 1381210, + "ts": 1696942194640.672, "dur": 2.919, + "args": { + "External id": 4553668,"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": 1336753, "tid": 1381210, + "ts": 1696942194642.984, "dur": 0.537, + "args": { + "External id": 4553669,"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": 1336753, "tid": 1381210, + "ts": 1696942194647.550, "dur": 3.348, + "args": { + "External id": 4553670,"Record function id": 0, "Ev Idx": 1989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942194648.466, "dur": 2.034, + "args": { + "External id": 4553671,"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": 1336753, "tid": 1381210, + "ts": 1696942194648.929, "dur": 1.186, + "args": { + "External id": 4553672,"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": 1336753, "tid": 1381210, + "ts": 1696942194649.208, "dur": 0.842, + "args": { + "External id": 4553673,"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": 1336753, "tid": 1381210, + "ts": 1696942194653.958, "dur": 5.478, + "args": { + "External id": 4553674,"Record function id": 0, "Ev Idx": 1993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942194654.885, "dur": 4.117, + "args": { + "External id": 4553675,"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": 1336753, "tid": 1381210, + "ts": 1696942194655.424, "dur": 3.184, + "args": { + "External id": 4553676,"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": 1336753, "tid": 1381210, + "ts": 1696942194655.866, "dur": 2.680, + "args": { + "External id": 4553677,"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": 1336753, "tid": 1381210, + "ts": 1696942194663.308, "dur": 39276.434, + "args": { + "External id": 4553678,"Record function id": 0, "Sequence number": 45295635, "Fwd thread id": 1, "Ev Idx": 1997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942194664.814, "dur": 39266.326, + "args": { + "External id": 4553679,"Sequence number": 45295635, "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": 1336753, "tid": 1381210, "ts": 1696942194664.814, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1696942194699.323, "dur": 42.111, + "args": { + "External id": 4553680,"Record function id": 0, "Ev Idx": 1999 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1696942194749.593, "dur": 66.340, + "args": { + "External id": 4553681,"Record function id": 0, "Ev Idx": 2000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1696942194823.409, "dur": 39099.427, + "args": { + "External id": 4553682,"Record function id": 0, "Ev Idx": 2001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942194912.445, "dur": 6.742, + "args": { + "External id": 4553683,"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": 1336753, "tid": 1381210, + "ts": 1696942194930.428, "dur": 4.750, + "args": { + "External id": 4553684,"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": 1336753, "tid": 1381210, + "ts": 1696942194949.382, "dur": 38172.346, + "args": { + "External id": 4553685,"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": 1336753, "tid": 1381210, + "ts": 1696942194962.183, "dur": 38150.168, + "args": { + "External id": 4553686,"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": 1336753, "tid": 1381210, + "ts": 1696942195041.008, "dur": 14.666, + "args": { + "External id": 4553687,"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": 1336753, "tid": 1381210, + "ts": 1696942195062.541, "dur": 38011.457, + "args": { + "External id": 4553688,"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": 1336753, "tid": 1381210, + "ts": 1696942195065.172, "dur": 38008.021, + "args": { + "External id": 4553689,"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": 1336753, "tid": 1381210, + "ts": 1696942195068.679, "dur": 7.820, + "args": { + "External id": 4553690,"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": 1336753, "tid": 1381210, + "ts": 1696942195080.531, "dur": 37989.110, + "args": { + "External id": 4553691,"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": 1336753, "tid": 1381210, + "ts": 1696942233210.934, "dur": 8.598, + "args": { + "External id": 4553692,"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": 1336753, "tid": 1381210, + "ts": 1696942233213.700, "dur": 5.486, + "args": { + "External id": 4553693,"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": 1336753, "tid": 1381210, + "ts": 1696942233247.289, "dur": 376.259, + "args": { + "External id": 4553694,"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": 1336753, "tid": 1381210, + "ts": 1696942233280.290, "dur": 338.412, + "args": { + "External id": 4553695,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942233292.257, "dur": 320.889, + "args": { + "External id": 4553696,"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": 1336753, "tid": 1381210, + "ts": 1696942233648.409, "dur": 2.540, + "args": { + "External id": 4553697,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942233713.146, "dur": 6.663, + "args": { + "External id": 4553698,"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": 1336753, "tid": 1381210, + "ts": 1696942233765.076, "dur": 3.267, + "args": { + "External id": 4553699,"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": 1336753, "tid": 1381210, + "ts": 1696942233783.692, "dur": 1.685, + "args": { + "External id": 4553700,"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": 1336753, "tid": 1381210, + "ts": 1696942233798.049, "dur": 0.953, + "args": { + "External id": 4553701,"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": 1336753, "tid": 1381210, + "ts": 1696942233809.384, "dur": 1.001, + "args": { + "External id": 4553702,"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": 1336753, "tid": 1381210, + "ts": 1696942233819.866, "dur": 3.134, + "args": { + "External id": 4553703,"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": 1336753, "tid": 1381210, + "ts": 1696942233836.394, "dur": 1.187, + "args": { + "External id": 4553704,"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": 1336753, "tid": 1381210, + "ts": 1696942233847.693, "dur": 2.833, + "args": { + "External id": 4553705,"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": 1336753, "tid": 1381210, + "ts": 1696942233859.615, "dur": 0.943, + "args": { + "External id": 4553706,"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": 1336753, "tid": 1381210, + "ts": 1696942233954.219, "dur": 2829.301, + "args": { + "External id": 4553707,"Record function id": 0, "Ev Idx": 2026 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1696942233973.371, "dur": 1147.522, + "args": { + "External id": 4553708,"Record function id": 0, "Ev Idx": 2027 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1696942234026.803, "dur": 343.725, + "args": { + "External id": 4553709,"Record function id": 0, "Ev Idx": 2028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942234113.265, "dur": 6.317, + "args": { + "External id": 4553710,"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": 1336753, "tid": 1381210, + "ts": 1696942234122.948, "dur": 1.348, + "args": { + "External id": 4553711,"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": 1336753, "tid": 1381210, + "ts": 1696942234127.878, "dur": 1.087, + "args": { + "External id": 4553712,"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": 1336753, "tid": 1381210, + "ts": 1696942234130.153, "dur": 0.955, + "args": { + "External id": 4553713,"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": 1336753, "tid": 1381210, + "ts": 1696942234132.342, "dur": 0.956, + "args": { + "External id": 4553714,"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": 1336753, "tid": 1381210, + "ts": 1696942234134.594, "dur": 0.865, + "args": { + "External id": 4553715,"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": 1336753, "tid": 1381210, + "ts": 1696942234138.711, "dur": 2.672, + "args": { + "External id": 4553716,"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": 1336753, "tid": 1381210, + "ts": 1696942234142.686, "dur": 0.804, + "args": { + "External id": 4553717,"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": 1336753, "tid": 1381210, + "ts": 1696942234148.443, "dur": 2.707, + "args": { + "External id": 4553718,"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": 1336753, "tid": 1381210, + "ts": 1696942234152.417, "dur": 0.733, + "args": { + "External id": 4553719,"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": 1336753, "tid": 1381210, + "ts": 1696942234174.007, "dur": 162.646, + "args": { + "External id": 4553720,"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": 1336753, "tid": 1381210, + "ts": 1696942234191.262, "dur": 137.892, + "args": { + "External id": 4553721,"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": 1336753, "tid": 1381210, + "ts": 1696942234211.478, "dur": 12.987, + "args": { + "External id": 4553722,"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": 1336753, "tid": 1381210, + "ts": 1696942234227.767, "dur": 73.355, + "args": { + "External id": 4553723,"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": 1336753, "tid": 1381210, + "ts": 1696942234230.426, "dur": 70.396, + "args": { + "External id": 4553724,"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": 1336753, "tid": 1381210, + "ts": 1696942234234.313, "dur": 9.192, + "args": { + "External id": 4553725,"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": 1336753, "tid": 1381210, + "ts": 1696942234245.305, "dur": 55.080, + "args": { + "External id": 4553726,"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": 1336753, "tid": 1381210, + "ts": 1696942234466.631, "dur": 645.587, + "args": { + "External id": 4553727,"Record function id": 0, "Ev Idx": 2046 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1696942234482.346, "dur": 617.417, + "args": { + "External id": 4553728,"Record function id": 0, "Ev Idx": 2047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942234583.812, "dur": 6.840, + "args": { + "External id": 4553729,"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": 1336753, "tid": 1381210, + "ts": 1696942234607.630, "dur": 35.748, + "args": { + "External id": 4553730,"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": 1336753, "tid": 1381210, + "ts": 1696942234612.845, "dur": 3.255, + "args": { + "External id": 4553731,"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": 1336753, "tid": 1381210, + "ts": 1696942234618.095, "dur": 0.460, + "args": { + "External id": 4553732,"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": 1336753, "tid": 1381210, + "ts": 1696942234619.743, "dur": 0.358, + "args": { + "External id": 4553733,"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": 1336753, "tid": 1381210, + "ts": 1696942234623.474, "dur": 2.436, + "args": { + "External id": 4553734,"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": 1336753, "tid": 1381210, + "ts": 1696942234627.198, "dur": 0.301, + "args": { + "External id": 4553735,"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": 1336753, "tid": 1381210, + "ts": 1696942234628.893, "dur": 0.386, + "args": { + "External id": 4553736,"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": 1336753, "tid": 1381210, + "ts": 1696942234632.212, "dur": 0.251, + "args": { + "External id": 4553737,"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": 1336753, "tid": 1381210, + "ts": 1696942234633.764, "dur": 0.239, + "args": { + "External id": 4553738,"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": 1336753, "tid": 1381210, + "ts": 1696942234635.261, "dur": 2.131, + "args": { + "External id": 4553739,"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": 1336753, "tid": 1381210, + "ts": 1696942234653.945, "dur": 33.938, + "args": { + "External id": 4553740,"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": 1336753, "tid": 1381210, + "ts": 1696942234719.730, "dur": 105.851, + "args": { + "External id": 4553741,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942234729.592, "dur": 3.263, + "args": { + "External id": 4553742,"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": 1336753, "tid": 1381210, + "ts": 1696942234738.029, "dur": 9.670, + "args": { + "External id": 4553743,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942234742.248, "dur": 5.045, + "args": { + "External id": 4553744,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942234745.741, "dur": 0.401, + "args": { + "External id": 4553745,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942234755.183, "dur": 30.509, + "args": { + "External id": 4553746,"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": 1336753, "tid": 1381210, + "ts": 1696942234757.167, "dur": 2.571, + "args": { + "External id": 4553747,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942234761.253, "dur": 0.336, + "args": { + "External id": 4553748,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942234762.723, "dur": 2.190, + "args": { + "External id": 4553749,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942234766.215, "dur": 0.288, + "args": { + "External id": 4553750,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942234767.881, "dur": 0.337, + "args": { + "External id": 4553751,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942234771.611, "dur": 0.310, + "args": { + "External id": 4553752,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942234773.219, "dur": 0.383, + "args": { + "External id": 4553753,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942234775.086, "dur": 0.353, + "args": { + "External id": 4553754,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942234778.071, "dur": 1.932, + "args": { + "External id": 4553755,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942234799.215, "dur": 18.427, + "args": { + "External id": 4553756,"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": 1336753, "tid": 1381210, + "ts": 1696942234870.897, "dur": 153.659, + "args": { + "External id": 4553757,"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": 1336753, "tid": 1381210, + "ts": 1696942234899.087, "dur": 120.847, + "args": { + "External id": 4553758,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942234908.297, "dur": 69.539, + "args": { + "External id": 4553759,"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": 1336753, "tid": 1381210, + "ts": 1696942235043.964, "dur": 2.285, + "args": { + "External id": 4553760,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942235129.352, "dur": 1629.242, + "args": { + "External id": 4553761,"Sequence number": 45295634, "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": 1336753, "tid": 1381210, "ts": 1696942235129.352, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942235240.802, "dur": 105.860, + "args": { + "External id": 4553762,"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": 1336753, "tid": 1381210, + "ts": 1696942235390.858, "dur": 38.294, + "args": { + "External id": 4553763,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942235447.427, "dur": 47.378, + "args": { + "External id": 4553764,"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": 1336753, "tid": 1381210, + "ts": 1696942235504.018, "dur": 47.339, + "args": { + "External id": 4553765,"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": 1336753, "tid": 1381210, + "ts": 1696942235560.977, "dur": 48.217, + "args": { + "External id": 4553766,"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": 1336753, "tid": 1381210, + "ts": 1696942235616.315, "dur": 26.931, + "args": { + "External id": 4553767,"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": 1336753, "tid": 1381210, + "ts": 1696942235651.937, "dur": 42.262, + "args": { + "External id": 4553768,"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": 1336753, "tid": 1381210, + "ts": 1696942235719.954, "dur": 24.442, + "args": { + "External id": 4553769,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942235766.170, "dur": 28.470, + "args": { + "External id": 4553770,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942235814.814, "dur": 20.882, + "args": { + "External id": 4553771,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942235851.996, "dur": 14.659, + "args": { + "External id": 4553772,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942235876.814, "dur": 26.895, + "args": { + "External id": 4553773,"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": 1336753, "tid": 1381210, + "ts": 1696942235906.749, "dur": 31.793, + "args": { + "External id": 4553774,"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": 1336753, "tid": 1381210, + "ts": 1696942235972.104, "dur": 212.934, + "args": { + "External id": 4553775,"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": 1336753, "tid": 1381210, + "ts": 1696942236091.938, "dur": 6.253, + "args": { + "External id": 4553776,"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": 1336753, "tid": 1381210, + "ts": 1696942236100.514, "dur": 2.264, + "args": { + "External id": 4553777,"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": 1336753, "tid": 1381210, + "ts": 1696942236222.129, "dur": 25.079, + "args": { + "External id": 4553778,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942236259.138, "dur": 13.987, + "args": { + "External id": 4553779,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942236281.297, "dur": 39.863, + "args": { + "External id": 4553780,"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": 1336753, "tid": 1381210, + "ts": 1696942236328.777, "dur": 44.355, + "args": { + "External id": 4553781,"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": 1336753, "tid": 1381210, + "ts": 1696942236388.319, "dur": 28.575, + "args": { + "External id": 4553782,"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": 1336753, "tid": 1381210, + "ts": 1696942236421.417, "dur": 36.755, + "args": { + "External id": 4553783,"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": 1336753, "tid": 1381210, + "ts": 1696942236463.101, "dur": 18.226, + "args": { + "External id": 4553784,"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": 1336753, "tid": 1381210, + "ts": 1696942236490.141, "dur": 31.297, + "args": { + "External id": 4553785,"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": 1336753, "tid": 1381210, + "ts": 1696942236564.691, "dur": 25.074, + "args": { + "External id": 4553786,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942236613.657, "dur": 23.389, + "args": { + "External id": 4553787,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942236652.030, "dur": 16.772, + "args": { + "External id": 4553788,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942236688.318, "dur": 14.174, + "args": { + "External id": 4553789,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942236715.572, "dur": 16.889, + "args": { + "External id": 4553790,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942236805.864, "dur": 16.692, + "args": { + "External id": 4553791,"Record function id": 0, "Ev Idx": 2110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942236809.205, "dur": 12.455, + "args": { + "External id": 4553792,"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": 1336753, "tid": 1381210, + "ts": 1696942236813.693, "dur": 7.063, + "args": { + "External id": 4553793,"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": 1336753, "tid": 1381210, + "ts": 1696942236815.163, "dur": 5.503, + "args": { + "External id": 4553794,"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": 1336753, "tid": 1381210, + "ts": 1696942236826.550, "dur": 5.126, + "args": { + "External id": 4553795,"Record function id": 0, "Ev Idx": 2114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942236828.021, "dur": 3.240, + "args": { + "External id": 4553796,"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": 1336753, "tid": 1381210, + "ts": 1696942236829.003, "dur": 1.774, + "args": { + "External id": 4553797,"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": 1336753, "tid": 1381210, + "ts": 1696942236829.352, "dur": 1.358, + "args": { + "External id": 4553798,"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": 1336753, "tid": 1381210, + "ts": 1696942236834.951, "dur": 5.016, + "args": { + "External id": 4553799,"Record function id": 0, "Ev Idx": 2118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942236836.616, "dur": 2.954, + "args": { + "External id": 4553800,"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": 1336753, "tid": 1381210, + "ts": 1696942236837.729, "dur": 1.433, + "args": { + "External id": 4553801,"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": 1336753, "tid": 1381210, + "ts": 1696942236838.486, "dur": 0.597, + "args": { + "External id": 4553802,"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": 1336753, "tid": 1381210, + "ts": 1696942236843.366, "dur": 4.543, + "args": { + "External id": 4553803,"Record function id": 0, "Ev Idx": 2122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942236844.703, "dur": 2.819, + "args": { + "External id": 4553804,"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": 1336753, "tid": 1381210, + "ts": 1696942236845.524, "dur": 1.424, + "args": { + "External id": 4553805,"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": 1336753, "tid": 1381210, + "ts": 1696942236845.989, "dur": 0.882, + "args": { + "External id": 4553806,"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": 1336753, "tid": 1381210, + "ts": 1696942236851.376, "dur": 4.261, + "args": { + "External id": 4553807,"Record function id": 0, "Ev Idx": 2126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942236852.627, "dur": 2.597, + "args": { + "External id": 4553808,"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": 1336753, "tid": 1381210, + "ts": 1696942236853.464, "dur": 1.099, + "args": { + "External id": 4553809,"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": 1336753, "tid": 1381210, + "ts": 1696942236853.889, "dur": 0.608, + "args": { + "External id": 4553810,"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": 1336753, "tid": 1381210, + "ts": 1696942236858.752, "dur": 3.404, + "args": { + "External id": 4553811,"Record function id": 0, "Ev Idx": 2130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942236859.844, "dur": 1.898, + "args": { + "External id": 4553812,"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": 1336753, "tid": 1381210, + "ts": 1696942236860.353, "dur": 0.963, + "args": { + "External id": 4553813,"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": 1336753, "tid": 1381210, + "ts": 1696942236860.707, "dur": 0.540, + "args": { + "External id": 4553814,"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": 1336753, "tid": 1381210, + "ts": 1696942236865.469, "dur": 5.360, + "args": { + "External id": 4553815,"Record function id": 0, "Ev Idx": 2134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942236866.576, "dur": 3.844, + "args": { + "External id": 4553816,"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": 1336753, "tid": 1381210, + "ts": 1696942236867.024, "dur": 2.806, + "args": { + "External id": 4553817,"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": 1336753, "tid": 1381210, + "ts": 1696942236869.127, "dur": 0.635, + "args": { + "External id": 4553818,"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": 1336753, "tid": 1381210, + "ts": 1696942236873.989, "dur": 5.491, + "args": { + "External id": 4553819,"Record function id": 0, "Ev Idx": 2138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942236875.093, "dur": 3.960, + "args": { + "External id": 4553820,"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": 1336753, "tid": 1381210, + "ts": 1696942236875.603, "dur": 3.005, + "args": { + "External id": 4553821,"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": 1336753, "tid": 1381210, + "ts": 1696942236875.931, "dur": 2.601, + "args": { + "External id": 4553822,"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": 1336753, "tid": 1381210, + "ts": 1696942236882.591, "dur": 4.041, + "args": { + "External id": 4553823,"Record function id": 0, "Ev Idx": 2142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942236883.761, "dur": 2.462, + "args": { + "External id": 4553824,"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": 1336753, "tid": 1381210, + "ts": 1696942236884.213, "dur": 1.472, + "args": { + "External id": 4553825,"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": 1336753, "tid": 1381210, + "ts": 1696942236884.478, "dur": 1.142, + "args": { + "External id": 4553826,"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": 1336753, "tid": 1381210, + "ts": 1696942236890.446, "dur": 37311.855, + "args": { + "External id": 4553827,"Record function id": 0, "Sequence number": 45295633, "Fwd thread id": 1, "Ev Idx": 2146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942236891.806, "dur": 37300.787, + "args": { + "External id": 4553828,"Sequence number": 45295633, "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": 1336753, "tid": 1381210, "ts": 1696942236891.806, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1696942236920.092, "dur": 39.038, + "args": { + "External id": 4553829,"Record function id": 0, "Ev Idx": 2148 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1696942236970.303, "dur": 110.981, + "args": { + "External id": 4553830,"Record function id": 0, "Ev Idx": 2149 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1696942237088.958, "dur": 37095.153, + "args": { + "External id": 4553831,"Record function id": 0, "Ev Idx": 2150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942237180.209, "dur": 7.712, + "args": { + "External id": 4553832,"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": 1336753, "tid": 1381210, + "ts": 1696942237198.658, "dur": 5.000, + "args": { + "External id": 4553833,"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": 1336753, "tid": 1381210, + "ts": 1696942237218.297, "dur": 36058.511, + "args": { + "External id": 4553834,"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": 1336753, "tid": 1381210, + "ts": 1696942237231.744, "dur": 36035.836, + "args": { + "External id": 4553835,"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": 1336753, "tid": 1381210, + "ts": 1696942237277.175, "dur": 14.188, + "args": { + "External id": 4553836,"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": 1336753, "tid": 1381210, + "ts": 1696942237297.273, "dur": 35934.816, + "args": { + "External id": 4553837,"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": 1336753, "tid": 1381210, + "ts": 1696942237301.266, "dur": 35929.864, + "args": { + "External id": 4553838,"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": 1336753, "tid": 1381210, + "ts": 1696942237305.208, "dur": 4.732, + "args": { + "External id": 4553839,"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": 1336753, "tid": 1381210, + "ts": 1696942237313.415, "dur": 35913.897, + "args": { + "External id": 4553840,"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": 1336753, "tid": 1381210, + "ts": 1696942273377.625, "dur": 8.841, + "args": { + "External id": 4553841,"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": 1336753, "tid": 1381210, + "ts": 1696942273380.461, "dur": 5.678, + "args": { + "External id": 4553842,"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": 1336753, "tid": 1381210, + "ts": 1696942273417.233, "dur": 418.796, + "args": { + "External id": 4553843,"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": 1336753, "tid": 1381210, + "ts": 1696942273451.360, "dur": 379.400, + "args": { + "External id": 4553844,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942273461.537, "dur": 362.721, + "args": { + "External id": 4553845,"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": 1336753, "tid": 1381210, + "ts": 1696942273859.599, "dur": 2.504, + "args": { + "External id": 4553846,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942273922.087, "dur": 6.995, + "args": { + "External id": 4553847,"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": 1336753, "tid": 1381210, + "ts": 1696942273976.235, "dur": 1.706, + "args": { + "External id": 4553848,"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": 1336753, "tid": 1381210, + "ts": 1696942274031.852, "dur": 1.869, + "args": { + "External id": 4553849,"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": 1336753, "tid": 1381210, + "ts": 1696942274046.495, "dur": 0.890, + "args": { + "External id": 4553850,"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": 1336753, "tid": 1381210, + "ts": 1696942274063.280, "dur": 1.032, + "args": { + "External id": 4553851,"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": 1336753, "tid": 1381210, + "ts": 1696942274077.820, "dur": 1.257, + "args": { + "External id": 4553852,"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": 1336753, "tid": 1381210, + "ts": 1696942274091.220, "dur": 0.823, + "args": { + "External id": 4553853,"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": 1336753, "tid": 1381210, + "ts": 1696942274104.182, "dur": 2.865, + "args": { + "External id": 4553854,"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": 1336753, "tid": 1381210, + "ts": 1696942274118.467, "dur": 1.114, + "args": { + "External id": 4553855,"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": 1336753, "tid": 1381210, + "ts": 1696942274218.685, "dur": 2746.594, + "args": { + "External id": 4553856,"Record function id": 0, "Ev Idx": 2175 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1696942274240.676, "dur": 1062.039, + "args": { + "External id": 4553857,"Record function id": 0, "Ev Idx": 2176 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1696942274254.703, "dur": 343.729, + "args": { + "External id": 4553858,"Record function id": 0, "Ev Idx": 2177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942274335.854, "dur": 4.172, + "args": { + "External id": 4553859,"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": 1336753, "tid": 1381210, + "ts": 1696942274343.178, "dur": 1.149, + "args": { + "External id": 4553860,"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": 1336753, "tid": 1381210, + "ts": 1696942274346.134, "dur": 1.164, + "args": { + "External id": 4553861,"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": 1336753, "tid": 1381210, + "ts": 1696942274349.443, "dur": 0.779, + "args": { + "External id": 4553862,"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": 1336753, "tid": 1381210, + "ts": 1696942274351.850, "dur": 0.764, + "args": { + "External id": 4553863,"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": 1336753, "tid": 1381210, + "ts": 1696942274355.874, "dur": 1.002, + "args": { + "External id": 4553864,"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": 1336753, "tid": 1381210, + "ts": 1696942274358.990, "dur": 2.255, + "args": { + "External id": 4553865,"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": 1336753, "tid": 1381210, + "ts": 1696942274362.775, "dur": 2.448, + "args": { + "External id": 4553866,"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": 1336753, "tid": 1381210, + "ts": 1696942274366.730, "dur": 0.858, + "args": { + "External id": 4553867,"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": 1336753, "tid": 1381210, + "ts": 1696942274370.637, "dur": 0.735, + "args": { + "External id": 4553868,"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": 1336753, "tid": 1381210, + "ts": 1696942274389.129, "dur": 171.738, + "args": { + "External id": 4553869,"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": 1336753, "tid": 1381210, + "ts": 1696942274405.276, "dur": 150.668, + "args": { + "External id": 4553870,"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": 1336753, "tid": 1381210, + "ts": 1696942274425.848, "dur": 13.974, + "args": { + "External id": 4553871,"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": 1336753, "tid": 1381210, + "ts": 1696942274442.900, "dur": 68.002, + "args": { + "External id": 4553872,"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": 1336753, "tid": 1381210, + "ts": 1696942274445.439, "dur": 65.079, + "args": { + "External id": 4553873,"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": 1336753, "tid": 1381210, + "ts": 1696942274449.599, "dur": 6.706, + "args": { + "External id": 4553874,"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": 1336753, "tid": 1381210, + "ts": 1696942274457.976, "dur": 51.830, + "args": { + "External id": 4553875,"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": 1336753, "tid": 1381210, + "ts": 1696942274695.115, "dur": 599.275, + "args": { + "External id": 4553876,"Record function id": 0, "Ev Idx": 2195 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1696942274714.795, "dur": 567.332, + "args": { + "External id": 4553877,"Record function id": 0, "Ev Idx": 2196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942274778.275, "dur": 5.800, + "args": { + "External id": 4553878,"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": 1336753, "tid": 1381210, + "ts": 1696942274800.624, "dur": 33.330, + "args": { + "External id": 4553879,"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": 1336753, "tid": 1381210, + "ts": 1696942274805.471, "dur": 1.677, + "args": { + "External id": 4553880,"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": 1336753, "tid": 1381210, + "ts": 1696942274811.480, "dur": 0.427, + "args": { + "External id": 4553881,"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": 1336753, "tid": 1381210, + "ts": 1696942274813.204, "dur": 2.138, + "args": { + "External id": 4553882,"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": 1336753, "tid": 1381210, + "ts": 1696942274816.805, "dur": 1.802, + "args": { + "External id": 4553883,"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": 1336753, "tid": 1381210, + "ts": 1696942274820.439, "dur": 0.238, + "args": { + "External id": 4553884,"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": 1336753, "tid": 1381210, + "ts": 1696942274822.308, "dur": 0.381, + "args": { + "External id": 4553885,"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": 1336753, "tid": 1381210, + "ts": 1696942274825.611, "dur": 0.254, + "args": { + "External id": 4553886,"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": 1336753, "tid": 1381210, + "ts": 1696942274827.227, "dur": 0.255, + "args": { + "External id": 4553887,"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": 1336753, "tid": 1381210, + "ts": 1696942274828.600, "dur": 0.270, + "args": { + "External id": 4553888,"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": 1336753, "tid": 1381210, + "ts": 1696942274844.689, "dur": 29.005, + "args": { + "External id": 4553889,"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": 1336753, "tid": 1381210, + "ts": 1696942274904.642, "dur": 147.890, + "args": { + "External id": 4553890,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942274914.878, "dur": 3.384, + "args": { + "External id": 4553891,"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": 1336753, "tid": 1381210, + "ts": 1696942274923.101, "dur": 15.152, + "args": { + "External id": 4553892,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942274929.334, "dur": 8.490, + "args": { + "External id": 4553893,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942274932.852, "dur": 3.907, + "args": { + "External id": 4553894,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942274945.108, "dur": 26.411, + "args": { + "External id": 4553895,"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": 1336753, "tid": 1381210, + "ts": 1696942274947.300, "dur": 0.654, + "args": { + "External id": 4553896,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942274949.333, "dur": 0.451, + "args": { + "External id": 4553897,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942274951.015, "dur": 0.365, + "args": { + "External id": 4553898,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942274953.865, "dur": 0.275, + "args": { + "External id": 4553899,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942274955.641, "dur": 0.365, + "args": { + "External id": 4553900,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942274957.064, "dur": 1.311, + "args": { + "External id": 4553901,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942274959.726, "dur": 0.483, + "args": { + "External id": 4553902,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942274961.716, "dur": 2.417, + "args": { + "External id": 4553903,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942274967.242, "dur": 0.317, + "args": { + "External id": 4553904,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942275018.417, "dur": 25.424, + "args": { + "External id": 4553905,"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": 1336753, "tid": 1381210, + "ts": 1696942275100.045, "dur": 115.872, + "args": { + "External id": 4553906,"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": 1336753, "tid": 1381210, + "ts": 1696942275129.173, "dur": 83.682, + "args": { + "External id": 4553907,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942275138.057, "dur": 70.653, + "args": { + "External id": 4553908,"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": 1336753, "tid": 1381210, + "ts": 1696942275232.512, "dur": 1.706, + "args": { + "External id": 4553909,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942275314.125, "dur": 1629.291, + "args": { + "External id": 4553910,"Sequence number": 45295632, "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": 1336753, "tid": 1381210, "ts": 1696942275314.125, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942275426.450, "dur": 117.587, + "args": { + "External id": 4553911,"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": 1336753, "tid": 1381210, + "ts": 1696942275589.550, "dur": 42.894, + "args": { + "External id": 4553912,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942275652.101, "dur": 50.827, + "args": { + "External id": 4553913,"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": 1336753, "tid": 1381210, + "ts": 1696942275712.024, "dur": 31.688, + "args": { + "External id": 4553914,"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": 1336753, "tid": 1381210, + "ts": 1696942275749.571, "dur": 48.525, + "args": { + "External id": 4553915,"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": 1336753, "tid": 1381210, + "ts": 1696942275804.587, "dur": 27.913, + "args": { + "External id": 4553916,"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": 1336753, "tid": 1381210, + "ts": 1696942275843.307, "dur": 41.899, + "args": { + "External id": 4553917,"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": 1336753, "tid": 1381210, + "ts": 1696942275908.607, "dur": 23.000, + "args": { + "External id": 4553918,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942275951.485, "dur": 27.667, + "args": { + "External id": 4553919,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942276043.829, "dur": 22.233, + "args": { + "External id": 4553920,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942276085.407, "dur": 15.486, + "args": { + "External id": 4553921,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942276110.784, "dur": 32.272, + "args": { + "External id": 4553922,"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": 1336753, "tid": 1381210, + "ts": 1696942276146.515, "dur": 34.091, + "args": { + "External id": 4553923,"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": 1336753, "tid": 1381210, + "ts": 1696942276207.102, "dur": 168.100, + "args": { + "External id": 4553924,"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": 1336753, "tid": 1381210, + "ts": 1696942276283.270, "dur": 6.463, + "args": { + "External id": 4553925,"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": 1336753, "tid": 1381210, + "ts": 1696942276291.417, "dur": 2.023, + "args": { + "External id": 4553926,"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": 1336753, "tid": 1381210, + "ts": 1696942276411.350, "dur": 21.620, + "args": { + "External id": 4553927,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942276444.708, "dur": 13.490, + "args": { + "External id": 4553928,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942276467.364, "dur": 31.290, + "args": { + "External id": 4553929,"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": 1336753, "tid": 1381210, + "ts": 1696942276504.071, "dur": 48.370, + "args": { + "External id": 4553930,"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": 1336753, "tid": 1381210, + "ts": 1696942276568.952, "dur": 24.076, + "args": { + "External id": 4553931,"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": 1336753, "tid": 1381210, + "ts": 1696942276597.614, "dur": 41.438, + "args": { + "External id": 4553932,"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": 1336753, "tid": 1381210, + "ts": 1696942276654.851, "dur": 27.689, + "args": { + "External id": 4553933,"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": 1336753, "tid": 1381210, + "ts": 1696942276691.005, "dur": 32.676, + "args": { + "External id": 4553934,"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": 1336753, "tid": 1381210, + "ts": 1696942276749.720, "dur": 22.097, + "args": { + "External id": 4553935,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942276790.706, "dur": 31.558, + "args": { + "External id": 4553936,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942276839.828, "dur": 15.996, + "args": { + "External id": 4553937,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942276870.464, "dur": 14.692, + "args": { + "External id": 4553938,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942276899.557, "dur": 14.779, + "args": { + "External id": 4553939,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942277021.445, "dur": 18.019, + "args": { + "External id": 4553940,"Record function id": 0, "Ev Idx": 2259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942277026.029, "dur": 12.115, + "args": { + "External id": 4553941,"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": 1336753, "tid": 1381210, + "ts": 1696942277030.357, "dur": 6.351, + "args": { + "External id": 4553942,"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": 1336753, "tid": 1381210, + "ts": 1696942277031.927, "dur": 4.541, + "args": { + "External id": 4553943,"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": 1336753, "tid": 1381210, + "ts": 1696942277044.962, "dur": 4.709, + "args": { + "External id": 4553944,"Record function id": 0, "Ev Idx": 2263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942277046.561, "dur": 2.714, + "args": { + "External id": 4553945,"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": 1336753, "tid": 1381210, + "ts": 1696942277047.378, "dur": 1.294, + "args": { + "External id": 4553946,"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": 1336753, "tid": 1381210, + "ts": 1696942277047.891, "dur": 0.693, + "args": { + "External id": 4553947,"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": 1336753, "tid": 1381210, + "ts": 1696942277053.046, "dur": 5.076, + "args": { + "External id": 4553948,"Record function id": 0, "Ev Idx": 2267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942277054.460, "dur": 3.267, + "args": { + "External id": 4553949,"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": 1336753, "tid": 1381210, + "ts": 1696942277055.293, "dur": 1.838, + "args": { + "External id": 4553950,"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": 1336753, "tid": 1381210, + "ts": 1696942277056.079, "dur": 0.934, + "args": { + "External id": 4553951,"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": 1336753, "tid": 1381210, + "ts": 1696942277061.295, "dur": 4.260, + "args": { + "External id": 4553952,"Record function id": 0, "Ev Idx": 2271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942277062.445, "dur": 2.717, + "args": { + "External id": 4553953,"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": 1336753, "tid": 1381210, + "ts": 1696942277063.221, "dur": 1.522, + "args": { + "External id": 4553954,"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": 1336753, "tid": 1381210, + "ts": 1696942277063.724, "dur": 0.923, + "args": { + "External id": 4553955,"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": 1336753, "tid": 1381210, + "ts": 1696942277068.649, "dur": 3.850, + "args": { + "External id": 4553956,"Record function id": 0, "Ev Idx": 2275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942277069.932, "dur": 2.177, + "args": { + "External id": 4553957,"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": 1336753, "tid": 1381210, + "ts": 1696942277070.471, "dur": 1.198, + "args": { + "External id": 4553958,"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": 1336753, "tid": 1381210, + "ts": 1696942277070.821, "dur": 0.779, + "args": { + "External id": 4553959,"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": 1336753, "tid": 1381210, + "ts": 1696942277075.858, "dur": 4.021, + "args": { + "External id": 4553960,"Record function id": 0, "Ev Idx": 2279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942277077.183, "dur": 2.282, + "args": { + "External id": 4553961,"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": 1336753, "tid": 1381210, + "ts": 1696942277077.616, "dur": 1.252, + "args": { + "External id": 4553962,"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": 1336753, "tid": 1381210, + "ts": 1696942277078.049, "dur": 0.753, + "args": { + "External id": 4553963,"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": 1336753, "tid": 1381210, + "ts": 1696942277083.318, "dur": 5.252, + "args": { + "External id": 4553964,"Record function id": 0, "Ev Idx": 2283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942277084.369, "dur": 3.806, + "args": { + "External id": 4553965,"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": 1336753, "tid": 1381210, + "ts": 1696942277084.795, "dur": 2.939, + "args": { + "External id": 4553966,"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": 1336753, "tid": 1381210, + "ts": 1696942277085.267, "dur": 2.405, + "args": { + "External id": 4553967,"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": 1336753, "tid": 1381210, + "ts": 1696942277091.971, "dur": 6.058, + "args": { + "External id": 4553968,"Record function id": 0, "Ev Idx": 2287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942277093.215, "dur": 4.419, + "args": { + "External id": 4553969,"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": 1336753, "tid": 1381210, + "ts": 1696942277093.937, "dur": 3.049, + "args": { + "External id": 4553970,"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": 1336753, "tid": 1381210, + "ts": 1696942277096.162, "dur": 0.722, + "args": { + "External id": 4553971,"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": 1336753, "tid": 1381210, + "ts": 1696942277101.127, "dur": 3.607, + "args": { + "External id": 4553972,"Record function id": 0, "Ev Idx": 2291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942277102.344, "dur": 1.996, + "args": { + "External id": 4553973,"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": 1336753, "tid": 1381210, + "ts": 1696942277102.789, "dur": 1.007, + "args": { + "External id": 4553974,"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": 1336753, "tid": 1381210, + "ts": 1696942277103.180, "dur": 0.548, + "args": { + "External id": 4553975,"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": 1336753, "tid": 1381210, + "ts": 1696942277108.697, "dur": 35138.591, + "args": { + "External id": 4553976,"Record function id": 0, "Sequence number": 45295631, "Fwd thread id": 1, "Ev Idx": 2295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942277110.184, "dur": 35125.293, + "args": { + "External id": 4553977,"Sequence number": 45295631, "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": 1336753, "tid": 1381210, "ts": 1696942277110.184, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1696942277142.238, "dur": 36.552, + "args": { + "External id": 4553978,"Record function id": 0, "Ev Idx": 2297 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1696942277189.219, "dur": 67.518, + "args": { + "External id": 4553979,"Record function id": 0, "Ev Idx": 2298 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1696942277262.586, "dur": 34964.773, + "args": { + "External id": 4553980,"Record function id": 0, "Ev Idx": 2299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942277350.387, "dur": 7.045, + "args": { + "External id": 4553981,"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": 1336753, "tid": 1381210, + "ts": 1696942277366.786, "dur": 5.252, + "args": { + "External id": 4553982,"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": 1336753, "tid": 1381210, + "ts": 1696942277391.796, "dur": 33995.648, + "args": { + "External id": 4553983,"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": 1336753, "tid": 1381210, + "ts": 1696942277405.474, "dur": 33973.323, + "args": { + "External id": 4553984,"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": 1336753, "tid": 1381210, + "ts": 1696942277450.476, "dur": 13.471, + "args": { + "External id": 4553985,"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": 1336753, "tid": 1381210, + "ts": 1696942277470.362, "dur": 33870.390, + "args": { + "External id": 4553986,"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": 1336753, "tid": 1381210, + "ts": 1696942277473.239, "dur": 33866.735, + "args": { + "External id": 4553987,"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": 1336753, "tid": 1381210, + "ts": 1696942277477.488, "dur": 5.228, + "args": { + "External id": 4553988,"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": 1336753, "tid": 1381210, + "ts": 1696942277484.749, "dur": 33851.633, + "args": { + "External id": 4553989,"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": 1336753, "tid": 1381210, + "ts": 1696942311474.617, "dur": 9.228, + "args": { + "External id": 4553990,"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": 1336753, "tid": 1381210, + "ts": 1696942311478.463, "dur": 5.042, + "args": { + "External id": 4553991,"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": 1336753, "tid": 1381210, + "ts": 1696942311513.261, "dur": 371.554, + "args": { + "External id": 4553992,"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": 1336753, "tid": 1381210, + "ts": 1696942311552.997, "dur": 326.782, + "args": { + "External id": 4553993,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942311568.298, "dur": 306.246, + "args": { + "External id": 4553994,"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": 1336753, "tid": 1381210, + "ts": 1696942311903.964, "dur": 2.475, + "args": { + "External id": 4553995,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942311964.442, "dur": 8.421, + "args": { + "External id": 4553996,"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": 1336753, "tid": 1381210, + "ts": 1696942312051.316, "dur": 2.285, + "args": { + "External id": 4553997,"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": 1336753, "tid": 1381210, + "ts": 1696942312074.625, "dur": 0.952, + "args": { + "External id": 4553998,"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": 1336753, "tid": 1381210, + "ts": 1696942312088.193, "dur": 0.797, + "args": { + "External id": 4553999,"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": 1336753, "tid": 1381210, + "ts": 1696942312102.093, "dur": 2.993, + "args": { + "External id": 4554000,"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": 1336753, "tid": 1381210, + "ts": 1696942312116.022, "dur": 4.674, + "args": { + "External id": 4554001,"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": 1336753, "tid": 1381210, + "ts": 1696942312132.236, "dur": 1.131, + "args": { + "External id": 4554002,"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": 1336753, "tid": 1381210, + "ts": 1696942312145.706, "dur": 1.984, + "args": { + "External id": 4554003,"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": 1336753, "tid": 1381210, + "ts": 1696942312159.793, "dur": 2.496, + "args": { + "External id": 4554004,"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": 1336753, "tid": 1381210, + "ts": 1696942312264.491, "dur": 2820.415, + "args": { + "External id": 4554005,"Record function id": 0, "Ev Idx": 2324 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1696942312283.959, "dur": 1061.283, + "args": { + "External id": 4554006,"Record function id": 0, "Ev Idx": 2325 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1696942312297.126, "dur": 345.606, + "args": { + "External id": 4554007,"Record function id": 0, "Ev Idx": 2326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942312379.797, "dur": 3.852, + "args": { + "External id": 4554008,"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": 1336753, "tid": 1381210, + "ts": 1696942312386.610, "dur": 1.420, + "args": { + "External id": 4554009,"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": 1336753, "tid": 1381210, + "ts": 1696942312389.927, "dur": 1.290, + "args": { + "External id": 4554010,"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": 1336753, "tid": 1381210, + "ts": 1696942312393.060, "dur": 1.132, + "args": { + "External id": 4554011,"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": 1336753, "tid": 1381210, + "ts": 1696942312395.709, "dur": 0.995, + "args": { + "External id": 4554012,"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": 1336753, "tid": 1381210, + "ts": 1696942312398.800, "dur": 0.920, + "args": { + "External id": 4554013,"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": 1336753, "tid": 1381210, + "ts": 1696942312401.433, "dur": 4.034, + "args": { + "External id": 4554014,"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": 1336753, "tid": 1381210, + "ts": 1696942312407.014, "dur": 1.123, + "args": { + "External id": 4554015,"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": 1336753, "tid": 1381210, + "ts": 1696942312409.590, "dur": 0.952, + "args": { + "External id": 4554016,"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": 1336753, "tid": 1381210, + "ts": 1696942312412.451, "dur": 0.805, + "args": { + "External id": 4554017,"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": 1336753, "tid": 1381210, + "ts": 1696942312431.694, "dur": 175.939, + "args": { + "External id": 4554018,"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": 1336753, "tid": 1381210, + "ts": 1696942312447.884, "dur": 154.927, + "args": { + "External id": 4554019,"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": 1336753, "tid": 1381210, + "ts": 1696942312470.800, "dur": 11.998, + "args": { + "External id": 4554020,"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": 1336753, "tid": 1381210, + "ts": 1696942312486.029, "dur": 87.216, + "args": { + "External id": 4554021,"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": 1336753, "tid": 1381210, + "ts": 1696942312488.657, "dur": 84.060, + "args": { + "External id": 4554022,"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": 1336753, "tid": 1381210, + "ts": 1696942312492.984, "dur": 6.983, + "args": { + "External id": 4554023,"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": 1336753, "tid": 1381210, + "ts": 1696942312501.838, "dur": 69.819, + "args": { + "External id": 4554024,"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": 1336753, "tid": 1381210, + "ts": 1696942312738.042, "dur": 598.170, + "args": { + "External id": 4554025,"Record function id": 0, "Ev Idx": 2344 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1696942312754.188, "dur": 569.268, + "args": { + "External id": 4554026,"Record function id": 0, "Ev Idx": 2345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942312814.707, "dur": 5.417, + "args": { + "External id": 4554027,"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": 1336753, "tid": 1381210, + "ts": 1696942312836.111, "dur": 32.235, + "args": { + "External id": 4554028,"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": 1336753, "tid": 1381210, + "ts": 1696942312841.626, "dur": 1.428, + "args": { + "External id": 4554029,"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": 1336753, "tid": 1381210, + "ts": 1696942312845.289, "dur": 2.242, + "args": { + "External id": 4554030,"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": 1336753, "tid": 1381210, + "ts": 1696942312849.540, "dur": 0.460, + "args": { + "External id": 4554031,"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": 1336753, "tid": 1381210, + "ts": 1696942312851.629, "dur": 0.425, + "args": { + "External id": 4554032,"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": 1336753, "tid": 1381210, + "ts": 1696942312853.821, "dur": 0.430, + "args": { + "External id": 4554033,"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": 1336753, "tid": 1381210, + "ts": 1696942312855.824, "dur": 0.593, + "args": { + "External id": 4554034,"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": 1336753, "tid": 1381210, + "ts": 1696942312858.228, "dur": 0.498, + "args": { + "External id": 4554035,"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": 1336753, "tid": 1381210, + "ts": 1696942312860.366, "dur": 0.439, + "args": { + "External id": 4554036,"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": 1336753, "tid": 1381210, + "ts": 1696942312862.740, "dur": 0.417, + "args": { + "External id": 4554037,"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": 1336753, "tid": 1381210, + "ts": 1696942312883.952, "dur": 30.836, + "args": { + "External id": 4554038,"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": 1336753, "tid": 1381210, + "ts": 1696942312948.106, "dur": 149.289, + "args": { + "External id": 4554039,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942312958.249, "dur": 5.037, + "args": { + "External id": 4554040,"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": 1336753, "tid": 1381210, + "ts": 1696942312968.999, "dur": 10.115, + "args": { + "External id": 4554041,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942312973.050, "dur": 5.649, + "args": { + "External id": 4554042,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942312976.794, "dur": 0.812, + "args": { + "External id": 4554043,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942313024.253, "dur": 29.793, + "args": { + "External id": 4554044,"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": 1336753, "tid": 1381210, + "ts": 1696942313027.661, "dur": 0.865, + "args": { + "External id": 4554045,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942313030.707, "dur": 0.552, + "args": { + "External id": 4554046,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942313033.438, "dur": 0.462, + "args": { + "External id": 4554047,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942313035.420, "dur": 0.469, + "args": { + "External id": 4554048,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942313037.997, "dur": 0.427, + "args": { + "External id": 4554049,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942313040.085, "dur": 0.415, + "args": { + "External id": 4554050,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942313042.512, "dur": 2.458, + "args": { + "External id": 4554051,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942313046.836, "dur": 0.420, + "args": { + "External id": 4554052,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942313048.893, "dur": 0.469, + "args": { + "External id": 4554053,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942313066.892, "dur": 22.804, + "args": { + "External id": 4554054,"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": 1336753, "tid": 1381210, + "ts": 1696942313144.095, "dur": 108.350, + "args": { + "External id": 4554055,"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": 1336753, "tid": 1381210, + "ts": 1696942313166.315, "dur": 82.382, + "args": { + "External id": 4554056,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942313176.353, "dur": 67.916, + "args": { + "External id": 4554057,"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": 1336753, "tid": 1381210, + "ts": 1696942313270.050, "dur": 1.712, + "args": { + "External id": 4554058,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942313352.314, "dur": 1708.501, + "args": { + "External id": 4554059,"Sequence number": 45295630, "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": 1336753, "tid": 1381210, "ts": 1696942313352.314, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942313472.655, "dur": 121.762, + "args": { + "External id": 4554060,"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": 1336753, "tid": 1381210, + "ts": 1696942313635.214, "dur": 39.317, + "args": { + "External id": 4554061,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942313699.763, "dur": 50.566, + "args": { + "External id": 4554062,"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": 1336753, "tid": 1381210, + "ts": 1696942313762.223, "dur": 32.685, + "args": { + "External id": 4554063,"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": 1336753, "tid": 1381210, + "ts": 1696942313802.051, "dur": 49.414, + "args": { + "External id": 4554064,"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": 1336753, "tid": 1381210, + "ts": 1696942313860.946, "dur": 31.813, + "args": { + "External id": 4554065,"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": 1336753, "tid": 1381210, + "ts": 1696942313900.442, "dur": 44.316, + "args": { + "External id": 4554066,"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": 1336753, "tid": 1381210, + "ts": 1696942313965.888, "dur": 59.978, + "args": { + "External id": 4554067,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942314057.989, "dur": 30.560, + "args": { + "External id": 4554068,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942314110.714, "dur": 19.313, + "args": { + "External id": 4554069,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942314145.393, "dur": 14.199, + "args": { + "External id": 4554070,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942314170.584, "dur": 33.627, + "args": { + "External id": 4554071,"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": 1336753, "tid": 1381210, + "ts": 1696942314207.823, "dur": 33.767, + "args": { + "External id": 4554072,"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": 1336753, "tid": 1381210, + "ts": 1696942314269.774, "dur": 177.120, + "args": { + "External id": 4554073,"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": 1336753, "tid": 1381210, + "ts": 1696942314349.542, "dur": 5.528, + "args": { + "External id": 4554074,"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": 1336753, "tid": 1381210, + "ts": 1696942314357.498, "dur": 3.691, + "args": { + "External id": 4554075,"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": 1336753, "tid": 1381210, + "ts": 1696942314480.378, "dur": 26.003, + "args": { + "External id": 4554076,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942314516.845, "dur": 31.574, + "args": { + "External id": 4554077,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942314560.011, "dur": 37.925, + "args": { + "External id": 4554078,"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": 1336753, "tid": 1381210, + "ts": 1696942314604.794, "dur": 33.915, + "args": { + "External id": 4554079,"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": 1336753, "tid": 1381210, + "ts": 1696942314647.578, "dur": 20.551, + "args": { + "External id": 4554080,"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": 1336753, "tid": 1381210, + "ts": 1696942314676.456, "dur": 41.706, + "args": { + "External id": 4554081,"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": 1336753, "tid": 1381210, + "ts": 1696942314730.688, "dur": 27.646, + "args": { + "External id": 4554082,"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": 1336753, "tid": 1381210, + "ts": 1696942314766.785, "dur": 32.146, + "args": { + "External id": 4554083,"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": 1336753, "tid": 1381210, + "ts": 1696942314817.026, "dur": 25.639, + "args": { + "External id": 4554084,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942314859.340, "dur": 27.449, + "args": { + "External id": 4554085,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942314900.956, "dur": 17.186, + "args": { + "External id": 4554086,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942314932.257, "dur": 18.467, + "args": { + "External id": 4554087,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942314972.421, "dur": 52.130, + "args": { + "External id": 4554088,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942315108.926, "dur": 18.645, + "args": { + "External id": 4554089,"Record function id": 0, "Ev Idx": 2408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942315115.379, "dur": 11.335, + "args": { + "External id": 4554090,"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": 1336753, "tid": 1381210, + "ts": 1696942315119.689, "dur": 6.118, + "args": { + "External id": 4554091,"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": 1336753, "tid": 1381210, + "ts": 1696942315121.604, "dur": 4.073, + "args": { + "External id": 4554092,"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": 1336753, "tid": 1381210, + "ts": 1696942315132.021, "dur": 5.899, + "args": { + "External id": 4554093,"Record function id": 0, "Ev Idx": 2412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942315133.491, "dur": 3.990, + "args": { + "External id": 4554094,"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": 1336753, "tid": 1381210, + "ts": 1696942315134.986, "dur": 2.036, + "args": { + "External id": 4554095,"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": 1336753, "tid": 1381210, + "ts": 1696942315135.877, "dur": 1.060, + "args": { + "External id": 4554096,"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": 1336753, "tid": 1381210, + "ts": 1696942315141.085, "dur": 5.308, + "args": { + "External id": 4554097,"Record function id": 0, "Ev Idx": 2416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942315142.405, "dur": 3.590, + "args": { + "External id": 4554098,"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": 1336753, "tid": 1381210, + "ts": 1696942315143.415, "dur": 2.172, + "args": { + "External id": 4554099,"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": 1336753, "tid": 1381210, + "ts": 1696942315144.164, "dur": 1.356, + "args": { + "External id": 4554100,"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": 1336753, "tid": 1381210, + "ts": 1696942315149.539, "dur": 6.143, + "args": { + "External id": 4554101,"Record function id": 0, "Ev Idx": 2420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942315150.843, "dur": 4.430, + "args": { + "External id": 4554102,"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": 1336753, "tid": 1381210, + "ts": 1696942315151.418, "dur": 3.458, + "args": { + "External id": 4554103,"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": 1336753, "tid": 1381210, + "ts": 1696942315152.088, "dur": 2.725, + "args": { + "External id": 4554104,"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": 1336753, "tid": 1381210, + "ts": 1696942315158.984, "dur": 3.825, + "args": { + "External id": 4554105,"Record function id": 0, "Ev Idx": 2424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942315160.355, "dur": 2.060, + "args": { + "External id": 4554106,"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": 1336753, "tid": 1381210, + "ts": 1696942315160.786, "dur": 1.217, + "args": { + "External id": 4554107,"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": 1336753, "tid": 1381210, + "ts": 1696942315161.140, "dur": 0.792, + "args": { + "External id": 4554108,"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": 1336753, "tid": 1381210, + "ts": 1696942315165.923, "dur": 4.630, + "args": { + "External id": 4554109,"Record function id": 0, "Ev Idx": 2428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942315167.120, "dur": 2.984, + "args": { + "External id": 4554110,"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": 1336753, "tid": 1381210, + "ts": 1696942315168.328, "dur": 1.307, + "args": { + "External id": 4554111,"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": 1336753, "tid": 1381210, + "ts": 1696942315168.794, "dur": 0.744, + "args": { + "External id": 4554112,"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": 1336753, "tid": 1381210, + "ts": 1696942315173.873, "dur": 3.761, + "args": { + "External id": 4554113,"Record function id": 0, "Ev Idx": 2432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942315174.893, "dur": 2.322, + "args": { + "External id": 4554114,"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": 1336753, "tid": 1381210, + "ts": 1696942315175.493, "dur": 1.326, + "args": { + "External id": 4554115,"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": 1336753, "tid": 1381210, + "ts": 1696942315175.796, "dur": 0.945, + "args": { + "External id": 4554116,"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": 1336753, "tid": 1381210, + "ts": 1696942315180.859, "dur": 4.375, + "args": { + "External id": 4554117,"Record function id": 0, "Ev Idx": 2436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942315182.035, "dur": 2.737, + "args": { + "External id": 4554118,"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": 1336753, "tid": 1381210, + "ts": 1696942315182.859, "dur": 1.482, + "args": { + "External id": 4554119,"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": 1336753, "tid": 1381210, + "ts": 1696942315183.322, "dur": 0.923, + "args": { + "External id": 4554120,"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": 1336753, "tid": 1381210, + "ts": 1696942315188.239, "dur": 3.545, + "args": { + "External id": 4554121,"Record function id": 0, "Ev Idx": 2440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942315189.205, "dur": 2.157, + "args": { + "External id": 4554122,"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": 1336753, "tid": 1381210, + "ts": 1696942315189.668, "dur": 1.244, + "args": { + "External id": 4554123,"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": 1336753, "tid": 1381210, + "ts": 1696942315190.078, "dur": 0.720, + "args": { + "External id": 4554124,"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": 1336753, "tid": 1381210, + "ts": 1696942315195.622, "dur": 36873.297, + "args": { + "External id": 4554125,"Record function id": 0, "Sequence number": 45295629, "Fwd thread id": 1, "Ev Idx": 2444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942315196.959, "dur": 36861.690, + "args": { + "External id": 4554126,"Sequence number": 45295629, "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": 1336753, "tid": 1381210, "ts": 1696942315196.959, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1696942315227.680, "dur": 37.936, + "args": { + "External id": 4554127,"Record function id": 0, "Ev Idx": 2446 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1696942315273.510, "dur": 67.080, + "args": { + "External id": 4554128,"Record function id": 0, "Ev Idx": 2447 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1696942315345.720, "dur": 36704.031, + "args": { + "External id": 4554129,"Record function id": 0, "Ev Idx": 2448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942315434.487, "dur": 6.491, + "args": { + "External id": 4554130,"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": 1336753, "tid": 1381210, + "ts": 1696942315450.416, "dur": 4.902, + "args": { + "External id": 4554131,"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": 1336753, "tid": 1381210, + "ts": 1696942315470.255, "dur": 35740.825, + "args": { + "External id": 4554132,"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": 1336753, "tid": 1381210, + "ts": 1696942315484.383, "dur": 35718.210, + "args": { + "External id": 4554133,"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": 1336753, "tid": 1381210, + "ts": 1696942315567.585, "dur": 16.573, + "args": { + "External id": 4554134,"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": 1336753, "tid": 1381210, + "ts": 1696942315591.051, "dur": 35572.748, + "args": { + "External id": 4554135,"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": 1336753, "tid": 1381210, + "ts": 1696942315594.003, "dur": 35569.088, + "args": { + "External id": 4554136,"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": 1336753, "tid": 1381210, + "ts": 1696942315598.554, "dur": 6.005, + "args": { + "External id": 4554137,"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": 1336753, "tid": 1381210, + "ts": 1696942315606.495, "dur": 35552.865, + "args": { + "External id": 4554138,"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": 1336753, "tid": 1381210, + "ts": 1696942351298.763, "dur": 8.683, + "args": { + "External id": 4554139,"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": 1336753, "tid": 1381210, + "ts": 1696942351302.020, "dur": 5.147, + "args": { + "External id": 4554140,"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": 1336753, "tid": 1381210, + "ts": 1696942351337.315, "dur": 366.216, + "args": { + "External id": 4554141,"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": 1336753, "tid": 1381210, + "ts": 1696942351363.503, "dur": 334.953, + "args": { + "External id": 4554142,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942351374.388, "dur": 318.344, + "args": { + "External id": 4554143,"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": 1336753, "tid": 1381210, + "ts": 1696942351725.057, "dur": 2.445, + "args": { + "External id": 4554144,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942351790.751, "dur": 6.945, + "args": { + "External id": 4554145,"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": 1336753, "tid": 1381210, + "ts": 1696942351846.558, "dur": 1.549, + "args": { + "External id": 4554146,"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": 1336753, "tid": 1381210, + "ts": 1696942351865.276, "dur": 1.054, + "args": { + "External id": 4554147,"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": 1336753, "tid": 1381210, + "ts": 1696942351882.399, "dur": 0.990, + "args": { + "External id": 4554148,"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": 1336753, "tid": 1381210, + "ts": 1696942351895.525, "dur": 1.049, + "args": { + "External id": 4554149,"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": 1336753, "tid": 1381210, + "ts": 1696942351908.790, "dur": 1.337, + "args": { + "External id": 4554150,"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": 1336753, "tid": 1381210, + "ts": 1696942351922.212, "dur": 0.961, + "args": { + "External id": 4554151,"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": 1336753, "tid": 1381210, + "ts": 1696942351936.739, "dur": 2.162, + "args": { + "External id": 4554152,"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": 1336753, "tid": 1381210, + "ts": 1696942351950.697, "dur": 0.994, + "args": { + "External id": 4554153,"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": 1336753, "tid": 1381210, + "ts": 1696942352086.142, "dur": 2831.098, + "args": { + "External id": 4554154,"Record function id": 0, "Ev Idx": 2473 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1696942352106.804, "dur": 1089.983, + "args": { + "External id": 4554155,"Record function id": 0, "Ev Idx": 2474 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1696942352122.276, "dur": 339.362, + "args": { + "External id": 4554156,"Record function id": 0, "Ev Idx": 2475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942352207.970, "dur": 4.612, + "args": { + "External id": 4554157,"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": 1336753, "tid": 1381210, + "ts": 1696942352215.981, "dur": 1.304, + "args": { + "External id": 4554158,"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": 1336753, "tid": 1381210, + "ts": 1696942352219.313, "dur": 1.049, + "args": { + "External id": 4554159,"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": 1336753, "tid": 1381210, + "ts": 1696942352222.035, "dur": 2.832, + "args": { + "External id": 4554160,"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": 1336753, "tid": 1381210, + "ts": 1696942352226.631, "dur": 1.106, + "args": { + "External id": 4554161,"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": 1336753, "tid": 1381210, + "ts": 1696942352229.524, "dur": 1.202, + "args": { + "External id": 4554162,"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": 1336753, "tid": 1381210, + "ts": 1696942352232.461, "dur": 1.782, + "args": { + "External id": 4554163,"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": 1336753, "tid": 1381210, + "ts": 1696942352235.676, "dur": 1.027, + "args": { + "External id": 4554164,"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": 1336753, "tid": 1381210, + "ts": 1696942352238.312, "dur": 0.977, + "args": { + "External id": 4554165,"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": 1336753, "tid": 1381210, + "ts": 1696942352240.786, "dur": 0.939, + "args": { + "External id": 4554166,"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": 1336753, "tid": 1381210, + "ts": 1696942352259.126, "dur": 169.319, + "args": { + "External id": 4554167,"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": 1336753, "tid": 1381210, + "ts": 1696942352288.987, "dur": 135.144, + "args": { + "External id": 4554168,"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": 1336753, "tid": 1381210, + "ts": 1696942352307.612, "dur": 12.438, + "args": { + "External id": 4554169,"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": 1336753, "tid": 1381210, + "ts": 1696942352323.289, "dur": 72.759, + "args": { + "External id": 4554170,"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": 1336753, "tid": 1381210, + "ts": 1696942352326.239, "dur": 69.445, + "args": { + "External id": 4554171,"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": 1336753, "tid": 1381210, + "ts": 1696942352330.627, "dur": 8.309, + "args": { + "External id": 4554172,"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": 1336753, "tid": 1381210, + "ts": 1696942352341.334, "dur": 53.881, + "args": { + "External id": 4554173,"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": 1336753, "tid": 1381210, + "ts": 1696942352578.387, "dur": 600.452, + "args": { + "External id": 4554174,"Record function id": 0, "Ev Idx": 2493 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1696942352597.516, "dur": 566.717, + "args": { + "External id": 4554175,"Record function id": 0, "Ev Idx": 2494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942352662.367, "dur": 5.378, + "args": { + "External id": 4554176,"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": 1336753, "tid": 1381210, + "ts": 1696942352684.735, "dur": 32.810, + "args": { + "External id": 4554177,"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": 1336753, "tid": 1381210, + "ts": 1696942352690.174, "dur": 1.492, + "args": { + "External id": 4554178,"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": 1336753, "tid": 1381210, + "ts": 1696942352694.573, "dur": 0.427, + "args": { + "External id": 4554179,"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": 1336753, "tid": 1381210, + "ts": 1696942352696.942, "dur": 0.389, + "args": { + "External id": 4554180,"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": 1336753, "tid": 1381210, + "ts": 1696942352698.978, "dur": 0.603, + "args": { + "External id": 4554181,"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": 1336753, "tid": 1381210, + "ts": 1696942352701.186, "dur": 0.572, + "args": { + "External id": 4554182,"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": 1336753, "tid": 1381210, + "ts": 1696942352703.647, "dur": 0.371, + "args": { + "External id": 4554183,"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": 1336753, "tid": 1381210, + "ts": 1696942352705.849, "dur": 2.168, + "args": { + "External id": 4554184,"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": 1336753, "tid": 1381210, + "ts": 1696942352709.787, "dur": 0.338, + "args": { + "External id": 4554185,"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": 1336753, "tid": 1381210, + "ts": 1696942352711.965, "dur": 0.430, + "args": { + "External id": 4554186,"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": 1336753, "tid": 1381210, + "ts": 1696942352728.334, "dur": 32.479, + "args": { + "External id": 4554187,"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": 1336753, "tid": 1381210, + "ts": 1696942352792.193, "dur": 101.265, + "args": { + "External id": 4554188,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942352802.520, "dur": 3.024, + "args": { + "External id": 4554189,"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": 1336753, "tid": 1381210, + "ts": 1696942352811.094, "dur": 9.990, + "args": { + "External id": 4554190,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942352815.340, "dur": 5.306, + "args": { + "External id": 4554191,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942352818.968, "dur": 0.485, + "args": { + "External id": 4554192,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942352828.069, "dur": 26.906, + "args": { + "External id": 4554193,"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": 1336753, "tid": 1381210, + "ts": 1696942352830.236, "dur": 0.390, + "args": { + "External id": 4554194,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942352832.664, "dur": 0.390, + "args": { + "External id": 4554195,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942352834.751, "dur": 0.516, + "args": { + "External id": 4554196,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942352837.016, "dur": 2.356, + "args": { + "External id": 4554197,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942352841.013, "dur": 0.595, + "args": { + "External id": 4554198,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942352843.559, "dur": 0.378, + "args": { + "External id": 4554199,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942352845.401, "dur": 0.383, + "args": { + "External id": 4554200,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942352847.652, "dur": 0.563, + "args": { + "External id": 4554201,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942352850.247, "dur": 0.433, + "args": { + "External id": 4554202,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942352866.011, "dur": 19.814, + "args": { + "External id": 4554203,"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": 1336753, "tid": 1381210, + "ts": 1696942352936.405, "dur": 153.014, + "args": { + "External id": 4554204,"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": 1336753, "tid": 1381210, + "ts": 1696942352959.130, "dur": 125.979, + "args": { + "External id": 4554205,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942352969.156, "dur": 110.690, + "args": { + "External id": 4554206,"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": 1336753, "tid": 1381210, + "ts": 1696942353105.709, "dur": 1.825, + "args": { + "External id": 4554207,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942353205.280, "dur": 1686.345, + "args": { + "External id": 4554208,"Sequence number": 45295628, "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": 1336753, "tid": 1381210, "ts": 1696942353205.280, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942353315.372, "dur": 102.297, + "args": { + "External id": 4554209,"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": 1336753, "tid": 1381210, + "ts": 1696942353462.789, "dur": 43.932, + "args": { + "External id": 4554210,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942353524.175, "dur": 76.182, + "args": { + "External id": 4554211,"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": 1336753, "tid": 1381210, + "ts": 1696942353613.124, "dur": 35.371, + "args": { + "External id": 4554212,"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": 1336753, "tid": 1381210, + "ts": 1696942353657.845, "dur": 49.630, + "args": { + "External id": 4554213,"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": 1336753, "tid": 1381210, + "ts": 1696942353715.738, "dur": 27.557, + "args": { + "External id": 4554214,"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": 1336753, "tid": 1381210, + "ts": 1696942353750.848, "dur": 43.235, + "args": { + "External id": 4554215,"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": 1336753, "tid": 1381210, + "ts": 1696942353817.037, "dur": 26.646, + "args": { + "External id": 4554216,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942353865.251, "dur": 28.965, + "args": { + "External id": 4554217,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942353913.469, "dur": 19.596, + "args": { + "External id": 4554218,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942353947.166, "dur": 15.052, + "args": { + "External id": 4554219,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942353971.112, "dur": 67.115, + "args": { + "External id": 4554220,"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": 1336753, "tid": 1381210, + "ts": 1696942354044.103, "dur": 36.664, + "args": { + "External id": 4554221,"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": 1336753, "tid": 1381210, + "ts": 1696942354111.706, "dur": 174.627, + "args": { + "External id": 4554222,"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": 1336753, "tid": 1381210, + "ts": 1696942354194.567, "dur": 5.988, + "args": { + "External id": 4554223,"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": 1336753, "tid": 1381210, + "ts": 1696942354202.636, "dur": 2.063, + "args": { + "External id": 4554224,"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": 1336753, "tid": 1381210, + "ts": 1696942354343.691, "dur": 24.995, + "args": { + "External id": 4554225,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942354381.636, "dur": 15.028, + "args": { + "External id": 4554226,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942354406.228, "dur": 35.965, + "args": { + "External id": 4554227,"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": 1336753, "tid": 1381210, + "ts": 1696942354449.768, "dur": 35.484, + "args": { + "External id": 4554228,"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": 1336753, "tid": 1381210, + "ts": 1696942354495.187, "dur": 20.294, + "args": { + "External id": 4554229,"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": 1336753, "tid": 1381210, + "ts": 1696942354520.747, "dur": 71.138, + "args": { + "External id": 4554230,"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": 1336753, "tid": 1381210, + "ts": 1696942354609.825, "dur": 27.633, + "args": { + "External id": 4554231,"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": 1336753, "tid": 1381210, + "ts": 1696942354645.529, "dur": 32.455, + "args": { + "External id": 4554232,"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": 1336753, "tid": 1381210, + "ts": 1696942354700.603, "dur": 23.958, + "args": { + "External id": 4554233,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942354744.283, "dur": 24.460, + "args": { + "External id": 4554234,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942354782.679, "dur": 20.008, + "args": { + "External id": 4554235,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942354818.254, "dur": 14.002, + "args": { + "External id": 4554236,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942354844.398, "dur": 19.121, + "args": { + "External id": 4554237,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942354940.787, "dur": 85.371, + "args": { + "External id": 4554238,"Record function id": 0, "Ev Idx": 2557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942354943.866, "dur": 80.522, + "args": { + "External id": 4554239,"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": 1336753, "tid": 1381210, + "ts": 1696942354947.933, "dur": 74.693, + "args": { + "External id": 4554240,"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": 1336753, "tid": 1381210, + "ts": 1696942355016.758, "dur": 5.408, + "args": { + "External id": 4554241,"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": 1336753, "tid": 1381210, + "ts": 1696942355036.768, "dur": 6.506, + "args": { + "External id": 4554242,"Record function id": 0, "Ev Idx": 2561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942355038.382, "dur": 4.464, + "args": { + "External id": 4554243,"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": 1336753, "tid": 1381210, + "ts": 1696942355039.895, "dur": 2.408, + "args": { + "External id": 4554244,"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": 1336753, "tid": 1381210, + "ts": 1696942355040.952, "dur": 1.231, + "args": { + "External id": 4554245,"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": 1336753, "tid": 1381210, + "ts": 1696942355046.612, "dur": 6.294, + "args": { + "External id": 4554246,"Record function id": 0, "Ev Idx": 2565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942355048.050, "dur": 4.414, + "args": { + "External id": 4554247,"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": 1336753, "tid": 1381210, + "ts": 1696942355048.578, "dur": 3.428, + "args": { + "External id": 4554248,"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": 1336753, "tid": 1381210, + "ts": 1696942355049.077, "dur": 2.847, + "args": { + "External id": 4554249,"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": 1336753, "tid": 1381210, + "ts": 1696942355056.107, "dur": 3.721, + "args": { + "External id": 4554250,"Record function id": 0, "Ev Idx": 2569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942355057.336, "dur": 2.107, + "args": { + "External id": 4554251,"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": 1336753, "tid": 1381210, + "ts": 1696942355057.893, "dur": 1.130, + "args": { + "External id": 4554252,"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": 1336753, "tid": 1381210, + "ts": 1696942355058.209, "dur": 0.735, + "args": { + "External id": 4554253,"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": 1336753, "tid": 1381210, + "ts": 1696942355062.980, "dur": 3.563, + "args": { + "External id": 4554254,"Record function id": 0, "Ev Idx": 2573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942355064.150, "dur": 1.972, + "args": { + "External id": 4554255,"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": 1336753, "tid": 1381210, + "ts": 1696942355064.610, "dur": 1.057, + "args": { + "External id": 4554256,"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": 1336753, "tid": 1381210, + "ts": 1696942355064.900, "dur": 0.706, + "args": { + "External id": 4554257,"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": 1336753, "tid": 1381210, + "ts": 1696942355069.800, "dur": 4.095, + "args": { + "External id": 4554258,"Record function id": 0, "Ev Idx": 2577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942355071.037, "dur": 2.465, + "args": { + "External id": 4554259,"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": 1336753, "tid": 1381210, + "ts": 1696942355071.884, "dur": 1.105, + "args": { + "External id": 4554260,"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": 1336753, "tid": 1381210, + "ts": 1696942355072.272, "dur": 0.658, + "args": { + "External id": 4554261,"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": 1336753, "tid": 1381210, + "ts": 1696942355078.441, "dur": 4.017, + "args": { + "External id": 4554262,"Record function id": 0, "Ev Idx": 2581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942355079.746, "dur": 2.289, + "args": { + "External id": 4554263,"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": 1336753, "tid": 1381210, + "ts": 1696942355080.422, "dur": 1.080, + "args": { + "External id": 4554264,"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": 1336753, "tid": 1381210, + "ts": 1696942355080.704, "dur": 0.718, + "args": { + "External id": 4554265,"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": 1336753, "tid": 1381210, + "ts": 1696942355085.793, "dur": 6.416, + "args": { + "External id": 4554266,"Record function id": 0, "Ev Idx": 2585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942355087.268, "dur": 4.549, + "args": { + "External id": 4554267,"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": 1336753, "tid": 1381210, + "ts": 1696942355088.254, "dur": 3.135, + "args": { + "External id": 4554268,"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": 1336753, "tid": 1381210, + "ts": 1696942355090.584, "dur": 0.676, + "args": { + "External id": 4554269,"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": 1336753, "tid": 1381210, + "ts": 1696942355095.349, "dur": 3.982, + "args": { + "External id": 4554270,"Record function id": 0, "Ev Idx": 2589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942355096.507, "dur": 2.433, + "args": { + "External id": 4554271,"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": 1336753, "tid": 1381210, + "ts": 1696942355097.041, "dur": 1.297, + "args": { + "External id": 4554272,"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": 1336753, "tid": 1381210, + "ts": 1696942355097.741, "dur": 0.512, + "args": { + "External id": 4554273,"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": 1336753, "tid": 1381210, + "ts": 1696942355103.401, "dur": 35019.381, + "args": { + "External id": 4554274,"Record function id": 0, "Sequence number": 45295627, "Fwd thread id": 1, "Ev Idx": 2593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942355105.048, "dur": 35007.998, + "args": { + "External id": 4554275,"Sequence number": 45295627, "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": 1336753, "tid": 1381210, "ts": 1696942355105.048, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1696942355142.013, "dur": 39.097, + "args": { + "External id": 4554276,"Record function id": 0, "Ev Idx": 2595 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1696942355192.894, "dur": 69.919, + "args": { + "External id": 4554277,"Record function id": 0, "Ev Idx": 2596 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1696942355268.879, "dur": 34835.833, + "args": { + "External id": 4554278,"Record function id": 0, "Ev Idx": 2597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942355362.426, "dur": 6.959, + "args": { + "External id": 4554279,"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": 1336753, "tid": 1381210, + "ts": 1696942355382.057, "dur": 6.745, + "args": { + "External id": 4554280,"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": 1336753, "tid": 1381210, + "ts": 1696942355408.473, "dur": 33825.978, + "args": { + "External id": 4554281,"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": 1336753, "tid": 1381210, + "ts": 1696942355422.421, "dur": 33802.464, + "args": { + "External id": 4554282,"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": 1336753, "tid": 1381210, + "ts": 1696942355476.605, "dur": 13.991, + "args": { + "External id": 4554283,"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": 1336753, "tid": 1381210, + "ts": 1696942355497.512, "dur": 33688.602, + "args": { + "External id": 4554284,"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": 1336753, "tid": 1381210, + "ts": 1696942355500.150, "dur": 33685.228, + "args": { + "External id": 4554285,"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": 1336753, "tid": 1381210, + "ts": 1696942355504.709, "dur": 5.117, + "args": { + "External id": 4554286,"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": 1336753, "tid": 1381210, + "ts": 1696942355511.746, "dur": 33669.557, + "args": { + "External id": 4554287,"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": 1336753, "tid": 1381210, + "ts": 1696942389325.220, "dur": 9.374, + "args": { + "External id": 4554288,"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": 1336753, "tid": 1381210, + "ts": 1696942389329.021, "dur": 5.215, + "args": { + "External id": 4554289,"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": 1336753, "tid": 1381210, + "ts": 1696942389365.680, "dur": 396.884, + "args": { + "External id": 4554290,"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": 1336753, "tid": 1381210, + "ts": 1696942389392.363, "dur": 364.827, + "args": { + "External id": 4554291,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942389402.684, "dur": 347.965, + "args": { + "External id": 4554292,"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": 1336753, "tid": 1381210, + "ts": 1696942389784.723, "dur": 2.344, + "args": { + "External id": 4554293,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942389847.512, "dur": 7.145, + "args": { + "External id": 4554294,"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": 1336753, "tid": 1381210, + "ts": 1696942389899.370, "dur": 1.306, + "args": { + "External id": 4554295,"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": 1336753, "tid": 1381210, + "ts": 1696942389918.525, "dur": 2.780, + "args": { + "External id": 4554296,"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": 1336753, "tid": 1381210, + "ts": 1696942389934.103, "dur": 1.216, + "args": { + "External id": 4554297,"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": 1336753, "tid": 1381210, + "ts": 1696942389949.115, "dur": 1.007, + "args": { + "External id": 4554298,"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": 1336753, "tid": 1381210, + "ts": 1696942389961.508, "dur": 0.819, + "args": { + "External id": 4554299,"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": 1336753, "tid": 1381210, + "ts": 1696942389973.736, "dur": 2.856, + "args": { + "External id": 4554300,"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": 1336753, "tid": 1381210, + "ts": 1696942390025.129, "dur": 2.864, + "args": { + "External id": 4554301,"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": 1336753, "tid": 1381210, + "ts": 1696942390040.217, "dur": 1.009, + "args": { + "External id": 4554302,"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": 1336753, "tid": 1381210, + "ts": 1696942390138.987, "dur": 2751.245, + "args": { + "External id": 4554303,"Record function id": 0, "Ev Idx": 2622 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1696942390158.745, "dur": 1059.598, + "args": { + "External id": 4554304,"Record function id": 0, "Ev Idx": 2623 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1696942390174.824, "dur": 326.326, + "args": { + "External id": 4554305,"Record function id": 0, "Ev Idx": 2624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942390255.188, "dur": 4.277, + "args": { + "External id": 4554306,"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": 1336753, "tid": 1381210, + "ts": 1696942390262.621, "dur": 1.615, + "args": { + "External id": 4554307,"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": 1336753, "tid": 1381210, + "ts": 1696942390266.523, "dur": 2.710, + "args": { + "External id": 4554308,"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": 1336753, "tid": 1381210, + "ts": 1696942390271.166, "dur": 0.956, + "args": { + "External id": 4554309,"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": 1336753, "tid": 1381210, + "ts": 1696942390273.480, "dur": 1.250, + "args": { + "External id": 4554310,"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": 1336753, "tid": 1381210, + "ts": 1696942390276.442, "dur": 0.861, + "args": { + "External id": 4554311,"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": 1336753, "tid": 1381210, + "ts": 1696942390279.002, "dur": 2.448, + "args": { + "External id": 4554312,"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": 1336753, "tid": 1381210, + "ts": 1696942390283.318, "dur": 0.985, + "args": { + "External id": 4554313,"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": 1336753, "tid": 1381210, + "ts": 1696942390285.866, "dur": 0.877, + "args": { + "External id": 4554314,"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": 1336753, "tid": 1381210, + "ts": 1696942390288.598, "dur": 1.007, + "args": { + "External id": 4554315,"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": 1336753, "tid": 1381210, + "ts": 1696942390307.848, "dur": 161.391, + "args": { + "External id": 4554316,"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": 1336753, "tid": 1381210, + "ts": 1696942390325.098, "dur": 139.513, + "args": { + "External id": 4554317,"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": 1336753, "tid": 1381210, + "ts": 1696942390349.460, "dur": 14.077, + "args": { + "External id": 4554318,"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": 1336753, "tid": 1381210, + "ts": 1696942390367.356, "dur": 70.628, + "args": { + "External id": 4554319,"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": 1336753, "tid": 1381210, + "ts": 1696942390370.363, "dur": 67.245, + "args": { + "External id": 4554320,"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": 1336753, "tid": 1381210, + "ts": 1696942390375.487, "dur": 6.778, + "args": { + "External id": 4554321,"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": 1336753, "tid": 1381210, + "ts": 1696942390384.098, "dur": 52.944, + "args": { + "External id": 4554322,"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": 1336753, "tid": 1381210, + "ts": 1696942390621.673, "dur": 587.922, + "args": { + "External id": 4554323,"Record function id": 0, "Ev Idx": 2642 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1696942390640.505, "dur": 555.849, + "args": { + "External id": 4554324,"Record function id": 0, "Ev Idx": 2643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942390701.790, "dur": 5.830, + "args": { + "External id": 4554325,"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": 1336753, "tid": 1381210, + "ts": 1696942390724.380, "dur": 32.539, + "args": { + "External id": 4554326,"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": 1336753, "tid": 1381210, + "ts": 1696942390729.740, "dur": 1.526, + "args": { + "External id": 4554327,"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": 1336753, "tid": 1381210, + "ts": 1696942390733.449, "dur": 0.553, + "args": { + "External id": 4554328,"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": 1336753, "tid": 1381210, + "ts": 1696942390736.115, "dur": 0.430, + "args": { + "External id": 4554329,"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": 1336753, "tid": 1381210, + "ts": 1696942390737.933, "dur": 0.509, + "args": { + "External id": 4554330,"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": 1336753, "tid": 1381210, + "ts": 1696942390740.566, "dur": 0.420, + "args": { + "External id": 4554331,"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": 1336753, "tid": 1381210, + "ts": 1696942390742.872, "dur": 2.279, + "args": { + "External id": 4554332,"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": 1336753, "tid": 1381210, + "ts": 1696942390746.699, "dur": 0.316, + "args": { + "External id": 4554333,"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": 1336753, "tid": 1381210, + "ts": 1696942390748.584, "dur": 0.438, + "args": { + "External id": 4554334,"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": 1336753, "tid": 1381210, + "ts": 1696942390750.535, "dur": 0.562, + "args": { + "External id": 4554335,"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": 1336753, "tid": 1381210, + "ts": 1696942390766.728, "dur": 31.188, + "args": { + "External id": 4554336,"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": 1336753, "tid": 1381210, + "ts": 1696942390830.022, "dur": 101.227, + "args": { + "External id": 4554337,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942390840.061, "dur": 2.902, + "args": { + "External id": 4554338,"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": 1336753, "tid": 1381210, + "ts": 1696942390848.070, "dur": 10.225, + "args": { + "External id": 4554339,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942390852.290, "dur": 5.608, + "args": { + "External id": 4554340,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942390856.284, "dur": 0.479, + "args": { + "External id": 4554341,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942390865.094, "dur": 26.984, + "args": { + "External id": 4554342,"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": 1336753, "tid": 1381210, + "ts": 1696942390867.319, "dur": 0.759, + "args": { + "External id": 4554343,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942390869.863, "dur": 0.326, + "args": { + "External id": 4554344,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942390872.057, "dur": 2.404, + "args": { + "External id": 4554345,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942390876.120, "dur": 0.399, + "args": { + "External id": 4554346,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942390878.466, "dur": 0.413, + "args": { + "External id": 4554347,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942390880.517, "dur": 0.457, + "args": { + "External id": 4554348,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942390882.817, "dur": 0.270, + "args": { + "External id": 4554349,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942390884.758, "dur": 0.302, + "args": { + "External id": 4554350,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942390886.669, "dur": 0.404, + "args": { + "External id": 4554351,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942390903.951, "dur": 19.654, + "args": { + "External id": 4554352,"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": 1336753, "tid": 1381210, + "ts": 1696942390976.312, "dur": 152.245, + "args": { + "External id": 4554353,"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": 1336753, "tid": 1381210, + "ts": 1696942391037.682, "dur": 87.144, + "args": { + "External id": 4554354,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942391048.710, "dur": 71.571, + "args": { + "External id": 4554355,"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": 1336753, "tid": 1381210, + "ts": 1696942391142.752, "dur": 1.728, + "args": { + "External id": 4554356,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942391226.735, "dur": 1638.907, + "args": { + "External id": 4554357,"Sequence number": 45295626, "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": 1336753, "tid": 1381210, "ts": 1696942391226.735, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942391338.235, "dur": 100.193, + "args": { + "External id": 4554358,"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": 1336753, "tid": 1381210, + "ts": 1696942391476.408, "dur": 40.629, + "args": { + "External id": 4554359,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942391555.097, "dur": 54.522, + "args": { + "External id": 4554360,"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": 1336753, "tid": 1381210, + "ts": 1696942391622.211, "dur": 32.527, + "args": { + "External id": 4554361,"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": 1336753, "tid": 1381210, + "ts": 1696942391661.925, "dur": 47.889, + "args": { + "External id": 4554362,"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": 1336753, "tid": 1381210, + "ts": 1696942391717.546, "dur": 26.960, + "args": { + "External id": 4554363,"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": 1336753, "tid": 1381210, + "ts": 1696942391752.408, "dur": 47.132, + "args": { + "External id": 4554364,"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": 1336753, "tid": 1381210, + "ts": 1696942391823.423, "dur": 26.953, + "args": { + "External id": 4554365,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942391871.204, "dur": 28.851, + "args": { + "External id": 4554366,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942391921.884, "dur": 18.891, + "args": { + "External id": 4554367,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942391953.636, "dur": 17.802, + "args": { + "External id": 4554368,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942391979.976, "dur": 76.675, + "args": { + "External id": 4554369,"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": 1336753, "tid": 1381210, + "ts": 1696942392062.394, "dur": 33.514, + "args": { + "External id": 4554370,"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": 1336753, "tid": 1381210, + "ts": 1696942392127.140, "dur": 168.172, + "args": { + "External id": 4554371,"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": 1336753, "tid": 1381210, + "ts": 1696942392202.990, "dur": 6.082, + "args": { + "External id": 4554372,"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": 1336753, "tid": 1381210, + "ts": 1696942392210.995, "dur": 2.213, + "args": { + "External id": 4554373,"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": 1336753, "tid": 1381210, + "ts": 1696942392329.218, "dur": 23.822, + "args": { + "External id": 4554374,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942392364.418, "dur": 14.257, + "args": { + "External id": 4554375,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942392387.200, "dur": 30.879, + "args": { + "External id": 4554376,"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": 1336753, "tid": 1381210, + "ts": 1696942392425.191, "dur": 37.163, + "args": { + "External id": 4554377,"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": 1336753, "tid": 1381210, + "ts": 1696942392471.188, "dur": 20.122, + "args": { + "External id": 4554378,"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": 1336753, "tid": 1381210, + "ts": 1696942392500.076, "dur": 64.080, + "args": { + "External id": 4554379,"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": 1336753, "tid": 1381210, + "ts": 1696942392583.945, "dur": 30.097, + "args": { + "External id": 4554380,"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": 1336753, "tid": 1381210, + "ts": 1696942392622.150, "dur": 31.804, + "args": { + "External id": 4554381,"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": 1336753, "tid": 1381210, + "ts": 1696942392678.611, "dur": 22.386, + "args": { + "External id": 4554382,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942392717.306, "dur": 27.579, + "args": { + "External id": 4554383,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942392759.749, "dur": 16.925, + "args": { + "External id": 4554384,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942392795.055, "dur": 15.616, + "args": { + "External id": 4554385,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942392822.986, "dur": 14.808, + "args": { + "External id": 4554386,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942392917.136, "dur": 15.742, + "args": { + "External id": 4554387,"Record function id": 0, "Ev Idx": 2706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942392920.862, "dur": 11.110, + "args": { + "External id": 4554388,"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": 1336753, "tid": 1381210, + "ts": 1696942392925.193, "dur": 5.812, + "args": { + "External id": 4554389,"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": 1336753, "tid": 1381210, + "ts": 1696942392926.968, "dur": 3.912, + "args": { + "External id": 4554390,"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": 1336753, "tid": 1381210, + "ts": 1696942392936.772, "dur": 12.691, + "args": { + "External id": 4554391,"Record function id": 0, "Ev Idx": 2710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942392938.496, "dur": 10.504, + "args": { + "External id": 4554392,"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": 1336753, "tid": 1381210, + "ts": 1696942392939.553, "dur": 8.918, + "args": { + "External id": 4554393,"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": 1336753, "tid": 1381210, + "ts": 1696942392940.360, "dur": 8.010, + "args": { + "External id": 4554394,"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": 1336753, "tid": 1381210, + "ts": 1696942392952.909, "dur": 5.495, + "args": { + "External id": 4554395,"Record function id": 0, "Ev Idx": 2714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942392954.586, "dur": 3.397, + "args": { + "External id": 4554396,"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": 1336753, "tid": 1381210, + "ts": 1696942392955.272, "dur": 2.296, + "args": { + "External id": 4554397,"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": 1336753, "tid": 1381210, + "ts": 1696942392956.264, "dur": 1.242, + "args": { + "External id": 4554398,"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": 1336753, "tid": 1381210, + "ts": 1696942392965.147, "dur": 3.924, + "args": { + "External id": 4554399,"Record function id": 0, "Ev Idx": 2718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942392966.396, "dur": 2.273, + "args": { + "External id": 4554400,"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": 1336753, "tid": 1381210, + "ts": 1696942392967.047, "dur": 1.083, + "args": { + "External id": 4554401,"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": 1336753, "tid": 1381210, + "ts": 1696942392967.434, "dur": 0.633, + "args": { + "External id": 4554402,"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": 1336753, "tid": 1381210, + "ts": 1696942392972.180, "dur": 3.649, + "args": { + "External id": 4554403,"Record function id": 0, "Ev Idx": 2722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942392973.272, "dur": 2.134, + "args": { + "External id": 4554404,"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": 1336753, "tid": 1381210, + "ts": 1696942392973.787, "dur": 1.186, + "args": { + "External id": 4554405,"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": 1336753, "tid": 1381210, + "ts": 1696942392974.193, "dur": 0.711, + "args": { + "External id": 4554406,"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": 1336753, "tid": 1381210, + "ts": 1696942392978.926, "dur": 4.137, + "args": { + "External id": 4554407,"Record function id": 0, "Ev Idx": 2726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942392980.143, "dur": 2.505, + "args": { + "External id": 4554408,"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": 1336753, "tid": 1381210, + "ts": 1696942392980.677, "dur": 1.408, + "args": { + "External id": 4554409,"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": 1336753, "tid": 1381210, + "ts": 1696942392981.385, "dur": 0.590, + "args": { + "External id": 4554410,"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": 1336753, "tid": 1381210, + "ts": 1696942393023.792, "dur": 6.859, + "args": { + "External id": 4554411,"Record function id": 0, "Ev Idx": 2730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942393026.034, "dur": 3.947, + "args": { + "External id": 4554412,"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": 1336753, "tid": 1381210, + "ts": 1696942393027.208, "dur": 1.868, + "args": { + "External id": 4554413,"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": 1336753, "tid": 1381210, + "ts": 1696942393027.658, "dur": 1.221, + "args": { + "External id": 4554414,"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": 1336753, "tid": 1381210, + "ts": 1696942393034.097, "dur": 3.937, + "args": { + "External id": 4554415,"Record function id": 0, "Ev Idx": 2734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942393035.781, "dur": 1.837, + "args": { + "External id": 4554416,"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": 1336753, "tid": 1381210, + "ts": 1696942393036.296, "dur": 0.891, + "args": { + "External id": 4554417,"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": 1336753, "tid": 1381210, + "ts": 1696942393036.559, "dur": 0.563, + "args": { + "External id": 4554418,"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": 1336753, "tid": 1381210, + "ts": 1696942393041.331, "dur": 5.833, + "args": { + "External id": 4554419,"Record function id": 0, "Ev Idx": 2738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942393042.714, "dur": 4.039, + "args": { + "External id": 4554420,"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": 1336753, "tid": 1381210, + "ts": 1696942393043.339, "dur": 2.920, + "args": { + "External id": 4554421,"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": 1336753, "tid": 1381210, + "ts": 1696942393043.891, "dur": 2.282, + "args": { + "External id": 4554422,"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": 1336753, "tid": 1381210, + "ts": 1696942393051.244, "dur": 34896.250, + "args": { + "External id": 4554423,"Record function id": 0, "Sequence number": 45295625, "Fwd thread id": 1, "Ev Idx": 2742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942393052.779, "dur": 34886.456, + "args": { + "External id": 4554424,"Sequence number": 45295625, "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": 1336753, "tid": 1381210, "ts": 1696942393052.779, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1696942393081.930, "dur": 40.213, + "args": { + "External id": 4554425,"Record function id": 0, "Ev Idx": 2744 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1696942393130.292, "dur": 67.931, + "args": { + "External id": 4554426,"Record function id": 0, "Ev Idx": 2745 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1696942393204.146, "dur": 34727.164, + "args": { + "External id": 4554427,"Record function id": 0, "Ev Idx": 2746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942393291.435, "dur": 7.094, + "args": { + "External id": 4554428,"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": 1336753, "tid": 1381210, + "ts": 1696942393308.275, "dur": 5.274, + "args": { + "External id": 4554429,"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": 1336753, "tid": 1381210, + "ts": 1696942393331.522, "dur": 33816.842, + "args": { + "External id": 4554430,"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": 1336753, "tid": 1381210, + "ts": 1696942393345.080, "dur": 33794.188, + "args": { + "External id": 4554431,"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": 1336753, "tid": 1381210, + "ts": 1696942393426.997, "dur": 14.140, + "args": { + "External id": 4554432,"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": 1336753, "tid": 1381210, + "ts": 1696942393447.673, "dur": 33651.618, + "args": { + "External id": 4554433,"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": 1336753, "tid": 1381210, + "ts": 1696942393453.502, "dur": 33645.075, + "args": { + "External id": 4554434,"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": 1336753, "tid": 1381210, + "ts": 1696942393457.748, "dur": 5.444, + "args": { + "External id": 4554435,"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": 1336753, "tid": 1381210, + "ts": 1696942393465.137, "dur": 33629.729, + "args": { + "External id": 4554436,"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": 1336753, "tid": 1381210, + "ts": 1696942427236.550, "dur": 8.537, + "args": { + "External id": 4554437,"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": 1336753, "tid": 1381210, + "ts": 1696942427239.732, "dur": 5.065, + "args": { + "External id": 4554438,"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": 1336753, "tid": 1381210, + "ts": 1696942427279.978, "dur": 358.465, + "args": { + "External id": 4554439,"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": 1336753, "tid": 1381210, + "ts": 1696942427309.820, "dur": 323.527, + "args": { + "External id": 4554440,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942427320.794, "dur": 307.037, + "args": { + "External id": 4554441,"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": 1336753, "tid": 1381210, + "ts": 1696942427658.495, "dur": 2.058, + "args": { + "External id": 4554442,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942427717.248, "dur": 6.390, + "args": { + "External id": 4554443,"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": 1336753, "tid": 1381210, + "ts": 1696942427768.905, "dur": 3.379, + "args": { + "External id": 4554444,"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": 1336753, "tid": 1381210, + "ts": 1696942427789.247, "dur": 1.054, + "args": { + "External id": 4554445,"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": 1336753, "tid": 1381210, + "ts": 1696942427802.137, "dur": 1.053, + "args": { + "External id": 4554446,"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": 1336753, "tid": 1381210, + "ts": 1696942427816.123, "dur": 1.093, + "args": { + "External id": 4554447,"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": 1336753, "tid": 1381210, + "ts": 1696942427829.115, "dur": 2.298, + "args": { + "External id": 4554448,"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": 1336753, "tid": 1381210, + "ts": 1696942427843.528, "dur": 1.180, + "args": { + "External id": 4554449,"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": 1336753, "tid": 1381210, + "ts": 1696942427857.014, "dur": 2.252, + "args": { + "External id": 4554450,"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": 1336753, "tid": 1381210, + "ts": 1696942427870.480, "dur": 0.949, + "args": { + "External id": 4554451,"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": 1336753, "tid": 1381210, + "ts": 1696942427963.322, "dur": 2763.886, + "args": { + "External id": 4554452,"Record function id": 0, "Ev Idx": 2771 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1696942428016.473, "dur": 1037.427, + "args": { + "External id": 4554453,"Record function id": 0, "Ev Idx": 2772 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1696942428036.223, "dur": 325.639, + "args": { + "External id": 4554454,"Record function id": 0, "Ev Idx": 2773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942428119.924, "dur": 7.005, + "args": { + "External id": 4554455,"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": 1336753, "tid": 1381210, + "ts": 1696942428130.239, "dur": 1.581, + "args": { + "External id": 4554456,"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": 1336753, "tid": 1381210, + "ts": 1696942428133.835, "dur": 1.007, + "args": { + "External id": 4554457,"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": 1336753, "tid": 1381210, + "ts": 1696942428136.687, "dur": 1.027, + "args": { + "External id": 4554458,"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": 1336753, "tid": 1381210, + "ts": 1696942428139.130, "dur": 0.900, + "args": { + "External id": 4554459,"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": 1336753, "tid": 1381210, + "ts": 1696942428147.540, "dur": 1.048, + "args": { + "External id": 4554460,"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": 1336753, "tid": 1381210, + "ts": 1696942428150.492, "dur": 1.839, + "args": { + "External id": 4554461,"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": 1336753, "tid": 1381210, + "ts": 1696942428154.014, "dur": 1.256, + "args": { + "External id": 4554462,"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": 1336753, "tid": 1381210, + "ts": 1696942428156.620, "dur": 3.105, + "args": { + "External id": 4554463,"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": 1336753, "tid": 1381210, + "ts": 1696942428161.099, "dur": 0.762, + "args": { + "External id": 4554464,"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": 1336753, "tid": 1381210, + "ts": 1696942428179.289, "dur": 150.732, + "args": { + "External id": 4554465,"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": 1336753, "tid": 1381210, + "ts": 1696942428195.334, "dur": 130.250, + "args": { + "External id": 4554466,"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": 1336753, "tid": 1381210, + "ts": 1696942428213.249, "dur": 12.863, + "args": { + "External id": 4554467,"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": 1336753, "tid": 1381210, + "ts": 1696942428229.421, "dur": 68.327, + "args": { + "External id": 4554468,"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": 1336753, "tid": 1381210, + "ts": 1696942428232.275, "dur": 65.094, + "args": { + "External id": 4554469,"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": 1336753, "tid": 1381210, + "ts": 1696942428236.417, "dur": 5.612, + "args": { + "External id": 4554470,"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": 1336753, "tid": 1381210, + "ts": 1696942428243.974, "dur": 52.635, + "args": { + "External id": 4554471,"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": 1336753, "tid": 1381210, + "ts": 1696942428452.686, "dur": 592.586, + "args": { + "External id": 4554472,"Record function id": 0, "Ev Idx": 2791 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1696942428469.762, "dur": 561.116, + "args": { + "External id": 4554473,"Record function id": 0, "Ev Idx": 2792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942428544.343, "dur": 6.299, + "args": { + "External id": 4554474,"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": 1336753, "tid": 1381210, + "ts": 1696942428568.268, "dur": 32.323, + "args": { + "External id": 4554475,"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": 1336753, "tid": 1381210, + "ts": 1696942428573.965, "dur": 1.556, + "args": { + "External id": 4554476,"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": 1336753, "tid": 1381210, + "ts": 1696942428577.965, "dur": 0.756, + "args": { + "External id": 4554477,"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": 1336753, "tid": 1381210, + "ts": 1696942428580.478, "dur": 0.433, + "args": { + "External id": 4554478,"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": 1336753, "tid": 1381210, + "ts": 1696942428582.969, "dur": 2.481, + "args": { + "External id": 4554479,"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": 1336753, "tid": 1381210, + "ts": 1696942428587.047, "dur": 0.405, + "args": { + "External id": 4554480,"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": 1336753, "tid": 1381210, + "ts": 1696942428589.247, "dur": 0.438, + "args": { + "External id": 4554481,"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": 1336753, "tid": 1381210, + "ts": 1696942428591.642, "dur": 0.312, + "args": { + "External id": 4554482,"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": 1336753, "tid": 1381210, + "ts": 1696942428593.623, "dur": 0.540, + "args": { + "External id": 4554483,"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": 1336753, "tid": 1381210, + "ts": 1696942428596.121, "dur": 0.394, + "args": { + "External id": 4554484,"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": 1336753, "tid": 1381210, + "ts": 1696942428611.068, "dur": 33.052, + "args": { + "External id": 4554485,"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": 1336753, "tid": 1381210, + "ts": 1696942428677.380, "dur": 101.249, + "args": { + "External id": 4554486,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942428687.897, "dur": 2.864, + "args": { + "External id": 4554487,"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": 1336753, "tid": 1381210, + "ts": 1696942428696.016, "dur": 10.702, + "args": { + "External id": 4554488,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942428700.485, "dur": 5.835, + "args": { + "External id": 4554489,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942428704.617, "dur": 0.594, + "args": { + "External id": 4554490,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942428713.833, "dur": 27.917, + "args": { + "External id": 4554491,"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": 1336753, "tid": 1381210, + "ts": 1696942428716.007, "dur": 2.126, + "args": { + "External id": 4554492,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942428720.087, "dur": 0.593, + "args": { + "External id": 4554493,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942428722.394, "dur": 0.524, + "args": { + "External id": 4554494,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942428724.680, "dur": 0.586, + "args": { + "External id": 4554495,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942428727.004, "dur": 0.543, + "args": { + "External id": 4554496,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942428729.732, "dur": 0.444, + "args": { + "External id": 4554497,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942428731.945, "dur": 0.591, + "args": { + "External id": 4554498,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942428734.005, "dur": 0.419, + "args": { + "External id": 4554499,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942428735.943, "dur": 2.072, + "args": { + "External id": 4554500,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942428751.586, "dur": 19.720, + "args": { + "External id": 4554501,"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": 1336753, "tid": 1381210, + "ts": 1696942428824.128, "dur": 107.203, + "args": { + "External id": 4554502,"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": 1336753, "tid": 1381210, + "ts": 1696942428846.423, "dur": 81.316, + "args": { + "External id": 4554503,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942428856.042, "dur": 67.596, + "args": { + "External id": 4554504,"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": 1336753, "tid": 1381210, + "ts": 1696942428944.249, "dur": 1.782, + "args": { + "External id": 4554505,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942429063.139, "dur": 1640.498, + "args": { + "External id": 4554506,"Sequence number": 45295624, "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": 1336753, "tid": 1381210, "ts": 1696942429063.139, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942429174.572, "dur": 103.124, + "args": { + "External id": 4554507,"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": 1336753, "tid": 1381210, + "ts": 1696942429316.031, "dur": 41.222, + "args": { + "External id": 4554508,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942429378.449, "dur": 49.000, + "args": { + "External id": 4554509,"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": 1336753, "tid": 1381210, + "ts": 1696942429437.237, "dur": 32.019, + "args": { + "External id": 4554510,"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": 1336753, "tid": 1381210, + "ts": 1696942429476.548, "dur": 45.285, + "args": { + "External id": 4554511,"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": 1336753, "tid": 1381210, + "ts": 1696942429549.620, "dur": 33.201, + "args": { + "External id": 4554512,"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": 1336753, "tid": 1381210, + "ts": 1696942429594.783, "dur": 43.161, + "args": { + "External id": 4554513,"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": 1336753, "tid": 1381210, + "ts": 1696942429663.417, "dur": 24.678, + "args": { + "External id": 4554514,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942429706.219, "dur": 27.160, + "args": { + "External id": 4554515,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942429753.943, "dur": 18.603, + "args": { + "External id": 4554516,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942429786.167, "dur": 14.939, + "args": { + "External id": 4554517,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942429812.519, "dur": 28.221, + "args": { + "External id": 4554518,"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": 1336753, "tid": 1381210, + "ts": 1696942429847.497, "dur": 32.836, + "args": { + "External id": 4554519,"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": 1336753, "tid": 1381210, + "ts": 1696942429909.655, "dur": 219.620, + "args": { + "External id": 4554520,"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": 1336753, "tid": 1381210, + "ts": 1696942430026.960, "dur": 7.261, + "args": { + "External id": 4554521,"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": 1336753, "tid": 1381210, + "ts": 1696942430036.339, "dur": 2.634, + "args": { + "External id": 4554522,"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": 1336753, "tid": 1381210, + "ts": 1696942430167.516, "dur": 24.057, + "args": { + "External id": 4554523,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942430203.011, "dur": 15.372, + "args": { + "External id": 4554524,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942430227.411, "dur": 42.407, + "args": { + "External id": 4554525,"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": 1336753, "tid": 1381210, + "ts": 1696942430279.183, "dur": 37.610, + "args": { + "External id": 4554526,"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": 1336753, "tid": 1381210, + "ts": 1696942430323.590, "dur": 20.560, + "args": { + "External id": 4554527,"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": 1336753, "tid": 1381210, + "ts": 1696942430349.731, "dur": 33.720, + "args": { + "External id": 4554528,"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": 1336753, "tid": 1381210, + "ts": 1696942430390.318, "dur": 34.062, + "args": { + "External id": 4554529,"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": 1336753, "tid": 1381210, + "ts": 1696942430439.422, "dur": 36.546, + "args": { + "External id": 4554530,"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": 1336753, "tid": 1381210, + "ts": 1696942430494.634, "dur": 24.841, + "args": { + "External id": 4554531,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942430553.448, "dur": 30.064, + "args": { + "External id": 4554532,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942430599.896, "dur": 17.431, + "args": { + "External id": 4554533,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942430633.149, "dur": 14.725, + "args": { + "External id": 4554534,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942430660.597, "dur": 16.450, + "args": { + "External id": 4554535,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942430751.192, "dur": 20.293, + "args": { + "External id": 4554536,"Record function id": 0, "Ev Idx": 2855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942430754.617, "dur": 15.955, + "args": { + "External id": 4554537,"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": 1336753, "tid": 1381210, + "ts": 1696942430758.586, "dur": 10.934, + "args": { + "External id": 4554538,"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": 1336753, "tid": 1381210, + "ts": 1696942430760.576, "dur": 8.805, + "args": { + "External id": 4554539,"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": 1336753, "tid": 1381210, + "ts": 1696942430775.649, "dur": 5.537, + "args": { + "External id": 4554540,"Record function id": 0, "Ev Idx": 2859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942430777.103, "dur": 3.586, + "args": { + "External id": 4554541,"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": 1336753, "tid": 1381210, + "ts": 1696942430777.911, "dur": 2.290, + "args": { + "External id": 4554542,"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": 1336753, "tid": 1381210, + "ts": 1696942430778.917, "dur": 1.058, + "args": { + "External id": 4554543,"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": 1336753, "tid": 1381210, + "ts": 1696942430784.745, "dur": 4.096, + "args": { + "External id": 4554544,"Record function id": 0, "Ev Idx": 2863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942430786.074, "dur": 2.346, + "args": { + "External id": 4554545,"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": 1336753, "tid": 1381210, + "ts": 1696942430786.563, "dur": 1.407, + "args": { + "External id": 4554546,"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": 1336753, "tid": 1381210, + "ts": 1696942430786.995, "dur": 0.897, + "args": { + "External id": 4554547,"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": 1336753, "tid": 1381210, + "ts": 1696942430792.267, "dur": 3.780, + "args": { + "External id": 4554548,"Record function id": 0, "Ev Idx": 2867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942430793.371, "dur": 2.277, + "args": { + "External id": 4554549,"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": 1336753, "tid": 1381210, + "ts": 1696942430794.133, "dur": 1.021, + "args": { + "External id": 4554550,"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": 1336753, "tid": 1381210, + "ts": 1696942430794.525, "dur": 0.566, + "args": { + "External id": 4554551,"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": 1336753, "tid": 1381210, + "ts": 1696942430799.434, "dur": 3.660, + "args": { + "External id": 4554552,"Record function id": 0, "Ev Idx": 2871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942430800.505, "dur": 2.168, + "args": { + "External id": 4554553,"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": 1336753, "tid": 1381210, + "ts": 1696942430801.103, "dur": 1.035, + "args": { + "External id": 4554554,"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": 1336753, "tid": 1381210, + "ts": 1696942430801.406, "dur": 0.670, + "args": { + "External id": 4554555,"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": 1336753, "tid": 1381210, + "ts": 1696942430806.457, "dur": 3.822, + "args": { + "External id": 4554556,"Record function id": 0, "Ev Idx": 2875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942430807.661, "dur": 2.206, + "args": { + "External id": 4554557,"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": 1336753, "tid": 1381210, + "ts": 1696942430808.230, "dur": 1.238, + "args": { + "External id": 4554558,"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": 1336753, "tid": 1381210, + "ts": 1696942430808.727, "dur": 0.585, + "args": { + "External id": 4554559,"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": 1336753, "tid": 1381210, + "ts": 1696942430813.532, "dur": 4.061, + "args": { + "External id": 4554560,"Record function id": 0, "Ev Idx": 2879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942430814.826, "dur": 2.327, + "args": { + "External id": 4554561,"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": 1336753, "tid": 1381210, + "ts": 1696942430815.260, "dur": 1.230, + "args": { + "External id": 4554562,"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": 1336753, "tid": 1381210, + "ts": 1696942430815.552, "dur": 0.842, + "args": { + "External id": 4554563,"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": 1336753, "tid": 1381210, + "ts": 1696942430824.099, "dur": 5.917, + "args": { + "External id": 4554564,"Record function id": 0, "Ev Idx": 2883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942430825.300, "dur": 4.313, + "args": { + "External id": 4554565,"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": 1336753, "tid": 1381210, + "ts": 1696942430825.957, "dur": 3.263, + "args": { + "External id": 4554566,"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": 1336753, "tid": 1381210, + "ts": 1696942430826.381, "dur": 2.760, + "args": { + "External id": 4554567,"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": 1336753, "tid": 1381210, + "ts": 1696942430833.377, "dur": 4.607, + "args": { + "External id": 4554568,"Record function id": 0, "Ev Idx": 2887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942430834.724, "dur": 2.834, + "args": { + "External id": 4554569,"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": 1336753, "tid": 1381210, + "ts": 1696942430835.343, "dur": 1.553, + "args": { + "External id": 4554570,"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": 1336753, "tid": 1381210, + "ts": 1696942430835.826, "dur": 0.988, + "args": { + "External id": 4554571,"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": 1336753, "tid": 1381210, + "ts": 1696942430842.294, "dur": 35642.703, + "args": { + "External id": 4554572,"Record function id": 0, "Sequence number": 45295623, "Fwd thread id": 1, "Ev Idx": 2891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942430843.697, "dur": 35633.484, + "args": { + "External id": 4554573,"Sequence number": 45295623, "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": 1336753, "tid": 1381210, "ts": 1696942430843.697, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1696942430872.346, "dur": 37.267, + "args": { + "External id": 4554574,"Record function id": 0, "Ev Idx": 2893 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1696942430917.714, "dur": 62.424, + "args": { + "External id": 4554575,"Record function id": 0, "Ev Idx": 2894 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1696942431023.474, "dur": 35445.944, + "args": { + "External id": 4554576,"Record function id": 0, "Ev Idx": 2895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942431116.400, "dur": 7.111, + "args": { + "External id": 4554577,"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": 1336753, "tid": 1381210, + "ts": 1696942431134.043, "dur": 5.109, + "args": { + "External id": 4554578,"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": 1336753, "tid": 1381210, + "ts": 1696942431154.834, "dur": 34499.710, + "args": { + "External id": 4554579,"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": 1336753, "tid": 1381210, + "ts": 1696942431168.728, "dur": 34476.838, + "args": { + "External id": 4554580,"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": 1336753, "tid": 1381210, + "ts": 1696942431261.004, "dur": 13.963, + "args": { + "External id": 4554581,"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": 1336753, "tid": 1381210, + "ts": 1696942431281.331, "dur": 34326.659, + "args": { + "External id": 4554582,"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": 1336753, "tid": 1381210, + "ts": 1696942431284.077, "dur": 34323.064, + "args": { + "External id": 4554583,"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": 1336753, "tid": 1381210, + "ts": 1696942431288.377, "dur": 5.442, + "args": { + "External id": 4554584,"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": 1336753, "tid": 1381210, + "ts": 1696942431296.124, "dur": 34307.336, + "args": { + "External id": 4554585,"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": 1336753, "tid": 1381210, + "ts": 1696942465746.970, "dur": 8.944, + "args": { + "External id": 4554586,"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": 1336753, "tid": 1381210, + "ts": 1696942465750.388, "dur": 5.238, + "args": { + "External id": 4554587,"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": 1336753, "tid": 1381210, + "ts": 1696942465788.739, "dur": 377.374, + "args": { + "External id": 4554588,"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": 1336753, "tid": 1381210, + "ts": 1696942465814.916, "dur": 346.056, + "args": { + "External id": 4554589,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942465825.779, "dur": 329.600, + "args": { + "External id": 4554590,"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": 1336753, "tid": 1381210, + "ts": 1696942466187.882, "dur": 2.715, + "args": { + "External id": 4554591,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942466250.684, "dur": 6.571, + "args": { + "External id": 4554592,"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": 1336753, "tid": 1381210, + "ts": 1696942466305.077, "dur": 1.340, + "args": { + "External id": 4554593,"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": 1336753, "tid": 1381210, + "ts": 1696942466323.507, "dur": 0.875, + "args": { + "External id": 4554594,"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": 1336753, "tid": 1381210, + "ts": 1696942466336.780, "dur": 1.228, + "args": { + "External id": 4554595,"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": 1336753, "tid": 1381210, + "ts": 1696942466349.970, "dur": 1.095, + "args": { + "External id": 4554596,"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": 1336753, "tid": 1381210, + "ts": 1696942466364.239, "dur": 1.322, + "args": { + "External id": 4554597,"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": 1336753, "tid": 1381210, + "ts": 1696942466377.595, "dur": 1.015, + "args": { + "External id": 4554598,"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": 1336753, "tid": 1381210, + "ts": 1696942466391.724, "dur": 1.936, + "args": { + "External id": 4554599,"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": 1336753, "tid": 1381210, + "ts": 1696942466405.044, "dur": 0.919, + "args": { + "External id": 4554600,"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": 1336753, "tid": 1381210, + "ts": 1696942466501.052, "dur": 2832.254, + "args": { + "External id": 4554601,"Record function id": 0, "Ev Idx": 2920 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1696942466520.876, "dur": 1091.904, + "args": { + "External id": 4554602,"Record function id": 0, "Ev Idx": 2921 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1696942466556.852, "dur": 330.368, + "args": { + "External id": 4554603,"Record function id": 0, "Ev Idx": 2922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942466641.906, "dur": 4.511, + "args": { + "External id": 4554604,"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": 1336753, "tid": 1381210, + "ts": 1696942466649.562, "dur": 1.313, + "args": { + "External id": 4554605,"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": 1336753, "tid": 1381210, + "ts": 1696942466652.801, "dur": 1.249, + "args": { + "External id": 4554606,"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": 1336753, "tid": 1381210, + "ts": 1696942466655.665, "dur": 1.157, + "args": { + "External id": 4554607,"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": 1336753, "tid": 1381210, + "ts": 1696942466658.153, "dur": 0.944, + "args": { + "External id": 4554608,"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": 1336753, "tid": 1381210, + "ts": 1696942466660.911, "dur": 0.814, + "args": { + "External id": 4554609,"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": 1336753, "tid": 1381210, + "ts": 1696942466663.260, "dur": 1.927, + "args": { + "External id": 4554610,"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": 1336753, "tid": 1381210, + "ts": 1696942466666.567, "dur": 3.057, + "args": { + "External id": 4554611,"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": 1336753, "tid": 1381210, + "ts": 1696942466671.327, "dur": 0.942, + "args": { + "External id": 4554612,"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": 1336753, "tid": 1381210, + "ts": 1696942466674.129, "dur": 0.892, + "args": { + "External id": 4554613,"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": 1336753, "tid": 1381210, + "ts": 1696942466694.770, "dur": 160.400, + "args": { + "External id": 4554614,"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": 1336753, "tid": 1381210, + "ts": 1696942466711.238, "dur": 139.367, + "args": { + "External id": 4554615,"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": 1336753, "tid": 1381210, + "ts": 1696942466735.232, "dur": 13.113, + "args": { + "External id": 4554616,"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": 1336753, "tid": 1381210, + "ts": 1696942466751.656, "dur": 69.191, + "args": { + "External id": 4554617,"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": 1336753, "tid": 1381210, + "ts": 1696942466754.283, "dur": 66.164, + "args": { + "External id": 4554618,"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": 1336753, "tid": 1381210, + "ts": 1696942466758.636, "dur": 5.693, + "args": { + "External id": 4554619,"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": 1336753, "tid": 1381210, + "ts": 1696942466766.365, "dur": 53.394, + "args": { + "External id": 4554620,"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": 1336753, "tid": 1381210, + "ts": 1696942466978.533, "dur": 625.088, + "args": { + "External id": 4554621,"Record function id": 0, "Ev Idx": 2940 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1696942467035.948, "dur": 554.521, + "args": { + "External id": 4554622,"Record function id": 0, "Ev Idx": 2941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942467102.555, "dur": 5.976, + "args": { + "External id": 4554623,"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": 1336753, "tid": 1381210, + "ts": 1696942467125.352, "dur": 36.384, + "args": { + "External id": 4554624,"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": 1336753, "tid": 1381210, + "ts": 1696942467130.850, "dur": 1.542, + "args": { + "External id": 4554625,"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": 1336753, "tid": 1381210, + "ts": 1696942467135.007, "dur": 0.449, + "args": { + "External id": 4554626,"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": 1336753, "tid": 1381210, + "ts": 1696942467137.385, "dur": 2.295, + "args": { + "External id": 4554627,"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": 1336753, "tid": 1381210, + "ts": 1696942467141.422, "dur": 0.569, + "args": { + "External id": 4554628,"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": 1336753, "tid": 1381210, + "ts": 1696942467143.661, "dur": 0.368, + "args": { + "External id": 4554629,"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": 1336753, "tid": 1381210, + "ts": 1696942467146.145, "dur": 0.393, + "args": { + "External id": 4554630,"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": 1336753, "tid": 1381210, + "ts": 1696942467152.274, "dur": 0.387, + "args": { + "External id": 4554631,"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": 1336753, "tid": 1381210, + "ts": 1696942467154.272, "dur": 0.507, + "args": { + "External id": 4554632,"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": 1336753, "tid": 1381210, + "ts": 1696942467156.495, "dur": 0.406, + "args": { + "External id": 4554633,"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": 1336753, "tid": 1381210, + "ts": 1696942467171.409, "dur": 34.864, + "args": { + "External id": 4554634,"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": 1336753, "tid": 1381210, + "ts": 1696942467241.511, "dur": 106.147, + "args": { + "External id": 4554635,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942467252.189, "dur": 3.142, + "args": { + "External id": 4554636,"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": 1336753, "tid": 1381210, + "ts": 1696942467260.549, "dur": 12.236, + "args": { + "External id": 4554637,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942467264.936, "dur": 7.418, + "args": { + "External id": 4554638,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942467268.864, "dur": 2.194, + "args": { + "External id": 4554639,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942467279.906, "dur": 25.951, + "args": { + "External id": 4554640,"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": 1336753, "tid": 1381210, + "ts": 1696942467282.287, "dur": 0.495, + "args": { + "External id": 4554641,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942467284.338, "dur": 0.490, + "args": { + "External id": 4554642,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942467286.702, "dur": 0.521, + "args": { + "External id": 4554643,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942467288.825, "dur": 0.346, + "args": { + "External id": 4554644,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942467290.885, "dur": 0.372, + "args": { + "External id": 4554645,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942467292.767, "dur": 0.547, + "args": { + "External id": 4554646,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942467295.327, "dur": 0.452, + "args": { + "External id": 4554647,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942467297.710, "dur": 2.068, + "args": { + "External id": 4554648,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942467301.493, "dur": 0.347, + "args": { + "External id": 4554649,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942467320.886, "dur": 19.660, + "args": { + "External id": 4554650,"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": 1336753, "tid": 1381210, + "ts": 1696942467392.038, "dur": 110.696, + "args": { + "External id": 4554651,"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": 1336753, "tid": 1381210, + "ts": 1696942467416.972, "dur": 82.312, + "args": { + "External id": 4554652,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942467426.526, "dur": 68.164, + "args": { + "External id": 4554653,"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": 1336753, "tid": 1381210, + "ts": 1696942467518.657, "dur": 1.892, + "args": { + "External id": 4554654,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942467620.936, "dur": 1690.060, + "args": { + "External id": 4554655,"Sequence number": 45295622, "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": 1336753, "tid": 1381210, "ts": 1696942467620.936, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942467731.675, "dur": 102.557, + "args": { + "External id": 4554656,"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": 1336753, "tid": 1381210, + "ts": 1696942467872.911, "dur": 39.885, + "args": { + "External id": 4554657,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942467932.935, "dur": 88.355, + "args": { + "External id": 4554658,"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": 1336753, "tid": 1381210, + "ts": 1696942468036.562, "dur": 38.274, + "args": { + "External id": 4554659,"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": 1336753, "tid": 1381210, + "ts": 1696942468083.478, "dur": 46.540, + "args": { + "External id": 4554660,"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": 1336753, "tid": 1381210, + "ts": 1696942468138.455, "dur": 28.001, + "args": { + "External id": 4554661,"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": 1336753, "tid": 1381210, + "ts": 1696942468176.495, "dur": 42.806, + "args": { + "External id": 4554662,"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": 1336753, "tid": 1381210, + "ts": 1696942468244.659, "dur": 24.792, + "args": { + "External id": 4554663,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942468288.991, "dur": 27.870, + "args": { + "External id": 4554664,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942468338.356, "dur": 19.574, + "args": { + "External id": 4554665,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942468371.183, "dur": 15.234, + "args": { + "External id": 4554666,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942468398.116, "dur": 28.405, + "args": { + "External id": 4554667,"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": 1336753, "tid": 1381210, + "ts": 1696942468429.904, "dur": 32.738, + "args": { + "External id": 4554668,"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": 1336753, "tid": 1381210, + "ts": 1696942468489.666, "dur": 204.681, + "args": { + "External id": 4554669,"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": 1336753, "tid": 1381210, + "ts": 1696942468590.691, "dur": 6.437, + "args": { + "External id": 4554670,"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": 1336753, "tid": 1381210, + "ts": 1696942468602.808, "dur": 2.861, + "args": { + "External id": 4554671,"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": 1336753, "tid": 1381210, + "ts": 1696942468731.564, "dur": 27.433, + "args": { + "External id": 4554672,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942468770.348, "dur": 14.951, + "args": { + "External id": 4554673,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942468796.368, "dur": 40.573, + "args": { + "External id": 4554674,"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": 1336753, "tid": 1381210, + "ts": 1696942468844.354, "dur": 39.486, + "args": { + "External id": 4554675,"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": 1336753, "tid": 1381210, + "ts": 1696942468891.125, "dur": 20.864, + "args": { + "External id": 4554676,"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": 1336753, "tid": 1381210, + "ts": 1696942468917.850, "dur": 50.903, + "args": { + "External id": 4554677,"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": 1336753, "tid": 1381210, + "ts": 1696942469016.084, "dur": 30.839, + "args": { + "External id": 4554678,"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": 1336753, "tid": 1381210, + "ts": 1696942469058.382, "dur": 33.626, + "args": { + "External id": 4554679,"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": 1336753, "tid": 1381210, + "ts": 1696942469117.567, "dur": 23.445, + "args": { + "External id": 4554680,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942469159.980, "dur": 27.610, + "args": { + "External id": 4554681,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942469203.115, "dur": 17.105, + "args": { + "External id": 4554682,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942469234.720, "dur": 14.235, + "args": { + "External id": 4554683,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942469261.103, "dur": 16.033, + "args": { + "External id": 4554684,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942469360.060, "dur": 15.055, + "args": { + "External id": 4554685,"Record function id": 0, "Ev Idx": 3004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942469363.321, "dur": 10.847, + "args": { + "External id": 4554686,"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": 1336753, "tid": 1381210, + "ts": 1696942469367.420, "dur": 5.726, + "args": { + "External id": 4554687,"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": 1336753, "tid": 1381210, + "ts": 1696942469369.146, "dur": 3.859, + "args": { + "External id": 4554688,"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": 1336753, "tid": 1381210, + "ts": 1696942469379.299, "dur": 6.149, + "args": { + "External id": 4554689,"Record function id": 0, "Ev Idx": 3008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942469380.626, "dur": 4.415, + "args": { + "External id": 4554690,"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": 1336753, "tid": 1381210, + "ts": 1696942469382.103, "dur": 2.287, + "args": { + "External id": 4554691,"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": 1336753, "tid": 1381210, + "ts": 1696942469383.308, "dur": 0.969, + "args": { + "External id": 4554692,"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": 1336753, "tid": 1381210, + "ts": 1696942469389.193, "dur": 5.815, + "args": { + "External id": 4554693,"Record function id": 0, "Ev Idx": 3012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942469390.848, "dur": 3.748, + "args": { + "External id": 4554694,"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": 1336753, "tid": 1381210, + "ts": 1696942469392.017, "dur": 1.920, + "args": { + "External id": 4554695,"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": 1336753, "tid": 1381210, + "ts": 1696942469392.672, "dur": 1.187, + "args": { + "External id": 4554696,"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": 1336753, "tid": 1381210, + "ts": 1696942469398.386, "dur": 4.330, + "args": { + "External id": 4554697,"Record function id": 0, "Ev Idx": 3016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942469399.905, "dur": 2.372, + "args": { + "External id": 4554698,"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": 1336753, "tid": 1381210, + "ts": 1696942469400.473, "dur": 1.305, + "args": { + "External id": 4554699,"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": 1336753, "tid": 1381210, + "ts": 1696942469401.062, "dur": 0.630, + "args": { + "External id": 4554700,"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": 1336753, "tid": 1381210, + "ts": 1696942469406.153, "dur": 4.287, + "args": { + "External id": 4554701,"Record function id": 0, "Ev Idx": 3020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942469407.765, "dur": 2.279, + "args": { + "External id": 4554702,"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": 1336753, "tid": 1381210, + "ts": 1696942469408.227, "dur": 1.117, + "args": { + "External id": 4554703,"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": 1336753, "tid": 1381210, + "ts": 1696942469408.686, "dur": 0.583, + "args": { + "External id": 4554704,"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": 1336753, "tid": 1381210, + "ts": 1696942469413.837, "dur": 3.587, + "args": { + "External id": 4554705,"Record function id": 0, "Ev Idx": 3024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942469414.857, "dur": 2.135, + "args": { + "External id": 4554706,"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": 1336753, "tid": 1381210, + "ts": 1696942469415.342, "dur": 1.211, + "args": { + "External id": 4554707,"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": 1336753, "tid": 1381210, + "ts": 1696942469415.841, "dur": 0.611, + "args": { + "External id": 4554708,"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": 1336753, "tid": 1381210, + "ts": 1696942469420.848, "dur": 5.845, + "args": { + "External id": 4554709,"Record function id": 0, "Ev Idx": 3028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942469421.992, "dur": 4.244, + "args": { + "External id": 4554710,"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": 1336753, "tid": 1381210, + "ts": 1696942469422.698, "dur": 3.139, + "args": { + "External id": 4554711,"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": 1336753, "tid": 1381210, + "ts": 1696942469423.070, "dur": 2.687, + "args": { + "External id": 4554712,"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": 1336753, "tid": 1381210, + "ts": 1696942469429.998, "dur": 3.916, + "args": { + "External id": 4554713,"Record function id": 0, "Ev Idx": 3032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942469431.219, "dur": 2.290, + "args": { + "External id": 4554714,"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": 1336753, "tid": 1381210, + "ts": 1696942469431.795, "dur": 1.151, + "args": { + "External id": 4554715,"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": 1336753, "tid": 1381210, + "ts": 1696942469432.078, "dur": 0.785, + "args": { + "External id": 4554716,"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": 1336753, "tid": 1381210, + "ts": 1696942469437.314, "dur": 4.504, + "args": { + "External id": 4554717,"Record function id": 0, "Ev Idx": 3036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942469438.556, "dur": 2.660, + "args": { + "External id": 4554718,"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": 1336753, "tid": 1381210, + "ts": 1696942469439.221, "dur": 1.346, + "args": { + "External id": 4554719,"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": 1336753, "tid": 1381210, + "ts": 1696942469439.829, "dur": 0.648, + "args": { + "External id": 4554720,"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": 1336753, "tid": 1381210, + "ts": 1696942469446.052, "dur": 35815.147, + "args": { + "External id": 4554721,"Record function id": 0, "Sequence number": 45295621, "Fwd thread id": 1, "Ev Idx": 3040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942469447.669, "dur": 35804.524, + "args": { + "External id": 4554722,"Sequence number": 45295621, "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": 1336753, "tid": 1381210, "ts": 1696942469447.669, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1696942469476.678, "dur": 37.269, + "args": { + "External id": 4554723,"Record function id": 0, "Ev Idx": 3042 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1696942469521.553, "dur": 84.249, + "args": { + "External id": 4554724,"Record function id": 0, "Ev Idx": 3043 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1696942469613.814, "dur": 35630.409, + "args": { + "External id": 4554725,"Record function id": 0, "Ev Idx": 3044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942469704.629, "dur": 7.740, + "args": { + "External id": 4554726,"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": 1336753, "tid": 1381210, + "ts": 1696942469722.468, "dur": 5.181, + "args": { + "External id": 4554727,"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": 1336753, "tid": 1381210, + "ts": 1696942469743.247, "dur": 34613.374, + "args": { + "External id": 4554728,"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": 1336753, "tid": 1381210, + "ts": 1696942469789.529, "dur": 34557.352, + "args": { + "External id": 4554729,"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": 1336753, "tid": 1381210, + "ts": 1696942469831.093, "dur": 14.082, + "args": { + "External id": 4554730,"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": 1336753, "tid": 1381210, + "ts": 1696942469851.637, "dur": 34457.394, + "args": { + "External id": 4554731,"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": 1336753, "tid": 1381210, + "ts": 1696942469854.389, "dur": 34453.816, + "args": { + "External id": 4554732,"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": 1336753, "tid": 1381210, + "ts": 1696942469858.774, "dur": 5.689, + "args": { + "External id": 4554733,"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": 1336753, "tid": 1381210, + "ts": 1696942469866.606, "dur": 34437.894, + "args": { + "External id": 4554734,"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": 1336753, "tid": 1381210, + "ts": 1696942504448.193, "dur": 9.338, + "args": { + "External id": 4554735,"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": 1336753, "tid": 1381210, + "ts": 1696942504451.777, "dur": 5.436, + "args": { + "External id": 4554736,"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": 1336753, "tid": 1381210, + "ts": 1696942504489.258, "dur": 402.245, + "args": { + "External id": 4554737,"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": 1336753, "tid": 1381210, + "ts": 1696942504516.368, "dur": 369.533, + "args": { + "External id": 4554738,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942504539.515, "dur": 340.670, + "args": { + "External id": 4554739,"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": 1336753, "tid": 1381210, + "ts": 1696942504912.403, "dur": 2.685, + "args": { + "External id": 4554740,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942504976.035, "dur": 41.007, + "args": { + "External id": 4554741,"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": 1336753, "tid": 1381210, + "ts": 1696942505068.388, "dur": 1.695, + "args": { + "External id": 4554742,"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": 1336753, "tid": 1381210, + "ts": 1696942505089.489, "dur": 1.281, + "args": { + "External id": 4554743,"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": 1336753, "tid": 1381210, + "ts": 1696942505104.455, "dur": 1.157, + "args": { + "External id": 4554744,"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": 1336753, "tid": 1381210, + "ts": 1696942505118.412, "dur": 2.524, + "args": { + "External id": 4554745,"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": 1336753, "tid": 1381210, + "ts": 1696942505132.827, "dur": 1.016, + "args": { + "External id": 4554746,"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": 1336753, "tid": 1381210, + "ts": 1696942505147.846, "dur": 1.348, + "args": { + "External id": 4554747,"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": 1336753, "tid": 1381210, + "ts": 1696942505162.572, "dur": 1.918, + "args": { + "External id": 4554748,"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": 1336753, "tid": 1381210, + "ts": 1696942505176.683, "dur": 2.860, + "args": { + "External id": 4554749,"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": 1336753, "tid": 1381210, + "ts": 1696942505278.936, "dur": 2853.438, + "args": { + "External id": 4554750,"Record function id": 0, "Ev Idx": 3069 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1696942505299.081, "dur": 1122.614, + "args": { + "External id": 4554751,"Record function id": 0, "Ev Idx": 3070 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1696942505314.602, "dur": 376.494, + "args": { + "External id": 4554752,"Record function id": 0, "Ev Idx": 3071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942505428.614, "dur": 4.704, + "args": { + "External id": 4554753,"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": 1336753, "tid": 1381210, + "ts": 1696942505436.599, "dur": 1.088, + "args": { + "External id": 4554754,"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": 1336753, "tid": 1381210, + "ts": 1696942505439.519, "dur": 0.860, + "args": { + "External id": 4554755,"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": 1336753, "tid": 1381210, + "ts": 1696942505441.979, "dur": 0.788, + "args": { + "External id": 4554756,"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": 1336753, "tid": 1381210, + "ts": 1696942505444.634, "dur": 0.843, + "args": { + "External id": 4554757,"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": 1336753, "tid": 1381210, + "ts": 1696942505448.585, "dur": 0.914, + "args": { + "External id": 4554758,"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": 1336753, "tid": 1381210, + "ts": 1696942505451.086, "dur": 3.946, + "args": { + "External id": 4554759,"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": 1336753, "tid": 1381210, + "ts": 1696942505456.474, "dur": 0.915, + "args": { + "External id": 4554760,"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": 1336753, "tid": 1381210, + "ts": 1696942505458.969, "dur": 0.755, + "args": { + "External id": 4554761,"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": 1336753, "tid": 1381210, + "ts": 1696942505461.226, "dur": 0.746, + "args": { + "External id": 4554762,"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": 1336753, "tid": 1381210, + "ts": 1696942505480.278, "dur": 174.120, + "args": { + "External id": 4554763,"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": 1336753, "tid": 1381210, + "ts": 1696942505496.402, "dur": 153.010, + "args": { + "External id": 4554764,"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": 1336753, "tid": 1381210, + "ts": 1696942505515.172, "dur": 29.277, + "args": { + "External id": 4554765,"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": 1336753, "tid": 1381210, + "ts": 1696942505548.662, "dur": 72.556, + "args": { + "External id": 4554766,"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": 1336753, "tid": 1381210, + "ts": 1696942505551.458, "dur": 69.440, + "args": { + "External id": 4554767,"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": 1336753, "tid": 1381210, + "ts": 1696942505555.845, "dur": 6.700, + "args": { + "External id": 4554768,"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": 1336753, "tid": 1381210, + "ts": 1696942505564.467, "dur": 55.683, + "args": { + "External id": 4554769,"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": 1336753, "tid": 1381210, + "ts": 1696942505787.665, "dur": 624.636, + "args": { + "External id": 4554770,"Record function id": 0, "Ev Idx": 3089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1696942505804.785, "dur": 593.856, + "args": { + "External id": 4554771,"Record function id": 0, "Ev Idx": 3090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942505868.851, "dur": 5.069, + "args": { + "External id": 4554772,"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": 1336753, "tid": 1381210, + "ts": 1696942505890.017, "dur": 33.129, + "args": { + "External id": 4554773,"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": 1336753, "tid": 1381210, + "ts": 1696942505895.450, "dur": 1.708, + "args": { + "External id": 4554774,"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": 1336753, "tid": 1381210, + "ts": 1696942505899.525, "dur": 2.440, + "args": { + "External id": 4554775,"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": 1336753, "tid": 1381210, + "ts": 1696942505904.127, "dur": 0.395, + "args": { + "External id": 4554776,"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": 1336753, "tid": 1381210, + "ts": 1696942505906.568, "dur": 0.308, + "args": { + "External id": 4554777,"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": 1336753, "tid": 1381210, + "ts": 1696942505908.302, "dur": 0.349, + "args": { + "External id": 4554778,"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": 1336753, "tid": 1381210, + "ts": 1696942505910.578, "dur": 0.293, + "args": { + "External id": 4554779,"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": 1336753, "tid": 1381210, + "ts": 1696942505913.141, "dur": 0.543, + "args": { + "External id": 4554780,"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": 1336753, "tid": 1381210, + "ts": 1696942505915.245, "dur": 0.414, + "args": { + "External id": 4554781,"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": 1336753, "tid": 1381210, + "ts": 1696942505917.298, "dur": 0.350, + "args": { + "External id": 4554782,"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": 1336753, "tid": 1381210, + "ts": 1696942505933.373, "dur": 29.622, + "args": { + "External id": 4554783,"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": 1336753, "tid": 1381210, + "ts": 1696942506045.818, "dur": 120.805, + "args": { + "External id": 4554784,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942506057.441, "dur": 6.827, + "args": { + "External id": 4554785,"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": 1336753, "tid": 1381210, + "ts": 1696942506070.467, "dur": 11.639, + "args": { + "External id": 4554786,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942506074.948, "dur": 6.713, + "args": { + "External id": 4554787,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942506079.303, "dur": 0.785, + "args": { + "External id": 4554788,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942506090.264, "dur": 26.682, + "args": { + "External id": 4554789,"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": 1336753, "tid": 1381210, + "ts": 1696942506093.060, "dur": 0.781, + "args": { + "External id": 4554790,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942506095.912, "dur": 0.556, + "args": { + "External id": 4554791,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942506098.201, "dur": 0.454, + "args": { + "External id": 4554792,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942506100.228, "dur": 0.400, + "args": { + "External id": 4554793,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942506102.099, "dur": 0.408, + "args": { + "External id": 4554794,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942506104.361, "dur": 0.348, + "args": { + "External id": 4554795,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942506106.208, "dur": 2.287, + "args": { + "External id": 4554796,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942506110.100, "dur": 0.501, + "args": { + "External id": 4554797,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942506112.154, "dur": 0.446, + "args": { + "External id": 4554798,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942506135.241, "dur": 23.082, + "args": { + "External id": 4554799,"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": 1336753, "tid": 1381210, + "ts": 1696942506217.130, "dur": 113.572, + "args": { + "External id": 4554800,"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": 1336753, "tid": 1381210, + "ts": 1696942506243.760, "dur": 83.155, + "args": { + "External id": 4554801,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942506253.726, "dur": 69.092, + "args": { + "External id": 4554802,"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": 1336753, "tid": 1381210, + "ts": 1696942506346.464, "dur": 1.649, + "args": { + "External id": 4554803,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942506429.620, "dur": 1680.570, + "args": { + "External id": 4554804,"Sequence number": 45295620, "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": 1336753, "tid": 1381210, "ts": 1696942506429.620, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942506561.433, "dur": 103.323, + "args": { + "External id": 4554805,"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": 1336753, "tid": 1381210, + "ts": 1696942506703.996, "dur": 40.316, + "args": { + "External id": 4554806,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942506765.473, "dur": 48.178, + "args": { + "External id": 4554807,"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": 1336753, "tid": 1381210, + "ts": 1696942506824.107, "dur": 31.541, + "args": { + "External id": 4554808,"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": 1336753, "tid": 1381210, + "ts": 1696942506863.055, "dur": 46.018, + "args": { + "External id": 4554809,"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": 1336753, "tid": 1381210, + "ts": 1696942506918.626, "dur": 27.377, + "args": { + "External id": 4554810,"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": 1336753, "tid": 1381210, + "ts": 1696942506954.719, "dur": 75.780, + "args": { + "External id": 4554811,"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": 1336753, "tid": 1381210, + "ts": 1696942507058.133, "dur": 27.407, + "args": { + "External id": 4554812,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942507104.222, "dur": 28.667, + "args": { + "External id": 4554813,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942507156.733, "dur": 18.569, + "args": { + "External id": 4554814,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942507188.162, "dur": 15.781, + "args": { + "External id": 4554815,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942507216.030, "dur": 32.067, + "args": { + "External id": 4554816,"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": 1336753, "tid": 1381210, + "ts": 1696942507251.634, "dur": 33.878, + "args": { + "External id": 4554817,"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": 1336753, "tid": 1381210, + "ts": 1696942507312.008, "dur": 176.321, + "args": { + "External id": 4554818,"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": 1336753, "tid": 1381210, + "ts": 1696942507386.448, "dur": 8.702, + "args": { + "External id": 4554819,"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": 1336753, "tid": 1381210, + "ts": 1696942507397.351, "dur": 4.206, + "args": { + "External id": 4554820,"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": 1336753, "tid": 1381210, + "ts": 1696942507522.098, "dur": 46.510, + "args": { + "External id": 4554821,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942507597.757, "dur": 16.101, + "args": { + "External id": 4554822,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942507624.555, "dur": 50.518, + "args": { + "External id": 4554823,"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": 1336753, "tid": 1381210, + "ts": 1696942507687.199, "dur": 40.123, + "args": { + "External id": 4554824,"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": 1336753, "tid": 1381210, + "ts": 1696942507735.405, "dur": 20.580, + "args": { + "External id": 4554825,"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": 1336753, "tid": 1381210, + "ts": 1696942507763.706, "dur": 32.957, + "args": { + "External id": 4554826,"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": 1336753, "tid": 1381210, + "ts": 1696942507802.922, "dur": 20.172, + "args": { + "External id": 4554827,"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": 1336753, "tid": 1381210, + "ts": 1696942507830.689, "dur": 32.875, + "args": { + "External id": 4554828,"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": 1336753, "tid": 1381210, + "ts": 1696942507880.695, "dur": 24.705, + "args": { + "External id": 4554829,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942507922.631, "dur": 23.908, + "args": { + "External id": 4554830,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942507964.506, "dur": 47.320, + "args": { + "External id": 4554831,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942508032.201, "dur": 17.785, + "args": { + "External id": 4554832,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942508065.632, "dur": 16.913, + "args": { + "External id": 4554833,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942508154.981, "dur": 18.879, + "args": { + "External id": 4554834,"Record function id": 0, "Ev Idx": 3153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942508161.878, "dur": 10.997, + "args": { + "External id": 4554835,"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": 1336753, "tid": 1381210, + "ts": 1696942508165.967, "dur": 6.089, + "args": { + "External id": 4554836,"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": 1336753, "tid": 1381210, + "ts": 1696942508167.835, "dur": 4.093, + "args": { + "External id": 4554837,"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": 1336753, "tid": 1381210, + "ts": 1696942508177.967, "dur": 5.479, + "args": { + "External id": 4554838,"Record function id": 0, "Ev Idx": 3157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942508179.488, "dur": 3.498, + "args": { + "External id": 4554839,"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": 1336753, "tid": 1381210, + "ts": 1696942508180.344, "dur": 2.143, + "args": { + "External id": 4554840,"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": 1336753, "tid": 1381210, + "ts": 1696942508181.308, "dur": 1.070, + "args": { + "External id": 4554841,"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": 1336753, "tid": 1381210, + "ts": 1696942508186.778, "dur": 4.876, + "args": { + "External id": 4554842,"Record function id": 0, "Ev Idx": 3161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942508188.276, "dur": 2.973, + "args": { + "External id": 4554843,"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": 1336753, "tid": 1381210, + "ts": 1696942508189.092, "dur": 1.747, + "args": { + "External id": 4554844,"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": 1336753, "tid": 1381210, + "ts": 1696942508189.785, "dur": 0.981, + "args": { + "External id": 4554845,"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": 1336753, "tid": 1381210, + "ts": 1696942508194.871, "dur": 6.859, + "args": { + "External id": 4554846,"Record function id": 0, "Ev Idx": 3165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942508196.331, "dur": 4.984, + "args": { + "External id": 4554847,"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": 1336753, "tid": 1381210, + "ts": 1696942508197.171, "dur": 3.606, + "args": { + "External id": 4554848,"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": 1336753, "tid": 1381210, + "ts": 1696942508197.682, "dur": 3.020, + "args": { + "External id": 4554849,"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": 1336753, "tid": 1381210, + "ts": 1696942508205.060, "dur": 4.191, + "args": { + "External id": 4554850,"Record function id": 0, "Ev Idx": 3169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942508206.537, "dur": 2.270, + "args": { + "External id": 4554851,"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": 1336753, "tid": 1381210, + "ts": 1696942508207.001, "dur": 1.290, + "args": { + "External id": 4554852,"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": 1336753, "tid": 1381210, + "ts": 1696942508207.473, "dur": 0.752, + "args": { + "External id": 4554853,"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": 1336753, "tid": 1381210, + "ts": 1696942508212.581, "dur": 3.872, + "args": { + "External id": 4554854,"Record function id": 0, "Ev Idx": 3173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942508213.809, "dur": 2.201, + "args": { + "External id": 4554855,"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": 1336753, "tid": 1381210, + "ts": 1696942508214.398, "dur": 1.190, + "args": { + "External id": 4554856,"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": 1336753, "tid": 1381210, + "ts": 1696942508214.844, "dur": 0.617, + "args": { + "External id": 4554857,"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": 1336753, "tid": 1381210, + "ts": 1696942508222.885, "dur": 3.850, + "args": { + "External id": 4554858,"Record function id": 0, "Ev Idx": 3177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942508224.004, "dur": 2.306, + "args": { + "External id": 4554859,"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": 1336753, "tid": 1381210, + "ts": 1696942508224.458, "dur": 1.434, + "args": { + "External id": 4554860,"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": 1336753, "tid": 1381210, + "ts": 1696942508224.931, "dur": 0.880, + "args": { + "External id": 4554861,"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": 1336753, "tid": 1381210, + "ts": 1696942508229.990, "dur": 5.056, + "args": { + "External id": 4554862,"Record function id": 0, "Ev Idx": 3181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942508231.292, "dur": 3.325, + "args": { + "External id": 4554863,"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": 1336753, "tid": 1381210, + "ts": 1696942508232.313, "dur": 1.676, + "args": { + "External id": 4554864,"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": 1336753, "tid": 1381210, + "ts": 1696942508233.043, "dur": 0.880, + "args": { + "External id": 4554865,"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": 1336753, "tid": 1381210, + "ts": 1696942508238.283, "dur": 3.871, + "args": { + "External id": 4554866,"Record function id": 0, "Ev Idx": 3185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942508239.335, "dur": 2.391, + "args": { + "External id": 4554867,"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": 1336753, "tid": 1381210, + "ts": 1696942508239.805, "dur": 1.534, + "args": { + "External id": 4554868,"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": 1336753, "tid": 1381210, + "ts": 1696942508240.640, "dur": 0.609, + "args": { + "External id": 4554869,"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": 1336753, "tid": 1381210, + "ts": 1696942508246.738, "dur": 36147.423, + "args": { + "External id": 4554870,"Record function id": 0, "Sequence number": 45295619, "Fwd thread id": 1, "Ev Idx": 3189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942508248.302, "dur": 36137.075, + "args": { + "External id": 4554871,"Sequence number": 45295619, "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": 1336753, "tid": 1381210, "ts": 1696942508248.302, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1696942508278.117, "dur": 37.069, + "args": { + "External id": 4554872,"Record function id": 0, "Ev Idx": 3191 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1696942508323.146, "dur": 66.733, + "args": { + "External id": 4554873,"Record function id": 0, "Ev Idx": 3192 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1696942508395.367, "dur": 35982.642, + "args": { + "External id": 4554874,"Record function id": 0, "Ev Idx": 3193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942508481.828, "dur": 6.434, + "args": { + "External id": 4554875,"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": 1336753, "tid": 1381210, + "ts": 1696942508497.919, "dur": 4.735, + "args": { + "External id": 4554876,"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": 1336753, "tid": 1381210, + "ts": 1696942508517.042, "dur": 35049.764, + "args": { + "External id": 4554877,"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": 1336753, "tid": 1381210, + "ts": 1696942508551.818, "dur": 35006.590, + "args": { + "External id": 4554878,"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": 1336753, "tid": 1381210, + "ts": 1696942508601.691, "dur": 16.368, + "args": { + "External id": 4554879,"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": 1336753, "tid": 1381210, + "ts": 1696942508625.037, "dur": 34881.214, + "args": { + "External id": 4554880,"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": 1336753, "tid": 1381210, + "ts": 1696942508627.781, "dur": 34877.841, + "args": { + "External id": 4554881,"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": 1336753, "tid": 1381210, + "ts": 1696942508631.892, "dur": 6.056, + "args": { + "External id": 4554882,"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": 1336753, "tid": 1381210, + "ts": 1696942508639.936, "dur": 34862.050, + "args": { + "External id": 4554883,"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": 1336753, "tid": 1381210, + "ts": 1696942543654.500, "dur": 9.157, + "args": { + "External id": 4554884,"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": 1336753, "tid": 1381210, + "ts": 1696942543657.873, "dur": 5.438, + "args": { + "External id": 4554885,"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": 1336753, "tid": 1381210, + "ts": 1696942543693.285, "dur": 382.046, + "args": { + "External id": 4554886,"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": 1336753, "tid": 1381210, + "ts": 1696942543719.443, "dur": 350.192, + "args": { + "External id": 4554887,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942543729.803, "dur": 333.965, + "args": { + "External id": 4554888,"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": 1336753, "tid": 1381210, + "ts": 1696942544096.200, "dur": 2.497, + "args": { + "External id": 4554889,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942544158.221, "dur": 6.806, + "args": { + "External id": 4554890,"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": 1336753, "tid": 1381210, + "ts": 1696942544211.373, "dur": 1.169, + "args": { + "External id": 4554891,"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": 1336753, "tid": 1381210, + "ts": 1696942544231.036, "dur": 0.846, + "args": { + "External id": 4554892,"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": 1336753, "tid": 1381210, + "ts": 1696942544247.795, "dur": 0.867, + "args": { + "External id": 4554893,"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": 1336753, "tid": 1381210, + "ts": 1696942544261.080, "dur": 0.903, + "args": { + "External id": 4554894,"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": 1336753, "tid": 1381210, + "ts": 1696942544273.969, "dur": 0.992, + "args": { + "External id": 4554895,"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": 1336753, "tid": 1381210, + "ts": 1696942544287.702, "dur": 1.018, + "args": { + "External id": 4554896,"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": 1336753, "tid": 1381210, + "ts": 1696942544302.739, "dur": 1.826, + "args": { + "External id": 4554897,"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": 1336753, "tid": 1381210, + "ts": 1696942544316.188, "dur": 0.883, + "args": { + "External id": 4554898,"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": 1336753, "tid": 1381210, + "ts": 1696942544409.796, "dur": 2810.191, + "args": { + "External id": 4554899,"Record function id": 0, "Ev Idx": 3218 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1696942544428.635, "dur": 1064.976, + "args": { + "External id": 4554900,"Record function id": 0, "Ev Idx": 3219 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1696942544443.423, "dur": 348.844, + "args": { + "External id": 4554901,"Record function id": 0, "Ev Idx": 3220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942544525.555, "dur": 20.540, + "args": { + "External id": 4554902,"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": 1336753, "tid": 1381210, + "ts": 1696942544551.568, "dur": 1.215, + "args": { + "External id": 4554903,"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": 1336753, "tid": 1381210, + "ts": 1696942544554.605, "dur": 1.161, + "args": { + "External id": 4554904,"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": 1336753, "tid": 1381210, + "ts": 1696942544557.389, "dur": 2.750, + "args": { + "External id": 4554905,"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": 1336753, "tid": 1381210, + "ts": 1696942544561.699, "dur": 1.052, + "args": { + "External id": 4554906,"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": 1336753, "tid": 1381210, + "ts": 1696942544564.652, "dur": 0.859, + "args": { + "External id": 4554907,"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": 1336753, "tid": 1381210, + "ts": 1696942544567.424, "dur": 2.057, + "args": { + "External id": 4554908,"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": 1336753, "tid": 1381210, + "ts": 1696942544570.825, "dur": 1.415, + "args": { + "External id": 4554909,"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": 1336753, "tid": 1381210, + "ts": 1696942544573.753, "dur": 0.759, + "args": { + "External id": 4554910,"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": 1336753, "tid": 1381210, + "ts": 1696942544575.835, "dur": 1.219, + "args": { + "External id": 4554911,"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": 1336753, "tid": 1381210, + "ts": 1696942544596.333, "dur": 163.670, + "args": { + "External id": 4554912,"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": 1336753, "tid": 1381210, + "ts": 1696942544613.431, "dur": 141.959, + "args": { + "External id": 4554913,"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": 1336753, "tid": 1381210, + "ts": 1696942544640.131, "dur": 12.770, + "args": { + "External id": 4554914,"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": 1336753, "tid": 1381210, + "ts": 1696942544655.991, "dur": 71.834, + "args": { + "External id": 4554915,"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": 1336753, "tid": 1381210, + "ts": 1696942544658.742, "dur": 68.751, + "args": { + "External id": 4554916,"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": 1336753, "tid": 1381210, + "ts": 1696942544662.983, "dur": 7.224, + "args": { + "External id": 4554917,"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": 1336753, "tid": 1381210, + "ts": 1696942544672.101, "dur": 54.452, + "args": { + "External id": 4554918,"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": 1336753, "tid": 1381210, + "ts": 1696942544890.708, "dur": 593.760, + "args": { + "External id": 4554919,"Record function id": 0, "Ev Idx": 3238 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1696942544907.495, "dur": 563.964, + "args": { + "External id": 4554920,"Record function id": 0, "Ev Idx": 3239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942544970.888, "dur": 5.278, + "args": { + "External id": 4554921,"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": 1336753, "tid": 1381210, + "ts": 1696942545044.308, "dur": 32.158, + "args": { + "External id": 4554922,"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": 1336753, "tid": 1381210, + "ts": 1696942545049.707, "dur": 1.884, + "args": { + "External id": 4554923,"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": 1336753, "tid": 1381210, + "ts": 1696942545054.235, "dur": 0.618, + "args": { + "External id": 4554924,"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": 1336753, "tid": 1381210, + "ts": 1696942545056.456, "dur": 0.733, + "args": { + "External id": 4554925,"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": 1336753, "tid": 1381210, + "ts": 1696942545059.084, "dur": 0.586, + "args": { + "External id": 4554926,"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": 1336753, "tid": 1381210, + "ts": 1696942545061.810, "dur": 0.421, + "args": { + "External id": 4554927,"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": 1336753, "tid": 1381210, + "ts": 1696942545064.013, "dur": 0.554, + "args": { + "External id": 4554928,"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": 1336753, "tid": 1381210, + "ts": 1696942545066.207, "dur": 1.881, + "args": { + "External id": 4554929,"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": 1336753, "tid": 1381210, + "ts": 1696942545069.844, "dur": 0.442, + "args": { + "External id": 4554930,"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": 1336753, "tid": 1381210, + "ts": 1696942545071.938, "dur": 0.329, + "args": { + "External id": 4554931,"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": 1336753, "tid": 1381210, + "ts": 1696942545086.804, "dur": 33.769, + "args": { + "External id": 4554932,"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": 1336753, "tid": 1381210, + "ts": 1696942545153.823, "dur": 101.327, + "args": { + "External id": 4554933,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942545164.729, "dur": 4.460, + "args": { + "External id": 4554934,"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": 1336753, "tid": 1381210, + "ts": 1696942545174.601, "dur": 10.643, + "args": { + "External id": 4554935,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942545179.083, "dur": 5.784, + "args": { + "External id": 4554936,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942545183.003, "dur": 0.479, + "args": { + "External id": 4554937,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942545192.125, "dur": 25.199, + "args": { + "External id": 4554938,"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": 1336753, "tid": 1381210, + "ts": 1696942545194.478, "dur": 0.445, + "args": { + "External id": 4554939,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942545196.695, "dur": 0.321, + "args": { + "External id": 4554940,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942545198.644, "dur": 0.575, + "args": { + "External id": 4554941,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942545200.755, "dur": 2.181, + "args": { + "External id": 4554942,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942545204.642, "dur": 0.415, + "args": { + "External id": 4554943,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942545206.741, "dur": 0.332, + "args": { + "External id": 4554944,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942545209.013, "dur": 0.370, + "args": { + "External id": 4554945,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942545211.002, "dur": 0.358, + "args": { + "External id": 4554946,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942545212.871, "dur": 0.302, + "args": { + "External id": 4554947,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942545228.763, "dur": 19.014, + "args": { + "External id": 4554948,"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": 1336753, "tid": 1381210, + "ts": 1696942545300.836, "dur": 110.054, + "args": { + "External id": 4554949,"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": 1336753, "tid": 1381210, + "ts": 1696942545322.994, "dur": 84.509, + "args": { + "External id": 4554950,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942545332.939, "dur": 69.482, + "args": { + "External id": 4554951,"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": 1336753, "tid": 1381210, + "ts": 1696942545424.378, "dur": 1.754, + "args": { + "External id": 4554952,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942545502.061, "dur": 1695.605, + "args": { + "External id": 4554953,"Sequence number": 45295618, "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": 1336753, "tid": 1381210, "ts": 1696942545502.061, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942545634.792, "dur": 103.516, + "args": { + "External id": 4554954,"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": 1336753, "tid": 1381210, + "ts": 1696942545778.568, "dur": 43.527, + "args": { + "External id": 4554955,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942545841.238, "dur": 51.759, + "args": { + "External id": 4554956,"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": 1336753, "tid": 1381210, + "ts": 1696942545902.675, "dur": 32.662, + "args": { + "External id": 4554957,"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": 1336753, "tid": 1381210, + "ts": 1696942545943.933, "dur": 84.705, + "args": { + "External id": 4554958,"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": 1336753, "tid": 1381210, + "ts": 1696942546056.981, "dur": 33.556, + "args": { + "External id": 4554959,"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": 1336753, "tid": 1381210, + "ts": 1696942546099.843, "dur": 42.648, + "args": { + "External id": 4554960,"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": 1336753, "tid": 1381210, + "ts": 1696942546169.049, "dur": 24.532, + "args": { + "External id": 4554961,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942546213.553, "dur": 29.429, + "args": { + "External id": 4554962,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942546264.044, "dur": 18.102, + "args": { + "External id": 4554963,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942546296.794, "dur": 14.998, + "args": { + "External id": 4554964,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942546322.058, "dur": 31.795, + "args": { + "External id": 4554965,"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": 1336753, "tid": 1381210, + "ts": 1696942546357.292, "dur": 33.283, + "args": { + "External id": 4554966,"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": 1336753, "tid": 1381210, + "ts": 1696942546421.514, "dur": 193.460, + "args": { + "External id": 4554967,"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": 1336753, "tid": 1381210, + "ts": 1696942546498.016, "dur": 5.579, + "args": { + "External id": 4554968,"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": 1336753, "tid": 1381210, + "ts": 1696942546505.493, "dur": 2.826, + "args": { + "External id": 4554969,"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": 1336753, "tid": 1381210, + "ts": 1696942546651.741, "dur": 22.921, + "args": { + "External id": 4554970,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942546686.442, "dur": 14.917, + "args": { + "External id": 4554971,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942546711.241, "dur": 38.109, + "args": { + "External id": 4554972,"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": 1336753, "tid": 1381210, + "ts": 1696942546756.466, "dur": 33.717, + "args": { + "External id": 4554973,"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": 1336753, "tid": 1381210, + "ts": 1696942546799.107, "dur": 21.181, + "args": { + "External id": 4554974,"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": 1336753, "tid": 1381210, + "ts": 1696942546825.908, "dur": 45.005, + "args": { + "External id": 4554975,"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": 1336753, "tid": 1381210, + "ts": 1696942546883.412, "dur": 24.604, + "args": { + "External id": 4554976,"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": 1336753, "tid": 1381210, + "ts": 1696942546916.397, "dur": 31.525, + "args": { + "External id": 4554977,"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": 1336753, "tid": 1381210, + "ts": 1696942546968.474, "dur": 57.037, + "args": { + "External id": 4554978,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942547045.770, "dur": 25.935, + "args": { + "External id": 4554979,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942547087.233, "dur": 16.600, + "args": { + "External id": 4554980,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942547121.807, "dur": 14.539, + "args": { + "External id": 4554981,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942547149.418, "dur": 16.668, + "args": { + "External id": 4554982,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942547246.070, "dur": 16.251, + "args": { + "External id": 4554983,"Record function id": 0, "Ev Idx": 3302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942547249.691, "dur": 11.491, + "args": { + "External id": 4554984,"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": 1336753, "tid": 1381210, + "ts": 1696942547253.986, "dur": 6.273, + "args": { + "External id": 4554985,"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": 1336753, "tid": 1381210, + "ts": 1696942547256.058, "dur": 4.030, + "args": { + "External id": 4554986,"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": 1336753, "tid": 1381210, + "ts": 1696942547266.355, "dur": 6.343, + "args": { + "External id": 4554987,"Record function id": 0, "Ev Idx": 3306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942547268.152, "dur": 4.099, + "args": { + "External id": 4554988,"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": 1336753, "tid": 1381210, + "ts": 1696942547269.461, "dur": 2.333, + "args": { + "External id": 4554989,"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": 1336753, "tid": 1381210, + "ts": 1696942547270.655, "dur": 1.028, + "args": { + "External id": 4554990,"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": 1336753, "tid": 1381210, + "ts": 1696942547276.119, "dur": 6.826, + "args": { + "External id": 4554991,"Record function id": 0, "Ev Idx": 3310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942547277.647, "dur": 4.870, + "args": { + "External id": 4554992,"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": 1336753, "tid": 1381210, + "ts": 1696942547278.624, "dur": 3.469, + "args": { + "External id": 4554993,"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": 1336753, "tid": 1381210, + "ts": 1696942547279.099, "dur": 2.906, + "args": { + "External id": 4554994,"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": 1336753, "tid": 1381210, + "ts": 1696942547286.432, "dur": 4.499, + "args": { + "External id": 4554995,"Record function id": 0, "Ev Idx": 3314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942547287.912, "dur": 2.621, + "args": { + "External id": 4554996,"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": 1336753, "tid": 1381210, + "ts": 1696942547288.792, "dur": 1.343, + "args": { + "External id": 4554997,"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": 1336753, "tid": 1381210, + "ts": 1696942547289.227, "dur": 0.835, + "args": { + "External id": 4554998,"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": 1336753, "tid": 1381210, + "ts": 1696942547294.379, "dur": 6.484, + "args": { + "External id": 4554999,"Record function id": 0, "Ev Idx": 3318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942547295.599, "dur": 4.842, + "args": { + "External id": 4555000,"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": 1336753, "tid": 1381210, + "ts": 1696942547296.215, "dur": 3.803, + "args": { + "External id": 4555001,"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": 1336753, "tid": 1381210, + "ts": 1696942547296.476, "dur": 3.474, + "args": { + "External id": 4555002,"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": 1336753, "tid": 1381210, + "ts": 1696942547304.193, "dur": 4.802, + "args": { + "External id": 4555003,"Record function id": 0, "Ev Idx": 3322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942547305.461, "dur": 3.116, + "args": { + "External id": 4555004,"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": 1336753, "tid": 1381210, + "ts": 1696942547306.426, "dur": 1.595, + "args": { + "External id": 4555005,"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": 1336753, "tid": 1381210, + "ts": 1696942547307.216, "dur": 0.694, + "args": { + "External id": 4555006,"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": 1336753, "tid": 1381210, + "ts": 1696942547312.274, "dur": 4.343, + "args": { + "External id": 4555007,"Record function id": 0, "Ev Idx": 3326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942547313.595, "dur": 2.617, + "args": { + "External id": 4555008,"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": 1336753, "tid": 1381210, + "ts": 1696942547314.361, "dur": 1.455, + "args": { + "External id": 4555009,"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": 1336753, "tid": 1381210, + "ts": 1696942547314.968, "dur": 0.767, + "args": { + "External id": 4555010,"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": 1336753, "tid": 1381210, + "ts": 1696942547319.945, "dur": 7.039, + "args": { + "External id": 4555011,"Record function id": 0, "Ev Idx": 3330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942547321.169, "dur": 2.340, + "args": { + "External id": 4555012,"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": 1336753, "tid": 1381210, + "ts": 1696942547321.986, "dur": 1.120, + "args": { + "External id": 4555013,"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": 1336753, "tid": 1381210, + "ts": 1696942547322.469, "dur": 0.566, + "args": { + "External id": 4555014,"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": 1336753, "tid": 1381210, + "ts": 1696942547330.180, "dur": 3.609, + "args": { + "External id": 4555015,"Record function id": 0, "Ev Idx": 3334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942547331.175, "dur": 2.193, + "args": { + "External id": 4555016,"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": 1336753, "tid": 1381210, + "ts": 1696942547331.714, "dur": 1.092, + "args": { + "External id": 4555017,"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": 1336753, "tid": 1381210, + "ts": 1696942547332.145, "dur": 0.575, + "args": { + "External id": 4555018,"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": 1336753, "tid": 1381210, + "ts": 1696942547337.849, "dur": 37148.387, + "args": { + "External id": 4555019,"Record function id": 0, "Sequence number": 45295617, "Fwd thread id": 1, "Ev Idx": 3338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942547339.229, "dur": 37138.618, + "args": { + "External id": 4555020,"Sequence number": 45295617, "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": 1336753, "tid": 1381210, "ts": 1696942547339.229, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1696942547367.162, "dur": 40.816, + "args": { + "External id": 4555021,"Record function id": 0, "Ev Idx": 3340 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1696942547415.657, "dur": 65.423, + "args": { + "External id": 4555022,"Record function id": 0, "Ev Idx": 3341 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1696942547486.849, "dur": 36983.413, + "args": { + "External id": 4555023,"Record function id": 0, "Ev Idx": 3342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942547601.847, "dur": 7.254, + "args": { + "External id": 4555024,"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": 1336753, "tid": 1381210, + "ts": 1696942547623.026, "dur": 7.213, + "args": { + "External id": 4555025,"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": 1336753, "tid": 1381210, + "ts": 1696942547646.410, "dur": 35977.563, + "args": { + "External id": 4555026,"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": 1336753, "tid": 1381210, + "ts": 1696942547659.804, "dur": 35955.194, + "args": { + "External id": 4555027,"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": 1336753, "tid": 1381210, + "ts": 1696942547715.387, "dur": 14.149, + "args": { + "External id": 4555028,"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": 1336753, "tid": 1381210, + "ts": 1696942547736.049, "dur": 35840.787, + "args": { + "External id": 4555029,"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": 1336753, "tid": 1381210, + "ts": 1696942547738.968, "dur": 35837.022, + "args": { + "External id": 4555030,"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": 1336753, "tid": 1381210, + "ts": 1696942547743.100, "dur": 5.579, + "args": { + "External id": 4555031,"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": 1336753, "tid": 1381210, + "ts": 1696942547750.498, "dur": 35821.517, + "args": { + "External id": 4555032,"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": 1336753, "tid": 1381210, + "ts": 1696942583715.801, "dur": 9.057, + "args": { + "External id": 4555033,"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": 1336753, "tid": 1381210, + "ts": 1696942583719.146, "dur": 5.415, + "args": { + "External id": 4555034,"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": 1336753, "tid": 1381210, + "ts": 1696942583755.462, "dur": 396.424, + "args": { + "External id": 4555035,"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": 1336753, "tid": 1381210, + "ts": 1696942583781.649, "dur": 364.728, + "args": { + "External id": 4555036,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942583792.349, "dur": 348.133, + "args": { + "External id": 4555037,"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": 1336753, "tid": 1381210, + "ts": 1696942584184.695, "dur": 3.394, + "args": { + "External id": 4555038,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942584255.537, "dur": 6.977, + "args": { + "External id": 4555039,"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": 1336753, "tid": 1381210, + "ts": 1696942584308.810, "dur": 1.531, + "args": { + "External id": 4555040,"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": 1336753, "tid": 1381210, + "ts": 1696942584327.522, "dur": 2.641, + "args": { + "External id": 4555041,"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": 1336753, "tid": 1381210, + "ts": 1696942584342.349, "dur": 0.789, + "args": { + "External id": 4555042,"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": 1336753, "tid": 1381210, + "ts": 1696942584353.786, "dur": 0.988, + "args": { + "External id": 4555043,"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": 1336753, "tid": 1381210, + "ts": 1696942584365.626, "dur": 1.324, + "args": { + "External id": 4555044,"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": 1336753, "tid": 1381210, + "ts": 1696942584378.718, "dur": 2.581, + "args": { + "External id": 4555045,"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": 1336753, "tid": 1381210, + "ts": 1696942584393.887, "dur": 1.728, + "args": { + "External id": 4555046,"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": 1336753, "tid": 1381210, + "ts": 1696942584406.578, "dur": 0.814, + "args": { + "External id": 4555047,"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": 1336753, "tid": 1381210, + "ts": 1696942584502.740, "dur": 2821.055, + "args": { + "External id": 4555048,"Record function id": 0, "Ev Idx": 3367 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1696942584523.052, "dur": 1077.480, + "args": { + "External id": 4555049,"Record function id": 0, "Ev Idx": 3368 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1696942584558.835, "dur": 324.789, + "args": { + "External id": 4555050,"Record function id": 0, "Ev Idx": 3369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942584644.138, "dur": 4.572, + "args": { + "External id": 4555051,"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": 1336753, "tid": 1381210, + "ts": 1696942584651.854, "dur": 1.069, + "args": { + "External id": 4555052,"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": 1336753, "tid": 1381210, + "ts": 1696942584655.027, "dur": 2.717, + "args": { + "External id": 4555053,"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": 1336753, "tid": 1381210, + "ts": 1696942584659.411, "dur": 0.970, + "args": { + "External id": 4555054,"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": 1336753, "tid": 1381210, + "ts": 1696942584661.734, "dur": 1.102, + "args": { + "External id": 4555055,"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": 1336753, "tid": 1381210, + "ts": 1696942584664.350, "dur": 1.101, + "args": { + "External id": 4555056,"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": 1336753, "tid": 1381210, + "ts": 1696942584666.979, "dur": 1.870, + "args": { + "External id": 4555057,"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": 1336753, "tid": 1381210, + "ts": 1696942584670.176, "dur": 1.146, + "args": { + "External id": 4555058,"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": 1336753, "tid": 1381210, + "ts": 1696942584672.796, "dur": 0.732, + "args": { + "External id": 4555059,"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": 1336753, "tid": 1381210, + "ts": 1696942584674.783, "dur": 1.061, + "args": { + "External id": 4555060,"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": 1336753, "tid": 1381210, + "ts": 1696942584693.446, "dur": 156.930, + "args": { + "External id": 4555061,"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": 1336753, "tid": 1381210, + "ts": 1696942584709.383, "dur": 136.846, + "args": { + "External id": 4555062,"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": 1336753, "tid": 1381210, + "ts": 1696942584732.585, "dur": 14.024, + "args": { + "External id": 4555063,"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": 1336753, "tid": 1381210, + "ts": 1696942584749.635, "dur": 67.945, + "args": { + "External id": 4555064,"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": 1336753, "tid": 1381210, + "ts": 1696942584752.659, "dur": 64.545, + "args": { + "External id": 4555065,"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": 1336753, "tid": 1381210, + "ts": 1696942584757.014, "dur": 5.126, + "args": { + "External id": 4555066,"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": 1336753, "tid": 1381210, + "ts": 1696942584764.164, "dur": 52.433, + "args": { + "External id": 4555067,"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": 1336753, "tid": 1381210, + "ts": 1696942584975.962, "dur": 615.776, + "args": { + "External id": 4555068,"Record function id": 0, "Ev Idx": 3387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1696942585033.553, "dur": 543.682, + "args": { + "External id": 4555069,"Record function id": 0, "Ev Idx": 3388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942585101.200, "dur": 6.580, + "args": { + "External id": 4555070,"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": 1336753, "tid": 1381210, + "ts": 1696942585124.382, "dur": 31.577, + "args": { + "External id": 4555071,"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": 1336753, "tid": 1381210, + "ts": 1696942585129.447, "dur": 1.782, + "args": { + "External id": 4555072,"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": 1336753, "tid": 1381210, + "ts": 1696942585133.460, "dur": 0.450, + "args": { + "External id": 4555073,"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": 1336753, "tid": 1381210, + "ts": 1696942585135.404, "dur": 0.444, + "args": { + "External id": 4555074,"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": 1336753, "tid": 1381210, + "ts": 1696942585137.783, "dur": 0.439, + "args": { + "External id": 4555075,"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": 1336753, "tid": 1381210, + "ts": 1696942585140.027, "dur": 0.427, + "args": { + "External id": 4555076,"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": 1336753, "tid": 1381210, + "ts": 1696942585142.051, "dur": 2.296, + "args": { + "External id": 4555077,"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": 1336753, "tid": 1381210, + "ts": 1696942585145.820, "dur": 0.382, + "args": { + "External id": 4555078,"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": 1336753, "tid": 1381210, + "ts": 1696942585147.940, "dur": 0.604, + "args": { + "External id": 4555079,"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": 1336753, "tid": 1381210, + "ts": 1696942585150.506, "dur": 0.414, + "args": { + "External id": 4555080,"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": 1336753, "tid": 1381210, + "ts": 1696942585165.202, "dur": 34.110, + "args": { + "External id": 4555081,"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": 1336753, "tid": 1381210, + "ts": 1696942585231.260, "dur": 103.301, + "args": { + "External id": 4555082,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942585241.765, "dur": 3.273, + "args": { + "External id": 4555083,"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": 1336753, "tid": 1381210, + "ts": 1696942585250.356, "dur": 11.057, + "args": { + "External id": 4555084,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942585255.174, "dur": 5.805, + "args": { + "External id": 4555085,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942585259.116, "dur": 0.813, + "args": { + "External id": 4555086,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942585267.872, "dur": 29.822, + "args": { + "External id": 4555087,"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": 1336753, "tid": 1381210, + "ts": 1696942585269.878, "dur": 0.390, + "args": { + "External id": 4555088,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942585272.157, "dur": 0.346, + "args": { + "External id": 4555089,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942585274.334, "dur": 2.402, + "args": { + "External id": 4555090,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942585278.454, "dur": 3.788, + "args": { + "External id": 4555091,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942585283.954, "dur": 0.432, + "args": { + "External id": 4555092,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942585286.160, "dur": 0.346, + "args": { + "External id": 4555093,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942585288.092, "dur": 0.530, + "args": { + "External id": 4555094,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942585290.871, "dur": 0.321, + "args": { + "External id": 4555095,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942585292.899, "dur": 0.393, + "args": { + "External id": 4555096,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942585308.321, "dur": 18.918, + "args": { + "External id": 4555097,"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": 1336753, "tid": 1381210, + "ts": 1696942585383.685, "dur": 112.315, + "args": { + "External id": 4555098,"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": 1336753, "tid": 1381210, + "ts": 1696942585405.096, "dur": 87.212, + "args": { + "External id": 4555099,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942585414.209, "dur": 70.681, + "args": { + "External id": 4555100,"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": 1336753, "tid": 1381210, + "ts": 1696942585508.330, "dur": 1.984, + "args": { + "External id": 4555101,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942585608.269, "dur": 1690.736, + "args": { + "External id": 4555102,"Sequence number": 45295616, "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": 1336753, "tid": 1381210, "ts": 1696942585608.269, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942585720.569, "dur": 101.622, + "args": { + "External id": 4555103,"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": 1336753, "tid": 1381210, + "ts": 1696942585858.762, "dur": 39.595, + "args": { + "External id": 4555104,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942585918.933, "dur": 47.097, + "args": { + "External id": 4555105,"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": 1336753, "tid": 1381210, + "ts": 1696942585977.850, "dur": 76.855, + "args": { + "External id": 4555106,"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": 1336753, "tid": 1381210, + "ts": 1696942586065.879, "dur": 51.441, + "args": { + "External id": 4555107,"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": 1336753, "tid": 1381210, + "ts": 1696942586125.662, "dur": 30.998, + "args": { + "External id": 4555108,"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": 1336753, "tid": 1381210, + "ts": 1696942586164.903, "dur": 44.814, + "args": { + "External id": 4555109,"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": 1336753, "tid": 1381210, + "ts": 1696942586234.712, "dur": 24.574, + "args": { + "External id": 4555110,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942586277.421, "dur": 29.379, + "args": { + "External id": 4555111,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942586327.238, "dur": 18.400, + "args": { + "External id": 4555112,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942586358.264, "dur": 14.946, + "args": { + "External id": 4555113,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942586383.578, "dur": 27.031, + "args": { + "External id": 4555114,"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": 1336753, "tid": 1381210, + "ts": 1696942586414.294, "dur": 32.907, + "args": { + "External id": 4555115,"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": 1336753, "tid": 1381210, + "ts": 1696942586492.435, "dur": 190.765, + "args": { + "External id": 4555116,"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": 1336753, "tid": 1381210, + "ts": 1696942586587.497, "dur": 6.430, + "args": { + "External id": 4555117,"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": 1336753, "tid": 1381210, + "ts": 1696942586596.330, "dur": 2.802, + "args": { + "External id": 4555118,"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": 1336753, "tid": 1381210, + "ts": 1696942586720.969, "dur": 25.707, + "args": { + "External id": 4555119,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942586758.855, "dur": 15.297, + "args": { + "External id": 4555120,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942586783.261, "dur": 41.887, + "args": { + "External id": 4555121,"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": 1336753, "tid": 1381210, + "ts": 1696942586832.575, "dur": 38.736, + "args": { + "External id": 4555122,"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": 1336753, "tid": 1381210, + "ts": 1696942586880.519, "dur": 20.591, + "args": { + "External id": 4555123,"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": 1336753, "tid": 1381210, + "ts": 1696942586910.142, "dur": 46.397, + "args": { + "External id": 4555124,"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": 1336753, "tid": 1381210, + "ts": 1696942586972.074, "dur": 61.778, + "args": { + "External id": 4555125,"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": 1336753, "tid": 1381210, + "ts": 1696942587045.235, "dur": 37.745, + "args": { + "External id": 4555126,"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": 1336753, "tid": 1381210, + "ts": 1696942587105.827, "dur": 23.783, + "args": { + "External id": 4555127,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942587151.359, "dur": 24.103, + "args": { + "External id": 4555128,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942587190.933, "dur": 19.868, + "args": { + "External id": 4555129,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942587225.438, "dur": 14.812, + "args": { + "External id": 4555130,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942587252.254, "dur": 18.866, + "args": { + "External id": 4555131,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942587347.451, "dur": 15.207, + "args": { + "External id": 4555132,"Record function id": 0, "Ev Idx": 3451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942587350.638, "dur": 11.057, + "args": { + "External id": 4555133,"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": 1336753, "tid": 1381210, + "ts": 1696942587354.893, "dur": 5.836, + "args": { + "External id": 4555134,"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": 1336753, "tid": 1381210, + "ts": 1696942587356.712, "dur": 3.901, + "args": { + "External id": 4555135,"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": 1336753, "tid": 1381210, + "ts": 1696942587366.769, "dur": 10.227, + "args": { + "External id": 4555136,"Record function id": 0, "Ev Idx": 3455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942587368.310, "dur": 8.291, + "args": { + "External id": 4555137,"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": 1336753, "tid": 1381210, + "ts": 1696942587369.151, "dur": 6.891, + "args": { + "External id": 4555138,"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": 1336753, "tid": 1381210, + "ts": 1696942587369.931, "dur": 5.998, + "args": { + "External id": 4555139,"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": 1336753, "tid": 1381210, + "ts": 1696942587380.500, "dur": 4.934, + "args": { + "External id": 4555140,"Record function id": 0, "Ev Idx": 3459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942587381.936, "dur": 3.103, + "args": { + "External id": 4555141,"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": 1336753, "tid": 1381210, + "ts": 1696942587382.708, "dur": 1.876, + "args": { + "External id": 4555142,"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": 1336753, "tid": 1381210, + "ts": 1696942587383.285, "dur": 1.224, + "args": { + "External id": 4555143,"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": 1336753, "tid": 1381210, + "ts": 1696942587388.757, "dur": 4.548, + "args": { + "External id": 4555144,"Record function id": 0, "Ev Idx": 3463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942587390.415, "dur": 2.481, + "args": { + "External id": 4555145,"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": 1336753, "tid": 1381210, + "ts": 1696942587391.367, "dur": 1.098, + "args": { + "External id": 4555146,"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": 1336753, "tid": 1381210, + "ts": 1696942587391.814, "dur": 0.585, + "args": { + "External id": 4555147,"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": 1336753, "tid": 1381210, + "ts": 1696942587396.509, "dur": 4.067, + "args": { + "External id": 4555148,"Record function id": 0, "Ev Idx": 3467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942587398.039, "dur": 2.153, + "args": { + "External id": 4555149,"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": 1336753, "tid": 1381210, + "ts": 1696942587398.475, "dur": 1.208, + "args": { + "External id": 4555150,"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": 1336753, "tid": 1381210, + "ts": 1696942587398.786, "dur": 0.830, + "args": { + "External id": 4555151,"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": 1336753, "tid": 1381210, + "ts": 1696942587403.763, "dur": 4.019, + "args": { + "External id": 4555152,"Record function id": 0, "Ev Idx": 3471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942587404.936, "dur": 2.455, + "args": { + "External id": 4555153,"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": 1336753, "tid": 1381210, + "ts": 1696942587405.765, "dur": 1.199, + "args": { + "External id": 4555154,"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": 1336753, "tid": 1381210, + "ts": 1696942587406.212, "dur": 0.656, + "args": { + "External id": 4555155,"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": 1336753, "tid": 1381210, + "ts": 1696942587410.978, "dur": 3.784, + "args": { + "External id": 4555156,"Record function id": 0, "Ev Idx": 3475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942587412.180, "dur": 2.149, + "args": { + "External id": 4555157,"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": 1336753, "tid": 1381210, + "ts": 1696942587412.817, "dur": 1.103, + "args": { + "External id": 4555158,"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": 1336753, "tid": 1381210, + "ts": 1696942587413.280, "dur": 0.542, + "args": { + "External id": 4555159,"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": 1336753, "tid": 1381210, + "ts": 1696942587417.881, "dur": 4.080, + "args": { + "External id": 4555160,"Record function id": 0, "Ev Idx": 3479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942587419.133, "dur": 2.424, + "args": { + "External id": 4555161,"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": 1336753, "tid": 1381210, + "ts": 1696942587419.770, "dur": 1.283, + "args": { + "External id": 4555162,"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": 1336753, "tid": 1381210, + "ts": 1696942587420.343, "dur": 0.618, + "args": { + "External id": 4555163,"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": 1336753, "tid": 1381210, + "ts": 1696942587425.108, "dur": 5.479, + "args": { + "External id": 4555164,"Record function id": 0, "Ev Idx": 3483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942587426.060, "dur": 4.074, + "args": { + "External id": 4555165,"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": 1336753, "tid": 1381210, + "ts": 1696942587426.698, "dur": 3.024, + "args": { + "External id": 4555166,"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": 1336753, "tid": 1381210, + "ts": 1696942587427.185, "dur": 2.452, + "args": { + "External id": 4555167,"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": 1336753, "tid": 1381210, + "ts": 1696942587434.374, "dur": 36203.549, + "args": { + "External id": 4555168,"Record function id": 0, "Sequence number": 45295615, "Fwd thread id": 1, "Ev Idx": 3487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942587435.917, "dur": 36193.537, + "args": { + "External id": 4555169,"Sequence number": 45295615, "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": 1336753, "tid": 1381210, "ts": 1696942587435.917, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1696942587464.036, "dur": 37.060, + "args": { + "External id": 4555170,"Record function id": 0, "Ev Idx": 3489 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1696942587508.977, "dur": 84.497, + "args": { + "External id": 4555171,"Record function id": 0, "Ev Idx": 3490 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1696942587601.439, "dur": 36020.358, + "args": { + "External id": 4555172,"Record function id": 0, "Ev Idx": 3491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942587691.746, "dur": 7.009, + "args": { + "External id": 4555173,"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": 1336753, "tid": 1381210, + "ts": 1696942587709.159, "dur": 5.228, + "args": { + "External id": 4555174,"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": 1336753, "tid": 1381210, + "ts": 1696942587733.116, "dur": 35059.404, + "args": { + "External id": 4555175,"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": 1336753, "tid": 1381210, + "ts": 1696942587747.170, "dur": 35036.152, + "args": { + "External id": 4555176,"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": 1336753, "tid": 1381210, + "ts": 1696942587799.611, "dur": 13.892, + "args": { + "External id": 4555177,"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": 1336753, "tid": 1381210, + "ts": 1696942587819.951, "dur": 34924.319, + "args": { + "External id": 4555178,"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": 1336753, "tid": 1381210, + "ts": 1696942587822.690, "dur": 34920.904, + "args": { + "External id": 4555179,"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": 1336753, "tid": 1381210, + "ts": 1696942587826.564, "dur": 5.210, + "args": { + "External id": 4555180,"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": 1336753, "tid": 1381210, + "ts": 1696942587833.792, "dur": 34906.442, + "args": { + "External id": 4555181,"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": 1336753, "tid": 1381210, + "ts": 1696942622881.213, "dur": 9.223, + "args": { + "External id": 4555182,"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": 1336753, "tid": 1381210, + "ts": 1696942622884.739, "dur": 5.346, + "args": { + "External id": 4555183,"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": 1336753, "tid": 1381210, + "ts": 1696942622920.279, "dur": 381.882, + "args": { + "External id": 4555184,"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": 1336753, "tid": 1381210, + "ts": 1696942622947.226, "dur": 349.588, + "args": { + "External id": 4555185,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942622957.958, "dur": 332.544, + "args": { + "External id": 4555186,"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": 1336753, "tid": 1381210, + "ts": 1696942623323.715, "dur": 2.545, + "args": { + "External id": 4555187,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942623386.476, "dur": 6.780, + "args": { + "External id": 4555188,"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": 1336753, "tid": 1381210, + "ts": 1696942623440.265, "dur": 3.227, + "args": { + "External id": 4555189,"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": 1336753, "tid": 1381210, + "ts": 1696942623460.196, "dur": 1.097, + "args": { + "External id": 4555190,"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": 1336753, "tid": 1381210, + "ts": 1696942623473.559, "dur": 1.066, + "args": { + "External id": 4555191,"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": 1336753, "tid": 1381210, + "ts": 1696942623486.234, "dur": 1.237, + "args": { + "External id": 4555192,"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": 1336753, "tid": 1381210, + "ts": 1696942623498.552, "dur": 2.688, + "args": { + "External id": 4555193,"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": 1336753, "tid": 1381210, + "ts": 1696942623512.768, "dur": 0.932, + "args": { + "External id": 4555194,"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": 1336753, "tid": 1381210, + "ts": 1696942623525.580, "dur": 17.735, + "args": { + "External id": 4555195,"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": 1336753, "tid": 1381210, + "ts": 1696942623558.774, "dur": 1.073, + "args": { + "External id": 4555196,"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": 1336753, "tid": 1381210, + "ts": 1696942623654.778, "dur": 2831.830, + "args": { + "External id": 4555197,"Record function id": 0, "Ev Idx": 3516 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1696942623674.254, "dur": 1066.835, + "args": { + "External id": 4555198,"Record function id": 0, "Ev Idx": 3517 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1696942623689.134, "dur": 365.054, + "args": { + "External id": 4555199,"Record function id": 0, "Ev Idx": 3518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942623770.716, "dur": 5.873, + "args": { + "External id": 4555200,"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": 1336753, "tid": 1381210, + "ts": 1696942623779.882, "dur": 1.276, + "args": { + "External id": 4555201,"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": 1336753, "tid": 1381210, + "ts": 1696942623783.057, "dur": 0.833, + "args": { + "External id": 4555202,"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": 1336753, "tid": 1381210, + "ts": 1696942623785.649, "dur": 0.971, + "args": { + "External id": 4555203,"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": 1336753, "tid": 1381210, + "ts": 1696942623788.133, "dur": 1.073, + "args": { + "External id": 4555204,"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": 1336753, "tid": 1381210, + "ts": 1696942623790.922, "dur": 0.813, + "args": { + "External id": 4555205,"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": 1336753, "tid": 1381210, + "ts": 1696942623793.236, "dur": 1.787, + "args": { + "External id": 4555206,"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": 1336753, "tid": 1381210, + "ts": 1696942623796.376, "dur": 1.141, + "args": { + "External id": 4555207,"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": 1336753, "tid": 1381210, + "ts": 1696942623798.996, "dur": 3.230, + "args": { + "External id": 4555208,"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": 1336753, "tid": 1381210, + "ts": 1696942623803.693, "dur": 1.135, + "args": { + "External id": 4555209,"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": 1336753, "tid": 1381210, + "ts": 1696942623822.110, "dur": 157.295, + "args": { + "External id": 4555210,"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": 1336753, "tid": 1381210, + "ts": 1696942623838.229, "dur": 137.076, + "args": { + "External id": 4555211,"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": 1336753, "tid": 1381210, + "ts": 1696942623864.315, "dur": 12.373, + "args": { + "External id": 4555212,"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": 1336753, "tid": 1381210, + "ts": 1696942623879.849, "dur": 67.515, + "args": { + "External id": 4555213,"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": 1336753, "tid": 1381210, + "ts": 1696942623882.770, "dur": 64.152, + "args": { + "External id": 4555214,"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": 1336753, "tid": 1381210, + "ts": 1696942623887.068, "dur": 4.962, + "args": { + "External id": 4555215,"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": 1336753, "tid": 1381210, + "ts": 1696942623894.214, "dur": 51.767, + "args": { + "External id": 4555216,"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": 1336753, "tid": 1381210, + "ts": 1696942624154.734, "dur": 577.605, + "args": { + "External id": 4555217,"Record function id": 0, "Ev Idx": 3536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1696942624173.332, "dur": 542.990, + "args": { + "External id": 4555218,"Record function id": 0, "Ev Idx": 3537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942624235.890, "dur": 5.420, + "args": { + "External id": 4555219,"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": 1336753, "tid": 1381210, + "ts": 1696942624257.302, "dur": 32.594, + "args": { + "External id": 4555220,"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": 1336753, "tid": 1381210, + "ts": 1696942624262.723, "dur": 1.891, + "args": { + "External id": 4555221,"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": 1336753, "tid": 1381210, + "ts": 1696942624267.034, "dur": 0.656, + "args": { + "External id": 4555222,"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": 1336753, "tid": 1381210, + "ts": 1696942624269.592, "dur": 0.891, + "args": { + "External id": 4555223,"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": 1336753, "tid": 1381210, + "ts": 1696942624272.006, "dur": 2.745, + "args": { + "External id": 4555224,"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": 1336753, "tid": 1381210, + "ts": 1696942624276.875, "dur": 0.566, + "args": { + "External id": 4555225,"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": 1336753, "tid": 1381210, + "ts": 1696942624278.845, "dur": 0.337, + "args": { + "External id": 4555226,"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": 1336753, "tid": 1381210, + "ts": 1696942624280.555, "dur": 0.570, + "args": { + "External id": 4555227,"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": 1336753, "tid": 1381210, + "ts": 1696942624282.639, "dur": 0.382, + "args": { + "External id": 4555228,"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": 1336753, "tid": 1381210, + "ts": 1696942624284.985, "dur": 0.738, + "args": { + "External id": 4555229,"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": 1336753, "tid": 1381210, + "ts": 1696942624299.955, "dur": 33.790, + "args": { + "External id": 4555230,"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": 1336753, "tid": 1381210, + "ts": 1696942624364.990, "dur": 107.921, + "args": { + "External id": 4555231,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942624374.807, "dur": 3.077, + "args": { + "External id": 4555232,"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": 1336753, "tid": 1381210, + "ts": 1696942624388.780, "dur": 10.364, + "args": { + "External id": 4555233,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942624393.204, "dur": 5.529, + "args": { + "External id": 4555234,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942624397.040, "dur": 0.511, + "args": { + "External id": 4555235,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942624409.033, "dur": 26.084, + "args": { + "External id": 4555236,"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": 1336753, "tid": 1381210, + "ts": 1696942624411.090, "dur": 2.040, + "args": { + "External id": 4555237,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942624414.991, "dur": 0.526, + "args": { + "External id": 4555238,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942624417.228, "dur": 0.389, + "args": { + "External id": 4555239,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942624419.094, "dur": 0.376, + "args": { + "External id": 4555240,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942624420.977, "dur": 0.423, + "args": { + "External id": 4555241,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942624422.844, "dur": 0.384, + "args": { + "External id": 4555242,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942624425.051, "dur": 0.401, + "args": { + "External id": 4555243,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942624426.969, "dur": 0.372, + "args": { + "External id": 4555244,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942624429.160, "dur": 2.142, + "args": { + "External id": 4555245,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942624446.796, "dur": 19.071, + "args": { + "External id": 4555246,"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": 1336753, "tid": 1381210, + "ts": 1696942624516.757, "dur": 129.614, + "args": { + "External id": 4555247,"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": 1336753, "tid": 1381210, + "ts": 1696942624558.058, "dur": 84.155, + "args": { + "External id": 4555248,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942624568.224, "dur": 69.820, + "args": { + "External id": 4555249,"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": 1336753, "tid": 1381210, + "ts": 1696942624661.200, "dur": 1.723, + "args": { + "External id": 4555250,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942624748.410, "dur": 1714.298, + "args": { + "External id": 4555251,"Sequence number": 45295614, "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": 1336753, "tid": 1381210, "ts": 1696942624748.410, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942624865.247, "dur": 100.475, + "args": { + "External id": 4555252,"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": 1336753, "tid": 1381210, + "ts": 1696942625045.352, "dur": 45.741, + "args": { + "External id": 4555253,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942625114.124, "dur": 59.724, + "args": { + "External id": 4555254,"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": 1336753, "tid": 1381210, + "ts": 1696942625183.719, "dur": 32.871, + "args": { + "External id": 4555255,"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": 1336753, "tid": 1381210, + "ts": 1696942625224.254, "dur": 46.690, + "args": { + "External id": 4555256,"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": 1336753, "tid": 1381210, + "ts": 1696942625278.951, "dur": 28.172, + "args": { + "External id": 4555257,"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": 1336753, "tid": 1381210, + "ts": 1696942625317.106, "dur": 42.494, + "args": { + "External id": 4555258,"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": 1336753, "tid": 1381210, + "ts": 1696942625381.534, "dur": 22.080, + "args": { + "External id": 4555259,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942625420.631, "dur": 28.135, + "args": { + "External id": 4555260,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942625467.942, "dur": 18.159, + "args": { + "External id": 4555261,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942625498.203, "dur": 14.636, + "args": { + "External id": 4555262,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942625523.838, "dur": 46.071, + "args": { + "External id": 4555263,"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": 1336753, "tid": 1381210, + "ts": 1696942625574.849, "dur": 34.707, + "args": { + "External id": 4555264,"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": 1336753, "tid": 1381210, + "ts": 1696942625666.982, "dur": 171.459, + "args": { + "External id": 4555265,"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": 1336753, "tid": 1381210, + "ts": 1696942625745.975, "dur": 6.063, + "args": { + "External id": 4555266,"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": 1336753, "tid": 1381210, + "ts": 1696942625754.165, "dur": 2.118, + "args": { + "External id": 4555267,"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": 1336753, "tid": 1381210, + "ts": 1696942625873.850, "dur": 24.463, + "args": { + "External id": 4555268,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942625909.639, "dur": 16.405, + "args": { + "External id": 4555269,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942625937.931, "dur": 34.271, + "args": { + "External id": 4555270,"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": 1336753, "tid": 1381210, + "ts": 1696942625979.927, "dur": 77.314, + "args": { + "External id": 4555271,"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": 1336753, "tid": 1381210, + "ts": 1696942626067.926, "dur": 21.627, + "args": { + "External id": 4555272,"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": 1336753, "tid": 1381210, + "ts": 1696942626105.200, "dur": 43.290, + "args": { + "External id": 4555273,"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": 1336753, "tid": 1381210, + "ts": 1696942626157.779, "dur": 20.373, + "args": { + "External id": 4555274,"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": 1336753, "tid": 1381210, + "ts": 1696942626191.890, "dur": 32.564, + "args": { + "External id": 4555275,"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": 1336753, "tid": 1381210, + "ts": 1696942626247.986, "dur": 23.647, + "args": { + "External id": 4555276,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942626297.563, "dur": 28.814, + "args": { + "External id": 4555277,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942626347.522, "dur": 20.565, + "args": { + "External id": 4555278,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942626384.673, "dur": 13.357, + "args": { + "External id": 4555279,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942626412.978, "dur": 20.480, + "args": { + "External id": 4555280,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942626509.599, "dur": 38.628, + "args": { + "External id": 4555281,"Record function id": 0, "Ev Idx": 3600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942626513.179, "dur": 32.880, + "args": { + "External id": 4555282,"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": 1336753, "tid": 1381210, + "ts": 1696942626517.196, "dur": 7.610, + "args": { + "External id": 4555283,"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": 1336753, "tid": 1381210, + "ts": 1696942626518.740, "dur": 5.947, + "args": { + "External id": 4555284,"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": 1336753, "tid": 1381210, + "ts": 1696942626555.192, "dur": 7.299, + "args": { + "External id": 4555285,"Record function id": 0, "Ev Idx": 3604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942626556.945, "dur": 5.030, + "args": { + "External id": 4555286,"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": 1336753, "tid": 1381210, + "ts": 1696942626558.350, "dur": 2.777, + "args": { + "External id": 4555287,"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": 1336753, "tid": 1381210, + "ts": 1696942626559.204, "dur": 1.822, + "args": { + "External id": 4555288,"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": 1336753, "tid": 1381210, + "ts": 1696942626565.968, "dur": 4.477, + "args": { + "External id": 4555289,"Record function id": 0, "Ev Idx": 3608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942626567.334, "dur": 2.677, + "args": { + "External id": 4555290,"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": 1336753, "tid": 1381210, + "ts": 1696942626568.071, "dur": 1.426, + "args": { + "External id": 4555291,"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": 1336753, "tid": 1381210, + "ts": 1696942626568.351, "dur": 1.050, + "args": { + "External id": 4555292,"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": 1336753, "tid": 1381210, + "ts": 1696942626573.688, "dur": 4.041, + "args": { + "External id": 4555293,"Record function id": 0, "Ev Idx": 3612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942626574.785, "dur": 2.526, + "args": { + "External id": 4555294,"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": 1336753, "tid": 1381210, + "ts": 1696942626575.387, "dur": 1.454, + "args": { + "External id": 4555295,"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": 1336753, "tid": 1381210, + "ts": 1696942626575.761, "dur": 1.000, + "args": { + "External id": 4555296,"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": 1336753, "tid": 1381210, + "ts": 1696942626580.861, "dur": 3.607, + "args": { + "External id": 4555297,"Record function id": 0, "Ev Idx": 3616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942626581.978, "dur": 2.067, + "args": { + "External id": 4555298,"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": 1336753, "tid": 1381210, + "ts": 1696942626582.451, "dur": 1.172, + "args": { + "External id": 4555299,"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": 1336753, "tid": 1381210, + "ts": 1696942626582.930, "dur": 0.628, + "args": { + "External id": 4555300,"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": 1336753, "tid": 1381210, + "ts": 1696942626587.741, "dur": 4.384, + "args": { + "External id": 4555301,"Record function id": 0, "Ev Idx": 3620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942626589.018, "dur": 2.663, + "args": { + "External id": 4555302,"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": 1336753, "tid": 1381210, + "ts": 1696942626589.613, "dur": 1.351, + "args": { + "External id": 4555303,"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": 1336753, "tid": 1381210, + "ts": 1696942626590.136, "dur": 0.718, + "args": { + "External id": 4555304,"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": 1336753, "tid": 1381210, + "ts": 1696942626599.120, "dur": 4.279, + "args": { + "External id": 4555305,"Record function id": 0, "Ev Idx": 3624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942626600.227, "dur": 2.702, + "args": { + "External id": 4555306,"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": 1336753, "tid": 1381210, + "ts": 1696942626600.969, "dur": 1.369, + "args": { + "External id": 4555307,"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": 1336753, "tid": 1381210, + "ts": 1696942626601.544, "dur": 0.707, + "args": { + "External id": 4555308,"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": 1336753, "tid": 1381210, + "ts": 1696942626606.587, "dur": 5.934, + "args": { + "External id": 4555309,"Record function id": 0, "Ev Idx": 3628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942626607.808, "dur": 4.290, + "args": { + "External id": 4555310,"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": 1336753, "tid": 1381210, + "ts": 1696942626608.363, "dur": 3.326, + "args": { + "External id": 4555311,"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": 1336753, "tid": 1381210, + "ts": 1696942626608.742, "dur": 2.885, + "args": { + "External id": 4555312,"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": 1336753, "tid": 1381210, + "ts": 1696942626615.887, "dur": 4.462, + "args": { + "External id": 4555313,"Record function id": 0, "Ev Idx": 3632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942626617.339, "dur": 2.588, + "args": { + "External id": 4555314,"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": 1336753, "tid": 1381210, + "ts": 1696942626617.949, "dur": 1.352, + "args": { + "External id": 4555315,"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": 1336753, "tid": 1381210, + "ts": 1696942626618.514, "dur": 0.695, + "args": { + "External id": 4555316,"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": 1336753, "tid": 1381210, + "ts": 1696942626624.342, "dur": 35874.961, + "args": { + "External id": 4555317,"Record function id": 0, "Sequence number": 45295613, "Fwd thread id": 1, "Ev Idx": 3636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942626625.864, "dur": 35864.879, + "args": { + "External id": 4555318,"Sequence number": 45295613, "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": 1336753, "tid": 1381210, "ts": 1696942626625.864, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1696942626660.316, "dur": 38.614, + "args": { + "External id": 4555319,"Record function id": 0, "Ev Idx": 3638 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1696942626707.056, "dur": 71.641, + "args": { + "External id": 4555320,"Record function id": 0, "Ev Idx": 3639 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1696942626784.561, "dur": 35698.016, + "args": { + "External id": 4555321,"Record function id": 0, "Ev Idx": 3640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942626875.032, "dur": 7.300, + "args": { + "External id": 4555322,"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": 1336753, "tid": 1381210, + "ts": 1696942626895.481, "dur": 4.928, + "args": { + "External id": 4555323,"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": 1336753, "tid": 1381210, + "ts": 1696942626915.371, "dur": 34771.605, + "args": { + "External id": 4555324,"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": 1336753, "tid": 1381210, + "ts": 1696942626928.752, "dur": 34749.733, + "args": { + "External id": 4555325,"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": 1336753, "tid": 1381210, + "ts": 1696942626980.442, "dur": 52.557, + "args": { + "External id": 4555326,"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": 1336753, "tid": 1381210, + "ts": 1696942627040.902, "dur": 34598.025, + "args": { + "External id": 4555327,"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": 1336753, "tid": 1381210, + "ts": 1696942627043.694, "dur": 34594.621, + "args": { + "External id": 4555328,"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": 1336753, "tid": 1381210, + "ts": 1696942627048.102, "dur": 6.646, + "args": { + "External id": 4555329,"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": 1336753, "tid": 1381210, + "ts": 1696942627056.599, "dur": 34578.830, + "args": { + "External id": 4555330,"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": 1336753, "tid": 1381210, + "ts": 1696942661776.112, "dur": 8.237, + "args": { + "External id": 4555331,"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": 1336753, "tid": 1381210, + "ts": 1696942661779.120, "dur": 4.868, + "args": { + "External id": 4555332,"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": 1336753, "tid": 1381210, + "ts": 1696942661813.976, "dur": 372.016, + "args": { + "External id": 4555333,"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": 1336753, "tid": 1381210, + "ts": 1696942661839.335, "dur": 340.945, + "args": { + "External id": 4555334,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942661849.305, "dur": 325.377, + "args": { + "External id": 4555335,"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": 1336753, "tid": 1381210, + "ts": 1696942662206.323, "dur": 2.704, + "args": { + "External id": 4555336,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942662268.834, "dur": 6.531, + "args": { + "External id": 4555337,"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": 1336753, "tid": 1381210, + "ts": 1696942662323.733, "dur": 1.211, + "args": { + "External id": 4555338,"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": 1336753, "tid": 1381210, + "ts": 1696942662341.108, "dur": 1.060, + "args": { + "External id": 4555339,"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": 1336753, "tid": 1381210, + "ts": 1696942662354.668, "dur": 0.933, + "args": { + "External id": 4555340,"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": 1336753, "tid": 1381210, + "ts": 1696942662368.027, "dur": 1.061, + "args": { + "External id": 4555341,"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": 1336753, "tid": 1381210, + "ts": 1696942662381.357, "dur": 1.089, + "args": { + "External id": 4555342,"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": 1336753, "tid": 1381210, + "ts": 1696942662392.938, "dur": 0.928, + "args": { + "External id": 4555343,"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": 1336753, "tid": 1381210, + "ts": 1696942662405.824, "dur": 2.001, + "args": { + "External id": 4555344,"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": 1336753, "tid": 1381210, + "ts": 1696942662418.615, "dur": 1.086, + "args": { + "External id": 4555345,"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": 1336753, "tid": 1381210, + "ts": 1696942662514.032, "dur": 2758.351, + "args": { + "External id": 4555346,"Record function id": 0, "Ev Idx": 3665 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1696942662551.127, "dur": 1034.513, + "args": { + "External id": 4555347,"Record function id": 0, "Ev Idx": 3666 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1696942662566.347, "dur": 323.009, + "args": { + "External id": 4555348,"Record function id": 0, "Ev Idx": 3667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942662651.096, "dur": 4.573, + "args": { + "External id": 4555349,"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": 1336753, "tid": 1381210, + "ts": 1696942662658.698, "dur": 0.994, + "args": { + "External id": 4555350,"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": 1336753, "tid": 1381210, + "ts": 1696942662661.458, "dur": 0.958, + "args": { + "External id": 4555351,"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": 1336753, "tid": 1381210, + "ts": 1696942662663.861, "dur": 1.084, + "args": { + "External id": 4555352,"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": 1336753, "tid": 1381210, + "ts": 1696942662666.237, "dur": 0.969, + "args": { + "External id": 4555353,"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": 1336753, "tid": 1381210, + "ts": 1696942662668.851, "dur": 0.928, + "args": { + "External id": 4555354,"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": 1336753, "tid": 1381210, + "ts": 1696942662671.262, "dur": 1.809, + "args": { + "External id": 4555355,"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": 1336753, "tid": 1381210, + "ts": 1696942662674.251, "dur": 3.221, + "args": { + "External id": 4555356,"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": 1336753, "tid": 1381210, + "ts": 1696942662679.096, "dur": 0.995, + "args": { + "External id": 4555357,"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": 1336753, "tid": 1381210, + "ts": 1696942662681.358, "dur": 0.921, + "args": { + "External id": 4555358,"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": 1336753, "tid": 1381210, + "ts": 1696942662699.975, "dur": 157.990, + "args": { + "External id": 4555359,"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": 1336753, "tid": 1381210, + "ts": 1696942662715.712, "dur": 138.448, + "args": { + "External id": 4555360,"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": 1336753, "tid": 1381210, + "ts": 1696942662742.255, "dur": 12.504, + "args": { + "External id": 4555361,"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": 1336753, "tid": 1381210, + "ts": 1696942662757.980, "dur": 69.643, + "args": { + "External id": 4555362,"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": 1336753, "tid": 1381210, + "ts": 1696942662761.011, "dur": 66.237, + "args": { + "External id": 4555363,"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": 1336753, "tid": 1381210, + "ts": 1696942662765.679, "dur": 5.400, + "args": { + "External id": 4555364,"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": 1336753, "tid": 1381210, + "ts": 1696942662773.092, "dur": 53.139, + "args": { + "External id": 4555365,"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": 1336753, "tid": 1381210, + "ts": 1696942662980.220, "dur": 596.598, + "args": { + "External id": 4555366,"Record function id": 0, "Ev Idx": 3685 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1696942663036.079, "dur": 526.250, + "args": { + "External id": 4555367,"Record function id": 0, "Ev Idx": 3686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942663102.650, "dur": 6.465, + "args": { + "External id": 4555368,"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": 1336753, "tid": 1381210, + "ts": 1696942663125.114, "dur": 30.773, + "args": { + "External id": 4555369,"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": 1336753, "tid": 1381210, + "ts": 1696942663130.321, "dur": 1.561, + "args": { + "External id": 4555370,"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": 1336753, "tid": 1381210, + "ts": 1696942663134.428, "dur": 0.333, + "args": { + "External id": 4555371,"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": 1336753, "tid": 1381210, + "ts": 1696942663136.370, "dur": 2.529, + "args": { + "External id": 4555372,"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": 1336753, "tid": 1381210, + "ts": 1696942663140.566, "dur": 0.397, + "args": { + "External id": 4555373,"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": 1336753, "tid": 1381210, + "ts": 1696942663142.408, "dur": 0.417, + "args": { + "External id": 4555374,"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": 1336753, "tid": 1381210, + "ts": 1696942663144.367, "dur": 0.445, + "args": { + "External id": 4555375,"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": 1336753, "tid": 1381210, + "ts": 1696942663146.586, "dur": 0.384, + "args": { + "External id": 4555376,"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": 1336753, "tid": 1381210, + "ts": 1696942663148.579, "dur": 0.350, + "args": { + "External id": 4555377,"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": 1336753, "tid": 1381210, + "ts": 1696942663150.893, "dur": 0.373, + "args": { + "External id": 4555378,"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": 1336753, "tid": 1381210, + "ts": 1696942663166.594, "dur": 32.498, + "args": { + "External id": 4555379,"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": 1336753, "tid": 1381210, + "ts": 1696942663230.285, "dur": 100.250, + "args": { + "External id": 4555380,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942663240.395, "dur": 3.062, + "args": { + "External id": 4555381,"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": 1336753, "tid": 1381210, + "ts": 1696942663248.859, "dur": 12.320, + "args": { + "External id": 4555382,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942663253.458, "dur": 7.329, + "args": { + "External id": 4555383,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942663257.001, "dur": 2.584, + "args": { + "External id": 4555384,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942663268.339, "dur": 25.761, + "args": { + "External id": 4555385,"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": 1336753, "tid": 1381210, + "ts": 1696942663270.639, "dur": 0.393, + "args": { + "External id": 4555386,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942663272.728, "dur": 0.407, + "args": { + "External id": 4555387,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942663274.809, "dur": 0.371, + "args": { + "External id": 4555388,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942663277.293, "dur": 0.653, + "args": { + "External id": 4555389,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942663279.824, "dur": 0.448, + "args": { + "External id": 4555390,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942663282.113, "dur": 0.480, + "args": { + "External id": 4555391,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942663284.175, "dur": 0.366, + "args": { + "External id": 4555392,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942663286.450, "dur": 2.310, + "args": { + "External id": 4555393,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942663290.375, "dur": 0.576, + "args": { + "External id": 4555394,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942663304.047, "dur": 19.164, + "args": { + "External id": 4555395,"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": 1336753, "tid": 1381210, + "ts": 1696942663374.443, "dur": 106.741, + "args": { + "External id": 4555396,"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": 1336753, "tid": 1381210, + "ts": 1696942663396.138, "dur": 81.568, + "args": { + "External id": 4555397,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942663405.754, "dur": 67.637, + "args": { + "External id": 4555398,"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": 1336753, "tid": 1381210, + "ts": 1696942663493.521, "dur": 1.778, + "args": { + "External id": 4555399,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942663593.319, "dur": 1656.341, + "args": { + "External id": 4555400,"Sequence number": 45295612, "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": 1336753, "tid": 1381210, "ts": 1696942663593.319, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942663705.478, "dur": 103.734, + "args": { + "External id": 4555401,"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": 1336753, "tid": 1381210, + "ts": 1696942663845.947, "dur": 38.818, + "args": { + "External id": 4555402,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942663905.284, "dur": 47.976, + "args": { + "External id": 4555403,"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": 1336753, "tid": 1381210, + "ts": 1696942663963.311, "dur": 73.242, + "args": { + "External id": 4555404,"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": 1336753, "tid": 1381210, + "ts": 1696942664047.786, "dur": 50.444, + "args": { + "External id": 4555405,"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": 1336753, "tid": 1381210, + "ts": 1696942664106.379, "dur": 28.289, + "args": { + "External id": 4555406,"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": 1336753, "tid": 1381210, + "ts": 1696942664144.121, "dur": 42.105, + "args": { + "External id": 4555407,"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": 1336753, "tid": 1381210, + "ts": 1696942664210.658, "dur": 22.799, + "args": { + "External id": 4555408,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942664250.902, "dur": 28.925, + "args": { + "External id": 4555409,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942664299.979, "dur": 17.635, + "args": { + "External id": 4555410,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942664329.842, "dur": 14.029, + "args": { + "External id": 4555411,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942664354.600, "dur": 26.895, + "args": { + "External id": 4555412,"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": 1336753, "tid": 1381210, + "ts": 1696942664384.668, "dur": 31.791, + "args": { + "External id": 4555413,"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": 1336753, "tid": 1381210, + "ts": 1696942664442.628, "dur": 193.018, + "args": { + "External id": 4555414,"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": 1336753, "tid": 1381210, + "ts": 1696942664520.854, "dur": 22.240, + "args": { + "External id": 4555415,"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": 1336753, "tid": 1381210, + "ts": 1696942664546.074, "dur": 2.738, + "args": { + "External id": 4555416,"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": 1336753, "tid": 1381210, + "ts": 1696942664670.178, "dur": 24.491, + "args": { + "External id": 4555417,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942664725.008, "dur": 16.395, + "args": { + "External id": 4555418,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942664752.249, "dur": 38.710, + "args": { + "External id": 4555419,"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": 1336753, "tid": 1381210, + "ts": 1696942664798.447, "dur": 34.232, + "args": { + "External id": 4555420,"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": 1336753, "tid": 1381210, + "ts": 1696942664839.745, "dur": 20.472, + "args": { + "External id": 4555421,"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": 1336753, "tid": 1381210, + "ts": 1696942664866.438, "dur": 29.779, + "args": { + "External id": 4555422,"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": 1336753, "tid": 1381210, + "ts": 1696942664904.592, "dur": 19.762, + "args": { + "External id": 4555423,"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": 1336753, "tid": 1381210, + "ts": 1696942664932.593, "dur": 30.070, + "args": { + "External id": 4555424,"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": 1336753, "tid": 1381210, + "ts": 1696942665042.490, "dur": 31.316, + "args": { + "External id": 4555425,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942665093.607, "dur": 23.830, + "args": { + "External id": 4555426,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942665132.819, "dur": 16.131, + "args": { + "External id": 4555427,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942665170.930, "dur": 14.864, + "args": { + "External id": 4555428,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942665198.969, "dur": 15.919, + "args": { + "External id": 4555429,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942665294.543, "dur": 16.123, + "args": { + "External id": 4555430,"Record function id": 0, "Ev Idx": 3749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942665298.209, "dur": 11.526, + "args": { + "External id": 4555431,"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": 1336753, "tid": 1381210, + "ts": 1696942665302.337, "dur": 6.322, + "args": { + "External id": 4555432,"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": 1336753, "tid": 1381210, + "ts": 1696942665304.380, "dur": 4.169, + "args": { + "External id": 4555433,"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": 1336753, "tid": 1381210, + "ts": 1696942665314.604, "dur": 5.431, + "args": { + "External id": 4555434,"Record function id": 0, "Ev Idx": 3753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942665316.014, "dur": 3.610, + "args": { + "External id": 4555435,"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": 1336753, "tid": 1381210, + "ts": 1696942665316.862, "dur": 2.143, + "args": { + "External id": 4555436,"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": 1336753, "tid": 1381210, + "ts": 1696942665317.823, "dur": 1.091, + "args": { + "External id": 4555437,"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": 1336753, "tid": 1381210, + "ts": 1696942665323.244, "dur": 4.627, + "args": { + "External id": 4555438,"Record function id": 0, "Ev Idx": 3757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942665324.646, "dur": 2.799, + "args": { + "External id": 4555439,"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": 1336753, "tid": 1381210, + "ts": 1696942665325.155, "dur": 1.717, + "args": { + "External id": 4555440,"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": 1336753, "tid": 1381210, + "ts": 1696942665325.955, "dur": 0.838, + "args": { + "External id": 4555441,"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": 1336753, "tid": 1381210, + "ts": 1696942665331.073, "dur": 4.573, + "args": { + "External id": 4555442,"Record function id": 0, "Ev Idx": 3761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942665332.352, "dur": 2.881, + "args": { + "External id": 4555443,"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": 1336753, "tid": 1381210, + "ts": 1696942665333.497, "dur": 1.307, + "args": { + "External id": 4555444,"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": 1336753, "tid": 1381210, + "ts": 1696942665333.878, "dur": 0.859, + "args": { + "External id": 4555445,"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": 1336753, "tid": 1381210, + "ts": 1696942665338.750, "dur": 3.756, + "args": { + "External id": 4555446,"Record function id": 0, "Ev Idx": 3765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942665340.061, "dur": 2.046, + "args": { + "External id": 4555447,"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": 1336753, "tid": 1381210, + "ts": 1696942665340.686, "dur": 0.887, + "args": { + "External id": 4555448,"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": 1336753, "tid": 1381210, + "ts": 1696942665340.975, "dur": 0.533, + "args": { + "External id": 4555449,"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": 1336753, "tid": 1381210, + "ts": 1696942665345.601, "dur": 3.710, + "args": { + "External id": 4555450,"Record function id": 0, "Ev Idx": 3769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942665346.668, "dur": 2.214, + "args": { + "External id": 4555451,"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": 1336753, "tid": 1381210, + "ts": 1696942665347.126, "dur": 1.278, + "args": { + "External id": 4555452,"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": 1336753, "tid": 1381210, + "ts": 1696942665347.645, "dur": 0.633, + "args": { + "External id": 4555453,"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": 1336753, "tid": 1381210, + "ts": 1696942665352.485, "dur": 5.353, + "args": { + "External id": 4555454,"Record function id": 0, "Ev Idx": 3773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942665353.579, "dur": 3.847, + "args": { + "External id": 4555455,"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": 1336753, "tid": 1381210, + "ts": 1696942665354.042, "dur": 2.941, + "args": { + "External id": 4555456,"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": 1336753, "tid": 1381210, + "ts": 1696942665354.551, "dur": 2.325, + "args": { + "External id": 4555457,"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": 1336753, "tid": 1381210, + "ts": 1696942665361.032, "dur": 4.059, + "args": { + "External id": 4555458,"Record function id": 0, "Ev Idx": 3777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942665362.112, "dur": 2.543, + "args": { + "External id": 4555459,"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": 1336753, "tid": 1381210, + "ts": 1696942665362.768, "dur": 1.212, + "args": { + "External id": 4555460,"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": 1336753, "tid": 1381210, + "ts": 1696942665363.106, "dur": 0.809, + "args": { + "External id": 4555461,"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": 1336753, "tid": 1381210, + "ts": 1696942665368.257, "dur": 3.609, + "args": { + "External id": 4555462,"Record function id": 0, "Ev Idx": 3781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942665369.291, "dur": 2.174, + "args": { + "External id": 4555463,"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": 1336753, "tid": 1381210, + "ts": 1696942665369.788, "dur": 1.252, + "args": { + "External id": 4555464,"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": 1336753, "tid": 1381210, + "ts": 1696942665370.304, "dur": 0.644, + "args": { + "External id": 4555465,"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": 1336753, "tid": 1381210, + "ts": 1696942665375.518, "dur": 37191.267, + "args": { + "External id": 4555466,"Record function id": 0, "Sequence number": 45295611, "Fwd thread id": 1, "Ev Idx": 3785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942665376.992, "dur": 37180.050, + "args": { + "External id": 4555467,"Sequence number": 45295611, "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": 1336753, "tid": 1381210, "ts": 1696942665376.992, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1696942665406.233, "dur": 38.679, + "args": { + "External id": 4555468,"Record function id": 0, "Ev Idx": 3787 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1696942665452.386, "dur": 65.042, + "args": { + "External id": 4555469,"Record function id": 0, "Ev Idx": 3788 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1696942665523.104, "dur": 37024.552, + "args": { + "External id": 4555470,"Record function id": 0, "Ev Idx": 3789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942665638.248, "dur": 7.858, + "args": { + "External id": 4555471,"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": 1336753, "tid": 1381210, + "ts": 1696942665656.871, "dur": 5.037, + "args": { + "External id": 4555472,"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": 1336753, "tid": 1381210, + "ts": 1696942665676.899, "dur": 36013.670, + "args": { + "External id": 4555473,"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": 1336753, "tid": 1381210, + "ts": 1696942665690.328, "dur": 35991.513, + "args": { + "External id": 4555474,"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": 1336753, "tid": 1381210, + "ts": 1696942665743.991, "dur": 13.234, + "args": { + "External id": 4555475,"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": 1336753, "tid": 1381210, + "ts": 1696942665763.636, "dur": 35881.375, + "args": { + "External id": 4555476,"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": 1336753, "tid": 1381210, + "ts": 1696942665766.379, "dur": 35877.920, + "args": { + "External id": 4555477,"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": 1336753, "tid": 1381210, + "ts": 1696942665770.851, "dur": 5.200, + "args": { + "External id": 4555478,"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": 1336753, "tid": 1381210, + "ts": 1696942665777.917, "dur": 35862.415, + "args": { + "External id": 4555479,"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": 1336753, "tid": 1381210, + "ts": 1696942701780.710, "dur": 8.972, + "args": { + "External id": 4555480,"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": 1336753, "tid": 1381210, + "ts": 1696942701783.835, "dur": 5.509, + "args": { + "External id": 4555481,"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": 1336753, "tid": 1381210, + "ts": 1696942701820.282, "dur": 411.293, + "args": { + "External id": 4555482,"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": 1336753, "tid": 1381210, + "ts": 1696942701846.020, "dur": 380.109, + "args": { + "External id": 4555483,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942701856.205, "dur": 363.885, + "args": { + "External id": 4555484,"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": 1336753, "tid": 1381210, + "ts": 1696942702253.183, "dur": 2.515, + "args": { + "External id": 4555485,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942702317.006, "dur": 8.606, + "args": { + "External id": 4555486,"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": 1336753, "tid": 1381210, + "ts": 1696942702370.564, "dur": 1.208, + "args": { + "External id": 4555487,"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": 1336753, "tid": 1381210, + "ts": 1696942702388.105, "dur": 0.924, + "args": { + "External id": 4555488,"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": 1336753, "tid": 1381210, + "ts": 1696942702402.322, "dur": 1.005, + "args": { + "External id": 4555489,"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": 1336753, "tid": 1381210, + "ts": 1696942702414.690, "dur": 2.843, + "args": { + "External id": 4555490,"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": 1336753, "tid": 1381210, + "ts": 1696942702428.263, "dur": 1.032, + "args": { + "External id": 4555491,"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": 1336753, "tid": 1381210, + "ts": 1696942702440.913, "dur": 1.173, + "args": { + "External id": 4555492,"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": 1336753, "tid": 1381210, + "ts": 1696942702453.937, "dur": 2.243, + "args": { + "External id": 4555493,"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": 1336753, "tid": 1381210, + "ts": 1696942702467.260, "dur": 2.363, + "args": { + "External id": 4555494,"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": 1336753, "tid": 1381210, + "ts": 1696942702584.667, "dur": 2752.979, + "args": { + "External id": 4555495,"Record function id": 0, "Ev Idx": 3814 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1696942702607.094, "dur": 1046.675, + "args": { + "External id": 4555496,"Record function id": 0, "Ev Idx": 3815 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1696942702622.382, "dur": 326.566, + "args": { + "External id": 4555497,"Record function id": 0, "Ev Idx": 3816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942702707.803, "dur": 4.312, + "args": { + "External id": 4555498,"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": 1336753, "tid": 1381210, + "ts": 1696942702715.108, "dur": 1.153, + "args": { + "External id": 4555499,"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": 1336753, "tid": 1381210, + "ts": 1696942702718.355, "dur": 1.285, + "args": { + "External id": 4555500,"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": 1336753, "tid": 1381210, + "ts": 1696942702721.637, "dur": 1.086, + "args": { + "External id": 4555501,"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": 1336753, "tid": 1381210, + "ts": 1696942702724.167, "dur": 1.173, + "args": { + "External id": 4555502,"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": 1336753, "tid": 1381210, + "ts": 1696942702727.564, "dur": 1.002, + "args": { + "External id": 4555503,"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": 1336753, "tid": 1381210, + "ts": 1696942702730.125, "dur": 3.854, + "args": { + "External id": 4555504,"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": 1336753, "tid": 1381210, + "ts": 1696942702735.437, "dur": 1.151, + "args": { + "External id": 4555505,"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": 1336753, "tid": 1381210, + "ts": 1696942702738.346, "dur": 1.278, + "args": { + "External id": 4555506,"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": 1336753, "tid": 1381210, + "ts": 1696942702741.246, "dur": 0.913, + "args": { + "External id": 4555507,"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": 1336753, "tid": 1381210, + "ts": 1696942702760.382, "dur": 155.435, + "args": { + "External id": 4555508,"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": 1336753, "tid": 1381210, + "ts": 1696942702777.009, "dur": 134.623, + "args": { + "External id": 4555509,"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": 1336753, "tid": 1381210, + "ts": 1696942702801.447, "dur": 13.034, + "args": { + "External id": 4555510,"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": 1336753, "tid": 1381210, + "ts": 1696942702817.554, "dur": 66.989, + "args": { + "External id": 4555511,"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": 1336753, "tid": 1381210, + "ts": 1696942702820.538, "dur": 63.630, + "args": { + "External id": 4555512,"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": 1336753, "tid": 1381210, + "ts": 1696942702824.644, "dur": 5.292, + "args": { + "External id": 4555513,"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": 1336753, "tid": 1381210, + "ts": 1696942702831.894, "dur": 51.746, + "args": { + "External id": 4555514,"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": 1336753, "tid": 1381210, + "ts": 1696942703089.886, "dur": 554.666, + "args": { + "External id": 4555515,"Record function id": 0, "Ev Idx": 3834 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1696942703108.145, "dur": 522.692, + "args": { + "External id": 4555516,"Record function id": 0, "Ev Idx": 3835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942703171.889, "dur": 5.933, + "args": { + "External id": 4555517,"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": 1336753, "tid": 1381210, + "ts": 1696942703194.157, "dur": 31.292, + "args": { + "External id": 4555518,"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": 1336753, "tid": 1381210, + "ts": 1696942703199.587, "dur": 1.545, + "args": { + "External id": 4555519,"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": 1336753, "tid": 1381210, + "ts": 1696942703203.366, "dur": 2.673, + "args": { + "External id": 4555520,"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": 1336753, "tid": 1381210, + "ts": 1696942703207.678, "dur": 0.356, + "args": { + "External id": 4555521,"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": 1336753, "tid": 1381210, + "ts": 1696942703209.519, "dur": 0.479, + "args": { + "External id": 4555522,"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": 1336753, "tid": 1381210, + "ts": 1696942703211.687, "dur": 0.637, + "args": { + "External id": 4555523,"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": 1336753, "tid": 1381210, + "ts": 1696942703214.254, "dur": 0.527, + "args": { + "External id": 4555524,"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": 1336753, "tid": 1381210, + "ts": 1696942703216.488, "dur": 0.532, + "args": { + "External id": 4555525,"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": 1336753, "tid": 1381210, + "ts": 1696942703218.460, "dur": 0.398, + "args": { + "External id": 4555526,"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": 1336753, "tid": 1381210, + "ts": 1696942703220.447, "dur": 0.362, + "args": { + "External id": 4555527,"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": 1336753, "tid": 1381210, + "ts": 1696942703236.162, "dur": 32.736, + "args": { + "External id": 4555528,"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": 1336753, "tid": 1381210, + "ts": 1696942703299.556, "dur": 98.380, + "args": { + "External id": 4555529,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942703310.660, "dur": 4.449, + "args": { + "External id": 4555530,"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": 1336753, "tid": 1381210, + "ts": 1696942703320.654, "dur": 10.290, + "args": { + "External id": 4555531,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942703325.246, "dur": 5.275, + "args": { + "External id": 4555532,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942703328.997, "dur": 0.540, + "args": { + "External id": 4555533,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942703337.424, "dur": 23.461, + "args": { + "External id": 4555534,"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": 1336753, "tid": 1381210, + "ts": 1696942703339.514, "dur": 0.437, + "args": { + "External id": 4555535,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942703341.821, "dur": 0.360, + "args": { + "External id": 4555536,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942703344.194, "dur": 0.419, + "args": { + "External id": 4555537,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942703346.053, "dur": 0.438, + "args": { + "External id": 4555538,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942703348.181, "dur": 0.338, + "args": { + "External id": 4555539,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942703349.981, "dur": 0.422, + "args": { + "External id": 4555540,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942703352.360, "dur": 2.189, + "args": { + "External id": 4555541,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942703356.104, "dur": 0.356, + "args": { + "External id": 4555542,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942703357.817, "dur": 0.438, + "args": { + "External id": 4555543,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942703371.862, "dur": 18.995, + "args": { + "External id": 4555544,"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": 1336753, "tid": 1381210, + "ts": 1696942703441.772, "dur": 122.579, + "args": { + "External id": 4555545,"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": 1336753, "tid": 1381210, + "ts": 1696942703462.952, "dur": 97.412, + "args": { + "External id": 4555546,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942703471.839, "dur": 83.601, + "args": { + "External id": 4555547,"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": 1336753, "tid": 1381210, + "ts": 1696942703578.544, "dur": 2.098, + "args": { + "External id": 4555548,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942703661.681, "dur": 1656.752, + "args": { + "External id": 4555549,"Sequence number": 45295610, "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": 1336753, "tid": 1381210, "ts": 1696942703661.681, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942703769.337, "dur": 102.890, + "args": { + "External id": 4555550,"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": 1336753, "tid": 1381210, + "ts": 1696942703909.400, "dur": 40.001, + "args": { + "External id": 4555551,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942703972.661, "dur": 100.415, + "args": { + "External id": 4555552,"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": 1336753, "tid": 1381210, + "ts": 1696942704086.712, "dur": 35.078, + "args": { + "External id": 4555553,"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": 1336753, "tid": 1381210, + "ts": 1696942704128.854, "dur": 46.149, + "args": { + "External id": 4555554,"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": 1336753, "tid": 1381210, + "ts": 1696942704185.170, "dur": 28.606, + "args": { + "External id": 4555555,"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": 1336753, "tid": 1381210, + "ts": 1696942704221.652, "dur": 44.291, + "args": { + "External id": 4555556,"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": 1336753, "tid": 1381210, + "ts": 1696942704290.034, "dur": 23.332, + "args": { + "External id": 4555557,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942704334.229, "dur": 31.325, + "args": { + "External id": 4555558,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942704385.683, "dur": 22.536, + "args": { + "External id": 4555559,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942704420.901, "dur": 13.593, + "args": { + "External id": 4555560,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942704445.011, "dur": 32.013, + "args": { + "External id": 4555561,"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": 1336753, "tid": 1381210, + "ts": 1696942704480.662, "dur": 32.682, + "args": { + "External id": 4555562,"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": 1336753, "tid": 1381210, + "ts": 1696942704556.046, "dur": 178.684, + "args": { + "External id": 4555563,"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": 1336753, "tid": 1381210, + "ts": 1696942704635.109, "dur": 9.787, + "args": { + "External id": 4555564,"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": 1336753, "tid": 1381210, + "ts": 1696942704646.931, "dur": 4.215, + "args": { + "External id": 4555565,"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": 1336753, "tid": 1381210, + "ts": 1696942704767.490, "dur": 23.052, + "args": { + "External id": 4555566,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942704801.392, "dur": 14.426, + "args": { + "External id": 4555567,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942704824.203, "dur": 38.094, + "args": { + "External id": 4555568,"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": 1336753, "tid": 1381210, + "ts": 1696942704868.762, "dur": 35.258, + "args": { + "External id": 4555569,"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": 1336753, "tid": 1381210, + "ts": 1696942704910.740, "dur": 20.387, + "args": { + "External id": 4555570,"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": 1336753, "tid": 1381210, + "ts": 1696942704938.908, "dur": 29.918, + "args": { + "External id": 4555571,"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": 1336753, "tid": 1381210, + "ts": 1696942704975.479, "dur": 68.522, + "args": { + "External id": 4555572,"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": 1336753, "tid": 1381210, + "ts": 1696942705063.477, "dur": 44.106, + "args": { + "External id": 4555573,"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": 1336753, "tid": 1381210, + "ts": 1696942705127.978, "dur": 26.462, + "args": { + "External id": 4555574,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942705171.759, "dur": 27.125, + "args": { + "External id": 4555575,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942705213.709, "dur": 17.127, + "args": { + "External id": 4555576,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942705245.744, "dur": 13.124, + "args": { + "External id": 4555577,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942705272.485, "dur": 16.463, + "args": { + "External id": 4555578,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942705360.140, "dur": 15.819, + "args": { + "External id": 4555579,"Record function id": 0, "Ev Idx": 3898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942705363.541, "dur": 11.482, + "args": { + "External id": 4555580,"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": 1336753, "tid": 1381210, + "ts": 1696942705367.849, "dur": 5.973, + "args": { + "External id": 4555581,"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": 1336753, "tid": 1381210, + "ts": 1696942705369.740, "dur": 3.946, + "args": { + "External id": 4555582,"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": 1336753, "tid": 1381210, + "ts": 1696942705380.279, "dur": 5.209, + "args": { + "External id": 4555583,"Record function id": 0, "Ev Idx": 3902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942705381.695, "dur": 3.337, + "args": { + "External id": 4555584,"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": 1336753, "tid": 1381210, + "ts": 1696942705382.347, "dur": 2.242, + "args": { + "External id": 4555585,"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": 1336753, "tid": 1381210, + "ts": 1696942705383.368, "dur": 1.128, + "args": { + "External id": 4555586,"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": 1336753, "tid": 1381210, + "ts": 1696942705388.803, "dur": 4.924, + "args": { + "External id": 4555587,"Record function id": 0, "Ev Idx": 3906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942705390.066, "dur": 3.237, + "args": { + "External id": 4555588,"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": 1336753, "tid": 1381210, + "ts": 1696942705390.916, "dur": 1.873, + "args": { + "External id": 4555589,"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": 1336753, "tid": 1381210, + "ts": 1696942705391.584, "dur": 1.126, + "args": { + "External id": 4555590,"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": 1336753, "tid": 1381210, + "ts": 1696942705397.017, "dur": 9.108, + "args": { + "External id": 4555591,"Record function id": 0, "Ev Idx": 3910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942705398.050, "dur": 7.687, + "args": { + "External id": 4555592,"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": 1336753, "tid": 1381210, + "ts": 1696942705398.679, "dur": 6.651, + "args": { + "External id": 4555593,"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": 1336753, "tid": 1381210, + "ts": 1696942705399.290, "dur": 5.971, + "args": { + "External id": 4555594,"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": 1336753, "tid": 1381210, + "ts": 1696942705409.214, "dur": 4.075, + "args": { + "External id": 4555595,"Record function id": 0, "Ev Idx": 3914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942705410.264, "dur": 2.619, + "args": { + "External id": 4555596,"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": 1336753, "tid": 1381210, + "ts": 1696942705411.212, "dur": 1.222, + "args": { + "External id": 4555597,"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": 1336753, "tid": 1381210, + "ts": 1696942705411.506, "dur": 0.867, + "args": { + "External id": 4555598,"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": 1336753, "tid": 1381210, + "ts": 1696942705416.441, "dur": 3.482, + "args": { + "External id": 4555599,"Record function id": 0, "Ev Idx": 3918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942705417.459, "dur": 2.058, + "args": { + "External id": 4555600,"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": 1336753, "tid": 1381210, + "ts": 1696942705418.043, "dur": 1.083, + "args": { + "External id": 4555601,"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": 1336753, "tid": 1381210, + "ts": 1696942705418.483, "dur": 0.540, + "args": { + "External id": 4555602,"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": 1336753, "tid": 1381210, + "ts": 1696942705423.201, "dur": 3.639, + "args": { + "External id": 4555603,"Record function id": 0, "Ev Idx": 3922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942705424.246, "dur": 2.204, + "args": { + "External id": 4555604,"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": 1336753, "tid": 1381210, + "ts": 1696942705425.010, "dur": 1.016, + "args": { + "External id": 4555605,"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": 1336753, "tid": 1381210, + "ts": 1696942705425.289, "dur": 0.641, + "args": { + "External id": 4555606,"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": 1336753, "tid": 1381210, + "ts": 1696942705429.954, "dur": 3.411, + "args": { + "External id": 4555607,"Record function id": 0, "Ev Idx": 3926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942705430.983, "dur": 1.976, + "args": { + "External id": 4555608,"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": 1336753, "tid": 1381210, + "ts": 1696942705431.414, "dur": 1.140, + "args": { + "External id": 4555609,"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": 1336753, "tid": 1381210, + "ts": 1696942705431.905, "dur": 0.587, + "args": { + "External id": 4555610,"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": 1336753, "tid": 1381210, + "ts": 1696942705436.416, "dur": 28.008, + "args": { + "External id": 4555611,"Record function id": 0, "Ev Idx": 3930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942705437.547, "dur": 26.469, + "args": { + "External id": 4555612,"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": 1336753, "tid": 1381210, + "ts": 1696942705438.345, "dur": 25.110, + "args": { + "External id": 4555613,"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": 1336753, "tid": 1381210, + "ts": 1696942705462.515, "dur": 0.816, + "args": { + "External id": 4555614,"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": 1336753, "tid": 1381210, + "ts": 1696942705468.077, "dur": 36342.599, + "args": { + "External id": 4555615,"Record function id": 0, "Sequence number": 45295609, "Fwd thread id": 1, "Ev Idx": 3934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942705469.641, "dur": 36333.070, + "args": { + "External id": 4555616,"Sequence number": 45295609, "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": 1336753, "tid": 1381210, "ts": 1696942705469.641, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1696942705500.520, "dur": 56.326, + "args": { + "External id": 4555617,"Record function id": 0, "Ev Idx": 3936 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1696942705565.965, "dur": 72.290, + "args": { + "External id": 4555618,"Record function id": 0, "Ev Idx": 3937 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1696942705644.445, "dur": 36150.008, + "args": { + "External id": 4555619,"Record function id": 0, "Ev Idx": 3938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942705739.089, "dur": 7.276, + "args": { + "External id": 4555620,"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": 1336753, "tid": 1381210, + "ts": 1696942705756.595, "dur": 5.075, + "args": { + "External id": 4555621,"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": 1336753, "tid": 1381210, + "ts": 1696942705777.641, "dur": 35241.225, + "args": { + "External id": 4555622,"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": 1336753, "tid": 1381210, + "ts": 1696942705790.693, "dur": 35218.595, + "args": { + "External id": 4555623,"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": 1336753, "tid": 1381210, + "ts": 1696942705838.212, "dur": 18.444, + "args": { + "External id": 4555624,"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": 1336753, "tid": 1381210, + "ts": 1696942705863.112, "dur": 35083.840, + "args": { + "External id": 4555625,"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": 1336753, "tid": 1381210, + "ts": 1696942705865.900, "dur": 35080.160, + "args": { + "External id": 4555626,"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": 1336753, "tid": 1381210, + "ts": 1696942705870.014, "dur": 5.648, + "args": { + "External id": 4555627,"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": 1336753, "tid": 1381210, + "ts": 1696942705877.939, "dur": 35064.571, + "args": { + "External id": 4555628,"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": 1336753, "tid": 1381210, + "ts": 1696942741109.808, "dur": 8.737, + "args": { + "External id": 4555629,"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": 1336753, "tid": 1381210, + "ts": 1696942741112.974, "dur": 5.195, + "args": { + "External id": 4555630,"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": 1336753, "tid": 1381210, + "ts": 1696942741148.596, "dur": 335.673, + "args": { + "External id": 4555631,"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": 1336753, "tid": 1381210, + "ts": 1696942741174.440, "dur": 305.409, + "args": { + "External id": 4555632,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942741185.164, "dur": 289.913, + "args": { + "External id": 4555633,"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": 1336753, "tid": 1381210, + "ts": 1696942741502.163, "dur": 2.136, + "args": { + "External id": 4555634,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942741580.060, "dur": 7.278, + "args": { + "External id": 4555635,"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": 1336753, "tid": 1381210, + "ts": 1696942741636.132, "dur": 1.456, + "args": { + "External id": 4555636,"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": 1336753, "tid": 1381210, + "ts": 1696942741655.220, "dur": 1.275, + "args": { + "External id": 4555637,"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": 1336753, "tid": 1381210, + "ts": 1696942741670.176, "dur": 1.036, + "args": { + "External id": 4555638,"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": 1336753, "tid": 1381210, + "ts": 1696942741682.379, "dur": 0.846, + "args": { + "External id": 4555639,"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": 1336753, "tid": 1381210, + "ts": 1696942741694.408, "dur": 0.933, + "args": { + "External id": 4555640,"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": 1336753, "tid": 1381210, + "ts": 1696942741705.987, "dur": 0.908, + "args": { + "External id": 4555641,"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": 1336753, "tid": 1381210, + "ts": 1696942741719.977, "dur": 1.988, + "args": { + "External id": 4555642,"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": 1336753, "tid": 1381210, + "ts": 1696942741732.889, "dur": 0.739, + "args": { + "External id": 4555643,"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": 1336753, "tid": 1381210, + "ts": 1696942741826.854, "dur": 2736.903, + "args": { + "External id": 4555644,"Record function id": 0, "Ev Idx": 3963 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1696942741846.677, "dur": 1042.272, + "args": { + "External id": 4555645,"Record function id": 0, "Ev Idx": 3964 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1696942741862.302, "dur": 362.149, + "args": { + "External id": 4555646,"Record function id": 0, "Ev Idx": 3965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942741944.246, "dur": 3.872, + "args": { + "External id": 4555647,"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": 1336753, "tid": 1381210, + "ts": 1696942741950.986, "dur": 1.376, + "args": { + "External id": 4555648,"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": 1336753, "tid": 1381210, + "ts": 1696942741954.164, "dur": 1.178, + "args": { + "External id": 4555649,"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": 1336753, "tid": 1381210, + "ts": 1696942741956.955, "dur": 2.891, + "args": { + "External id": 4555650,"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": 1336753, "tid": 1381210, + "ts": 1696942741961.668, "dur": 1.306, + "args": { + "External id": 4555651,"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": 1336753, "tid": 1381210, + "ts": 1696942741964.335, "dur": 1.177, + "args": { + "External id": 4555652,"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": 1336753, "tid": 1381210, + "ts": 1696942741967.136, "dur": 1.873, + "args": { + "External id": 4555653,"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": 1336753, "tid": 1381210, + "ts": 1696942741970.364, "dur": 1.093, + "args": { + "External id": 4555654,"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": 1336753, "tid": 1381210, + "ts": 1696942741972.926, "dur": 0.800, + "args": { + "External id": 4555655,"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": 1336753, "tid": 1381210, + "ts": 1696942741975.621, "dur": 0.897, + "args": { + "External id": 4555656,"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": 1336753, "tid": 1381210, + "ts": 1696942742031.819, "dur": 157.682, + "args": { + "External id": 4555657,"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": 1336753, "tid": 1381210, + "ts": 1696942742049.074, "dur": 135.633, + "args": { + "External id": 4555658,"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": 1336753, "tid": 1381210, + "ts": 1696942742068.803, "dur": 12.774, + "args": { + "External id": 4555659,"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": 1336753, "tid": 1381210, + "ts": 1696942742085.121, "dur": 71.404, + "args": { + "External id": 4555660,"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": 1336753, "tid": 1381210, + "ts": 1696942742087.817, "dur": 68.350, + "args": { + "External id": 4555661,"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": 1336753, "tid": 1381210, + "ts": 1696942742091.878, "dur": 7.316, + "args": { + "External id": 4555662,"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": 1336753, "tid": 1381210, + "ts": 1696942742101.091, "dur": 54.488, + "args": { + "External id": 4555663,"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": 1336753, "tid": 1381210, + "ts": 1696942742317.768, "dur": 561.942, + "args": { + "External id": 4555664,"Record function id": 0, "Ev Idx": 3983 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1696942742335.911, "dur": 531.294, + "args": { + "External id": 4555665,"Record function id": 0, "Ev Idx": 3984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942742395.159, "dur": 4.549, + "args": { + "External id": 4555666,"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": 1336753, "tid": 1381210, + "ts": 1696942742415.956, "dur": 30.985, + "args": { + "External id": 4555667,"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": 1336753, "tid": 1381210, + "ts": 1696942742420.839, "dur": 1.736, + "args": { + "External id": 4555668,"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": 1336753, "tid": 1381210, + "ts": 1696942742425.028, "dur": 0.533, + "args": { + "External id": 4555669,"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": 1336753, "tid": 1381210, + "ts": 1696942742427.293, "dur": 0.536, + "args": { + "External id": 4555670,"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": 1336753, "tid": 1381210, + "ts": 1696942742429.894, "dur": 0.506, + "args": { + "External id": 4555671,"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": 1336753, "tid": 1381210, + "ts": 1696942742432.188, "dur": 0.516, + "args": { + "External id": 4555672,"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": 1336753, "tid": 1381210, + "ts": 1696942742434.873, "dur": 0.639, + "args": { + "External id": 4555673,"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": 1336753, "tid": 1381210, + "ts": 1696942742436.990, "dur": 2.000, + "args": { + "External id": 4555674,"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": 1336753, "tid": 1381210, + "ts": 1696942742440.639, "dur": 0.421, + "args": { + "External id": 4555675,"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": 1336753, "tid": 1381210, + "ts": 1696942742442.682, "dur": 0.440, + "args": { + "External id": 4555676,"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": 1336753, "tid": 1381210, + "ts": 1696942742456.423, "dur": 29.658, + "args": { + "External id": 4555677,"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": 1336753, "tid": 1381210, + "ts": 1696942742516.748, "dur": 122.855, + "args": { + "External id": 4555678,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942742543.874, "dur": 4.977, + "args": { + "External id": 4555679,"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": 1336753, "tid": 1381210, + "ts": 1696942742555.708, "dur": 11.188, + "args": { + "External id": 4555680,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942742560.224, "dur": 6.236, + "args": { + "External id": 4555681,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942742564.166, "dur": 0.792, + "args": { + "External id": 4555682,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942742574.731, "dur": 24.142, + "args": { + "External id": 4555683,"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": 1336753, "tid": 1381210, + "ts": 1696942742577.052, "dur": 0.451, + "args": { + "External id": 4555684,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942742579.524, "dur": 0.360, + "args": { + "External id": 4555685,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942742581.427, "dur": 0.337, + "args": { + "External id": 4555686,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942742583.564, "dur": 2.025, + "args": { + "External id": 4555687,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942742587.282, "dur": 0.352, + "args": { + "External id": 4555688,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942742589.110, "dur": 0.393, + "args": { + "External id": 4555689,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942742590.963, "dur": 0.577, + "args": { + "External id": 4555690,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942742593.335, "dur": 0.424, + "args": { + "External id": 4555691,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942742595.245, "dur": 0.372, + "args": { + "External id": 4555692,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942742610.271, "dur": 21.843, + "args": { + "External id": 4555693,"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": 1336753, "tid": 1381210, + "ts": 1696942742690.333, "dur": 112.915, + "args": { + "External id": 4555694,"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": 1336753, "tid": 1381210, + "ts": 1696942742712.505, "dur": 87.066, + "args": { + "External id": 4555695,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942742725.183, "dur": 69.791, + "args": { + "External id": 4555696,"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": 1336753, "tid": 1381210, + "ts": 1696942742815.632, "dur": 1.951, + "args": { + "External id": 4555697,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942742895.975, "dur": 1629.164, + "args": { + "External id": 4555698,"Sequence number": 45295608, "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": 1336753, "tid": 1381210, "ts": 1696942742895.975, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942743045.373, "dur": 105.394, + "args": { + "External id": 4555699,"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": 1336753, "tid": 1381210, + "ts": 1696942743191.243, "dur": 40.032, + "args": { + "External id": 4555700,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942743249.245, "dur": 46.499, + "args": { + "External id": 4555701,"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": 1336753, "tid": 1381210, + "ts": 1696942743304.201, "dur": 31.525, + "args": { + "External id": 4555702,"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": 1336753, "tid": 1381210, + "ts": 1696942743344.048, "dur": 45.996, + "args": { + "External id": 4555703,"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": 1336753, "tid": 1381210, + "ts": 1696942743397.734, "dur": 28.069, + "args": { + "External id": 4555704,"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": 1336753, "tid": 1381210, + "ts": 1696942743433.501, "dur": 43.022, + "args": { + "External id": 4555705,"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": 1336753, "tid": 1381210, + "ts": 1696942743500.358, "dur": 22.043, + "args": { + "External id": 4555706,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942743560.634, "dur": 30.628, + "args": { + "External id": 4555707,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942743615.648, "dur": 18.840, + "args": { + "External id": 4555708,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942743648.815, "dur": 16.718, + "args": { + "External id": 4555709,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942743674.111, "dur": 31.044, + "args": { + "External id": 4555710,"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": 1336753, "tid": 1381210, + "ts": 1696942743708.344, "dur": 36.884, + "args": { + "External id": 4555711,"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": 1336753, "tid": 1381210, + "ts": 1696942743774.489, "dur": 170.597, + "args": { + "External id": 4555712,"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": 1336753, "tid": 1381210, + "ts": 1696942743852.705, "dur": 5.733, + "args": { + "External id": 4555713,"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": 1336753, "tid": 1381210, + "ts": 1696942743860.193, "dur": 2.155, + "args": { + "External id": 4555714,"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": 1336753, "tid": 1381210, + "ts": 1696942743977.646, "dur": 65.542, + "args": { + "External id": 4555715,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942744056.606, "dur": 16.101, + "args": { + "External id": 4555716,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942744082.982, "dur": 39.058, + "args": { + "External id": 4555717,"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": 1336753, "tid": 1381210, + "ts": 1696942744129.502, "dur": 36.541, + "args": { + "External id": 4555718,"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": 1336753, "tid": 1381210, + "ts": 1696942744174.309, "dur": 21.073, + "args": { + "External id": 4555719,"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": 1336753, "tid": 1381210, + "ts": 1696942744201.269, "dur": 29.875, + "args": { + "External id": 4555720,"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": 1336753, "tid": 1381210, + "ts": 1696942744238.065, "dur": 19.039, + "args": { + "External id": 4555721,"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": 1336753, "tid": 1381210, + "ts": 1696942744265.496, "dur": 41.906, + "args": { + "External id": 4555722,"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": 1336753, "tid": 1381210, + "ts": 1696942744331.823, "dur": 28.175, + "args": { + "External id": 4555723,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942744376.552, "dur": 24.970, + "args": { + "External id": 4555724,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942744418.949, "dur": 16.738, + "args": { + "External id": 4555725,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942744453.279, "dur": 13.899, + "args": { + "External id": 4555726,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942744482.179, "dur": 15.144, + "args": { + "External id": 4555727,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942744590.224, "dur": 15.521, + "args": { + "External id": 4555728,"Record function id": 0, "Ev Idx": 4047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942744593.463, "dur": 11.350, + "args": { + "External id": 4555729,"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": 1336753, "tid": 1381210, + "ts": 1696942744597.740, "dur": 6.091, + "args": { + "External id": 4555730,"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": 1336753, "tid": 1381210, + "ts": 1696942744599.301, "dur": 4.440, + "args": { + "External id": 4555731,"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": 1336753, "tid": 1381210, + "ts": 1696942744609.528, "dur": 5.042, + "args": { + "External id": 4555732,"Record function id": 0, "Ev Idx": 4051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942744611.029, "dur": 3.104, + "args": { + "External id": 4555733,"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": 1336753, "tid": 1381210, + "ts": 1696942744612.133, "dur": 1.566, + "args": { + "External id": 4555734,"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": 1336753, "tid": 1381210, + "ts": 1696942744612.839, "dur": 0.778, + "args": { + "External id": 4555735,"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": 1336753, "tid": 1381210, + "ts": 1696942744617.837, "dur": 6.333, + "args": { + "External id": 4555736,"Record function id": 0, "Ev Idx": 4055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942744619.381, "dur": 4.393, + "args": { + "External id": 4555737,"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": 1336753, "tid": 1381210, + "ts": 1696942744619.944, "dur": 3.368, + "args": { + "External id": 4555738,"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": 1336753, "tid": 1381210, + "ts": 1696942744620.527, "dur": 2.707, + "args": { + "External id": 4555739,"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": 1336753, "tid": 1381210, + "ts": 1696942744627.408, "dur": 5.362, + "args": { + "External id": 4555740,"Record function id": 0, "Ev Idx": 4059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942744628.967, "dur": 3.363, + "args": { + "External id": 4555741,"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": 1336753, "tid": 1381210, + "ts": 1696942744629.735, "dur": 2.211, + "args": { + "External id": 4555742,"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": 1336753, "tid": 1381210, + "ts": 1696942744630.814, "dur": 1.036, + "args": { + "External id": 4555743,"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": 1336753, "tid": 1381210, + "ts": 1696942744635.939, "dur": 3.765, + "args": { + "External id": 4555744,"Record function id": 0, "Ev Idx": 4063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942744637.165, "dur": 2.143, + "args": { + "External id": 4555745,"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": 1336753, "tid": 1381210, + "ts": 1696942744637.770, "dur": 1.104, + "args": { + "External id": 4555746,"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": 1336753, "tid": 1381210, + "ts": 1696942744638.132, "dur": 0.634, + "args": { + "External id": 4555747,"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": 1336753, "tid": 1381210, + "ts": 1696942744642.815, "dur": 3.975, + "args": { + "External id": 4555748,"Record function id": 0, "Ev Idx": 4067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942744643.956, "dur": 2.441, + "args": { + "External id": 4555749,"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": 1336753, "tid": 1381210, + "ts": 1696942744644.770, "dur": 1.166, + "args": { + "External id": 4555750,"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": 1336753, "tid": 1381210, + "ts": 1696942744645.268, "dur": 0.577, + "args": { + "External id": 4555751,"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": 1336753, "tid": 1381210, + "ts": 1696942744650.101, "dur": 4.767, + "args": { + "External id": 4555752,"Record function id": 0, "Ev Idx": 4071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942744651.215, "dur": 3.233, + "args": { + "External id": 4555753,"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": 1336753, "tid": 1381210, + "ts": 1696942744651.852, "dur": 2.060, + "args": { + "External id": 4555754,"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": 1336753, "tid": 1381210, + "ts": 1696942744652.765, "dur": 1.027, + "args": { + "External id": 4555755,"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": 1336753, "tid": 1381210, + "ts": 1696942744657.994, "dur": 4.044, + "args": { + "External id": 4555756,"Record function id": 0, "Ev Idx": 4075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942744659.421, "dur": 2.220, + "args": { + "External id": 4555757,"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": 1336753, "tid": 1381210, + "ts": 1696942744659.972, "dur": 1.278, + "args": { + "External id": 4555758,"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": 1336753, "tid": 1381210, + "ts": 1696942744660.550, "dur": 0.638, + "args": { + "External id": 4555759,"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": 1336753, "tid": 1381210, + "ts": 1696942744665.113, "dur": 3.749, + "args": { + "External id": 4555760,"Record function id": 0, "Ev Idx": 4079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942744666.418, "dur": 2.042, + "args": { + "External id": 4555761,"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": 1336753, "tid": 1381210, + "ts": 1696942744666.847, "dur": 1.182, + "args": { + "External id": 4555762,"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": 1336753, "tid": 1381210, + "ts": 1696942744667.137, "dur": 0.806, + "args": { + "External id": 4555763,"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": 1336753, "tid": 1381210, + "ts": 1696942744672.704, "dur": 36559.284, + "args": { + "External id": 4555764,"Record function id": 0, "Sequence number": 45295607, "Fwd thread id": 1, "Ev Idx": 4083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942744674.167, "dur": 36545.320, + "args": { + "External id": 4555765,"Sequence number": 45295607, "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": 1336753, "tid": 1381210, "ts": 1696942744674.167, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1696942744704.230, "dur": 36.964, + "args": { + "External id": 4555766,"Record function id": 0, "Ev Idx": 4085 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1696942744748.546, "dur": 66.574, + "args": { + "External id": 4555767,"Record function id": 0, "Ev Idx": 4086 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1696942744821.131, "dur": 36389.901, + "args": { + "External id": 4555768,"Record function id": 0, "Ev Idx": 4087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942744911.004, "dur": 7.121, + "args": { + "External id": 4555769,"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": 1336753, "tid": 1381210, + "ts": 1696942744927.847, "dur": 6.536, + "args": { + "External id": 4555770,"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": 1336753, "tid": 1381210, + "ts": 1696942744949.190, "dur": 35446.611, + "args": { + "External id": 4555771,"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": 1336753, "tid": 1381210, + "ts": 1696942744963.794, "dur": 35421.826, + "args": { + "External id": 4555772,"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": 1336753, "tid": 1381210, + "ts": 1696942745063.269, "dur": 15.092, + "args": { + "External id": 4555773,"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": 1336753, "tid": 1381210, + "ts": 1696942745085.272, "dur": 35262.047, + "args": { + "External id": 4555774,"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": 1336753, "tid": 1381210, + "ts": 1696942745088.015, "dur": 35258.451, + "args": { + "External id": 4555775,"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": 1336753, "tid": 1381210, + "ts": 1696942745092.232, "dur": 6.351, + "args": { + "External id": 4555776,"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": 1336753, "tid": 1381210, + "ts": 1696942745124.882, "dur": 35217.850, + "args": { + "External id": 4555777,"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": 1336753, "tid": 1381210, + "ts": 1696942780489.445, "dur": 8.813, + "args": { + "External id": 4555778,"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": 1336753, "tid": 1381210, + "ts": 1696942780492.272, "dur": 5.676, + "args": { + "External id": 4555779,"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": 1336753, "tid": 1381210, + "ts": 1696942780541.807, "dur": 347.293, + "args": { + "External id": 4555780,"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": 1336753, "tid": 1381210, + "ts": 1696942780571.805, "dur": 312.626, + "args": { + "External id": 4555781,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942780582.793, "dur": 295.833, + "args": { + "External id": 4555782,"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": 1336753, "tid": 1381210, + "ts": 1696942780906.030, "dur": 2.044, + "args": { + "External id": 4555783,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942780965.035, "dur": 6.588, + "args": { + "External id": 4555784,"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": 1336753, "tid": 1381210, + "ts": 1696942781050.602, "dur": 2.089, + "args": { + "External id": 4555785,"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": 1336753, "tid": 1381210, + "ts": 1696942781070.332, "dur": 3.602, + "args": { + "External id": 4555786,"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": 1336753, "tid": 1381210, + "ts": 1696942781085.053, "dur": 0.743, + "args": { + "External id": 4555787,"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": 1336753, "tid": 1381210, + "ts": 1696942781096.491, "dur": 0.817, + "args": { + "External id": 4555788,"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": 1336753, "tid": 1381210, + "ts": 1696942781107.280, "dur": 0.981, + "args": { + "External id": 4555789,"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": 1336753, "tid": 1381210, + "ts": 1696942781122.684, "dur": 2.679, + "args": { + "External id": 4555790,"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": 1336753, "tid": 1381210, + "ts": 1696942781136.717, "dur": 2.022, + "args": { + "External id": 4555791,"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": 1336753, "tid": 1381210, + "ts": 1696942781148.294, "dur": 0.738, + "args": { + "External id": 4555792,"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": 1336753, "tid": 1381210, + "ts": 1696942781247.841, "dur": 2712.624, + "args": { + "External id": 4555793,"Record function id": 0, "Ev Idx": 4112 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1696942781267.618, "dur": 1038.191, + "args": { + "External id": 4555794,"Record function id": 0, "Ev Idx": 4113 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1696942781281.353, "dur": 331.891, + "args": { + "External id": 4555795,"Record function id": 0, "Ev Idx": 4114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942781363.174, "dur": 3.845, + "args": { + "External id": 4555796,"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": 1336753, "tid": 1381210, + "ts": 1696942781372.151, "dur": 0.986, + "args": { + "External id": 4555797,"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": 1336753, "tid": 1381210, + "ts": 1696942781375.122, "dur": 2.464, + "args": { + "External id": 4555798,"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": 1336753, "tid": 1381210, + "ts": 1696942781379.459, "dur": 0.890, + "args": { + "External id": 4555799,"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": 1336753, "tid": 1381210, + "ts": 1696942781381.952, "dur": 0.758, + "args": { + "External id": 4555800,"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": 1336753, "tid": 1381210, + "ts": 1696942781386.434, "dur": 0.616, + "args": { + "External id": 4555801,"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": 1336753, "tid": 1381210, + "ts": 1696942781388.837, "dur": 1.083, + "args": { + "External id": 4555802,"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": 1336753, "tid": 1381210, + "ts": 1696942781391.487, "dur": 0.773, + "args": { + "External id": 4555803,"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": 1336753, "tid": 1381210, + "ts": 1696942781393.758, "dur": 0.708, + "args": { + "External id": 4555804,"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": 1336753, "tid": 1381210, + "ts": 1696942781398.000, "dur": 1.445, + "args": { + "External id": 4555805,"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": 1336753, "tid": 1381210, + "ts": 1696942781416.665, "dur": 166.928, + "args": { + "External id": 4555806,"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": 1336753, "tid": 1381210, + "ts": 1696942781433.087, "dur": 145.903, + "args": { + "External id": 4555807,"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": 1336753, "tid": 1381210, + "ts": 1696942781451.134, "dur": 13.761, + "args": { + "External id": 4555808,"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": 1336753, "tid": 1381210, + "ts": 1696942781467.769, "dur": 83.134, + "args": { + "External id": 4555809,"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": 1336753, "tid": 1381210, + "ts": 1696942781470.114, "dur": 80.423, + "args": { + "External id": 4555810,"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": 1336753, "tid": 1381210, + "ts": 1696942781474.016, "dur": 5.277, + "args": { + "External id": 4555811,"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": 1336753, "tid": 1381210, + "ts": 1696942781480.964, "dur": 68.495, + "args": { + "External id": 4555812,"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": 1336753, "tid": 1381210, + "ts": 1696942781711.748, "dur": 585.454, + "args": { + "External id": 4555813,"Record function id": 0, "Ev Idx": 4132 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1696942781727.751, "dur": 557.682, + "args": { + "External id": 4555814,"Record function id": 0, "Ev Idx": 4133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942781789.475, "dur": 9.945, + "args": { + "External id": 4555815,"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": 1336753, "tid": 1381210, + "ts": 1696942781815.270, "dur": 28.880, + "args": { + "External id": 4555816,"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": 1336753, "tid": 1381210, + "ts": 1696942781819.904, "dur": 1.281, + "args": { + "External id": 4555817,"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": 1336753, "tid": 1381210, + "ts": 1696942781823.785, "dur": 0.352, + "args": { + "External id": 4555818,"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": 1336753, "tid": 1381210, + "ts": 1696942781825.840, "dur": 0.277, + "args": { + "External id": 4555819,"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": 1336753, "tid": 1381210, + "ts": 1696942781827.533, "dur": 0.486, + "args": { + "External id": 4555820,"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": 1336753, "tid": 1381210, + "ts": 1696942781829.618, "dur": 0.625, + "args": { + "External id": 4555821,"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": 1336753, "tid": 1381210, + "ts": 1696942781831.429, "dur": 2.540, + "args": { + "External id": 4555822,"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": 1336753, "tid": 1381210, + "ts": 1696942781838.513, "dur": 0.576, + "args": { + "External id": 4555823,"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": 1336753, "tid": 1381210, + "ts": 1696942781839.708, "dur": 0.374, + "args": { + "External id": 4555824,"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": 1336753, "tid": 1381210, + "ts": 1696942781841.080, "dur": 0.364, + "args": { + "External id": 4555825,"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": 1336753, "tid": 1381210, + "ts": 1696942781854.201, "dur": 27.900, + "args": { + "External id": 4555826,"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": 1336753, "tid": 1381210, + "ts": 1696942781911.879, "dur": 145.625, + "args": { + "External id": 4555827,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942781921.115, "dur": 3.537, + "args": { + "External id": 4555828,"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": 1336753, "tid": 1381210, + "ts": 1696942781929.578, "dur": 12.718, + "args": { + "External id": 4555829,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942781935.739, "dur": 6.137, + "args": { + "External id": 4555830,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942781939.775, "dur": 0.431, + "args": { + "External id": 4555831,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942781951.988, "dur": 26.065, + "args": { + "External id": 4555832,"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": 1336753, "tid": 1381210, + "ts": 1696942781953.856, "dur": 0.332, + "args": { + "External id": 4555833,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942781955.570, "dur": 0.619, + "args": { + "External id": 4555834,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942781957.853, "dur": 2.270, + "args": { + "External id": 4555835,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942781961.536, "dur": 0.421, + "args": { + "External id": 4555836,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942781963.272, "dur": 0.251, + "args": { + "External id": 4555837,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942781964.640, "dur": 0.284, + "args": { + "External id": 4555838,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942781966.856, "dur": 0.344, + "args": { + "External id": 4555839,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942781968.694, "dur": 0.745, + "args": { + "External id": 4555840,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942781970.932, "dur": 0.361, + "args": { + "External id": 4555841,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942782025.659, "dur": 23.025, + "args": { + "External id": 4555842,"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": 1336753, "tid": 1381210, + "ts": 1696942782105.835, "dur": 114.329, + "args": { + "External id": 4555843,"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": 1336753, "tid": 1381210, + "ts": 1696942782134.365, "dur": 82.405, + "args": { + "External id": 4555844,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942782143.729, "dur": 68.711, + "args": { + "External id": 4555845,"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": 1336753, "tid": 1381210, + "ts": 1696942782237.178, "dur": 1.817, + "args": { + "External id": 4555846,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942782312.735, "dur": 1627.692, + "args": { + "External id": 4555847,"Sequence number": 45295606, "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": 1336753, "tid": 1381210, "ts": 1696942782312.735, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942782425.970, "dur": 125.292, + "args": { + "External id": 4555848,"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": 1336753, "tid": 1381210, + "ts": 1696942782597.162, "dur": 38.090, + "args": { + "External id": 4555849,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942782651.747, "dur": 51.770, + "args": { + "External id": 4555850,"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": 1336753, "tid": 1381210, + "ts": 1696942782715.761, "dur": 32.311, + "args": { + "External id": 4555851,"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": 1336753, "tid": 1381210, + "ts": 1696942782754.308, "dur": 45.218, + "args": { + "External id": 4555852,"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": 1336753, "tid": 1381210, + "ts": 1696942782806.474, "dur": 27.387, + "args": { + "External id": 4555853,"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": 1336753, "tid": 1381210, + "ts": 1696942782840.928, "dur": 44.802, + "args": { + "External id": 4555854,"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": 1336753, "tid": 1381210, + "ts": 1696942782913.614, "dur": 23.162, + "args": { + "External id": 4555855,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942782965.865, "dur": 67.645, + "args": { + "External id": 4555856,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942783059.400, "dur": 17.313, + "args": { + "External id": 4555857,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942783092.775, "dur": 13.389, + "args": { + "External id": 4555858,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942783114.414, "dur": 36.737, + "args": { + "External id": 4555859,"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": 1336753, "tid": 1381210, + "ts": 1696942783154.512, "dur": 35.690, + "args": { + "External id": 4555860,"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": 1336753, "tid": 1381210, + "ts": 1696942783218.270, "dur": 170.062, + "args": { + "External id": 4555861,"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": 1336753, "tid": 1381210, + "ts": 1696942783295.557, "dur": 8.866, + "args": { + "External id": 4555862,"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": 1336753, "tid": 1381210, + "ts": 1696942783306.710, "dur": 2.207, + "args": { + "External id": 4555863,"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": 1336753, "tid": 1381210, + "ts": 1696942783423.282, "dur": 21.457, + "args": { + "External id": 4555864,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942783456.637, "dur": 13.676, + "args": { + "External id": 4555865,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942783476.885, "dur": 37.293, + "args": { + "External id": 4555866,"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": 1336753, "tid": 1381210, + "ts": 1696942783519.040, "dur": 52.139, + "args": { + "External id": 4555867,"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": 1336753, "tid": 1381210, + "ts": 1696942783582.823, "dur": 21.550, + "args": { + "External id": 4555868,"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": 1336753, "tid": 1381210, + "ts": 1696942783608.756, "dur": 29.203, + "args": { + "External id": 4555869,"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": 1336753, "tid": 1381210, + "ts": 1696942783644.299, "dur": 32.361, + "args": { + "External id": 4555870,"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": 1336753, "tid": 1381210, + "ts": 1696942783688.166, "dur": 36.564, + "args": { + "External id": 4555871,"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": 1336753, "tid": 1381210, + "ts": 1696942783751.170, "dur": 22.084, + "args": { + "External id": 4555872,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942783791.162, "dur": 24.302, + "args": { + "External id": 4555873,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942783835.018, "dur": 16.172, + "args": { + "External id": 4555874,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942783866.874, "dur": 13.788, + "args": { + "External id": 4555875,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942783897.220, "dur": 15.595, + "args": { + "External id": 4555876,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942784016.881, "dur": 18.180, + "args": { + "External id": 4555877,"Record function id": 0, "Ev Idx": 4196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942784021.530, "dur": 12.311, + "args": { + "External id": 4555878,"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": 1336753, "tid": 1381210, + "ts": 1696942784025.882, "dur": 6.554, + "args": { + "External id": 4555879,"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": 1336753, "tid": 1381210, + "ts": 1696942784027.541, "dur": 4.639, + "args": { + "External id": 4555880,"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": 1336753, "tid": 1381210, + "ts": 1696942784040.879, "dur": 6.899, + "args": { + "External id": 4555881,"Record function id": 0, "Ev Idx": 4200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942784042.142, "dur": 5.144, + "args": { + "External id": 4555882,"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": 1336753, "tid": 1381210, + "ts": 1696942784043.155, "dur": 3.606, + "args": { + "External id": 4555883,"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": 1336753, "tid": 1381210, + "ts": 1696942784043.848, "dur": 2.852, + "args": { + "External id": 4555884,"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": 1336753, "tid": 1381210, + "ts": 1696942784051.053, "dur": 4.833, + "args": { + "External id": 4555885,"Record function id": 0, "Ev Idx": 4204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942784052.482, "dur": 3.005, + "args": { + "External id": 4555886,"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": 1336753, "tid": 1381210, + "ts": 1696942784053.330, "dur": 1.723, + "args": { + "External id": 4555887,"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": 1336753, "tid": 1381210, + "ts": 1696942784054.047, "dur": 0.939, + "args": { + "External id": 4555888,"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": 1336753, "tid": 1381210, + "ts": 1696942784059.182, "dur": 7.591, + "args": { + "External id": 4555889,"Record function id": 0, "Ev Idx": 4208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942784060.333, "dur": 5.978, + "args": { + "External id": 4555890,"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": 1336753, "tid": 1381210, + "ts": 1696942784060.939, "dur": 4.641, + "args": { + "External id": 4555891,"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": 1336753, "tid": 1381210, + "ts": 1696942784064.802, "dur": 0.649, + "args": { + "External id": 4555892,"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": 1336753, "tid": 1381210, + "ts": 1696942784070.012, "dur": 3.994, + "args": { + "External id": 4555893,"Record function id": 0, "Ev Idx": 4212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942784071.164, "dur": 2.435, + "args": { + "External id": 4555894,"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": 1336753, "tid": 1381210, + "ts": 1696942784072.019, "dur": 1.137, + "args": { + "External id": 4555895,"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": 1336753, "tid": 1381210, + "ts": 1696942784072.354, "dur": 0.711, + "args": { + "External id": 4555896,"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": 1336753, "tid": 1381210, + "ts": 1696942784077.105, "dur": 3.353, + "args": { + "External id": 4555897,"Record function id": 0, "Ev Idx": 4216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942784078.157, "dur": 1.891, + "args": { + "External id": 4555898,"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": 1336753, "tid": 1381210, + "ts": 1696942784078.672, "dur": 0.920, + "args": { + "External id": 4555899,"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": 1336753, "tid": 1381210, + "ts": 1696942784078.939, "dur": 0.570, + "args": { + "External id": 4555900,"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": 1336753, "tid": 1381210, + "ts": 1696942784083.822, "dur": 3.692, + "args": { + "External id": 4555901,"Record function id": 0, "Ev Idx": 4220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942784084.878, "dur": 2.233, + "args": { + "External id": 4555902,"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": 1336753, "tid": 1381210, + "ts": 1696942784085.385, "dur": 1.168, + "args": { + "External id": 4555903,"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": 1336753, "tid": 1381210, + "ts": 1696942784085.752, "dur": 0.736, + "args": { + "External id": 4555904,"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": 1336753, "tid": 1381210, + "ts": 1696942784090.541, "dur": 6.354, + "args": { + "External id": 4555905,"Record function id": 0, "Ev Idx": 4224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942784091.590, "dur": 4.841, + "args": { + "External id": 4555906,"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": 1336753, "tid": 1381210, + "ts": 1696942784092.100, "dur": 3.851, + "args": { + "External id": 4555907,"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": 1336753, "tid": 1381210, + "ts": 1696942784094.907, "dur": 0.955, + "args": { + "External id": 4555908,"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": 1336753, "tid": 1381210, + "ts": 1696942784100.064, "dur": 6.546, + "args": { + "External id": 4555909,"Record function id": 0, "Ev Idx": 4228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942784101.278, "dur": 4.915, + "args": { + "External id": 4555910,"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": 1336753, "tid": 1381210, + "ts": 1696942784102.177, "dur": 3.584, + "args": { + "External id": 4555911,"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": 1336753, "tid": 1381210, + "ts": 1696942784102.866, "dur": 2.815, + "args": { + "External id": 4555912,"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": 1336753, "tid": 1381210, + "ts": 1696942784110.540, "dur": 36906.558, + "args": { + "External id": 4555913,"Record function id": 0, "Sequence number": 45295605, "Fwd thread id": 1, "Ev Idx": 4232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942784111.684, "dur": 36864.080, + "args": { + "External id": 4555914,"Sequence number": 45295605, "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": 1336753, "tid": 1381210, "ts": 1696942784111.684, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1696942784146.572, "dur": 41.007, + "args": { + "External id": 4555915,"Record function id": 0, "Ev Idx": 4234 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1696942784195.290, "dur": 69.660, + "args": { + "External id": 4555916,"Record function id": 0, "Ev Idx": 4235 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1696942784271.392, "dur": 36695.666, + "args": { + "External id": 4555917,"Record function id": 0, "Ev Idx": 4236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942784364.679, "dur": 7.422, + "args": { + "External id": 4555918,"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": 1336753, "tid": 1381210, + "ts": 1696942784381.429, "dur": 4.733, + "args": { + "External id": 4555919,"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": 1336753, "tid": 1381210, + "ts": 1696942784402.241, "dur": 35787.733, + "args": { + "External id": 4555920,"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": 1336753, "tid": 1381210, + "ts": 1696942784416.407, "dur": 35763.972, + "args": { + "External id": 4555921,"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": 1336753, "tid": 1381210, + "ts": 1696942784467.813, "dur": 13.433, + "args": { + "External id": 4555922,"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": 1336753, "tid": 1381210, + "ts": 1696942784490.640, "dur": 35652.494, + "args": { + "External id": 4555923,"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": 1336753, "tid": 1381210, + "ts": 1696942784492.933, "dur": 35649.373, + "args": { + "External id": 4555924,"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": 1336753, "tid": 1381210, + "ts": 1696942784497.252, "dur": 5.978, + "args": { + "External id": 4555925,"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": 1336753, "tid": 1381210, + "ts": 1696942784504.864, "dur": 35633.756, + "args": { + "External id": 4555926,"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": 1336753, "tid": 1381210, + "ts": 1696942820278.193, "dur": 8.994, + "args": { + "External id": 4555927,"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": 1336753, "tid": 1381210, + "ts": 1696942820281.579, "dur": 5.283, + "args": { + "External id": 4555928,"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": 1336753, "tid": 1381210, + "ts": 1696942820316.563, "dur": 356.617, + "args": { + "External id": 4555929,"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": 1336753, "tid": 1381210, + "ts": 1696942820348.050, "dur": 319.949, + "args": { + "External id": 4555930,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942820358.183, "dur": 303.745, + "args": { + "External id": 4555931,"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": 1336753, "tid": 1381210, + "ts": 1696942820696.727, "dur": 2.965, + "args": { + "External id": 4555932,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942820760.388, "dur": 7.093, + "args": { + "External id": 4555933,"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": 1336753, "tid": 1381210, + "ts": 1696942820810.288, "dur": 3.498, + "args": { + "External id": 4555934,"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": 1336753, "tid": 1381210, + "ts": 1696942820829.940, "dur": 1.324, + "args": { + "External id": 4555935,"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": 1336753, "tid": 1381210, + "ts": 1696942820843.551, "dur": 0.939, + "args": { + "External id": 4555936,"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": 1336753, "tid": 1381210, + "ts": 1696942820854.798, "dur": 0.746, + "args": { + "External id": 4555937,"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": 1336753, "tid": 1381210, + "ts": 1696942820865.106, "dur": 2.791, + "args": { + "External id": 4555938,"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": 1336753, "tid": 1381210, + "ts": 1696942820881.199, "dur": 0.837, + "args": { + "External id": 4555939,"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": 1336753, "tid": 1381210, + "ts": 1696942820893.055, "dur": 1.158, + "args": { + "External id": 4555940,"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": 1336753, "tid": 1381210, + "ts": 1696942820904.103, "dur": 0.905, + "args": { + "External id": 4555941,"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": 1336753, "tid": 1381210, + "ts": 1696942821035.128, "dur": 2773.234, + "args": { + "External id": 4555942,"Record function id": 0, "Ev Idx": 4261 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1696942821057.859, "dur": 1080.278, + "args": { + "External id": 4555943,"Record function id": 0, "Ev Idx": 4262 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1696942821072.549, "dur": 338.297, + "args": { + "External id": 4555944,"Record function id": 0, "Ev Idx": 4263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942821162.090, "dur": 6.598, + "args": { + "External id": 4555945,"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": 1336753, "tid": 1381210, + "ts": 1696942821172.153, "dur": 1.403, + "args": { + "External id": 4555946,"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": 1336753, "tid": 1381210, + "ts": 1696942821177.208, "dur": 1.456, + "args": { + "External id": 4555947,"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": 1336753, "tid": 1381210, + "ts": 1696942821180.276, "dur": 1.115, + "args": { + "External id": 4555948,"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": 1336753, "tid": 1381210, + "ts": 1696942821183.077, "dur": 1.040, + "args": { + "External id": 4555949,"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": 1336753, "tid": 1381210, + "ts": 1696942821185.633, "dur": 1.142, + "args": { + "External id": 4555950,"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": 1336753, "tid": 1381210, + "ts": 1696942821190.256, "dur": 1.415, + "args": { + "External id": 4555951,"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": 1336753, "tid": 1381210, + "ts": 1696942821193.003, "dur": 1.178, + "args": { + "External id": 4555952,"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": 1336753, "tid": 1381210, + "ts": 1696942821195.828, "dur": 3.063, + "args": { + "External id": 4555953,"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": 1336753, "tid": 1381210, + "ts": 1696942821200.269, "dur": 1.196, + "args": { + "External id": 4555954,"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": 1336753, "tid": 1381210, + "ts": 1696942821226.132, "dur": 155.162, + "args": { + "External id": 4555955,"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": 1336753, "tid": 1381210, + "ts": 1696942821244.179, "dur": 132.181, + "args": { + "External id": 4555956,"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": 1336753, "tid": 1381210, + "ts": 1696942821264.688, "dur": 13.387, + "args": { + "External id": 4555957,"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": 1336753, "tid": 1381210, + "ts": 1696942821281.057, "dur": 68.238, + "args": { + "External id": 4555958,"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": 1336753, "tid": 1381210, + "ts": 1696942821283.686, "dur": 65.199, + "args": { + "External id": 4555959,"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": 1336753, "tid": 1381210, + "ts": 1696942821287.720, "dur": 5.695, + "args": { + "External id": 4555960,"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": 1336753, "tid": 1381210, + "ts": 1696942821296.675, "dur": 51.458, + "args": { + "External id": 4555961,"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": 1336753, "tid": 1381210, + "ts": 1696942821507.979, "dur": 618.903, + "args": { + "External id": 4555962,"Record function id": 0, "Ev Idx": 4281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1696942821523.717, "dur": 590.789, + "args": { + "External id": 4555963,"Record function id": 0, "Ev Idx": 4282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942821605.787, "dur": 9.530, + "args": { + "External id": 4555964,"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": 1336753, "tid": 1381210, + "ts": 1696942821631.537, "dur": 33.430, + "args": { + "External id": 4555965,"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": 1336753, "tid": 1381210, + "ts": 1696942821637.057, "dur": 1.572, + "args": { + "External id": 4555966,"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": 1336753, "tid": 1381210, + "ts": 1696942821640.883, "dur": 0.675, + "args": { + "External id": 4555967,"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": 1336753, "tid": 1381210, + "ts": 1696942821643.602, "dur": 0.652, + "args": { + "External id": 4555968,"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": 1336753, "tid": 1381210, + "ts": 1696942821645.830, "dur": 2.346, + "args": { + "External id": 4555969,"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": 1336753, "tid": 1381210, + "ts": 1696942821649.462, "dur": 0.542, + "args": { + "External id": 4555970,"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": 1336753, "tid": 1381210, + "ts": 1696942821652.123, "dur": 0.389, + "args": { + "External id": 4555971,"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": 1336753, "tid": 1381210, + "ts": 1696942821654.038, "dur": 0.330, + "args": { + "External id": 4555972,"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": 1336753, "tid": 1381210, + "ts": 1696942821655.771, "dur": 0.990, + "args": { + "External id": 4555973,"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": 1336753, "tid": 1381210, + "ts": 1696942821658.207, "dur": 0.522, + "args": { + "External id": 4555974,"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": 1336753, "tid": 1381210, + "ts": 1696942821678.929, "dur": 32.510, + "args": { + "External id": 4555975,"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": 1336753, "tid": 1381210, + "ts": 1696942821742.901, "dur": 101.865, + "args": { + "External id": 4555976,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942821752.264, "dur": 2.987, + "args": { + "External id": 4555977,"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": 1336753, "tid": 1381210, + "ts": 1696942821760.457, "dur": 10.227, + "args": { + "External id": 4555978,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942821764.581, "dur": 5.670, + "args": { + "External id": 4555979,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942821768.448, "dur": 0.579, + "args": { + "External id": 4555980,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942821777.557, "dur": 28.747, + "args": { + "External id": 4555981,"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": 1336753, "tid": 1381210, + "ts": 1696942821780.057, "dur": 2.619, + "args": { + "External id": 4555982,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942821784.291, "dur": 0.924, + "args": { + "External id": 4555983,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942821786.824, "dur": 0.542, + "args": { + "External id": 4555984,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942821789.009, "dur": 0.377, + "args": { + "External id": 4555985,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942821790.989, "dur": 0.438, + "args": { + "External id": 4555986,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942821792.884, "dur": 0.588, + "args": { + "External id": 4555987,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942821794.749, "dur": 0.271, + "args": { + "External id": 4555988,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942821796.215, "dur": 0.304, + "args": { + "External id": 4555989,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942821797.890, "dur": 2.590, + "args": { + "External id": 4555990,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942821818.893, "dur": 18.882, + "args": { + "External id": 4555991,"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": 1336753, "tid": 1381210, + "ts": 1696942821889.404, "dur": 150.894, + "args": { + "External id": 4555992,"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": 1336753, "tid": 1381210, + "ts": 1696942821918.496, "dur": 117.760, + "args": { + "External id": 4555993,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942821927.626, "dur": 103.861, + "args": { + "External id": 4555994,"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": 1336753, "tid": 1381210, + "ts": 1696942822059.016, "dur": 2.035, + "args": { + "External id": 4555995,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942822145.235, "dur": 1643.689, + "args": { + "External id": 4555996,"Sequence number": 45295604, "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": 1336753, "tid": 1381210, "ts": 1696942822145.235, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942822256.066, "dur": 103.768, + "args": { + "External id": 4555997,"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": 1336753, "tid": 1381210, + "ts": 1696942822401.650, "dur": 40.278, + "args": { + "External id": 4555998,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942822460.043, "dur": 46.920, + "args": { + "External id": 4555999,"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": 1336753, "tid": 1381210, + "ts": 1696942822516.380, "dur": 51.272, + "args": { + "External id": 4556000,"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": 1336753, "tid": 1381210, + "ts": 1696942822577.059, "dur": 47.304, + "args": { + "External id": 4556001,"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": 1336753, "tid": 1381210, + "ts": 1696942822634.743, "dur": 26.487, + "args": { + "External id": 4556002,"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": 1336753, "tid": 1381210, + "ts": 1696942822671.213, "dur": 44.190, + "args": { + "External id": 4556003,"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": 1336753, "tid": 1381210, + "ts": 1696942822739.618, "dur": 24.868, + "args": { + "External id": 4556004,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942822788.782, "dur": 27.626, + "args": { + "External id": 4556005,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942822841.161, "dur": 17.938, + "args": { + "External id": 4556006,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942822874.859, "dur": 14.416, + "args": { + "External id": 4556007,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942822899.841, "dur": 27.660, + "args": { + "External id": 4556008,"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": 1336753, "tid": 1381210, + "ts": 1696942822930.572, "dur": 31.929, + "args": { + "External id": 4556009,"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": 1336753, "tid": 1381210, + "ts": 1696942823024.822, "dur": 171.749, + "args": { + "External id": 4556010,"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": 1336753, "tid": 1381210, + "ts": 1696942823101.824, "dur": 5.969, + "args": { + "External id": 4556011,"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": 1336753, "tid": 1381210, + "ts": 1696942823110.422, "dur": 3.155, + "args": { + "External id": 4556012,"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": 1336753, "tid": 1381210, + "ts": 1696942823239.773, "dur": 25.208, + "args": { + "External id": 4556013,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942823280.143, "dur": 15.184, + "args": { + "External id": 4556014,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942823302.999, "dur": 37.529, + "args": { + "External id": 4556015,"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": 1336753, "tid": 1381210, + "ts": 1696942823348.022, "dur": 34.654, + "args": { + "External id": 4556016,"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": 1336753, "tid": 1381210, + "ts": 1696942823389.096, "dur": 19.155, + "args": { + "External id": 4556017,"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": 1336753, "tid": 1381210, + "ts": 1696942823422.808, "dur": 30.324, + "args": { + "External id": 4556018,"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": 1336753, "tid": 1381210, + "ts": 1696942823458.389, "dur": 33.561, + "args": { + "External id": 4556019,"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": 1336753, "tid": 1381210, + "ts": 1696942823508.450, "dur": 50.922, + "args": { + "External id": 4556020,"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": 1336753, "tid": 1381210, + "ts": 1696942823586.264, "dur": 26.138, + "args": { + "External id": 4556021,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942823631.694, "dur": 27.651, + "args": { + "External id": 4556022,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942823677.064, "dur": 16.761, + "args": { + "External id": 4556023,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942823712.162, "dur": 17.538, + "args": { + "External id": 4556024,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942823742.609, "dur": 15.845, + "args": { + "External id": 4556025,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942823833.887, "dur": 16.500, + "args": { + "External id": 4556026,"Record function id": 0, "Ev Idx": 4345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942823836.910, "dur": 12.449, + "args": { + "External id": 4556027,"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": 1336753, "tid": 1381210, + "ts": 1696942823841.275, "dur": 7.248, + "args": { + "External id": 4556028,"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": 1336753, "tid": 1381210, + "ts": 1696942823842.783, "dur": 5.624, + "args": { + "External id": 4556029,"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": 1336753, "tid": 1381210, + "ts": 1696942823854.303, "dur": 5.568, + "args": { + "External id": 4556030,"Record function id": 0, "Ev Idx": 4349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942823855.782, "dur": 3.634, + "args": { + "External id": 4556031,"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": 1336753, "tid": 1381210, + "ts": 1696942823857.230, "dur": 1.707, + "args": { + "External id": 4556032,"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": 1336753, "tid": 1381210, + "ts": 1696942823858.154, "dur": 0.706, + "args": { + "External id": 4556033,"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": 1336753, "tid": 1381210, + "ts": 1696942823863.232, "dur": 4.881, + "args": { + "External id": 4556034,"Record function id": 0, "Ev Idx": 4353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942823864.670, "dur": 3.013, + "args": { + "External id": 4556035,"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": 1336753, "tid": 1381210, + "ts": 1696942823865.573, "dur": 1.651, + "args": { + "External id": 4556036,"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": 1336753, "tid": 1381210, + "ts": 1696942823866.489, "dur": 0.643, + "args": { + "External id": 4556037,"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": 1336753, "tid": 1381210, + "ts": 1696942823871.324, "dur": 4.582, + "args": { + "External id": 4556038,"Record function id": 0, "Ev Idx": 4357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942823872.796, "dur": 2.724, + "args": { + "External id": 4556039,"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": 1336753, "tid": 1381210, + "ts": 1696942823873.641, "dur": 1.430, + "args": { + "External id": 4556040,"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": 1336753, "tid": 1381210, + "ts": 1696942823874.324, "dur": 0.663, + "args": { + "External id": 4556041,"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": 1336753, "tid": 1381210, + "ts": 1696942823879.094, "dur": 3.688, + "args": { + "External id": 4556042,"Record function id": 0, "Ev Idx": 4361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942823880.346, "dur": 2.033, + "args": { + "External id": 4556043,"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": 1336753, "tid": 1381210, + "ts": 1696942823880.926, "dur": 1.031, + "args": { + "External id": 4556044,"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": 1336753, "tid": 1381210, + "ts": 1696942823881.298, "dur": 0.589, + "args": { + "External id": 4556045,"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": 1336753, "tid": 1381210, + "ts": 1696942823885.981, "dur": 6.359, + "args": { + "External id": 4556046,"Record function id": 0, "Ev Idx": 4365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942823887.137, "dur": 4.817, + "args": { + "External id": 4556047,"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": 1336753, "tid": 1381210, + "ts": 1696942823887.565, "dur": 1.202, + "args": { + "External id": 4556048,"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": 1336753, "tid": 1381210, + "ts": 1696942823888.026, "dur": 0.680, + "args": { + "External id": 4556049,"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": 1336753, "tid": 1381210, + "ts": 1696942823895.753, "dur": 3.693, + "args": { + "External id": 4556050,"Record function id": 0, "Ev Idx": 4369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942823896.983, "dur": 2.044, + "args": { + "External id": 4556051,"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": 1336753, "tid": 1381210, + "ts": 1696942823897.436, "dur": 0.930, + "args": { + "External id": 4556052,"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": 1336753, "tid": 1381210, + "ts": 1696942823897.697, "dur": 0.606, + "args": { + "External id": 4556053,"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": 1336753, "tid": 1381210, + "ts": 1696942823902.511, "dur": 7.987, + "args": { + "External id": 4556054,"Record function id": 0, "Ev Idx": 4373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942823903.754, "dur": 6.338, + "args": { + "External id": 4556055,"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": 1336753, "tid": 1381210, + "ts": 1696942823904.716, "dur": 4.914, + "args": { + "External id": 4556056,"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": 1336753, "tid": 1381210, + "ts": 1696942823907.283, "dur": 2.284, + "args": { + "External id": 4556057,"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": 1336753, "tid": 1381210, + "ts": 1696942823913.627, "dur": 4.208, + "args": { + "External id": 4556058,"Record function id": 0, "Ev Idx": 4377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942823914.978, "dur": 2.449, + "args": { + "External id": 4556059,"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": 1336753, "tid": 1381210, + "ts": 1696942823915.533, "dur": 1.220, + "args": { + "External id": 4556060,"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": 1336753, "tid": 1381210, + "ts": 1696942823915.836, "dur": 0.851, + "args": { + "External id": 4556061,"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": 1336753, "tid": 1381210, + "ts": 1696942823922.029, "dur": 36514.008, + "args": { + "External id": 4556062,"Record function id": 0, "Sequence number": 45295603, "Fwd thread id": 1, "Ev Idx": 4381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942823923.982, "dur": 36503.293, + "args": { + "External id": 4556063,"Sequence number": 45295603, "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": 1336753, "tid": 1381210, "ts": 1696942823923.982, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1696942823952.326, "dur": 75.010, + "args": { + "External id": 4556064,"Record function id": 0, "Ev Idx": 4383 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1696942824036.973, "dur": 67.278, + "args": { + "External id": 4556065,"Record function id": 0, "Ev Idx": 4384 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1696942824110.501, "dur": 36309.484, + "args": { + "External id": 4556066,"Record function id": 0, "Ev Idx": 4385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942824199.195, "dur": 10.320, + "args": { + "External id": 4556067,"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": 1336753, "tid": 1381210, + "ts": 1696942824219.543, "dur": 5.566, + "args": { + "External id": 4556068,"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": 1336753, "tid": 1381210, + "ts": 1696942824240.721, "dur": 35356.023, + "args": { + "External id": 4556069,"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": 1336753, "tid": 1381210, + "ts": 1696942824255.047, "dur": 35333.101, + "args": { + "External id": 4556070,"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": 1336753, "tid": 1381210, + "ts": 1696942824306.590, "dur": 14.167, + "args": { + "External id": 4556071,"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": 1336753, "tid": 1381210, + "ts": 1696942824327.120, "dur": 35222.635, + "args": { + "External id": 4556072,"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": 1336753, "tid": 1381210, + "ts": 1696942824330.542, "dur": 35218.608, + "args": { + "External id": 4556073,"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": 1336753, "tid": 1381210, + "ts": 1696942824334.660, "dur": 5.169, + "args": { + "External id": 4556074,"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": 1336753, "tid": 1381210, + "ts": 1696942824341.728, "dur": 35203.627, + "args": { + "External id": 4556075,"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": 1336753, "tid": 1381210, + "ts": 1696942859679.573, "dur": 8.688, + "args": { + "External id": 4556076,"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": 1336753, "tid": 1381210, + "ts": 1696942859682.526, "dur": 5.359, + "args": { + "External id": 4556077,"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": 1336753, "tid": 1381210, + "ts": 1696942859721.433, "dur": 400.191, + "args": { + "External id": 4556078,"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": 1336753, "tid": 1381210, + "ts": 1696942859756.219, "dur": 359.901, + "args": { + "External id": 4556079,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942859767.159, "dur": 343.149, + "args": { + "External id": 4556080,"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": 1336753, "tid": 1381210, + "ts": 1696942860149.721, "dur": 2.556, + "args": { + "External id": 4556081,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942860213.058, "dur": 7.430, + "args": { + "External id": 4556082,"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": 1336753, "tid": 1381210, + "ts": 1696942860265.485, "dur": 1.487, + "args": { + "External id": 4556083,"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": 1336753, "tid": 1381210, + "ts": 1696942860281.972, "dur": 1.868, + "args": { + "External id": 4556084,"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": 1336753, "tid": 1381210, + "ts": 1696942860296.906, "dur": 1.238, + "args": { + "External id": 4556085,"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": 1336753, "tid": 1381210, + "ts": 1696942860310.394, "dur": 1.036, + "args": { + "External id": 4556086,"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": 1336753, "tid": 1381210, + "ts": 1696942860323.015, "dur": 0.817, + "args": { + "External id": 4556087,"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": 1336753, "tid": 1381210, + "ts": 1696942860334.398, "dur": 0.944, + "args": { + "External id": 4556088,"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": 1336753, "tid": 1381210, + "ts": 1696942860345.530, "dur": 0.923, + "args": { + "External id": 4556089,"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": 1336753, "tid": 1381210, + "ts": 1696942860357.594, "dur": 1.200, + "args": { + "External id": 4556090,"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": 1336753, "tid": 1381210, + "ts": 1696942860450.352, "dur": 2766.107, + "args": { + "External id": 4556091,"Record function id": 0, "Ev Idx": 4410 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1696942860470.327, "dur": 1080.161, + "args": { + "External id": 4556092,"Record function id": 0, "Ev Idx": 4411 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1696942860484.093, "dur": 344.815, + "args": { + "External id": 4556093,"Record function id": 0, "Ev Idx": 4412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942860589.583, "dur": 4.775, + "args": { + "External id": 4556094,"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": 1336753, "tid": 1381210, + "ts": 1696942860598.169, "dur": 1.185, + "args": { + "External id": 4556095,"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": 1336753, "tid": 1381210, + "ts": 1696942860601.378, "dur": 1.174, + "args": { + "External id": 4556096,"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": 1336753, "tid": 1381210, + "ts": 1696942860604.562, "dur": 0.863, + "args": { + "External id": 4556097,"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": 1336753, "tid": 1381210, + "ts": 1696942860609.038, "dur": 0.768, + "args": { + "External id": 4556098,"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": 1336753, "tid": 1381210, + "ts": 1696942860611.554, "dur": 0.914, + "args": { + "External id": 4556099,"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": 1336753, "tid": 1381210, + "ts": 1696942860617.274, "dur": 1.124, + "args": { + "External id": 4556100,"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": 1336753, "tid": 1381210, + "ts": 1696942860619.804, "dur": 3.357, + "args": { + "External id": 4556101,"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": 1336753, "tid": 1381210, + "ts": 1696942860626.167, "dur": 1.175, + "args": { + "External id": 4556102,"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": 1336753, "tid": 1381210, + "ts": 1696942860629.065, "dur": 0.902, + "args": { + "External id": 4556103,"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": 1336753, "tid": 1381210, + "ts": 1696942860649.767, "dur": 150.640, + "args": { + "External id": 4556104,"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": 1336753, "tid": 1381210, + "ts": 1696942860667.091, "dur": 128.616, + "args": { + "External id": 4556105,"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": 1336753, "tid": 1381210, + "ts": 1696942860687.346, "dur": 12.170, + "args": { + "External id": 4556106,"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": 1336753, "tid": 1381210, + "ts": 1696942860702.154, "dur": 67.279, + "args": { + "External id": 4556107,"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": 1336753, "tid": 1381210, + "ts": 1696942860705.912, "dur": 63.200, + "args": { + "External id": 4556108,"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": 1336753, "tid": 1381210, + "ts": 1696942860709.957, "dur": 5.485, + "args": { + "External id": 4556109,"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": 1336753, "tid": 1381210, + "ts": 1696942860718.551, "dur": 49.962, + "args": { + "External id": 4556110,"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": 1336753, "tid": 1381210, + "ts": 1696942860923.499, "dur": 600.362, + "args": { + "External id": 4556111,"Record function id": 0, "Ev Idx": 4430 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1696942860939.193, "dur": 572.767, + "args": { + "External id": 4556112,"Record function id": 0, "Ev Idx": 4431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942861041.506, "dur": 6.263, + "args": { + "External id": 4556113,"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": 1336753, "tid": 1381210, + "ts": 1696942861064.654, "dur": 33.982, + "args": { + "External id": 4556114,"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": 1336753, "tid": 1381210, + "ts": 1696942861069.793, "dur": 1.631, + "args": { + "External id": 4556115,"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": 1336753, "tid": 1381210, + "ts": 1696942861074.845, "dur": 0.474, + "args": { + "External id": 4556116,"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": 1336753, "tid": 1381210, + "ts": 1696942861077.030, "dur": 2.467, + "args": { + "External id": 4556117,"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": 1336753, "tid": 1381210, + "ts": 1696942861081.043, "dur": 0.739, + "args": { + "External id": 4556118,"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": 1336753, "tid": 1381210, + "ts": 1696942861083.857, "dur": 0.538, + "args": { + "External id": 4556119,"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": 1336753, "tid": 1381210, + "ts": 1696942861085.922, "dur": 0.828, + "args": { + "External id": 4556120,"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": 1336753, "tid": 1381210, + "ts": 1696942861088.415, "dur": 0.923, + "args": { + "External id": 4556121,"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": 1336753, "tid": 1381210, + "ts": 1696942861091.095, "dur": 0.411, + "args": { + "External id": 4556122,"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": 1336753, "tid": 1381210, + "ts": 1696942861093.253, "dur": 0.528, + "args": { + "External id": 4556123,"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": 1336753, "tid": 1381210, + "ts": 1696942861109.132, "dur": 33.571, + "args": { + "External id": 4556124,"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": 1336753, "tid": 1381210, + "ts": 1696942861175.491, "dur": 104.019, + "args": { + "External id": 4556125,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942861185.924, "dur": 3.093, + "args": { + "External id": 4556126,"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": 1336753, "tid": 1381210, + "ts": 1696942861194.186, "dur": 11.437, + "args": { + "External id": 4556127,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942861198.446, "dur": 6.737, + "args": { + "External id": 4556128,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942861201.838, "dur": 2.225, + "args": { + "External id": 4556129,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942861212.852, "dur": 26.000, + "args": { + "External id": 4556130,"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": 1336753, "tid": 1381210, + "ts": 1696942861214.818, "dur": 1.491, + "args": { + "External id": 4556131,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942861217.720, "dur": 0.499, + "args": { + "External id": 4556132,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942861219.866, "dur": 0.382, + "args": { + "External id": 4556133,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942861223.036, "dur": 0.432, + "args": { + "External id": 4556134,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942861225.285, "dur": 0.616, + "args": { + "External id": 4556135,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942861227.374, "dur": 0.485, + "args": { + "External id": 4556136,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942861230.356, "dur": 0.362, + "args": { + "External id": 4556137,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942861232.026, "dur": 1.950, + "args": { + "External id": 4556138,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942861235.452, "dur": 0.827, + "args": { + "External id": 4556139,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942861253.054, "dur": 19.473, + "args": { + "External id": 4556140,"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": 1336753, "tid": 1381210, + "ts": 1696942861328.644, "dur": 116.542, + "args": { + "External id": 4556141,"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": 1336753, "tid": 1381210, + "ts": 1696942861361.066, "dur": 80.678, + "args": { + "External id": 4556142,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942861370.622, "dur": 66.601, + "args": { + "External id": 4556143,"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": 1336753, "tid": 1381210, + "ts": 1696942861461.123, "dur": 1.750, + "args": { + "External id": 4556144,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942861562.662, "dur": 1632.034, + "args": { + "External id": 4556145,"Sequence number": 45295602, "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": 1336753, "tid": 1381210, "ts": 1696942861562.662, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942861672.893, "dur": 102.973, + "args": { + "External id": 4556146,"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": 1336753, "tid": 1381210, + "ts": 1696942861816.626, "dur": 37.208, + "args": { + "External id": 4556147,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942861871.417, "dur": 46.518, + "args": { + "External id": 4556148,"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": 1336753, "tid": 1381210, + "ts": 1696942861927.356, "dur": 30.360, + "args": { + "External id": 4556149,"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": 1336753, "tid": 1381210, + "ts": 1696942861963.538, "dur": 84.856, + "args": { + "External id": 4556150,"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": 1336753, "tid": 1381210, + "ts": 1696942862059.145, "dur": 30.879, + "args": { + "External id": 4556151,"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": 1336753, "tid": 1381210, + "ts": 1696942862099.248, "dur": 41.287, + "args": { + "External id": 4556152,"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": 1336753, "tid": 1381210, + "ts": 1696942862165.726, "dur": 26.780, + "args": { + "External id": 4556153,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942862212.189, "dur": 29.057, + "args": { + "External id": 4556154,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942862261.038, "dur": 17.846, + "args": { + "External id": 4556155,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942862294.415, "dur": 14.345, + "args": { + "External id": 4556156,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942862318.245, "dur": 29.336, + "args": { + "External id": 4556157,"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": 1336753, "tid": 1381210, + "ts": 1696942862350.917, "dur": 33.569, + "args": { + "External id": 4556158,"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": 1336753, "tid": 1381210, + "ts": 1696942862411.735, "dur": 191.076, + "args": { + "External id": 4556159,"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": 1336753, "tid": 1381210, + "ts": 1696942862487.083, "dur": 5.812, + "args": { + "External id": 4556160,"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": 1336753, "tid": 1381210, + "ts": 1696942862495.000, "dur": 2.071, + "args": { + "External id": 4556161,"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": 1336753, "tid": 1381210, + "ts": 1696942862641.295, "dur": 23.456, + "args": { + "External id": 4556162,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942862676.334, "dur": 14.359, + "args": { + "External id": 4556163,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942862700.231, "dur": 42.971, + "args": { + "External id": 4556164,"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": 1336753, "tid": 1381210, + "ts": 1696942862748.195, "dur": 36.795, + "args": { + "External id": 4556165,"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": 1336753, "tid": 1381210, + "ts": 1696942862791.340, "dur": 19.423, + "args": { + "External id": 4556166,"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": 1336753, "tid": 1381210, + "ts": 1696942862818.078, "dur": 28.487, + "args": { + "External id": 4556167,"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": 1336753, "tid": 1381210, + "ts": 1696942862853.357, "dur": 18.605, + "args": { + "External id": 4556168,"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": 1336753, "tid": 1381210, + "ts": 1696942862879.679, "dur": 28.848, + "args": { + "External id": 4556169,"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": 1336753, "tid": 1381210, + "ts": 1696942862939.858, "dur": 25.563, + "args": { + "External id": 4556170,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942863037.921, "dur": 26.513, + "args": { + "External id": 4556171,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942863083.998, "dur": 18.941, + "args": { + "External id": 4556172,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942863122.815, "dur": 13.373, + "args": { + "External id": 4556173,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942863148.816, "dur": 15.679, + "args": { + "External id": 4556174,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942863239.251, "dur": 14.668, + "args": { + "External id": 4556175,"Record function id": 0, "Ev Idx": 4494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942863242.183, "dur": 10.885, + "args": { + "External id": 4556176,"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": 1336753, "tid": 1381210, + "ts": 1696942863246.396, "dur": 5.550, + "args": { + "External id": 4556177,"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": 1336753, "tid": 1381210, + "ts": 1696942863247.811, "dur": 4.027, + "args": { + "External id": 4556178,"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": 1336753, "tid": 1381210, + "ts": 1696942863258.010, "dur": 5.056, + "args": { + "External id": 4556179,"Record function id": 0, "Ev Idx": 4498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942863259.574, "dur": 3.076, + "args": { + "External id": 4556180,"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": 1336753, "tid": 1381210, + "ts": 1696942863260.777, "dur": 1.386, + "args": { + "External id": 4556181,"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": 1336753, "tid": 1381210, + "ts": 1696942863261.197, "dur": 0.874, + "args": { + "External id": 4556182,"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": 1336753, "tid": 1381210, + "ts": 1696942863266.617, "dur": 4.956, + "args": { + "External id": 4556183,"Record function id": 0, "Ev Idx": 4502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942863268.145, "dur": 3.010, + "args": { + "External id": 4556184,"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": 1336753, "tid": 1381210, + "ts": 1696942863268.889, "dur": 1.524, + "args": { + "External id": 4556185,"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": 1336753, "tid": 1381210, + "ts": 1696942863269.427, "dur": 0.874, + "args": { + "External id": 4556186,"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": 1336753, "tid": 1381210, + "ts": 1696942863274.763, "dur": 4.584, + "args": { + "External id": 4556187,"Record function id": 0, "Ev Idx": 4506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942863275.971, "dur": 2.980, + "args": { + "External id": 4556188,"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": 1336753, "tid": 1381210, + "ts": 1696942863276.743, "dur": 1.546, + "args": { + "External id": 4556189,"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": 1336753, "tid": 1381210, + "ts": 1696942863277.142, "dur": 1.051, + "args": { + "External id": 4556190,"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": 1336753, "tid": 1381210, + "ts": 1696942863282.489, "dur": 5.068, + "args": { + "External id": 4556191,"Record function id": 0, "Ev Idx": 4510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942863284.069, "dur": 3.080, + "args": { + "External id": 4556192,"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": 1336753, "tid": 1381210, + "ts": 1696942863285.311, "dur": 1.427, + "args": { + "External id": 4556193,"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": 1336753, "tid": 1381210, + "ts": 1696942863285.780, "dur": 0.860, + "args": { + "External id": 4556194,"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": 1336753, "tid": 1381210, + "ts": 1696942863290.871, "dur": 3.717, + "args": { + "External id": 4556195,"Record function id": 0, "Ev Idx": 4514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942863292.062, "dur": 2.116, + "args": { + "External id": 4556196,"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": 1336753, "tid": 1381210, + "ts": 1696942863292.514, "dur": 1.186, + "args": { + "External id": 4556197,"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": 1336753, "tid": 1381210, + "ts": 1696942863292.937, "dur": 0.667, + "args": { + "External id": 4556198,"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": 1336753, "tid": 1381210, + "ts": 1696942863297.833, "dur": 8.045, + "args": { + "External id": 4556199,"Record function id": 0, "Ev Idx": 4518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942863298.841, "dur": 6.633, + "args": { + "External id": 4556200,"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": 1336753, "tid": 1381210, + "ts": 1696942863299.291, "dur": 5.436, + "args": { + "External id": 4556201,"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": 1336753, "tid": 1381210, + "ts": 1696942863301.797, "dur": 2.846, + "args": { + "External id": 4556202,"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": 1336753, "tid": 1381210, + "ts": 1696942863309.014, "dur": 4.421, + "args": { + "External id": 4556203,"Record function id": 0, "Ev Idx": 4522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942863310.522, "dur": 2.525, + "args": { + "External id": 4556204,"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": 1336753, "tid": 1381210, + "ts": 1696942863311.010, "dur": 1.611, + "args": { + "External id": 4556205,"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": 1336753, "tid": 1381210, + "ts": 1696942863311.479, "dur": 1.048, + "args": { + "External id": 4556206,"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": 1336753, "tid": 1381210, + "ts": 1696942863316.456, "dur": 3.907, + "args": { + "External id": 4556207,"Record function id": 0, "Ev Idx": 4526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942863317.899, "dur": 2.025, + "args": { + "External id": 4556208,"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": 1336753, "tid": 1381210, + "ts": 1696942863318.598, "dur": 0.897, + "args": { + "External id": 4556209,"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": 1336753, "tid": 1381210, + "ts": 1696942863318.859, "dur": 0.541, + "args": { + "External id": 4556210,"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": 1336753, "tid": 1381210, + "ts": 1696942863324.547, "dur": 37437.244, + "args": { + "External id": 4556211,"Record function id": 0, "Sequence number": 45295601, "Fwd thread id": 1, "Ev Idx": 4530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942863326.920, "dur": 37426.656, + "args": { + "External id": 4556212,"Sequence number": 45295601, "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": 1336753, "tid": 1381210, "ts": 1696942863326.920, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1696942863356.112, "dur": 39.244, + "args": { + "External id": 4556213,"Record function id": 0, "Ev Idx": 4532 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1696942863403.366, "dur": 66.667, + "args": { + "External id": 4556214,"Record function id": 0, "Ev Idx": 4533 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1696942863475.808, "dur": 37268.792, + "args": { + "External id": 4556215,"Record function id": 0, "Ev Idx": 4534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942863581.324, "dur": 8.275, + "args": { + "External id": 4556216,"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": 1336753, "tid": 1381210, + "ts": 1696942863600.046, "dur": 5.538, + "args": { + "External id": 4556217,"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": 1336753, "tid": 1381210, + "ts": 1696942863622.236, "dur": 36253.662, + "args": { + "External id": 4556218,"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": 1336753, "tid": 1381210, + "ts": 1696942863635.984, "dur": 36231.368, + "args": { + "External id": 4556219,"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": 1336753, "tid": 1381210, + "ts": 1696942863688.203, "dur": 14.013, + "args": { + "External id": 4556220,"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": 1336753, "tid": 1381210, + "ts": 1696942863708.507, "dur": 36122.839, + "args": { + "External id": 4556221,"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": 1336753, "tid": 1381210, + "ts": 1696942863712.427, "dur": 36118.239, + "args": { + "External id": 4556222,"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": 1336753, "tid": 1381210, + "ts": 1696942863716.819, "dur": 4.969, + "args": { + "External id": 4556223,"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": 1336753, "tid": 1381210, + "ts": 1696942863723.721, "dur": 36103.280, + "args": { + "External id": 4556224,"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": 1336753, "tid": 1381210, + "ts": 1696942899961.956, "dur": 7.906, + "args": { + "External id": 4556225,"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": 1336753, "tid": 1381210, + "ts": 1696942899964.519, "dur": 5.014, + "args": { + "External id": 4556226,"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": 1336753, "tid": 1381210, + "ts": 1696942900026.695, "dur": 392.575, + "args": { + "External id": 4556227,"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": 1336753, "tid": 1381210, + "ts": 1696942900059.257, "dur": 355.389, + "args": { + "External id": 4556228,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942900075.987, "dur": 332.959, + "args": { + "External id": 4556229,"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": 1336753, "tid": 1381210, + "ts": 1696942900443.631, "dur": 2.683, + "args": { + "External id": 4556230,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942900508.411, "dur": 9.424, + "args": { + "External id": 4556231,"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": 1336753, "tid": 1381210, + "ts": 1696942900581.066, "dur": 2.108, + "args": { + "External id": 4556232,"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": 1336753, "tid": 1381210, + "ts": 1696942900598.882, "dur": 1.211, + "args": { + "External id": 4556233,"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": 1336753, "tid": 1381210, + "ts": 1696942900611.180, "dur": 1.127, + "args": { + "External id": 4556234,"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": 1336753, "tid": 1381210, + "ts": 1696942900628.238, "dur": 2.875, + "args": { + "External id": 4556235,"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": 1336753, "tid": 1381210, + "ts": 1696942900642.820, "dur": 0.721, + "args": { + "External id": 4556236,"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": 1336753, "tid": 1381210, + "ts": 1696942900653.442, "dur": 1.154, + "args": { + "External id": 4556237,"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": 1336753, "tid": 1381210, + "ts": 1696942900664.993, "dur": 1.173, + "args": { + "External id": 4556238,"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": 1336753, "tid": 1381210, + "ts": 1696942900677.611, "dur": 2.916, + "args": { + "External id": 4556239,"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": 1336753, "tid": 1381210, + "ts": 1696942900777.238, "dur": 2821.425, + "args": { + "External id": 4556240,"Record function id": 0, "Ev Idx": 4559 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1696942900798.607, "dur": 1100.468, + "args": { + "External id": 4556241,"Record function id": 0, "Ev Idx": 4560 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1696942900817.219, "dur": 370.565, + "args": { + "External id": 4556242,"Record function id": 0, "Ev Idx": 4561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942900901.314, "dur": 5.944, + "args": { + "External id": 4556243,"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": 1336753, "tid": 1381210, + "ts": 1696942900910.438, "dur": 1.085, + "args": { + "External id": 4556244,"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": 1336753, "tid": 1381210, + "ts": 1696942900913.530, "dur": 0.991, + "args": { + "External id": 4556245,"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": 1336753, "tid": 1381210, + "ts": 1696942900916.152, "dur": 0.938, + "args": { + "External id": 4556246,"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": 1336753, "tid": 1381210, + "ts": 1696942900920.252, "dur": 0.816, + "args": { + "External id": 4556247,"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": 1336753, "tid": 1381210, + "ts": 1696942900922.460, "dur": 0.969, + "args": { + "External id": 4556248,"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": 1336753, "tid": 1381210, + "ts": 1696942900925.285, "dur": 2.403, + "args": { + "External id": 4556249,"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": 1336753, "tid": 1381210, + "ts": 1696942900932.642, "dur": 1.184, + "args": { + "External id": 4556250,"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": 1336753, "tid": 1381210, + "ts": 1696942900937.457, "dur": 0.940, + "args": { + "External id": 4556251,"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": 1336753, "tid": 1381210, + "ts": 1696942900940.139, "dur": 0.745, + "args": { + "External id": 4556252,"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": 1336753, "tid": 1381210, + "ts": 1696942900959.288, "dur": 196.018, + "args": { + "External id": 4556253,"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": 1336753, "tid": 1381210, + "ts": 1696942900976.133, "dur": 174.019, + "args": { + "External id": 4556254,"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": 1336753, "tid": 1381210, + "ts": 1696942901034.866, "dur": 13.251, + "args": { + "External id": 4556255,"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": 1336753, "tid": 1381210, + "ts": 1696942901051.210, "dur": 69.175, + "args": { + "External id": 4556256,"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": 1336753, "tid": 1381210, + "ts": 1696942901055.756, "dur": 64.227, + "args": { + "External id": 4556257,"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": 1336753, "tid": 1381210, + "ts": 1696942901059.662, "dur": 6.454, + "args": { + "External id": 4556258,"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": 1336753, "tid": 1381210, + "ts": 1696942901067.841, "dur": 51.550, + "args": { + "External id": 4556259,"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": 1336753, "tid": 1381210, + "ts": 1696942901288.211, "dur": 603.578, + "args": { + "External id": 4556260,"Record function id": 0, "Ev Idx": 4579 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1696942901304.806, "dur": 575.171, + "args": { + "External id": 4556261,"Record function id": 0, "Ev Idx": 4580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942901365.068, "dur": 4.852, + "args": { + "External id": 4556262,"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": 1336753, "tid": 1381210, + "ts": 1696942901385.486, "dur": 31.749, + "args": { + "External id": 4556263,"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": 1336753, "tid": 1381210, + "ts": 1696942901389.908, "dur": 2.938, + "args": { + "External id": 4556264,"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": 1336753, "tid": 1381210, + "ts": 1696942901394.954, "dur": 2.542, + "args": { + "External id": 4556265,"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": 1336753, "tid": 1381210, + "ts": 1696942901399.398, "dur": 0.543, + "args": { + "External id": 4556266,"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": 1336753, "tid": 1381210, + "ts": 1696942901402.431, "dur": 0.597, + "args": { + "External id": 4556267,"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": 1336753, "tid": 1381210, + "ts": 1696942901404.285, "dur": 0.560, + "args": { + "External id": 4556268,"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": 1336753, "tid": 1381210, + "ts": 1696942901406.429, "dur": 0.462, + "args": { + "External id": 4556269,"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": 1336753, "tid": 1381210, + "ts": 1696942901408.492, "dur": 0.477, + "args": { + "External id": 4556270,"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": 1336753, "tid": 1381210, + "ts": 1696942901410.637, "dur": 0.454, + "args": { + "External id": 4556271,"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": 1336753, "tid": 1381210, + "ts": 1696942901412.781, "dur": 1.560, + "args": { + "External id": 4556272,"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": 1336753, "tid": 1381210, + "ts": 1696942901427.897, "dur": 29.604, + "args": { + "External id": 4556273,"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": 1336753, "tid": 1381210, + "ts": 1696942901487.777, "dur": 150.618, + "args": { + "External id": 4556274,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942901498.005, "dur": 5.663, + "args": { + "External id": 4556275,"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": 1336753, "tid": 1381210, + "ts": 1696942901508.914, "dur": 9.918, + "args": { + "External id": 4556276,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942901512.999, "dur": 5.411, + "args": { + "External id": 4556277,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942901516.801, "dur": 0.463, + "args": { + "External id": 4556278,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942901543.251, "dur": 30.805, + "args": { + "External id": 4556279,"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": 1336753, "tid": 1381210, + "ts": 1696942901546.839, "dur": 0.661, + "args": { + "External id": 4556280,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942901549.801, "dur": 0.428, + "args": { + "External id": 4556281,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942901551.529, "dur": 1.351, + "args": { + "External id": 4556282,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942901554.637, "dur": 0.469, + "args": { + "External id": 4556283,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942901556.370, "dur": 0.421, + "args": { + "External id": 4556284,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942901559.132, "dur": 0.266, + "args": { + "External id": 4556285,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942901561.011, "dur": 2.565, + "args": { + "External id": 4556286,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942901564.969, "dur": 0.595, + "args": { + "External id": 4556287,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942901567.512, "dur": 0.471, + "args": { + "External id": 4556288,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942901607.163, "dur": 23.423, + "args": { + "External id": 4556289,"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": 1336753, "tid": 1381210, + "ts": 1696942901688.211, "dur": 122.894, + "args": { + "External id": 4556290,"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": 1336753, "tid": 1381210, + "ts": 1696942901719.308, "dur": 88.668, + "args": { + "External id": 4556291,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942901732.064, "dur": 71.534, + "args": { + "External id": 4556292,"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": 1336753, "tid": 1381210, + "ts": 1696942901827.129, "dur": 1.743, + "args": { + "External id": 4556293,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942901906.981, "dur": 1671.790, + "args": { + "External id": 4556294,"Sequence number": 45295600, "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": 1336753, "tid": 1381210, "ts": 1696942901906.981, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942902058.274, "dur": 104.296, + "args": { + "External id": 4556295,"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": 1336753, "tid": 1381210, + "ts": 1696942902208.545, "dur": 37.402, + "args": { + "External id": 4556296,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942902264.287, "dur": 46.275, + "args": { + "External id": 4556297,"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": 1336753, "tid": 1381210, + "ts": 1696942902320.541, "dur": 31.174, + "args": { + "External id": 4556298,"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": 1336753, "tid": 1381210, + "ts": 1696942902364.520, "dur": 46.697, + "args": { + "External id": 4556299,"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": 1336753, "tid": 1381210, + "ts": 1696942902419.836, "dur": 26.828, + "args": { + "External id": 4556300,"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": 1336753, "tid": 1381210, + "ts": 1696942902454.801, "dur": 42.131, + "args": { + "External id": 4556301,"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": 1336753, "tid": 1381210, + "ts": 1696942902520.410, "dur": 38.173, + "args": { + "External id": 4556302,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942902581.400, "dur": 27.895, + "args": { + "External id": 4556303,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942902636.595, "dur": 20.024, + "args": { + "External id": 4556304,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942902669.919, "dur": 17.375, + "args": { + "External id": 4556305,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942902698.050, "dur": 31.771, + "args": { + "External id": 4556306,"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": 1336753, "tid": 1381210, + "ts": 1696942902732.902, "dur": 35.055, + "args": { + "External id": 4556307,"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": 1336753, "tid": 1381210, + "ts": 1696942902801.272, "dur": 164.301, + "args": { + "External id": 4556308,"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": 1336753, "tid": 1381210, + "ts": 1696942902874.757, "dur": 5.911, + "args": { + "External id": 4556309,"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": 1336753, "tid": 1381210, + "ts": 1696942902882.185, "dur": 4.050, + "args": { + "External id": 4556310,"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": 1336753, "tid": 1381210, + "ts": 1696942903042.849, "dur": 27.876, + "args": { + "External id": 4556311,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942903083.487, "dur": 14.066, + "args": { + "External id": 4556312,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942903105.974, "dur": 41.093, + "args": { + "External id": 4556313,"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": 1336753, "tid": 1381210, + "ts": 1696942903153.098, "dur": 35.907, + "args": { + "External id": 4556314,"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": 1336753, "tid": 1381210, + "ts": 1696942903195.296, "dur": 19.813, + "args": { + "External id": 4556315,"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": 1336753, "tid": 1381210, + "ts": 1696942903232.474, "dur": 40.346, + "args": { + "External id": 4556316,"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": 1336753, "tid": 1381210, + "ts": 1696942903279.947, "dur": 18.871, + "args": { + "External id": 4556317,"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": 1336753, "tid": 1381210, + "ts": 1696942903307.043, "dur": 31.773, + "args": { + "External id": 4556318,"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": 1336753, "tid": 1381210, + "ts": 1696942903361.949, "dur": 22.384, + "args": { + "External id": 4556319,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942903406.842, "dur": 23.044, + "args": { + "External id": 4556320,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942903450.775, "dur": 16.573, + "args": { + "External id": 4556321,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942903484.711, "dur": 14.519, + "args": { + "External id": 4556322,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942903516.684, "dur": 32.514, + "args": { + "External id": 4556323,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942903621.392, "dur": 14.524, + "args": { + "External id": 4556324,"Record function id": 0, "Ev Idx": 4643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942903624.636, "dur": 10.350, + "args": { + "External id": 4556325,"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": 1336753, "tid": 1381210, + "ts": 1696942903628.879, "dur": 5.299, + "args": { + "External id": 4556326,"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": 1336753, "tid": 1381210, + "ts": 1696942903630.210, "dur": 3.878, + "args": { + "External id": 4556327,"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": 1336753, "tid": 1381210, + "ts": 1696942903639.843, "dur": 4.472, + "args": { + "External id": 4556328,"Record function id": 0, "Ev Idx": 4647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942903641.212, "dur": 2.678, + "args": { + "External id": 4556329,"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": 1336753, "tid": 1381210, + "ts": 1696942903641.961, "dur": 1.420, + "args": { + "External id": 4556330,"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": 1336753, "tid": 1381210, + "ts": 1696942903642.457, "dur": 0.820, + "args": { + "External id": 4556331,"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": 1336753, "tid": 1381210, + "ts": 1696942903647.643, "dur": 4.254, + "args": { + "External id": 4556332,"Record function id": 0, "Ev Idx": 4651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942903648.787, "dur": 2.682, + "args": { + "External id": 4556333,"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": 1336753, "tid": 1381210, + "ts": 1696942903649.486, "dur": 1.555, + "args": { + "External id": 4556334,"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": 1336753, "tid": 1381210, + "ts": 1696942903650.129, "dur": 0.812, + "args": { + "External id": 4556335,"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": 1336753, "tid": 1381210, + "ts": 1696942903655.155, "dur": 4.122, + "args": { + "External id": 4556336,"Record function id": 0, "Ev Idx": 4655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942903656.486, "dur": 2.375, + "args": { + "External id": 4556337,"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": 1336753, "tid": 1381210, + "ts": 1696942903657.230, "dur": 1.227, + "args": { + "External id": 4556338,"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": 1336753, "tid": 1381210, + "ts": 1696942903657.514, "dur": 0.860, + "args": { + "External id": 4556339,"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": 1336753, "tid": 1381210, + "ts": 1696942903662.463, "dur": 5.587, + "args": { + "External id": 4556340,"Record function id": 0, "Ev Idx": 4659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942903663.541, "dur": 4.096, + "args": { + "External id": 4556341,"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": 1336753, "tid": 1381210, + "ts": 1696942903664.244, "dur": 2.796, + "args": { + "External id": 4556342,"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": 1336753, "tid": 1381210, + "ts": 1696942903664.559, "dur": 2.411, + "args": { + "External id": 4556343,"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": 1336753, "tid": 1381210, + "ts": 1696942903671.159, "dur": 4.045, + "args": { + "External id": 4556344,"Record function id": 0, "Ev Idx": 4663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942903672.324, "dur": 2.476, + "args": { + "External id": 4556345,"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": 1336753, "tid": 1381210, + "ts": 1696942903672.862, "dur": 1.494, + "args": { + "External id": 4556346,"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": 1336753, "tid": 1381210, + "ts": 1696942903673.281, "dur": 1.008, + "args": { + "External id": 4556347,"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": 1336753, "tid": 1381210, + "ts": 1696942903678.483, "dur": 3.483, + "args": { + "External id": 4556348,"Record function id": 0, "Ev Idx": 4667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942903679.821, "dur": 1.714, + "args": { + "External id": 4556349,"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": 1336753, "tid": 1381210, + "ts": 1696942903680.264, "dur": 0.855, + "args": { + "External id": 4556350,"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": 1336753, "tid": 1381210, + "ts": 1696942903680.521, "dur": 0.532, + "args": { + "External id": 4556351,"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": 1336753, "tid": 1381210, + "ts": 1696942903685.092, "dur": 5.875, + "args": { + "External id": 4556352,"Record function id": 0, "Ev Idx": 4671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942903686.390, "dur": 4.170, + "args": { + "External id": 4556353,"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": 1336753, "tid": 1381210, + "ts": 1696942903687.019, "dur": 2.697, + "args": { + "External id": 4556354,"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": 1336753, "tid": 1381210, + "ts": 1696942903689.091, "dur": 0.558, + "args": { + "External id": 4556355,"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": 1336753, "tid": 1381210, + "ts": 1696942903694.172, "dur": 3.992, + "args": { + "External id": 4556356,"Record function id": 0, "Ev Idx": 4675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942903695.644, "dur": 2.108, + "args": { + "External id": 4556357,"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": 1336753, "tid": 1381210, + "ts": 1696942903696.073, "dur": 1.152, + "args": { + "External id": 4556358,"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": 1336753, "tid": 1381210, + "ts": 1696942903696.354, "dur": 0.803, + "args": { + "External id": 4556359,"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": 1336753, "tid": 1381210, + "ts": 1696942903702.051, "dur": 35753.711, + "args": { + "External id": 4556360,"Record function id": 0, "Sequence number": 45295599, "Fwd thread id": 1, "Ev Idx": 4679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942903703.439, "dur": 35744.214, + "args": { + "External id": 4556361,"Sequence number": 45295599, "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": 1336753, "tid": 1381210, "ts": 1696942903703.439, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1696942903731.795, "dur": 38.604, + "args": { + "External id": 4556362,"Record function id": 0, "Ev Idx": 4681 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1696942903778.223, "dur": 61.995, + "args": { + "External id": 4556363,"Record function id": 0, "Ev Idx": 4682 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1696942903846.132, "dur": 35593.845, + "args": { + "External id": 4556364,"Record function id": 0, "Ev Idx": 4683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942903934.469, "dur": 6.791, + "args": { + "External id": 4556365,"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": 1336753, "tid": 1381210, + "ts": 1696942903950.859, "dur": 4.999, + "args": { + "External id": 4556366,"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": 1336753, "tid": 1381210, + "ts": 1696942903971.563, "dur": 34676.797, + "args": { + "External id": 4556367,"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": 1336753, "tid": 1381210, + "ts": 1696942904021.235, "dur": 34618.298, + "args": { + "External id": 4556368,"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": 1336753, "tid": 1381210, + "ts": 1696942904070.059, "dur": 14.839, + "args": { + "External id": 4556369,"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": 1336753, "tid": 1381210, + "ts": 1696942904091.355, "dur": 34509.796, + "args": { + "External id": 4556370,"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": 1336753, "tid": 1381210, + "ts": 1696942904095.162, "dur": 34505.286, + "args": { + "External id": 4556371,"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": 1336753, "tid": 1381210, + "ts": 1696942904099.347, "dur": 7.486, + "args": { + "External id": 4556372,"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": 1336753, "tid": 1381210, + "ts": 1696942904108.504, "dur": 34488.627, + "args": { + "External id": 4556373,"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": 1336753, "tid": 1381210, + "ts": 1696942938735.722, "dur": 8.678, + "args": { + "External id": 4556374,"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": 1336753, "tid": 1381210, + "ts": 1696942938738.643, "dur": 5.463, + "args": { + "External id": 4556375,"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": 1336753, "tid": 1381210, + "ts": 1696942938773.246, "dur": 369.309, + "args": { + "External id": 4556376,"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": 1336753, "tid": 1381210, + "ts": 1696942938803.558, "dur": 333.936, + "args": { + "External id": 4556377,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942938813.858, "dur": 317.418, + "args": { + "External id": 4556378,"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": 1336753, "tid": 1381210, + "ts": 1696942939165.998, "dur": 2.034, + "args": { + "External id": 4556379,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942939226.067, "dur": 6.828, + "args": { + "External id": 4556380,"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": 1336753, "tid": 1381210, + "ts": 1696942939275.226, "dur": 1.401, + "args": { + "External id": 4556381,"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": 1336753, "tid": 1381210, + "ts": 1696942939291.599, "dur": 1.899, + "args": { + "External id": 4556382,"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": 1336753, "tid": 1381210, + "ts": 1696942939305.172, "dur": 3.065, + "args": { + "External id": 4556383,"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": 1336753, "tid": 1381210, + "ts": 1696942939322.809, "dur": 1.211, + "args": { + "External id": 4556384,"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": 1336753, "tid": 1381210, + "ts": 1696942939334.560, "dur": 1.040, + "args": { + "External id": 4556385,"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": 1336753, "tid": 1381210, + "ts": 1696942939345.819, "dur": 0.951, + "args": { + "External id": 4556386,"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": 1336753, "tid": 1381210, + "ts": 1696942939357.095, "dur": 3.231, + "args": { + "External id": 4556387,"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": 1336753, "tid": 1381210, + "ts": 1696942939371.405, "dur": 1.000, + "args": { + "External id": 4556388,"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": 1336753, "tid": 1381210, + "ts": 1696942939470.227, "dur": 2772.925, + "args": { + "External id": 4556389,"Record function id": 0, "Ev Idx": 4708 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1696942939489.949, "dur": 1096.000, + "args": { + "External id": 4556390,"Record function id": 0, "Ev Idx": 4709 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1696942939506.248, "dur": 340.488, + "args": { + "External id": 4556391,"Record function id": 0, "Ev Idx": 4710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942939606.563, "dur": 7.913, + "args": { + "External id": 4556392,"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": 1336753, "tid": 1381210, + "ts": 1696942939617.646, "dur": 1.018, + "args": { + "External id": 4556393,"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": 1336753, "tid": 1381210, + "ts": 1696942939620.373, "dur": 1.083, + "args": { + "External id": 4556394,"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": 1336753, "tid": 1381210, + "ts": 1696942939623.687, "dur": 0.962, + "args": { + "External id": 4556395,"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": 1336753, "tid": 1381210, + "ts": 1696942939627.838, "dur": 2.773, + "args": { + "External id": 4556396,"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": 1336753, "tid": 1381210, + "ts": 1696942939632.169, "dur": 1.288, + "args": { + "External id": 4556397,"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": 1336753, "tid": 1381210, + "ts": 1696942939635.126, "dur": 1.068, + "args": { + "External id": 4556398,"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": 1336753, "tid": 1381210, + "ts": 1696942939637.788, "dur": 0.999, + "args": { + "External id": 4556399,"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": 1336753, "tid": 1381210, + "ts": 1696942939641.942, "dur": 1.038, + "args": { + "External id": 4556400,"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": 1336753, "tid": 1381210, + "ts": 1696942939644.711, "dur": 0.717, + "args": { + "External id": 4556401,"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": 1336753, "tid": 1381210, + "ts": 1696942939664.833, "dur": 153.465, + "args": { + "External id": 4556402,"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": 1336753, "tid": 1381210, + "ts": 1696942939681.845, "dur": 132.148, + "args": { + "External id": 4556403,"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": 1336753, "tid": 1381210, + "ts": 1696942939701.142, "dur": 13.560, + "args": { + "External id": 4556404,"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": 1336753, "tid": 1381210, + "ts": 1696942939717.485, "dur": 69.950, + "args": { + "External id": 4556405,"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": 1336753, "tid": 1381210, + "ts": 1696942939719.932, "dur": 67.168, + "args": { + "External id": 4556406,"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": 1336753, "tid": 1381210, + "ts": 1696942939726.461, "dur": 5.836, + "args": { + "External id": 4556407,"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": 1336753, "tid": 1381210, + "ts": 1696942939735.916, "dur": 50.485, + "args": { + "External id": 4556408,"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": 1336753, "tid": 1381210, + "ts": 1696942939937.328, "dur": 641.311, + "args": { + "External id": 4556409,"Record function id": 0, "Ev Idx": 4728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1696942939957.280, "dur": 607.255, + "args": { + "External id": 4556410,"Record function id": 0, "Ev Idx": 4729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942940060.094, "dur": 8.408, + "args": { + "External id": 4556411,"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": 1336753, "tid": 1381210, + "ts": 1696942940084.698, "dur": 36.194, + "args": { + "External id": 4556412,"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": 1336753, "tid": 1381210, + "ts": 1696942940089.811, "dur": 3.330, + "args": { + "External id": 4556413,"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": 1336753, "tid": 1381210, + "ts": 1696942940095.280, "dur": 0.616, + "args": { + "External id": 4556414,"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": 1336753, "tid": 1381210, + "ts": 1696942940097.307, "dur": 0.576, + "args": { + "External id": 4556415,"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": 1336753, "tid": 1381210, + "ts": 1696942940100.490, "dur": 0.561, + "args": { + "External id": 4556416,"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": 1336753, "tid": 1381210, + "ts": 1696942940102.488, "dur": 0.418, + "args": { + "External id": 4556417,"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": 1336753, "tid": 1381210, + "ts": 1696942940104.397, "dur": 0.528, + "args": { + "External id": 4556418,"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": 1336753, "tid": 1381210, + "ts": 1696942940107.872, "dur": 0.385, + "args": { + "External id": 4556419,"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": 1336753, "tid": 1381210, + "ts": 1696942940109.510, "dur": 5.291, + "args": { + "External id": 4556420,"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": 1336753, "tid": 1381210, + "ts": 1696942940116.050, "dur": 1.381, + "args": { + "External id": 4556421,"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": 1336753, "tid": 1381210, + "ts": 1696942940131.308, "dur": 34.177, + "args": { + "External id": 4556422,"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": 1336753, "tid": 1381210, + "ts": 1696942940204.345, "dur": 115.311, + "args": { + "External id": 4556423,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942940214.369, "dur": 3.421, + "args": { + "External id": 4556424,"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": 1336753, "tid": 1381210, + "ts": 1696942940223.049, "dur": 13.186, + "args": { + "External id": 4556425,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942940230.297, "dur": 5.535, + "args": { + "External id": 4556426,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942940234.096, "dur": 0.619, + "args": { + "External id": 4556427,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942940244.191, "dur": 29.989, + "args": { + "External id": 4556428,"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": 1336753, "tid": 1381210, + "ts": 1696942940246.045, "dur": 0.591, + "args": { + "External id": 4556429,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942940248.562, "dur": 0.507, + "args": { + "External id": 4556430,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942940254.372, "dur": 1.688, + "args": { + "External id": 4556431,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942940257.629, "dur": 0.693, + "args": { + "External id": 4556432,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942940259.530, "dur": 2.003, + "args": { + "External id": 4556433,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942940263.302, "dur": 0.345, + "args": { + "External id": 4556434,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942940264.769, "dur": 0.324, + "args": { + "External id": 4556435,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942940266.482, "dur": 0.466, + "args": { + "External id": 4556436,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942940268.257, "dur": 0.261, + "args": { + "External id": 4556437,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942940293.343, "dur": 18.836, + "args": { + "External id": 4556438,"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": 1336753, "tid": 1381210, + "ts": 1696942940364.412, "dur": 115.881, + "args": { + "External id": 4556439,"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": 1336753, "tid": 1381210, + "ts": 1696942940395.187, "dur": 81.873, + "args": { + "External id": 4556440,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942940404.699, "dur": 67.786, + "args": { + "External id": 4556441,"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": 1336753, "tid": 1381210, + "ts": 1696942940495.445, "dur": 2.055, + "args": { + "External id": 4556442,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942940593.431, "dur": 1629.715, + "args": { + "External id": 4556443,"Sequence number": 45295598, "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": 1336753, "tid": 1381210, "ts": 1696942940593.431, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942940705.230, "dur": 103.172, + "args": { + "External id": 4556444,"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": 1336753, "tid": 1381210, + "ts": 1696942940851.029, "dur": 38.918, + "args": { + "External id": 4556445,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942940905.340, "dur": 46.253, + "args": { + "External id": 4556446,"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": 1336753, "tid": 1381210, + "ts": 1696942940960.238, "dur": 68.114, + "args": { + "External id": 4556447,"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": 1336753, "tid": 1381210, + "ts": 1696942941038.621, "dur": 52.049, + "args": { + "External id": 4556448,"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": 1336753, "tid": 1381210, + "ts": 1696942941099.698, "dur": 28.598, + "args": { + "External id": 4556449,"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": 1336753, "tid": 1381210, + "ts": 1696942941136.193, "dur": 44.076, + "args": { + "External id": 4556450,"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": 1336753, "tid": 1381210, + "ts": 1696942941205.082, "dur": 23.803, + "args": { + "External id": 4556451,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942941251.488, "dur": 27.143, + "args": { + "External id": 4556452,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942941298.255, "dur": 18.211, + "args": { + "External id": 4556453,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942941333.173, "dur": 14.854, + "args": { + "External id": 4556454,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942941355.836, "dur": 27.098, + "args": { + "External id": 4556455,"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": 1336753, "tid": 1381210, + "ts": 1696942941385.850, "dur": 31.967, + "args": { + "External id": 4556456,"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": 1336753, "tid": 1381210, + "ts": 1696942941449.367, "dur": 200.961, + "args": { + "External id": 4556457,"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": 1336753, "tid": 1381210, + "ts": 1696942941547.193, "dur": 8.949, + "args": { + "External id": 4556458,"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": 1336753, "tid": 1381210, + "ts": 1696942941558.275, "dur": 2.298, + "args": { + "External id": 4556459,"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": 1336753, "tid": 1381210, + "ts": 1696942941689.966, "dur": 22.954, + "args": { + "External id": 4556460,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942941725.040, "dur": 14.037, + "args": { + "External id": 4556461,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942941747.260, "dur": 37.590, + "args": { + "External id": 4556462,"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": 1336753, "tid": 1381210, + "ts": 1696942941790.423, "dur": 33.520, + "args": { + "External id": 4556463,"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": 1336753, "tid": 1381210, + "ts": 1696942941829.834, "dur": 19.272, + "args": { + "External id": 4556464,"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": 1336753, "tid": 1381210, + "ts": 1696942941855.255, "dur": 29.099, + "args": { + "External id": 4556465,"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": 1336753, "tid": 1381210, + "ts": 1696942941889.868, "dur": 18.293, + "args": { + "External id": 4556466,"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": 1336753, "tid": 1381210, + "ts": 1696942941918.140, "dur": 38.845, + "args": { + "External id": 4556467,"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": 1336753, "tid": 1381210, + "ts": 1696942942017.309, "dur": 29.593, + "args": { + "External id": 4556468,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942942069.552, "dur": 28.206, + "args": { + "External id": 4556469,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942942112.409, "dur": 16.791, + "args": { + "External id": 4556470,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942942150.546, "dur": 14.611, + "args": { + "External id": 4556471,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942942180.416, "dur": 15.713, + "args": { + "External id": 4556472,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942942266.150, "dur": 15.237, + "args": { + "External id": 4556473,"Record function id": 0, "Ev Idx": 4792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942942269.279, "dur": 11.127, + "args": { + "External id": 4556474,"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": 1336753, "tid": 1381210, + "ts": 1696942942273.651, "dur": 5.660, + "args": { + "External id": 4556475,"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": 1336753, "tid": 1381210, + "ts": 1696942942275.181, "dur": 4.039, + "args": { + "External id": 4556476,"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": 1336753, "tid": 1381210, + "ts": 1696942942285.157, "dur": 5.120, + "args": { + "External id": 4556477,"Record function id": 0, "Ev Idx": 4796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942942286.402, "dur": 3.347, + "args": { + "External id": 4556478,"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": 1336753, "tid": 1381210, + "ts": 1696942942287.653, "dur": 1.622, + "args": { + "External id": 4556479,"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": 1336753, "tid": 1381210, + "ts": 1696942942288.313, "dur": 0.849, + "args": { + "External id": 4556480,"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": 1336753, "tid": 1381210, + "ts": 1696942942293.574, "dur": 4.456, + "args": { + "External id": 4556481,"Record function id": 0, "Ev Idx": 4800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942942294.676, "dur": 2.954, + "args": { + "External id": 4556482,"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": 1336753, "tid": 1381210, + "ts": 1696942942295.592, "dur": 1.481, + "args": { + "External id": 4556483,"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": 1336753, "tid": 1381210, + "ts": 1696942942296.123, "dur": 0.885, + "args": { + "External id": 4556484,"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": 1336753, "tid": 1381210, + "ts": 1696942942301.219, "dur": 4.590, + "args": { + "External id": 4556485,"Record function id": 0, "Ev Idx": 4804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942942302.349, "dur": 3.059, + "args": { + "External id": 4556486,"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": 1336753, "tid": 1381210, + "ts": 1696942942303.922, "dur": 0.946, + "args": { + "External id": 4556487,"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": 1336753, "tid": 1381210, + "ts": 1696942942304.232, "dur": 0.567, + "args": { + "External id": 4556488,"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": 1336753, "tid": 1381210, + "ts": 1696942942308.928, "dur": 5.708, + "args": { + "External id": 4556489,"Record function id": 0, "Ev Idx": 4808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942942309.997, "dur": 4.213, + "args": { + "External id": 4556490,"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": 1336753, "tid": 1381210, + "ts": 1696942942310.549, "dur": 3.254, + "args": { + "External id": 4556491,"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": 1336753, "tid": 1381210, + "ts": 1696942942310.809, "dur": 2.933, + "args": { + "External id": 4556492,"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": 1336753, "tid": 1381210, + "ts": 1696942942317.795, "dur": 5.302, + "args": { + "External id": 4556493,"Record function id": 0, "Ev Idx": 4812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942942318.811, "dur": 3.870, + "args": { + "External id": 4556494,"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": 1336753, "tid": 1381210, + "ts": 1696942942319.333, "dur": 2.906, + "args": { + "External id": 4556495,"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": 1336753, "tid": 1381210, + "ts": 1696942942321.288, "dur": 0.835, + "args": { + "External id": 4556496,"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": 1336753, "tid": 1381210, + "ts": 1696942942326.325, "dur": 3.900, + "args": { + "External id": 4556497,"Record function id": 0, "Ev Idx": 4816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942942327.298, "dur": 2.496, + "args": { + "External id": 4556498,"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": 1336753, "tid": 1381210, + "ts": 1696942942328.155, "dur": 1.071, + "args": { + "External id": 4556499,"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": 1336753, "tid": 1381210, + "ts": 1696942942328.432, "dur": 0.727, + "args": { + "External id": 4556500,"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": 1336753, "tid": 1381210, + "ts": 1696942942333.330, "dur": 3.604, + "args": { + "External id": 4556501,"Record function id": 0, "Ev Idx": 4820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942942334.236, "dur": 2.298, + "args": { + "External id": 4556502,"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": 1336753, "tid": 1381210, + "ts": 1696942942334.714, "dur": 1.378, + "args": { + "External id": 4556503,"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": 1336753, "tid": 1381210, + "ts": 1696942942335.386, "dur": 0.635, + "args": { + "External id": 4556504,"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": 1336753, "tid": 1381210, + "ts": 1696942942340.057, "dur": 3.976, + "args": { + "External id": 4556505,"Record function id": 0, "Ev Idx": 4824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942942341.167, "dur": 2.451, + "args": { + "External id": 4556506,"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": 1336753, "tid": 1381210, + "ts": 1696942942341.660, "dur": 1.369, + "args": { + "External id": 4556507,"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": 1336753, "tid": 1381210, + "ts": 1696942942342.159, "dur": 0.809, + "args": { + "External id": 4556508,"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": 1336753, "tid": 1381210, + "ts": 1696942942347.966, "dur": 36018.200, + "args": { + "External id": 4556509,"Record function id": 0, "Sequence number": 45295597, "Fwd thread id": 1, "Ev Idx": 4828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942942349.677, "dur": 36007.288, + "args": { + "External id": 4556510,"Sequence number": 45295597, "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": 1336753, "tid": 1381210, "ts": 1696942942349.677, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1696942942377.792, "dur": 35.442, + "args": { + "External id": 4556511,"Record function id": 0, "Ev Idx": 4830 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1696942942420.223, "dur": 64.543, + "args": { + "External id": 4556512,"Record function id": 0, "Ev Idx": 4831 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1696942942490.190, "dur": 35859.587, + "args": { + "External id": 4556513,"Record function id": 0, "Ev Idx": 4832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942942595.261, "dur": 8.407, + "args": { + "External id": 4556514,"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": 1336753, "tid": 1381210, + "ts": 1696942942614.689, "dur": 5.136, + "args": { + "External id": 4556515,"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": 1336753, "tid": 1381210, + "ts": 1696942942634.852, "dur": 34905.818, + "args": { + "External id": 4556516,"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": 1336753, "tid": 1381210, + "ts": 1696942942648.564, "dur": 34872.843, + "args": { + "External id": 4556517,"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": 1336753, "tid": 1381210, + "ts": 1696942942686.170, "dur": 13.258, + "args": { + "External id": 4556518,"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": 1336753, "tid": 1381210, + "ts": 1696942942705.641, "dur": 34779.070, + "args": { + "External id": 4556519,"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": 1336753, "tid": 1381210, + "ts": 1696942942709.392, "dur": 34774.564, + "args": { + "External id": 4556520,"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": 1336753, "tid": 1381210, + "ts": 1696942942713.236, "dur": 6.814, + "args": { + "External id": 4556521,"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": 1336753, "tid": 1381210, + "ts": 1696942942723.269, "dur": 34757.069, + "args": { + "External id": 4556522,"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": 1336753, "tid": 1381210, + "ts": 1696942977629.725, "dur": 8.802, + "args": { + "External id": 4556523,"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": 1336753, "tid": 1381210, + "ts": 1696942977632.391, "dur": 5.798, + "args": { + "External id": 4556524,"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": 1336753, "tid": 1381210, + "ts": 1696942977668.219, "dur": 395.150, + "args": { + "External id": 4556525,"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": 1336753, "tid": 1381210, + "ts": 1696942977696.586, "dur": 361.639, + "args": { + "External id": 4556526,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942977707.801, "dur": 344.527, + "args": { + "External id": 4556527,"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": 1336753, "tid": 1381210, + "ts": 1696942978086.214, "dur": 2.586, + "args": { + "External id": 4556528,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696942978148.583, "dur": 7.199, + "args": { + "External id": 4556529,"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": 1336753, "tid": 1381210, + "ts": 1696942978199.234, "dur": 1.524, + "args": { + "External id": 4556530,"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": 1336753, "tid": 1381210, + "ts": 1696942978215.408, "dur": 1.499, + "args": { + "External id": 4556531,"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": 1336753, "tid": 1381210, + "ts": 1696942978228.016, "dur": 3.059, + "args": { + "External id": 4556532,"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": 1336753, "tid": 1381210, + "ts": 1696942978242.431, "dur": 1.010, + "args": { + "External id": 4556533,"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": 1336753, "tid": 1381210, + "ts": 1696942978253.221, "dur": 1.198, + "args": { + "External id": 4556534,"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": 1336753, "tid": 1381210, + "ts": 1696942978266.159, "dur": 0.930, + "args": { + "External id": 4556535,"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": 1336753, "tid": 1381210, + "ts": 1696942978277.212, "dur": 2.997, + "args": { + "External id": 4556536,"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": 1336753, "tid": 1381210, + "ts": 1696942978289.768, "dur": 1.037, + "args": { + "External id": 4556537,"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": 1336753, "tid": 1381210, + "ts": 1696942978380.178, "dur": 2721.671, + "args": { + "External id": 4556538,"Record function id": 0, "Ev Idx": 4857 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1696942978399.868, "dur": 1024.128, + "args": { + "External id": 4556539,"Record function id": 0, "Ev Idx": 4858 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1696942978414.149, "dur": 337.245, + "args": { + "External id": 4556540,"Record function id": 0, "Ev Idx": 4859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696942978502.071, "dur": 4.322, + "args": { + "External id": 4556541,"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": 1336753, "tid": 1381210, + "ts": 1696942978509.374, "dur": 1.116, + "args": { + "External id": 4556542,"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": 1336753, "tid": 1381210, + "ts": 1696942978513.554, "dur": 1.035, + "args": { + "External id": 4556543,"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": 1336753, "tid": 1381210, + "ts": 1696942978516.459, "dur": 0.965, + "args": { + "External id": 4556544,"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": 1336753, "tid": 1381210, + "ts": 1696942978518.650, "dur": 0.827, + "args": { + "External id": 4556545,"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": 1336753, "tid": 1381210, + "ts": 1696942978520.935, "dur": 2.549, + "args": { + "External id": 4556546,"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": 1336753, "tid": 1381210, + "ts": 1696942978541.936, "dur": 1.455, + "args": { + "External id": 4556547,"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": 1336753, "tid": 1381210, + "ts": 1696942978546.688, "dur": 0.859, + "args": { + "External id": 4556548,"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": 1336753, "tid": 1381210, + "ts": 1696942978549.201, "dur": 1.381, + "args": { + "External id": 4556549,"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": 1336753, "tid": 1381210, + "ts": 1696942978551.990, "dur": 1.453, + "args": { + "External id": 4556550,"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": 1336753, "tid": 1381210, + "ts": 1696942978573.371, "dur": 148.788, + "args": { + "External id": 4556551,"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": 1336753, "tid": 1381210, + "ts": 1696942978590.207, "dur": 127.487, + "args": { + "External id": 4556552,"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": 1336753, "tid": 1381210, + "ts": 1696942978608.739, "dur": 12.454, + "args": { + "External id": 4556553,"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": 1336753, "tid": 1381210, + "ts": 1696942978624.137, "dur": 66.842, + "args": { + "External id": 4556554,"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": 1336753, "tid": 1381210, + "ts": 1696942978627.498, "dur": 63.061, + "args": { + "External id": 4556555,"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": 1336753, "tid": 1381210, + "ts": 1696942978631.512, "dur": 6.120, + "args": { + "External id": 4556556,"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": 1336753, "tid": 1381210, + "ts": 1696942978639.499, "dur": 50.447, + "args": { + "External id": 4556557,"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": 1336753, "tid": 1381210, + "ts": 1696942978838.533, "dur": 578.087, + "args": { + "External id": 4556558,"Record function id": 0, "Ev Idx": 4877 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1696942978857.371, "dur": 547.600, + "args": { + "External id": 4556559,"Record function id": 0, "Ev Idx": 4878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942978921.802, "dur": 4.474, + "args": { + "External id": 4556560,"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": 1336753, "tid": 1381210, + "ts": 1696942978945.563, "dur": 28.171, + "args": { + "External id": 4556561,"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": 1336753, "tid": 1381210, + "ts": 1696942978950.313, "dur": 3.254, + "args": { + "External id": 4556562,"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": 1336753, "tid": 1381210, + "ts": 1696942978956.318, "dur": 0.270, + "args": { + "External id": 4556563,"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": 1336753, "tid": 1381210, + "ts": 1696942978958.228, "dur": 0.615, + "args": { + "External id": 4556564,"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": 1336753, "tid": 1381210, + "ts": 1696942978960.014, "dur": 0.492, + "args": { + "External id": 4556565,"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": 1336753, "tid": 1381210, + "ts": 1696942978962.170, "dur": 0.538, + "args": { + "External id": 4556566,"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": 1336753, "tid": 1381210, + "ts": 1696942978963.594, "dur": 0.511, + "args": { + "External id": 4556567,"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": 1336753, "tid": 1381210, + "ts": 1696942978965.314, "dur": 0.978, + "args": { + "External id": 4556568,"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": 1336753, "tid": 1381210, + "ts": 1696942978967.301, "dur": 0.398, + "args": { + "External id": 4556569,"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": 1336753, "tid": 1381210, + "ts": 1696942978968.915, "dur": 2.339, + "args": { + "External id": 4556570,"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": 1336753, "tid": 1381210, + "ts": 1696942979018.465, "dur": 32.840, + "args": { + "External id": 4556571,"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": 1336753, "tid": 1381210, + "ts": 1696942979085.033, "dur": 103.891, + "args": { + "External id": 4556572,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942979095.181, "dur": 4.715, + "args": { + "External id": 4556573,"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": 1336753, "tid": 1381210, + "ts": 1696942979105.376, "dur": 10.584, + "args": { + "External id": 4556574,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696942979109.576, "dur": 5.982, + "args": { + "External id": 4556575,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696942979113.086, "dur": 0.866, + "args": { + "External id": 4556576,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942979123.502, "dur": 26.475, + "args": { + "External id": 4556577,"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": 1336753, "tid": 1381210, + "ts": 1696942979125.726, "dur": 1.266, + "args": { + "External id": 4556578,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696942979128.093, "dur": 0.589, + "args": { + "External id": 4556579,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696942979129.679, "dur": 0.493, + "args": { + "External id": 4556580,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696942979132.306, "dur": 0.355, + "args": { + "External id": 4556581,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696942979133.887, "dur": 0.458, + "args": { + "External id": 4556582,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696942979135.837, "dur": 2.474, + "args": { + "External id": 4556583,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696942979139.700, "dur": 0.358, + "args": { + "External id": 4556584,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696942979140.827, "dur": 0.508, + "args": { + "External id": 4556585,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696942979142.832, "dur": 0.557, + "args": { + "External id": 4556586,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696942979163.250, "dur": 18.281, + "args": { + "External id": 4556587,"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": 1336753, "tid": 1381210, + "ts": 1696942979233.286, "dur": 110.618, + "args": { + "External id": 4556588,"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": 1336753, "tid": 1381210, + "ts": 1696942979258.679, "dur": 81.862, + "args": { + "External id": 4556589,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696942979267.754, "dur": 68.289, + "args": { + "External id": 4556590,"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": 1336753, "tid": 1381210, + "ts": 1696942979356.939, "dur": 1.947, + "args": { + "External id": 4556591,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942979430.854, "dur": 1649.986, + "args": { + "External id": 4556592,"Sequence number": 45295596, "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": 1336753, "tid": 1381210, "ts": 1696942979430.854, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696942979558.150, "dur": 104.421, + "args": { + "External id": 4556593,"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": 1336753, "tid": 1381210, + "ts": 1696942979705.877, "dur": 39.013, + "args": { + "External id": 4556594,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696942979761.096, "dur": 48.140, + "args": { + "External id": 4556595,"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": 1336753, "tid": 1381210, + "ts": 1696942979819.093, "dur": 31.160, + "args": { + "External id": 4556596,"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": 1336753, "tid": 1381210, + "ts": 1696942979855.813, "dur": 44.346, + "args": { + "External id": 4556597,"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": 1336753, "tid": 1381210, + "ts": 1696942979908.752, "dur": 26.654, + "args": { + "External id": 4556598,"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": 1336753, "tid": 1381210, + "ts": 1696942979943.592, "dur": 79.513, + "args": { + "External id": 4556599,"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": 1336753, "tid": 1381210, + "ts": 1696942980051.242, "dur": 26.875, + "args": { + "External id": 4556600,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696942980099.213, "dur": 31.664, + "args": { + "External id": 4556601,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696942980152.602, "dur": 18.437, + "args": { + "External id": 4556602,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942980188.760, "dur": 14.111, + "args": { + "External id": 4556603,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942980211.049, "dur": 31.472, + "args": { + "External id": 4556604,"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": 1336753, "tid": 1381210, + "ts": 1696942980245.805, "dur": 32.137, + "args": { + "External id": 4556605,"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": 1336753, "tid": 1381210, + "ts": 1696942980306.037, "dur": 165.477, + "args": { + "External id": 4556606,"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": 1336753, "tid": 1381210, + "ts": 1696942980379.846, "dur": 8.459, + "args": { + "External id": 4556607,"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": 1336753, "tid": 1381210, + "ts": 1696942980390.047, "dur": 3.098, + "args": { + "External id": 4556608,"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": 1336753, "tid": 1381210, + "ts": 1696942980509.907, "dur": 44.166, + "args": { + "External id": 4556609,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942980575.382, "dur": 16.121, + "args": { + "External id": 4556610,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696942980601.100, "dur": 40.434, + "args": { + "External id": 4556611,"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": 1336753, "tid": 1381210, + "ts": 1696942980647.061, "dur": 33.652, + "args": { + "External id": 4556612,"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": 1336753, "tid": 1381210, + "ts": 1696942980688.087, "dur": 22.823, + "args": { + "External id": 4556613,"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": 1336753, "tid": 1381210, + "ts": 1696942980717.101, "dur": 28.832, + "args": { + "External id": 4556614,"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": 1336753, "tid": 1381210, + "ts": 1696942980751.508, "dur": 19.008, + "args": { + "External id": 4556615,"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": 1336753, "tid": 1381210, + "ts": 1696942980777.528, "dur": 28.700, + "args": { + "External id": 4556616,"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": 1336753, "tid": 1381210, + "ts": 1696942980825.371, "dur": 34.651, + "args": { + "External id": 4556617,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696942980886.847, "dur": 29.649, + "args": { + "External id": 4556618,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696942980931.552, "dur": 16.371, + "args": { + "External id": 4556619,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696942980964.310, "dur": 12.956, + "args": { + "External id": 4556620,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696942981030.944, "dur": 18.051, + "args": { + "External id": 4556621,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696942981127.703, "dur": 15.032, + "args": { + "External id": 4556622,"Record function id": 0, "Ev Idx": 4941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942981130.710, "dur": 11.085, + "args": { + "External id": 4556623,"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": 1336753, "tid": 1381210, + "ts": 1696942981135.181, "dur": 5.756, + "args": { + "External id": 4556624,"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": 1336753, "tid": 1381210, + "ts": 1696942981136.928, "dur": 3.914, + "args": { + "External id": 4556625,"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": 1336753, "tid": 1381210, + "ts": 1696942981146.527, "dur": 5.317, + "args": { + "External id": 4556626,"Record function id": 0, "Ev Idx": 4945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942981148.198, "dur": 3.193, + "args": { + "External id": 4556627,"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": 1336753, "tid": 1381210, + "ts": 1696942981149.233, "dur": 1.665, + "args": { + "External id": 4556628,"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": 1336753, "tid": 1381210, + "ts": 1696942981149.911, "dur": 0.901, + "args": { + "External id": 4556629,"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": 1336753, "tid": 1381210, + "ts": 1696942981155.255, "dur": 4.449, + "args": { + "External id": 4556630,"Record function id": 0, "Ev Idx": 4949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942981156.395, "dur": 2.884, + "args": { + "External id": 4556631,"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": 1336753, "tid": 1381210, + "ts": 1696942981157.339, "dur": 1.544, + "args": { + "External id": 4556632,"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": 1336753, "tid": 1381210, + "ts": 1696942981157.953, "dur": 0.847, + "args": { + "External id": 4556633,"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": 1336753, "tid": 1381210, + "ts": 1696942981162.938, "dur": 3.477, + "args": { + "External id": 4556634,"Record function id": 0, "Ev Idx": 4953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942981163.949, "dur": 2.061, + "args": { + "External id": 4556635,"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": 1336753, "tid": 1381210, + "ts": 1696942981164.549, "dur": 1.055, + "args": { + "External id": 4556636,"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": 1336753, "tid": 1381210, + "ts": 1696942981164.943, "dur": 0.592, + "args": { + "External id": 4556637,"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": 1336753, "tid": 1381210, + "ts": 1696942981169.599, "dur": 5.339, + "args": { + "External id": 4556638,"Record function id": 0, "Ev Idx": 4957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942981170.493, "dur": 4.036, + "args": { + "External id": 4556639,"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": 1336753, "tid": 1381210, + "ts": 1696942981171.098, "dur": 2.972, + "args": { + "External id": 4556640,"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": 1336753, "tid": 1381210, + "ts": 1696942981171.352, "dur": 2.658, + "args": { + "External id": 4556641,"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": 1336753, "tid": 1381210, + "ts": 1696942981178.086, "dur": 6.917, + "args": { + "External id": 4556642,"Record function id": 0, "Ev Idx": 4961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942981179.121, "dur": 5.472, + "args": { + "External id": 4556643,"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": 1336753, "tid": 1381210, + "ts": 1696942981179.615, "dur": 4.489, + "args": { + "External id": 4556644,"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": 1336753, "tid": 1381210, + "ts": 1696942981179.956, "dur": 4.077, + "args": { + "External id": 4556645,"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": 1336753, "tid": 1381210, + "ts": 1696942981188.433, "dur": 4.853, + "args": { + "External id": 4556646,"Record function id": 0, "Ev Idx": 4965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942981189.478, "dur": 3.378, + "args": { + "External id": 4556647,"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": 1336753, "tid": 1381210, + "ts": 1696942981189.937, "dur": 2.500, + "args": { + "External id": 4556648,"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": 1336753, "tid": 1381210, + "ts": 1696942981191.584, "dur": 0.787, + "args": { + "External id": 4556649,"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": 1336753, "tid": 1381210, + "ts": 1696942981196.438, "dur": 3.868, + "args": { + "External id": 4556650,"Record function id": 0, "Ev Idx": 4969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942981197.465, "dur": 2.429, + "args": { + "External id": 4556651,"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": 1336753, "tid": 1381210, + "ts": 1696942981197.957, "dur": 1.535, + "args": { + "External id": 4556652,"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": 1336753, "tid": 1381210, + "ts": 1696942981198.515, "dur": 0.908, + "args": { + "External id": 4556653,"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": 1336753, "tid": 1381210, + "ts": 1696942981203.389, "dur": 3.983, + "args": { + "External id": 4556654,"Record function id": 0, "Ev Idx": 4973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696942981204.675, "dur": 2.097, + "args": { + "External id": 4556655,"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": 1336753, "tid": 1381210, + "ts": 1696942981205.346, "dur": 1.005, + "args": { + "External id": 4556656,"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": 1336753, "tid": 1381210, + "ts": 1696942981205.629, "dur": 0.655, + "args": { + "External id": 4556657,"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": 1336753, "tid": 1381210, + "ts": 1696942981211.170, "dur": 36991.361, + "args": { + "External id": 4556658,"Record function id": 0, "Sequence number": 45295595, "Fwd thread id": 1, "Ev Idx": 4977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696942981212.574, "dur": 36980.359, + "args": { + "External id": 4556659,"Sequence number": 45295595, "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": 1336753, "tid": 1381210, "ts": 1696942981212.574, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1696942981244.352, "dur": 38.001, + "args": { + "External id": 4556660,"Record function id": 0, "Ev Idx": 4979 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1696942981289.920, "dur": 67.503, + "args": { + "External id": 4556661,"Record function id": 0, "Ev Idx": 4980 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1696942981365.181, "dur": 36819.150, + "args": { + "External id": 4556662,"Record function id": 0, "Ev Idx": 4981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696942981453.071, "dur": 7.087, + "args": { + "External id": 4556663,"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": 1336753, "tid": 1381210, + "ts": 1696942981469.609, "dur": 5.194, + "args": { + "External id": 4556664,"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": 1336753, "tid": 1381210, + "ts": 1696942981490.331, "dur": 35829.253, + "args": { + "External id": 4556665,"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": 1336753, "tid": 1381210, + "ts": 1696942981503.507, "dur": 35807.318, + "args": { + "External id": 4556666,"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": 1336753, "tid": 1381210, + "ts": 1696942981558.696, "dur": 14.823, + "args": { + "External id": 4556667,"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": 1336753, "tid": 1381210, + "ts": 1696942981579.877, "dur": 35694.940, + "args": { + "External id": 4556668,"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": 1336753, "tid": 1381210, + "ts": 1696942981582.351, "dur": 35691.843, + "args": { + "External id": 4556669,"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": 1336753, "tid": 1381210, + "ts": 1696942981587.534, "dur": 7.257, + "args": { + "External id": 4556670,"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": 1336753, "tid": 1381210, + "ts": 1696942981596.491, "dur": 35674.053, + "args": { + "External id": 4556671,"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": 1336753, "tid": 1381210, + "ts": 1696943017408.384, "dur": 8.409, + "args": { + "External id": 4556672,"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": 1336753, "tid": 1381210, + "ts": 1696943017411.263, "dur": 5.254, + "args": { + "External id": 4556673,"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": 1336753, "tid": 1381210, + "ts": 1696943017445.773, "dur": 396.769, + "args": { + "External id": 4556674,"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": 1336753, "tid": 1381210, + "ts": 1696943017474.036, "dur": 363.364, + "args": { + "External id": 4556675,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696943017485.124, "dur": 346.051, + "args": { + "External id": 4556676,"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": 1336753, "tid": 1381210, + "ts": 1696943017864.655, "dur": 2.564, + "args": { + "External id": 4556677,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696943017927.539, "dur": 6.841, + "args": { + "External id": 4556678,"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": 1336753, "tid": 1381210, + "ts": 1696943017978.521, "dur": 1.685, + "args": { + "External id": 4556679,"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": 1336753, "tid": 1381210, + "ts": 1696943018045.631, "dur": 2.039, + "args": { + "External id": 4556680,"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": 1336753, "tid": 1381210, + "ts": 1696943018060.927, "dur": 2.645, + "args": { + "External id": 4556681,"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": 1336753, "tid": 1381210, + "ts": 1696943018074.781, "dur": 0.959, + "args": { + "External id": 4556682,"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": 1336753, "tid": 1381210, + "ts": 1696943018085.138, "dur": 0.760, + "args": { + "External id": 4556683,"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": 1336753, "tid": 1381210, + "ts": 1696943018097.880, "dur": 0.918, + "args": { + "External id": 4556684,"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": 1336753, "tid": 1381210, + "ts": 1696943018108.676, "dur": 3.220, + "args": { + "External id": 4556685,"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": 1336753, "tid": 1381210, + "ts": 1696943018121.116, "dur": 0.890, + "args": { + "External id": 4556686,"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": 1336753, "tid": 1381210, + "ts": 1696943018218.699, "dur": 2670.773, + "args": { + "External id": 4556687,"Record function id": 0, "Ev Idx": 5006 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1696943018238.899, "dur": 1029.012, + "args": { + "External id": 4556688,"Record function id": 0, "Ev Idx": 5007 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1696943018253.078, "dur": 341.562, + "args": { + "External id": 4556689,"Record function id": 0, "Ev Idx": 5008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696943018336.015, "dur": 4.065, + "args": { + "External id": 4556690,"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": 1336753, "tid": 1381210, + "ts": 1696943018343.034, "dur": 1.111, + "args": { + "External id": 4556691,"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": 1336753, "tid": 1381210, + "ts": 1696943018347.005, "dur": 1.026, + "args": { + "External id": 4556692,"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": 1336753, "tid": 1381210, + "ts": 1696943018349.704, "dur": 0.873, + "args": { + "External id": 4556693,"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": 1336753, "tid": 1381210, + "ts": 1696943018352.107, "dur": 1.089, + "args": { + "External id": 4556694,"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": 1336753, "tid": 1381210, + "ts": 1696943018354.348, "dur": 3.087, + "args": { + "External id": 4556695,"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": 1336753, "tid": 1381210, + "ts": 1696943018360.093, "dur": 0.875, + "args": { + "External id": 4556696,"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": 1336753, "tid": 1381210, + "ts": 1696943018362.327, "dur": 0.700, + "args": { + "External id": 4556697,"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": 1336753, "tid": 1381210, + "ts": 1696943018364.539, "dur": 1.093, + "args": { + "External id": 4556698,"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": 1336753, "tid": 1381210, + "ts": 1696943018367.063, "dur": 1.360, + "args": { + "External id": 4556699,"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": 1336753, "tid": 1381210, + "ts": 1696943018387.930, "dur": 175.894, + "args": { + "External id": 4556700,"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": 1336753, "tid": 1381210, + "ts": 1696943018404.035, "dur": 154.749, + "args": { + "External id": 4556701,"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": 1336753, "tid": 1381210, + "ts": 1696943018426.332, "dur": 12.031, + "args": { + "External id": 4556702,"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": 1336753, "tid": 1381210, + "ts": 1696943018441.342, "dur": 70.771, + "args": { + "External id": 4556703,"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": 1336753, "tid": 1381210, + "ts": 1696943018444.097, "dur": 67.683, + "args": { + "External id": 4556704,"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": 1336753, "tid": 1381210, + "ts": 1696943018448.619, "dur": 5.828, + "args": { + "External id": 4556705,"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": 1336753, "tid": 1381210, + "ts": 1696943018456.086, "dur": 55.114, + "args": { + "External id": 4556706,"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": 1336753, "tid": 1381210, + "ts": 1696943018686.787, "dur": 573.451, + "args": { + "External id": 4556707,"Record function id": 0, "Ev Idx": 5026 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1696943018705.970, "dur": 541.249, + "args": { + "External id": 4556708,"Record function id": 0, "Ev Idx": 5027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696943018769.894, "dur": 5.449, + "args": { + "External id": 4556709,"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": 1336753, "tid": 1381210, + "ts": 1696943018794.795, "dur": 30.338, + "args": { + "External id": 4556710,"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": 1336753, "tid": 1381210, + "ts": 1696943018799.531, "dur": 3.332, + "args": { + "External id": 4556711,"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": 1336753, "tid": 1381210, + "ts": 1696943018804.535, "dur": 1.608, + "args": { + "External id": 4556712,"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": 1336753, "tid": 1381210, + "ts": 1696943018806.914, "dur": 0.497, + "args": { + "External id": 4556713,"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": 1336753, "tid": 1381210, + "ts": 1696943018808.395, "dur": 0.552, + "args": { + "External id": 4556714,"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": 1336753, "tid": 1381210, + "ts": 1696943018811.822, "dur": 0.378, + "args": { + "External id": 4556715,"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": 1336753, "tid": 1381210, + "ts": 1696943018813.373, "dur": 0.531, + "args": { + "External id": 4556716,"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": 1336753, "tid": 1381210, + "ts": 1696943018815.174, "dur": 0.716, + "args": { + "External id": 4556717,"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": 1336753, "tid": 1381210, + "ts": 1696943018817.777, "dur": 0.952, + "args": { + "External id": 4556718,"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": 1336753, "tid": 1381210, + "ts": 1696943018819.868, "dur": 2.530, + "args": { + "External id": 4556719,"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": 1336753, "tid": 1381210, + "ts": 1696943018835.139, "dur": 29.394, + "args": { + "External id": 4556720,"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": 1336753, "tid": 1381210, + "ts": 1696943018893.896, "dur": 130.526, + "args": { + "External id": 4556721,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696943018903.254, "dur": 3.208, + "args": { + "External id": 4556722,"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": 1336753, "tid": 1381210, + "ts": 1696943018911.683, "dur": 10.039, + "args": { + "External id": 4556723,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696943018916.103, "dur": 5.225, + "args": { + "External id": 4556724,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696943018919.265, "dur": 0.988, + "args": { + "External id": 4556725,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696943018927.982, "dur": 23.504, + "args": { + "External id": 4556726,"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": 1336753, "tid": 1381210, + "ts": 1696943018929.787, "dur": 0.560, + "args": { + "External id": 4556727,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696943018932.207, "dur": 0.572, + "args": { + "External id": 4556728,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696943018933.794, "dur": 0.523, + "args": { + "External id": 4556729,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696943018935.361, "dur": 1.228, + "args": { + "External id": 4556730,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696943018937.471, "dur": 0.249, + "args": { + "External id": 4556731,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696943018938.887, "dur": 2.106, + "args": { + "External id": 4556732,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696943018942.474, "dur": 0.294, + "args": { + "External id": 4556733,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696943018943.726, "dur": 0.324, + "args": { + "External id": 4556734,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696943018945.093, "dur": 0.384, + "args": { + "External id": 4556735,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696943018961.816, "dur": 17.338, + "args": { + "External id": 4556736,"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": 1336753, "tid": 1381210, + "ts": 1696943019072.612, "dur": 111.415, + "args": { + "External id": 4556737,"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": 1336753, "tid": 1381210, + "ts": 1696943019098.438, "dur": 82.429, + "args": { + "External id": 4556738,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696943019107.873, "dur": 68.741, + "args": { + "External id": 4556739,"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": 1336753, "tid": 1381210, + "ts": 1696943019198.393, "dur": 1.633, + "args": { + "External id": 4556740,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696943019276.034, "dur": 1594.579, + "args": { + "External id": 4556741,"Sequence number": 45295594, "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": 1336753, "tid": 1381210, "ts": 1696943019276.034, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696943019383.023, "dur": 100.550, + "args": { + "External id": 4556742,"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": 1336753, "tid": 1381210, + "ts": 1696943019542.838, "dur": 43.210, + "args": { + "External id": 4556743,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696943019605.362, "dur": 53.906, + "args": { + "External id": 4556744,"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": 1336753, "tid": 1381210, + "ts": 1696943019668.522, "dur": 32.466, + "args": { + "External id": 4556745,"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": 1336753, "tid": 1381210, + "ts": 1696943019706.997, "dur": 44.863, + "args": { + "External id": 4556746,"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": 1336753, "tid": 1381210, + "ts": 1696943019763.053, "dur": 26.403, + "args": { + "External id": 4556747,"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": 1336753, "tid": 1381210, + "ts": 1696943019796.597, "dur": 45.834, + "args": { + "External id": 4556748,"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": 1336753, "tid": 1381210, + "ts": 1696943019865.590, "dur": 27.440, + "args": { + "External id": 4556749,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696943019910.683, "dur": 26.246, + "args": { + "External id": 4556750,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696943019956.814, "dur": 17.291, + "args": { + "External id": 4556751,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696943020026.747, "dur": 19.055, + "args": { + "External id": 4556752,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696943020057.334, "dur": 33.495, + "args": { + "External id": 4556753,"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": 1336753, "tid": 1381210, + "ts": 1696943020094.067, "dur": 32.671, + "args": { + "External id": 4556754,"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": 1336753, "tid": 1381210, + "ts": 1696943020155.805, "dur": 169.350, + "args": { + "External id": 4556755,"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": 1336753, "tid": 1381210, + "ts": 1696943020230.144, "dur": 5.900, + "args": { + "External id": 4556756,"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": 1336753, "tid": 1381210, + "ts": 1696943020238.006, "dur": 4.325, + "args": { + "External id": 4556757,"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": 1336753, "tid": 1381210, + "ts": 1696943020358.362, "dur": 26.298, + "args": { + "External id": 4556758,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696943020396.728, "dur": 14.046, + "args": { + "External id": 4556759,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696943020417.386, "dur": 31.150, + "args": { + "External id": 4556760,"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": 1336753, "tid": 1381210, + "ts": 1696943020454.362, "dur": 33.243, + "args": { + "External id": 4556761,"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": 1336753, "tid": 1381210, + "ts": 1696943020493.271, "dur": 18.960, + "args": { + "External id": 4556762,"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": 1336753, "tid": 1381210, + "ts": 1696943020521.665, "dur": 49.510, + "args": { + "External id": 4556763,"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": 1336753, "tid": 1381210, + "ts": 1696943020582.616, "dur": 19.573, + "args": { + "External id": 4556764,"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": 1336753, "tid": 1381210, + "ts": 1696943020609.395, "dur": 28.222, + "args": { + "External id": 4556765,"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": 1336753, "tid": 1381210, + "ts": 1696943020666.190, "dur": 29.234, + "args": { + "External id": 4556766,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696943020716.887, "dur": 23.893, + "args": { + "External id": 4556767,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696943020759.525, "dur": 19.107, + "args": { + "External id": 4556768,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696943020795.411, "dur": 13.595, + "args": { + "External id": 4556769,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696943020828.084, "dur": 15.286, + "args": { + "External id": 4556770,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696943020911.771, "dur": 15.561, + "args": { + "External id": 4556771,"Record function id": 0, "Ev Idx": 5090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943020915.181, "dur": 11.103, + "args": { + "External id": 4556772,"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": 1336753, "tid": 1381210, + "ts": 1696943020919.206, "dur": 6.230, + "args": { + "External id": 4556773,"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": 1336753, "tid": 1381210, + "ts": 1696943020921.177, "dur": 4.142, + "args": { + "External id": 4556774,"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": 1336753, "tid": 1381210, + "ts": 1696943020931.059, "dur": 4.930, + "args": { + "External id": 4556775,"Record function id": 0, "Ev Idx": 5094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943020932.326, "dur": 3.199, + "args": { + "External id": 4556776,"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": 1336753, "tid": 1381210, + "ts": 1696943020933.043, "dur": 1.998, + "args": { + "External id": 4556777,"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": 1336753, "tid": 1381210, + "ts": 1696943020934.043, "dur": 0.928, + "args": { + "External id": 4556778,"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": 1336753, "tid": 1381210, + "ts": 1696943020939.148, "dur": 4.274, + "args": { + "External id": 4556779,"Record function id": 0, "Ev Idx": 5098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943020940.154, "dur": 2.863, + "args": { + "External id": 4556780,"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": 1336753, "tid": 1381210, + "ts": 1696943020940.724, "dur": 1.706, + "args": { + "External id": 4556781,"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": 1336753, "tid": 1381210, + "ts": 1696943020941.360, "dur": 1.009, + "args": { + "External id": 4556782,"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": 1336753, "tid": 1381210, + "ts": 1696943020946.574, "dur": 3.826, + "args": { + "External id": 4556783,"Record function id": 0, "Ev Idx": 5102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943020947.502, "dur": 2.500, + "args": { + "External id": 4556784,"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": 1336753, "tid": 1381210, + "ts": 1696943020948.195, "dur": 1.387, + "args": { + "External id": 4556785,"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": 1336753, "tid": 1381210, + "ts": 1696943020948.846, "dur": 0.671, + "args": { + "External id": 4556786,"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": 1336753, "tid": 1381210, + "ts": 1696943020953.474, "dur": 5.385, + "args": { + "External id": 4556787,"Record function id": 0, "Ev Idx": 5106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943020954.455, "dur": 4.005, + "args": { + "External id": 4556788,"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": 1336753, "tid": 1381210, + "ts": 1696943020954.916, "dur": 3.107, + "args": { + "External id": 4556789,"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": 1336753, "tid": 1381210, + "ts": 1696943020955.208, "dur": 2.753, + "args": { + "External id": 4556790,"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": 1336753, "tid": 1381210, + "ts": 1696943020962.075, "dur": 4.070, + "args": { + "External id": 4556791,"Record function id": 0, "Ev Idx": 5110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943020963.272, "dur": 2.416, + "args": { + "External id": 4556792,"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": 1336753, "tid": 1381210, + "ts": 1696943020963.994, "dur": 1.251, + "args": { + "External id": 4556793,"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": 1336753, "tid": 1381210, + "ts": 1696943020964.497, "dur": 0.634, + "args": { + "External id": 4556794,"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": 1336753, "tid": 1381210, + "ts": 1696943020969.428, "dur": 3.697, + "args": { + "External id": 4556795,"Record function id": 0, "Ev Idx": 5114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943020970.391, "dur": 2.336, + "args": { + "External id": 4556796,"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": 1336753, "tid": 1381210, + "ts": 1696943020970.969, "dur": 1.303, + "args": { + "External id": 4556797,"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": 1336753, "tid": 1381210, + "ts": 1696943020971.404, "dur": 0.785, + "args": { + "External id": 4556798,"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": 1336753, "tid": 1381210, + "ts": 1696943020976.307, "dur": 63.780, + "args": { + "External id": 4556799,"Record function id": 0, "Ev Idx": 5118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943020977.370, "dur": 61.332, + "args": { + "External id": 4556800,"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": 1336753, "tid": 1381210, + "ts": 1696943021034.660, "dur": 2.946, + "args": { + "External id": 4556801,"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": 1336753, "tid": 1381210, + "ts": 1696943021035.784, "dur": 1.554, + "args": { + "External id": 4556802,"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": 1336753, "tid": 1381210, + "ts": 1696943021045.396, "dur": 6.008, + "args": { + "External id": 4556803,"Record function id": 0, "Ev Idx": 5122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943021046.932, "dur": 4.042, + "args": { + "External id": 4556804,"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": 1336753, "tid": 1381210, + "ts": 1696943021047.903, "dur": 2.582, + "args": { + "External id": 4556805,"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": 1336753, "tid": 1381210, + "ts": 1696943021049.664, "dur": 0.703, + "args": { + "External id": 4556806,"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": 1336753, "tid": 1381210, + "ts": 1696943021055.324, "dur": 36252.249, + "args": { + "External id": 4556807,"Record function id": 0, "Sequence number": 45295593, "Fwd thread id": 1, "Ev Idx": 5126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696943021056.591, "dur": 36241.223, + "args": { + "External id": 4556808,"Sequence number": 45295593, "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": 1336753, "tid": 1381210, "ts": 1696943021056.591, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1696943021086.828, "dur": 36.956, + "args": { + "External id": 4556809,"Record function id": 0, "Ev Idx": 5128 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1696943021131.589, "dur": 64.790, + "args": { + "External id": 4556810,"Record function id": 0, "Ev Idx": 5129 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1696943021202.119, "dur": 36088.219, + "args": { + "External id": 4556811,"Record function id": 0, "Ev Idx": 5130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696943021294.120, "dur": 7.494, + "args": { + "External id": 4556812,"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": 1336753, "tid": 1381210, + "ts": 1696943021314.275, "dur": 4.690, + "args": { + "External id": 4556813,"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": 1336753, "tid": 1381210, + "ts": 1696943021333.316, "dur": 35170.183, + "args": { + "External id": 4556814,"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": 1336753, "tid": 1381210, + "ts": 1696943021346.653, "dur": 35148.139, + "args": { + "External id": 4556815,"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": 1336753, "tid": 1381210, + "ts": 1696943021386.791, "dur": 13.981, + "args": { + "External id": 4556816,"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": 1336753, "tid": 1381210, + "ts": 1696943021406.958, "dur": 35049.673, + "args": { + "External id": 4556817,"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": 1336753, "tid": 1381210, + "ts": 1696943021409.738, "dur": 35046.131, + "args": { + "External id": 4556818,"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": 1336753, "tid": 1381210, + "ts": 1696943021413.645, "dur": 10.500, + "args": { + "External id": 4556819,"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": 1336753, "tid": 1381210, + "ts": 1696943021426.851, "dur": 35025.554, + "args": { + "External id": 4556820,"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": 1336753, "tid": 1381210, + "ts": 1696943056601.991, "dur": 10.281, + "args": { + "External id": 4556821,"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": 1336753, "tid": 1381210, + "ts": 1696943056606.446, "dur": 5.374, + "args": { + "External id": 4556822,"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": 1336753, "tid": 1381210, + "ts": 1696943056643.118, "dur": 334.882, + "args": { + "External id": 4556823,"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": 1336753, "tid": 1381210, + "ts": 1696943056670.503, "dur": 302.996, + "args": { + "External id": 4556824,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696943056680.851, "dur": 287.162, + "args": { + "External id": 4556825,"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": 1336753, "tid": 1381210, + "ts": 1696943057029.212, "dur": 3.113, + "args": { + "External id": 4556826,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696943057091.494, "dur": 6.669, + "args": { + "External id": 4556827,"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": 1336753, "tid": 1381210, + "ts": 1696943057140.431, "dur": 1.304, + "args": { + "External id": 4556828,"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": 1336753, "tid": 1381210, + "ts": 1696943057156.271, "dur": 1.240, + "args": { + "External id": 4556829,"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": 1336753, "tid": 1381210, + "ts": 1696943057168.026, "dur": 2.972, + "args": { + "External id": 4556830,"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": 1336753, "tid": 1381210, + "ts": 1696943057181.729, "dur": 1.000, + "args": { + "External id": 4556831,"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": 1336753, "tid": 1381210, + "ts": 1696943057192.235, "dur": 0.954, + "args": { + "External id": 4556832,"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": 1336753, "tid": 1381210, + "ts": 1696943057204.189, "dur": 0.805, + "args": { + "External id": 4556833,"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": 1336753, "tid": 1381210, + "ts": 1696943057215.367, "dur": 3.115, + "args": { + "External id": 4556834,"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": 1336753, "tid": 1381210, + "ts": 1696943057230.350, "dur": 0.735, + "args": { + "External id": 4556835,"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": 1336753, "tid": 1381210, + "ts": 1696943057322.866, "dur": 2694.856, + "args": { + "External id": 4556836,"Record function id": 0, "Ev Idx": 5155 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1696943057341.389, "dur": 1020.304, + "args": { + "External id": 4556837,"Record function id": 0, "Ev Idx": 5156 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1696943057356.713, "dur": 334.315, + "args": { + "External id": 4556838,"Record function id": 0, "Ev Idx": 5157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696943057439.150, "dur": 3.946, + "args": { + "External id": 4556839,"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": 1336753, "tid": 1381210, + "ts": 1696943057445.920, "dur": 1.329, + "args": { + "External id": 4556840,"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": 1336753, "tid": 1381210, + "ts": 1696943057448.864, "dur": 0.784, + "args": { + "External id": 4556841,"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": 1336753, "tid": 1381210, + "ts": 1696943057451.094, "dur": 0.670, + "args": { + "External id": 4556842,"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": 1336753, "tid": 1381210, + "ts": 1696943057454.736, "dur": 0.979, + "args": { + "External id": 4556843,"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": 1336753, "tid": 1381210, + "ts": 1696943057456.877, "dur": 2.903, + "args": { + "External id": 4556844,"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": 1336753, "tid": 1381210, + "ts": 1696943057460.982, "dur": 0.996, + "args": { + "External id": 4556845,"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": 1336753, "tid": 1381210, + "ts": 1696943057463.167, "dur": 0.873, + "args": { + "External id": 4556846,"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": 1336753, "tid": 1381210, + "ts": 1696943057466.641, "dur": 1.426, + "args": { + "External id": 4556847,"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": 1336753, "tid": 1381210, + "ts": 1696943057469.515, "dur": 1.439, + "args": { + "External id": 4556848,"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": 1336753, "tid": 1381210, + "ts": 1696943057488.244, "dur": 171.934, + "args": { + "External id": 4556849,"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": 1336753, "tid": 1381210, + "ts": 1696943057506.756, "dur": 148.830, + "args": { + "External id": 4556850,"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": 1336753, "tid": 1381210, + "ts": 1696943057525.331, "dur": 32.352, + "args": { + "External id": 4556851,"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": 1336753, "tid": 1381210, + "ts": 1696943057561.517, "dur": 67.478, + "args": { + "External id": 4556852,"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": 1336753, "tid": 1381210, + "ts": 1696943057564.345, "dur": 64.328, + "args": { + "External id": 4556853,"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": 1336753, "tid": 1381210, + "ts": 1696943057568.577, "dur": 6.348, + "args": { + "External id": 4556854,"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": 1336753, "tid": 1381210, + "ts": 1696943057576.395, "dur": 51.604, + "args": { + "External id": 4556855,"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": 1336753, "tid": 1381210, + "ts": 1696943057778.245, "dur": 575.815, + "args": { + "External id": 4556856,"Record function id": 0, "Ev Idx": 5175 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1696943057796.529, "dur": 545.509, + "args": { + "External id": 4556857,"Record function id": 0, "Ev Idx": 5176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696943057857.964, "dur": 4.573, + "args": { + "External id": 4556858,"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": 1336753, "tid": 1381210, + "ts": 1696943057878.757, "dur": 28.324, + "args": { + "External id": 4556859,"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": 1336753, "tid": 1381210, + "ts": 1696943057883.702, "dur": 3.731, + "args": { + "External id": 4556860,"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": 1336753, "tid": 1381210, + "ts": 1696943057889.342, "dur": 0.468, + "args": { + "External id": 4556861,"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": 1336753, "tid": 1381210, + "ts": 1696943057891.319, "dur": 0.533, + "args": { + "External id": 4556862,"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": 1336753, "tid": 1381210, + "ts": 1696943057892.866, "dur": 0.404, + "args": { + "External id": 4556863,"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": 1336753, "tid": 1381210, + "ts": 1696943057894.946, "dur": 0.358, + "args": { + "External id": 4556864,"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": 1336753, "tid": 1381210, + "ts": 1696943057896.761, "dur": 0.964, + "args": { + "External id": 4556865,"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": 1336753, "tid": 1381210, + "ts": 1696943057898.756, "dur": 0.583, + "args": { + "External id": 4556866,"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": 1336753, "tid": 1381210, + "ts": 1696943057900.678, "dur": 0.298, + "args": { + "External id": 4556867,"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": 1336753, "tid": 1381210, + "ts": 1696943057902.282, "dur": 2.143, + "args": { + "External id": 4556868,"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": 1336753, "tid": 1381210, + "ts": 1696943057917.082, "dur": 29.151, + "args": { + "External id": 4556869,"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": 1336753, "tid": 1381210, + "ts": 1696943057974.978, "dur": 142.417, + "args": { + "External id": 4556870,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696943058023.278, "dur": 5.025, + "args": { + "External id": 4556871,"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": 1336753, "tid": 1381210, + "ts": 1696943058034.138, "dur": 10.610, + "args": { + "External id": 4556872,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696943058038.418, "dur": 5.944, + "args": { + "External id": 4556873,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696943058042.200, "dur": 0.557, + "args": { + "External id": 4556874,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696943058052.373, "dur": 25.119, + "args": { + "External id": 4556875,"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": 1336753, "tid": 1381210, + "ts": 1696943058054.631, "dur": 0.476, + "args": { + "External id": 4556876,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696943058056.441, "dur": 0.626, + "args": { + "External id": 4556877,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696943058058.413, "dur": 0.618, + "args": { + "External id": 4556878,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696943058060.304, "dur": 0.409, + "args": { + "External id": 4556879,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696943058062.184, "dur": 0.352, + "args": { + "External id": 4556880,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696943058063.380, "dur": 1.623, + "args": { + "External id": 4556881,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696943058066.558, "dur": 0.305, + "args": { + "External id": 4556882,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696943058068.143, "dur": 0.732, + "args": { + "External id": 4556883,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696943058069.797, "dur": 0.449, + "args": { + "External id": 4556884,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696943058088.590, "dur": 21.199, + "args": { + "External id": 4556885,"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": 1336753, "tid": 1381210, + "ts": 1696943058165.824, "dur": 110.018, + "args": { + "External id": 4556886,"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": 1336753, "tid": 1381210, + "ts": 1696943058192.735, "dur": 79.703, + "args": { + "External id": 4556887,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696943058201.916, "dur": 65.729, + "args": { + "External id": 4556888,"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": 1336753, "tid": 1381210, + "ts": 1696943058291.019, "dur": 1.951, + "args": { + "External id": 4556889,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696943058369.861, "dur": 1591.727, + "args": { + "External id": 4556890,"Sequence number": 45295592, "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": 1336753, "tid": 1381210, "ts": 1696943058369.861, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696943058479.471, "dur": 127.284, + "args": { + "External id": 4556891,"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": 1336753, "tid": 1381210, + "ts": 1696943058650.113, "dur": 41.663, + "args": { + "External id": 4556892,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696943058711.327, "dur": 52.660, + "args": { + "External id": 4556893,"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": 1336753, "tid": 1381210, + "ts": 1696943058773.443, "dur": 34.171, + "args": { + "External id": 4556894,"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": 1336753, "tid": 1381210, + "ts": 1696943058813.676, "dur": 45.219, + "args": { + "External id": 4556895,"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": 1336753, "tid": 1381210, + "ts": 1696943058865.512, "dur": 27.578, + "args": { + "External id": 4556896,"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": 1336753, "tid": 1381210, + "ts": 1696943058901.149, "dur": 41.728, + "args": { + "External id": 4556897,"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": 1336753, "tid": 1381210, + "ts": 1696943058964.575, "dur": 62.149, + "args": { + "External id": 4556898,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696943059047.290, "dur": 29.014, + "args": { + "External id": 4556899,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696943059098.490, "dur": 18.165, + "args": { + "External id": 4556900,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696943059130.284, "dur": 14.948, + "args": { + "External id": 4556901,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696943059154.539, "dur": 32.422, + "args": { + "External id": 4556902,"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": 1336753, "tid": 1381210, + "ts": 1696943059189.975, "dur": 34.453, + "args": { + "External id": 4556903,"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": 1336753, "tid": 1381210, + "ts": 1696943059253.052, "dur": 165.992, + "args": { + "External id": 4556904,"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": 1336753, "tid": 1381210, + "ts": 1696943059327.471, "dur": 5.956, + "args": { + "External id": 4556905,"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": 1336753, "tid": 1381210, + "ts": 1696943059335.380, "dur": 2.050, + "args": { + "External id": 4556906,"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": 1336753, "tid": 1381210, + "ts": 1696943059452.571, "dur": 26.070, + "args": { + "External id": 4556907,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696943059489.397, "dur": 14.124, + "args": { + "External id": 4556908,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696943059511.146, "dur": 50.202, + "args": { + "External id": 4556909,"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": 1336753, "tid": 1381210, + "ts": 1696943059572.425, "dur": 37.196, + "args": { + "External id": 4556910,"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": 1336753, "tid": 1381210, + "ts": 1696943059617.093, "dur": 20.501, + "args": { + "External id": 4556911,"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": 1336753, "tid": 1381210, + "ts": 1696943059642.731, "dur": 29.371, + "args": { + "External id": 4556912,"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": 1336753, "tid": 1381210, + "ts": 1696943059677.773, "dur": 19.118, + "args": { + "External id": 4556913,"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": 1336753, "tid": 1381210, + "ts": 1696943059706.308, "dur": 31.436, + "args": { + "External id": 4556914,"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": 1336753, "tid": 1381210, + "ts": 1696943059754.860, "dur": 35.822, + "args": { + "External id": 4556915,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696943059815.258, "dur": 29.226, + "args": { + "External id": 4556916,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696943059859.045, "dur": 16.471, + "args": { + "External id": 4556917,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696943059889.599, "dur": 16.355, + "args": { + "External id": 4556918,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696943059917.680, "dur": 15.253, + "args": { + "External id": 4556919,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696943060041.163, "dur": 16.883, + "args": { + "External id": 4556920,"Record function id": 0, "Ev Idx": 5239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943060044.741, "dur": 12.197, + "args": { + "External id": 4556921,"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": 1336753, "tid": 1381210, + "ts": 1696943060049.073, "dur": 6.376, + "args": { + "External id": 4556922,"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": 1336753, "tid": 1381210, + "ts": 1696943060051.081, "dur": 4.265, + "args": { + "External id": 4556923,"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": 1336753, "tid": 1381210, + "ts": 1696943060061.666, "dur": 4.877, + "args": { + "External id": 4556924,"Record function id": 0, "Ev Idx": 5243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943060063.080, "dur": 3.013, + "args": { + "External id": 4556925,"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": 1336753, "tid": 1381210, + "ts": 1696943060064.085, "dur": 1.477, + "args": { + "External id": 4556926,"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": 1336753, "tid": 1381210, + "ts": 1696943060064.586, "dur": 0.894, + "args": { + "External id": 4556927,"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": 1336753, "tid": 1381210, + "ts": 1696943060069.746, "dur": 5.934, + "args": { + "External id": 4556928,"Record function id": 0, "Ev Idx": 5247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943060071.021, "dur": 4.241, + "args": { + "External id": 4556929,"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": 1336753, "tid": 1381210, + "ts": 1696943060071.491, "dur": 3.288, + "args": { + "External id": 4556930,"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": 1336753, "tid": 1381210, + "ts": 1696943060072.078, "dur": 2.636, + "args": { + "External id": 4556931,"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": 1336753, "tid": 1381210, + "ts": 1696943060078.922, "dur": 4.283, + "args": { + "External id": 4556932,"Record function id": 0, "Ev Idx": 5251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943060079.935, "dur": 2.859, + "args": { + "External id": 4556933,"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": 1336753, "tid": 1381210, + "ts": 1696943060080.742, "dur": 1.636, + "args": { + "External id": 4556934,"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": 1336753, "tid": 1381210, + "ts": 1696943060081.548, "dur": 0.764, + "args": { + "External id": 4556935,"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": 1336753, "tid": 1381210, + "ts": 1696943060086.283, "dur": 3.726, + "args": { + "External id": 4556936,"Record function id": 0, "Ev Idx": 5255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943060087.411, "dur": 2.187, + "args": { + "External id": 4556937,"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": 1336753, "tid": 1381210, + "ts": 1696943060088.237, "dur": 0.948, + "args": { + "External id": 4556938,"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": 1336753, "tid": 1381210, + "ts": 1696943060088.524, "dur": 0.595, + "args": { + "External id": 4556939,"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": 1336753, "tid": 1381210, + "ts": 1696943060093.147, "dur": 3.930, + "args": { + "External id": 4556940,"Record function id": 0, "Ev Idx": 5259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943060094.257, "dur": 2.381, + "args": { + "External id": 4556941,"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": 1336753, "tid": 1381210, + "ts": 1696943060094.755, "dur": 1.381, + "args": { + "External id": 4556942,"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": 1336753, "tid": 1381210, + "ts": 1696943060095.359, "dur": 0.685, + "args": { + "External id": 4556943,"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": 1336753, "tid": 1381210, + "ts": 1696943060100.362, "dur": 3.536, + "args": { + "External id": 4556944,"Record function id": 0, "Ev Idx": 5263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943060101.411, "dur": 2.078, + "args": { + "External id": 4556945,"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": 1336753, "tid": 1381210, + "ts": 1696943060101.999, "dur": 1.078, + "args": { + "External id": 4556946,"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": 1336753, "tid": 1381210, + "ts": 1696943060102.271, "dur": 0.715, + "args": { + "External id": 4556947,"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": 1336753, "tid": 1381210, + "ts": 1696943060106.985, "dur": 15.098, + "args": { + "External id": 4556948,"Record function id": 0, "Ev Idx": 5267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943060108.084, "dur": 13.552, + "args": { + "External id": 4556949,"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": 1336753, "tid": 1381210, + "ts": 1696943060120.027, "dur": 1.188, + "args": { + "External id": 4556950,"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": 1336753, "tid": 1381210, + "ts": 1696943060120.323, "dur": 0.785, + "args": { + "External id": 4556951,"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": 1336753, "tid": 1381210, + "ts": 1696943060125.163, "dur": 5.096, + "args": { + "External id": 4556952,"Record function id": 0, "Ev Idx": 5271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943060126.494, "dur": 3.330, + "args": { + "External id": 4556953,"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": 1336753, "tid": 1381210, + "ts": 1696943060126.982, "dur": 2.327, + "args": { + "External id": 4556954,"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": 1336753, "tid": 1381210, + "ts": 1696943060128.646, "dur": 0.561, + "args": { + "External id": 4556955,"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": 1336753, "tid": 1381210, + "ts": 1696943060133.820, "dur": 36544.394, + "args": { + "External id": 4556956,"Record function id": 0, "Sequence number": 45295591, "Fwd thread id": 1, "Ev Idx": 5275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696943060135.139, "dur": 36534.590, + "args": { + "External id": 4556957,"Sequence number": 45295591, "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": 1336753, "tid": 1381210, "ts": 1696943060135.139, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1696943060163.950, "dur": 41.895, + "args": { + "External id": 4556958,"Record function id": 0, "Ev Idx": 5277 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1696943060213.381, "dur": 63.879, + "args": { + "External id": 4556959,"Record function id": 0, "Ev Idx": 5278 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1696943060286.093, "dur": 36374.903, + "args": { + "External id": 4556960,"Record function id": 0, "Ev Idx": 5279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696943060375.582, "dur": 6.931, + "args": { + "External id": 4556961,"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": 1336753, "tid": 1381210, + "ts": 1696943060391.329, "dur": 4.979, + "args": { + "External id": 4556962,"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": 1336753, "tid": 1381210, + "ts": 1696943060413.068, "dur": 35441.245, + "args": { + "External id": 4556963,"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": 1336753, "tid": 1381210, + "ts": 1696943060425.779, "dur": 35420.194, + "args": { + "External id": 4556964,"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": 1336753, "tid": 1381210, + "ts": 1696943060465.012, "dur": 15.714, + "args": { + "External id": 4556965,"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": 1336753, "tid": 1381210, + "ts": 1696943060486.826, "dur": 35323.346, + "args": { + "External id": 4556966,"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": 1336753, "tid": 1381210, + "ts": 1696943060490.212, "dur": 35319.181, + "args": { + "External id": 4556967,"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": 1336753, "tid": 1381210, + "ts": 1696943060494.677, "dur": 5.533, + "args": { + "External id": 4556968,"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": 1336753, "tid": 1381210, + "ts": 1696943060502.873, "dur": 35302.911, + "args": { + "External id": 4556969,"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": 1336753, "tid": 1381210, + "ts": 1696943095940.858, "dur": 8.004, + "args": { + "External id": 4556970,"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": 1336753, "tid": 1381210, + "ts": 1696943095943.327, "dur": 5.136, + "args": { + "External id": 4556971,"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": 1336753, "tid": 1381210, + "ts": 1696943095979.670, "dur": 363.068, + "args": { + "External id": 4556972,"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": 1336753, "tid": 1381210, + "ts": 1696943096028.810, "dur": 309.565, + "args": { + "External id": 4556973,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696943096041.164, "dur": 291.612, + "args": { + "External id": 4556974,"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": 1336753, "tid": 1381210, + "ts": 1696943096360.756, "dur": 2.163, + "args": { + "External id": 4556975,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696943096419.964, "dur": 6.701, + "args": { + "External id": 4556976,"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": 1336753, "tid": 1381210, + "ts": 1696943096471.959, "dur": 1.227, + "args": { + "External id": 4556977,"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": 1336753, "tid": 1381210, + "ts": 1696943096488.701, "dur": 1.579, + "args": { + "External id": 4556978,"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": 1336753, "tid": 1381210, + "ts": 1696943096502.254, "dur": 3.083, + "args": { + "External id": 4556979,"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": 1336753, "tid": 1381210, + "ts": 1696943096516.857, "dur": 1.138, + "args": { + "External id": 4556980,"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": 1336753, "tid": 1381210, + "ts": 1696943096544.680, "dur": 1.638, + "args": { + "External id": 4556981,"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": 1336753, "tid": 1381210, + "ts": 1696943096560.726, "dur": 1.122, + "args": { + "External id": 4556982,"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": 1336753, "tid": 1381210, + "ts": 1696943096576.119, "dur": 6.345, + "args": { + "External id": 4556983,"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": 1336753, "tid": 1381210, + "ts": 1696943096592.685, "dur": 1.019, + "args": { + "External id": 4556984,"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": 1336753, "tid": 1381210, + "ts": 1696943096693.722, "dur": 2702.053, + "args": { + "External id": 4556985,"Record function id": 0, "Ev Idx": 5304 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1696943096713.999, "dur": 1043.492, + "args": { + "External id": 4556986,"Record function id": 0, "Ev Idx": 5305 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1696943096728.978, "dur": 352.987, + "args": { + "External id": 4556987,"Record function id": 0, "Ev Idx": 5306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696943096812.872, "dur": 4.337, + "args": { + "External id": 4556988,"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": 1336753, "tid": 1381210, + "ts": 1696943096820.385, "dur": 1.272, + "args": { + "External id": 4556989,"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": 1336753, "tid": 1381210, + "ts": 1696943096823.259, "dur": 1.033, + "args": { + "External id": 4556990,"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": 1336753, "tid": 1381210, + "ts": 1696943096826.959, "dur": 0.905, + "args": { + "External id": 4556991,"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": 1336753, "tid": 1381210, + "ts": 1696943096829.393, "dur": 0.624, + "args": { + "External id": 4556992,"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": 1336753, "tid": 1381210, + "ts": 1696943096831.572, "dur": 0.713, + "args": { + "External id": 4556993,"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": 1336753, "tid": 1381210, + "ts": 1696943096833.709, "dur": 2.307, + "args": { + "External id": 4556994,"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": 1336753, "tid": 1381210, + "ts": 1696943096838.525, "dur": 0.984, + "args": { + "External id": 4556995,"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": 1336753, "tid": 1381210, + "ts": 1696943096841.189, "dur": 0.914, + "args": { + "External id": 4556996,"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": 1336753, "tid": 1381210, + "ts": 1696943096843.324, "dur": 1.218, + "args": { + "External id": 4556997,"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": 1336753, "tid": 1381210, + "ts": 1696943096861.368, "dur": 187.683, + "args": { + "External id": 4556998,"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": 1336753, "tid": 1381210, + "ts": 1696943096876.974, "dur": 166.829, + "args": { + "External id": 4556999,"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": 1336753, "tid": 1381210, + "ts": 1696943096894.239, "dur": 11.880, + "args": { + "External id": 4557000,"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": 1336753, "tid": 1381210, + "ts": 1696943096909.338, "dur": 69.265, + "args": { + "External id": 4557001,"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": 1336753, "tid": 1381210, + "ts": 1696943096912.204, "dur": 66.059, + "args": { + "External id": 4557002,"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": 1336753, "tid": 1381210, + "ts": 1696943096916.543, "dur": 6.349, + "args": { + "External id": 4557003,"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": 1336753, "tid": 1381210, + "ts": 1696943096925.527, "dur": 51.831, + "args": { + "External id": 4557004,"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": 1336753, "tid": 1381210, + "ts": 1696943097183.221, "dur": 566.137, + "args": { + "External id": 4557005,"Record function id": 0, "Ev Idx": 5324 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1696943097203.255, "dur": 533.871, + "args": { + "External id": 4557006,"Record function id": 0, "Ev Idx": 5325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696943097266.856, "dur": 5.456, + "args": { + "External id": 4557007,"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": 1336753, "tid": 1381210, + "ts": 1696943097299.815, "dur": 25.420, + "args": { + "External id": 4557008,"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": 1336753, "tid": 1381210, + "ts": 1696943097304.747, "dur": 1.793, + "args": { + "External id": 4557009,"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": 1336753, "tid": 1381210, + "ts": 1696943097308.344, "dur": 2.326, + "args": { + "External id": 4557010,"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": 1336753, "tid": 1381210, + "ts": 1696943097311.594, "dur": 0.326, + "args": { + "External id": 4557011,"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": 1336753, "tid": 1381210, + "ts": 1696943097313.005, "dur": 0.360, + "args": { + "External id": 4557012,"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": 1336753, "tid": 1381210, + "ts": 1696943097314.919, "dur": 0.379, + "args": { + "External id": 4557013,"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": 1336753, "tid": 1381210, + "ts": 1696943097316.398, "dur": 0.710, + "args": { + "External id": 4557014,"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": 1336753, "tid": 1381210, + "ts": 1696943097318.620, "dur": 0.433, + "args": { + "External id": 4557015,"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": 1336753, "tid": 1381210, + "ts": 1696943097320.606, "dur": 0.262, + "args": { + "External id": 4557016,"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": 1336753, "tid": 1381210, + "ts": 1696943097322.135, "dur": 0.453, + "args": { + "External id": 4557017,"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": 1336753, "tid": 1381210, + "ts": 1696943097335.175, "dur": 30.053, + "args": { + "External id": 4557018,"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": 1336753, "tid": 1381210, + "ts": 1696943097398.088, "dur": 98.673, + "args": { + "External id": 4557019,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696943097407.997, "dur": 4.888, + "args": { + "External id": 4557020,"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": 1336753, "tid": 1381210, + "ts": 1696943097418.035, "dur": 10.353, + "args": { + "External id": 4557021,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696943097422.248, "dur": 5.742, + "args": { + "External id": 4557022,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696943097426.210, "dur": 0.678, + "args": { + "External id": 4557023,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696943097434.734, "dur": 29.205, + "args": { + "External id": 4557024,"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": 1336753, "tid": 1381210, + "ts": 1696943097436.635, "dur": 0.487, + "args": { + "External id": 4557025,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696943097438.730, "dur": 0.404, + "args": { + "External id": 4557026,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696943097440.167, "dur": 0.721, + "args": { + "External id": 4557027,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696943097442.461, "dur": 0.519, + "args": { + "External id": 4557028,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696943097444.510, "dur": 0.418, + "args": { + "External id": 4557029,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696943097445.754, "dur": 0.304, + "args": { + "External id": 4557030,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696943097449.752, "dur": 2.169, + "args": { + "External id": 4557031,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696943097452.770, "dur": 3.781, + "args": { + "External id": 4557032,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696943097457.839, "dur": 0.277, + "args": { + "External id": 4557033,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696943097473.075, "dur": 16.648, + "args": { + "External id": 4557034,"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": 1336753, "tid": 1381210, + "ts": 1696943097554.405, "dur": 111.248, + "args": { + "External id": 4557035,"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": 1336753, "tid": 1381210, + "ts": 1696943097579.327, "dur": 83.061, + "args": { + "External id": 4557036,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696943097589.489, "dur": 68.722, + "args": { + "External id": 4557037,"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": 1336753, "tid": 1381210, + "ts": 1696943097682.519, "dur": 1.494, + "args": { + "External id": 4557038,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696943097765.134, "dur": 1610.427, + "args": { + "External id": 4557039,"Sequence number": 45295590, "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": 1336753, "tid": 1381210, "ts": 1696943097765.134, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696943097874.242, "dur": 100.347, + "args": { + "External id": 4557040,"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": 1336753, "tid": 1381210, + "ts": 1696943098055.960, "dur": 41.343, + "args": { + "External id": 4557041,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696943098117.159, "dur": 55.266, + "args": { + "External id": 4557042,"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": 1336753, "tid": 1381210, + "ts": 1696943098182.996, "dur": 31.926, + "args": { + "External id": 4557043,"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": 1336753, "tid": 1381210, + "ts": 1696943098220.709, "dur": 44.934, + "args": { + "External id": 4557044,"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": 1336753, "tid": 1381210, + "ts": 1696943098272.123, "dur": 27.275, + "args": { + "External id": 4557045,"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": 1336753, "tid": 1381210, + "ts": 1696943098307.802, "dur": 43.227, + "args": { + "External id": 4557046,"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": 1336753, "tid": 1381210, + "ts": 1696943098373.595, "dur": 21.562, + "args": { + "External id": 4557047,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696943098413.122, "dur": 28.584, + "args": { + "External id": 4557048,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696943098461.181, "dur": 18.389, + "args": { + "External id": 4557049,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696943098492.851, "dur": 14.661, + "args": { + "External id": 4557050,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696943098515.718, "dur": 48.391, + "args": { + "External id": 4557051,"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": 1336753, "tid": 1381210, + "ts": 1696943098568.820, "dur": 35.896, + "args": { + "External id": 4557052,"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": 1336753, "tid": 1381210, + "ts": 1696943098634.504, "dur": 167.366, + "args": { + "External id": 4557053,"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": 1336753, "tid": 1381210, + "ts": 1696943098709.915, "dur": 5.566, + "args": { + "External id": 4557054,"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": 1336753, "tid": 1381210, + "ts": 1696943098717.591, "dur": 2.150, + "args": { + "External id": 4557055,"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": 1336753, "tid": 1381210, + "ts": 1696943098837.328, "dur": 23.041, + "args": { + "External id": 4557056,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696943098873.963, "dur": 14.001, + "args": { + "External id": 4557057,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696943098895.558, "dur": 36.618, + "args": { + "External id": 4557058,"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": 1336753, "tid": 1381210, + "ts": 1696943098940.742, "dur": 34.831, + "args": { + "External id": 4557059,"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": 1336753, "tid": 1381210, + "ts": 1696943099018.726, "dur": 26.456, + "args": { + "External id": 4557060,"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": 1336753, "tid": 1381210, + "ts": 1696943099054.466, "dur": 30.767, + "args": { + "External id": 4557061,"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": 1336753, "tid": 1381210, + "ts": 1696943099091.940, "dur": 23.762, + "args": { + "External id": 4557062,"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": 1336753, "tid": 1381210, + "ts": 1696943099125.169, "dur": 29.495, + "args": { + "External id": 4557063,"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": 1336753, "tid": 1381210, + "ts": 1696943099185.666, "dur": 27.108, + "args": { + "External id": 4557064,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696943099230.913, "dur": 23.742, + "args": { + "External id": 4557065,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696943099269.314, "dur": 15.800, + "args": { + "External id": 4557066,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696943099304.171, "dur": 13.363, + "args": { + "External id": 4557067,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696943099329.818, "dur": 14.886, + "args": { + "External id": 4557068,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696943099421.183, "dur": 14.337, + "args": { + "External id": 4557069,"Record function id": 0, "Ev Idx": 5388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943099424.035, "dur": 10.563, + "args": { + "External id": 4557070,"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": 1336753, "tid": 1381210, + "ts": 1696943099428.306, "dur": 5.472, + "args": { + "External id": 4557071,"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": 1336753, "tid": 1381210, + "ts": 1696943099429.828, "dur": 3.842, + "args": { + "External id": 4557072,"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": 1336753, "tid": 1381210, + "ts": 1696943099439.450, "dur": 5.171, + "args": { + "External id": 4557073,"Record function id": 0, "Ev Idx": 5392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943099440.608, "dur": 3.562, + "args": { + "External id": 4557074,"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": 1336753, "tid": 1381210, + "ts": 1696943099441.815, "dur": 1.875, + "args": { + "External id": 4557075,"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": 1336753, "tid": 1381210, + "ts": 1696943099442.583, "dur": 1.043, + "args": { + "External id": 4557076,"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": 1336753, "tid": 1381210, + "ts": 1696943099447.991, "dur": 4.697, + "args": { + "External id": 4557077,"Record function id": 0, "Ev Idx": 5396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943099449.201, "dur": 3.102, + "args": { + "External id": 4557078,"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": 1336753, "tid": 1381210, + "ts": 1696943099450.155, "dur": 1.742, + "args": { + "External id": 4557079,"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": 1336753, "tid": 1381210, + "ts": 1696943099450.829, "dur": 1.007, + "args": { + "External id": 4557080,"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": 1336753, "tid": 1381210, + "ts": 1696943099455.828, "dur": 3.756, + "args": { + "External id": 4557081,"Record function id": 0, "Ev Idx": 5400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943099457.010, "dur": 2.194, + "args": { + "External id": 4557082,"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": 1336753, "tid": 1381210, + "ts": 1696943099457.643, "dur": 1.172, + "args": { + "External id": 4557083,"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": 1336753, "tid": 1381210, + "ts": 1696943099457.961, "dur": 0.791, + "args": { + "External id": 4557084,"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": 1336753, "tid": 1381210, + "ts": 1696943099462.716, "dur": 8.815, + "args": { + "External id": 4557085,"Record function id": 0, "Ev Idx": 5404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943099464.068, "dur": 7.051, + "args": { + "External id": 4557086,"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": 1336753, "tid": 1381210, + "ts": 1696943099464.559, "dur": 6.060, + "args": { + "External id": 4557087,"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": 1336753, "tid": 1381210, + "ts": 1696943099464.935, "dur": 5.623, + "args": { + "External id": 4557088,"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": 1336753, "tid": 1381210, + "ts": 1696943099474.693, "dur": 3.961, + "args": { + "External id": 4557089,"Record function id": 0, "Ev Idx": 5408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943099475.741, "dur": 2.502, + "args": { + "External id": 4557090,"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": 1336753, "tid": 1381210, + "ts": 1696943099476.576, "dur": 1.257, + "args": { + "External id": 4557091,"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": 1336753, "tid": 1381210, + "ts": 1696943099476.974, "dur": 0.761, + "args": { + "External id": 4557092,"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": 1336753, "tid": 1381210, + "ts": 1696943099482.045, "dur": 3.742, + "args": { + "External id": 4557093,"Record function id": 0, "Ev Idx": 5412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943099483.147, "dur": 2.246, + "args": { + "External id": 4557094,"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": 1336753, "tid": 1381210, + "ts": 1696943099483.864, "dur": 1.136, + "args": { + "External id": 4557095,"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": 1336753, "tid": 1381210, + "ts": 1696943099484.303, "dur": 0.621, + "args": { + "External id": 4557096,"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": 1336753, "tid": 1381210, + "ts": 1696943099488.932, "dur": 3.552, + "args": { + "External id": 4557097,"Record function id": 0, "Ev Idx": 5416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943099489.865, "dur": 2.204, + "args": { + "External id": 4557098,"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": 1336753, "tid": 1381210, + "ts": 1696943099490.474, "dur": 1.145, + "args": { + "External id": 4557099,"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": 1336753, "tid": 1381210, + "ts": 1696943099490.760, "dur": 0.764, + "args": { + "External id": 4557100,"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": 1336753, "tid": 1381210, + "ts": 1696943099495.513, "dur": 4.397, + "args": { + "External id": 4557101,"Record function id": 0, "Ev Idx": 5420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943099496.683, "dur": 2.809, + "args": { + "External id": 4557102,"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": 1336753, "tid": 1381210, + "ts": 1696943099497.754, "dur": 1.342, + "args": { + "External id": 4557103,"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": 1336753, "tid": 1381210, + "ts": 1696943099498.359, "dur": 0.630, + "args": { + "External id": 4557104,"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": 1336753, "tid": 1381210, + "ts": 1696943099503.587, "dur": 36740.205, + "args": { + "External id": 4557105,"Record function id": 0, "Sequence number": 45295589, "Fwd thread id": 1, "Ev Idx": 5424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696943099504.863, "dur": 36726.924, + "args": { + "External id": 4557106,"Sequence number": 45295589, "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": 1336753, "tid": 1381210, "ts": 1696943099504.863, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1696943099551.489, "dur": 40.874, + "args": { + "External id": 4557107,"Record function id": 0, "Ev Idx": 5426 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1696943099601.674, "dur": 68.504, + "args": { + "External id": 4557108,"Record function id": 0, "Ev Idx": 5427 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1696943099676.913, "dur": 36546.850, + "args": { + "External id": 4557109,"Record function id": 0, "Ev Idx": 5428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696943099765.655, "dur": 6.587, + "args": { + "External id": 4557110,"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": 1336753, "tid": 1381210, + "ts": 1696943099782.236, "dur": 4.836, + "args": { + "External id": 4557111,"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": 1336753, "tid": 1381210, + "ts": 1696943099800.928, "dur": 35570.962, + "args": { + "External id": 4557112,"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": 1336753, "tid": 1381210, + "ts": 1696943099814.157, "dur": 35549.577, + "args": { + "External id": 4557113,"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": 1336753, "tid": 1381210, + "ts": 1696943099859.761, "dur": 13.296, + "args": { + "External id": 4557114,"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": 1336753, "tid": 1381210, + "ts": 1696943099879.274, "dur": 35448.233, + "args": { + "External id": 4557115,"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": 1336753, "tid": 1381210, + "ts": 1696943099881.960, "dur": 35444.860, + "args": { + "External id": 4557116,"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": 1336753, "tid": 1381210, + "ts": 1696943099885.633, "dur": 4.925, + "args": { + "External id": 4557117,"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": 1336753, "tid": 1381210, + "ts": 1696943099892.253, "dur": 35430.877, + "args": { + "External id": 4557118,"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": 1336753, "tid": 1381210, + "ts": 1696943135459.019, "dur": 10.295, + "args": { + "External id": 4557119,"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": 1336753, "tid": 1381210, + "ts": 1696943135463.381, "dur": 5.578, + "args": { + "External id": 4557120,"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": 1336753, "tid": 1381210, + "ts": 1696943135498.956, "dur": 400.384, + "args": { + "External id": 4557121,"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": 1336753, "tid": 1381210, + "ts": 1696943135539.990, "dur": 354.109, + "args": { + "External id": 4557122,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696943135552.151, "dur": 336.668, + "args": { + "External id": 4557123,"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": 1336753, "tid": 1381210, + "ts": 1696943135918.380, "dur": 2.771, + "args": { + "External id": 4557124,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696943135980.762, "dur": 38.088, + "args": { + "External id": 4557125,"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": 1336753, "tid": 1381210, + "ts": 1696943136066.942, "dur": 1.323, + "args": { + "External id": 4557126,"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": 1336753, "tid": 1381210, + "ts": 1696943136086.720, "dur": 0.965, + "args": { + "External id": 4557127,"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": 1336753, "tid": 1381210, + "ts": 1696943136098.617, "dur": 1.081, + "args": { + "External id": 4557128,"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": 1336753, "tid": 1381210, + "ts": 1696943136110.147, "dur": 0.807, + "args": { + "External id": 4557129,"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": 1336753, "tid": 1381210, + "ts": 1696943136120.404, "dur": 1.129, + "args": { + "External id": 4557130,"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": 1336753, "tid": 1381210, + "ts": 1696943136133.566, "dur": 0.807, + "args": { + "External id": 4557131,"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": 1336753, "tid": 1381210, + "ts": 1696943136145.595, "dur": 1.406, + "args": { + "External id": 4557132,"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": 1336753, "tid": 1381210, + "ts": 1696943136156.812, "dur": 0.930, + "args": { + "External id": 4557133,"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": 1336753, "tid": 1381210, + "ts": 1696943136259.524, "dur": 2700.331, + "args": { + "External id": 4557134,"Record function id": 0, "Ev Idx": 5453 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1696943136280.668, "dur": 1040.475, + "args": { + "External id": 4557135,"Record function id": 0, "Ev Idx": 5454 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1696943136298.068, "dur": 344.407, + "args": { + "External id": 4557136,"Record function id": 0, "Ev Idx": 5455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696943136386.132, "dur": 4.494, + "args": { + "External id": 4557137,"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": 1336753, "tid": 1381210, + "ts": 1696943136393.875, "dur": 0.858, + "args": { + "External id": 4557138,"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": 1336753, "tid": 1381210, + "ts": 1696943136396.377, "dur": 0.830, + "args": { + "External id": 4557139,"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": 1336753, "tid": 1381210, + "ts": 1696943136398.942, "dur": 2.497, + "args": { + "External id": 4557140,"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": 1336753, "tid": 1381210, + "ts": 1696943136402.810, "dur": 0.709, + "args": { + "External id": 4557141,"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": 1336753, "tid": 1381210, + "ts": 1696943136404.779, "dur": 0.713, + "args": { + "External id": 4557142,"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": 1336753, "tid": 1381210, + "ts": 1696943136407.625, "dur": 0.743, + "args": { + "External id": 4557143,"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": 1336753, "tid": 1381210, + "ts": 1696943136413.138, "dur": 0.586, + "args": { + "External id": 4557144,"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": 1336753, "tid": 1381210, + "ts": 1696943136415.035, "dur": 1.157, + "args": { + "External id": 4557145,"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": 1336753, "tid": 1381210, + "ts": 1696943136419.040, "dur": 0.931, + "args": { + "External id": 4557146,"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": 1336753, "tid": 1381210, + "ts": 1696943136437.731, "dur": 174.596, + "args": { + "External id": 4557147,"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": 1336753, "tid": 1381210, + "ts": 1696943136453.157, "dur": 154.376, + "args": { + "External id": 4557148,"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": 1336753, "tid": 1381210, + "ts": 1696943136474.375, "dur": 12.142, + "args": { + "External id": 4557149,"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": 1336753, "tid": 1381210, + "ts": 1696943136489.641, "dur": 89.128, + "args": { + "External id": 4557150,"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": 1336753, "tid": 1381210, + "ts": 1696943136492.227, "dur": 86.139, + "args": { + "External id": 4557151,"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": 1336753, "tid": 1381210, + "ts": 1696943136495.932, "dur": 8.417, + "args": { + "External id": 4557152,"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": 1336753, "tid": 1381210, + "ts": 1696943136506.034, "dur": 71.477, + "args": { + "External id": 4557153,"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": 1336753, "tid": 1381210, + "ts": 1696943136739.248, "dur": 573.850, + "args": { + "External id": 4557154,"Record function id": 0, "Ev Idx": 5473 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1696943136759.673, "dur": 541.927, + "args": { + "External id": 4557155,"Record function id": 0, "Ev Idx": 5474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696943136819.646, "dur": 5.781, + "args": { + "External id": 4557156,"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": 1336753, "tid": 1381210, + "ts": 1696943136841.416, "dur": 30.196, + "args": { + "External id": 4557157,"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": 1336753, "tid": 1381210, + "ts": 1696943136846.473, "dur": 1.328, + "args": { + "External id": 4557158,"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": 1336753, "tid": 1381210, + "ts": 1696943136850.023, "dur": 0.584, + "args": { + "External id": 4557159,"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": 1336753, "tid": 1381210, + "ts": 1696943136852.402, "dur": 0.339, + "args": { + "External id": 4557160,"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": 1336753, "tid": 1381210, + "ts": 1696943136856.948, "dur": 0.465, + "args": { + "External id": 4557161,"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": 1336753, "tid": 1381210, + "ts": 1696943136858.898, "dur": 0.411, + "args": { + "External id": 4557162,"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": 1336753, "tid": 1381210, + "ts": 1696943136861.133, "dur": 0.456, + "args": { + "External id": 4557163,"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": 1336753, "tid": 1381210, + "ts": 1696943136862.594, "dur": 2.523, + "args": { + "External id": 4557164,"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": 1336753, "tid": 1381210, + "ts": 1696943136866.721, "dur": 0.534, + "args": { + "External id": 4557165,"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": 1336753, "tid": 1381210, + "ts": 1696943136868.655, "dur": 0.341, + "args": { + "External id": 4557166,"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": 1336753, "tid": 1381210, + "ts": 1696943136881.698, "dur": 28.508, + "args": { + "External id": 4557167,"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": 1336753, "tid": 1381210, + "ts": 1696943136943.357, "dur": 139.946, + "args": { + "External id": 4557168,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 1336753, "tid": 1381210, + "ts": 1696943136953.152, "dur": 3.239, + "args": { + "External id": 4557169,"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": 1336753, "tid": 1381210, + "ts": 1696943136961.202, "dur": 9.811, + "args": { + "External id": 4557170,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "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": 1336753, "tid": 1381210, + "ts": 1696943136965.388, "dur": 5.193, + "args": { + "External id": 4557171,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "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": 1336753, "tid": 1381210, + "ts": 1696943136969.145, "dur": 0.390, + "args": { + "External id": 4557172,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696943136977.117, "dur": 65.560, + "args": { + "External id": 4557173,"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": 1336753, "tid": 1381210, + "ts": 1696943136978.964, "dur": 0.693, + "args": { + "External id": 4557174,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1381210, + "ts": 1696943137017.975, "dur": 1.018, + "args": { + "External id": 4557175,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1381210, + "ts": 1696943137021.356, "dur": 0.546, + "args": { + "External id": 4557176,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "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": 1336753, "tid": 1381210, + "ts": 1696943137023.831, "dur": 2.155, + "args": { + "External id": 4557177,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "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": 1336753, "tid": 1381210, + "ts": 1696943137027.321, "dur": 0.972, + "args": { + "External id": 4557178,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "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": 1336753, "tid": 1381210, + "ts": 1696943137029.401, "dur": 0.655, + "args": { + "External id": 4557179,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "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": 1336753, "tid": 1381210, + "ts": 1696943137031.711, "dur": 0.556, + "args": { + "External id": 4557180,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "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": 1336753, "tid": 1381210, + "ts": 1696943137033.926, "dur": 0.508, + "args": { + "External id": 4557181,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "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": 1336753, "tid": 1381210, + "ts": 1696943137035.536, "dur": 0.748, + "args": { + "External id": 4557182,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "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": 1336753, "tid": 1381210, + "ts": 1696943137054.104, "dur": 21.607, + "args": { + "External id": 4557183,"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": 1336753, "tid": 1381210, + "ts": 1696943137128.073, "dur": 108.335, + "args": { + "External id": 4557184,"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": 1336753, "tid": 1381210, + "ts": 1696943137152.205, "dur": 80.853, + "args": { + "External id": 4557185,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696943137161.723, "dur": 67.162, + "args": { + "External id": 4557186,"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": 1336753, "tid": 1381210, + "ts": 1696943137251.867, "dur": 1.893, + "args": { + "External id": 4557187,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696943137328.099, "dur": 1612.916, + "args": { + "External id": 4557188,"Sequence number": 45295588, "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": 1336753, "tid": 1381210, "ts": 1696943137328.099, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696943137441.121, "dur": 123.004, + "args": { + "External id": 4557189,"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": 1336753, "tid": 1381210, + "ts": 1696943137608.536, "dur": 38.921, + "args": { + "External id": 4557190,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696943137664.653, "dur": 50.242, + "args": { + "External id": 4557191,"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": 1336753, "tid": 1381210, + "ts": 1696943137724.817, "dur": 30.998, + "args": { + "External id": 4557192,"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": 1336753, "tid": 1381210, + "ts": 1696943137762.122, "dur": 44.281, + "args": { + "External id": 4557193,"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": 1336753, "tid": 1381210, + "ts": 1696943137817.372, "dur": 27.353, + "args": { + "External id": 4557194,"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": 1336753, "tid": 1381210, + "ts": 1696943137852.065, "dur": 45.164, + "args": { + "External id": 4557195,"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": 1336753, "tid": 1381210, + "ts": 1696943137920.266, "dur": 22.072, + "args": { + "External id": 4557196,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696943137960.502, "dur": 65.399, + "args": { + "External id": 4557197,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696943138052.418, "dur": 19.912, + "args": { + "External id": 4557198,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696943138086.235, "dur": 15.846, + "args": { + "External id": 4557199,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696943138112.388, "dur": 32.260, + "args": { + "External id": 4557200,"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": 1336753, "tid": 1381210, + "ts": 1696943138147.959, "dur": 33.164, + "args": { + "External id": 4557201,"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": 1336753, "tid": 1381210, + "ts": 1696943138209.078, "dur": 167.965, + "args": { + "External id": 4557202,"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": 1336753, "tid": 1381210, + "ts": 1696943138285.767, "dur": 5.727, + "args": { + "External id": 4557203,"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": 1336753, "tid": 1381210, + "ts": 1696943138293.487, "dur": 2.594, + "args": { + "External id": 4557204,"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": 1336753, "tid": 1381210, + "ts": 1696943138408.721, "dur": 23.308, + "args": { + "External id": 4557205,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696943138442.870, "dur": 14.975, + "args": { + "External id": 4557206,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696943138465.494, "dur": 35.844, + "args": { + "External id": 4557207,"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": 1336753, "tid": 1381210, + "ts": 1696943138509.876, "dur": 54.452, + "args": { + "External id": 4557208,"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": 1336753, "tid": 1381210, + "ts": 1696943138574.283, "dur": 26.268, + "args": { + "External id": 4557209,"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": 1336753, "tid": 1381210, + "ts": 1696943138606.386, "dur": 30.365, + "args": { + "External id": 4557210,"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": 1336753, "tid": 1381210, + "ts": 1696943138642.882, "dur": 22.875, + "args": { + "External id": 4557211,"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": 1336753, "tid": 1381210, + "ts": 1696943138674.750, "dur": 46.065, + "args": { + "External id": 4557212,"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": 1336753, "tid": 1381210, + "ts": 1696943138745.012, "dur": 24.025, + "args": { + "External id": 4557213,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696943138796.008, "dur": 25.047, + "args": { + "External id": 4557214,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696943138840.187, "dur": 15.831, + "args": { + "External id": 4557215,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696943138871.239, "dur": 13.671, + "args": { + "External id": 4557216,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696943138900.027, "dur": 15.401, + "args": { + "External id": 4557217,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696943139017.887, "dur": 18.144, + "args": { + "External id": 4557218,"Record function id": 0, "Ev Idx": 5537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943139022.574, "dur": 12.286, + "args": { + "External id": 4557219,"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": 1336753, "tid": 1381210, + "ts": 1696943139027.079, "dur": 6.384, + "args": { + "External id": 4557220,"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": 1336753, "tid": 1381210, + "ts": 1696943139028.955, "dur": 4.222, + "args": { + "External id": 4557221,"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": 1336753, "tid": 1381210, + "ts": 1696943139041.899, "dur": 5.182, + "args": { + "External id": 4557222,"Record function id": 0, "Ev Idx": 5541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943139043.233, "dur": 3.393, + "args": { + "External id": 4557223,"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": 1336753, "tid": 1381210, + "ts": 1696943139044.039, "dur": 1.979, + "args": { + "External id": 4557224,"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": 1336753, "tid": 1381210, + "ts": 1696943139044.860, "dur": 1.068, + "args": { + "External id": 4557225,"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": 1336753, "tid": 1381210, + "ts": 1696943139050.550, "dur": 4.471, + "args": { + "External id": 4557226,"Record function id": 0, "Ev Idx": 5545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943139051.805, "dur": 2.791, + "args": { + "External id": 4557227,"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": 1336753, "tid": 1381210, + "ts": 1696943139052.583, "dur": 1.570, + "args": { + "External id": 4557228,"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": 1336753, "tid": 1381210, + "ts": 1696943139053.071, "dur": 1.016, + "args": { + "External id": 4557229,"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": 1336753, "tid": 1381210, + "ts": 1696943139058.332, "dur": 4.270, + "args": { + "External id": 4557230,"Record function id": 0, "Ev Idx": 5549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943139059.489, "dur": 2.698, + "args": { + "External id": 4557231,"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": 1336753, "tid": 1381210, + "ts": 1696943139060.064, "dur": 1.655, + "args": { + "External id": 4557232,"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": 1336753, "tid": 1381210, + "ts": 1696943139060.774, "dur": 0.876, + "args": { + "External id": 4557233,"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": 1336753, "tid": 1381210, + "ts": 1696943139065.667, "dur": 9.777, + "args": { + "External id": 4557234,"Record function id": 0, "Ev Idx": 5553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943139067.000, "dur": 8.039, + "args": { + "External id": 4557235,"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": 1336753, "tid": 1381210, + "ts": 1696943139067.600, "dur": 7.007, + "args": { + "External id": 4557236,"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": 1336753, "tid": 1381210, + "ts": 1696943139068.223, "dur": 6.310, + "args": { + "External id": 4557237,"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": 1336753, "tid": 1381210, + "ts": 1696943139078.716, "dur": 4.323, + "args": { + "External id": 4557238,"Record function id": 0, "Ev Idx": 5557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943139079.772, "dur": 2.844, + "args": { + "External id": 4557239,"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": 1336753, "tid": 1381210, + "ts": 1696943139080.291, "dur": 1.913, + "args": { + "External id": 4557240,"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": 1336753, "tid": 1381210, + "ts": 1696943139080.832, "dur": 1.262, + "args": { + "External id": 4557241,"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": 1336753, "tid": 1381210, + "ts": 1696943139086.352, "dur": 3.792, + "args": { + "External id": 4557242,"Record function id": 0, "Ev Idx": 5561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943139087.592, "dur": 2.118, + "args": { + "External id": 4557243,"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": 1336753, "tid": 1381210, + "ts": 1696943139088.061, "dur": 1.231, + "args": { + "External id": 4557244,"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": 1336753, "tid": 1381210, + "ts": 1696943139088.367, "dur": 0.840, + "args": { + "External id": 4557245,"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": 1336753, "tid": 1381210, + "ts": 1696943139093.334, "dur": 4.080, + "args": { + "External id": 4557246,"Record function id": 0, "Ev Idx": 5565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943139094.501, "dur": 2.482, + "args": { + "External id": 4557247,"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": 1336753, "tid": 1381210, + "ts": 1696943139095.119, "dur": 1.384, + "args": { + "External id": 4557248,"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": 1336753, "tid": 1381210, + "ts": 1696943139095.374, "dur": 1.038, + "args": { + "External id": 4557249,"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": 1336753, "tid": 1381210, + "ts": 1696943139100.516, "dur": 3.976, + "args": { + "External id": 4557250,"Record function id": 0, "Ev Idx": 5569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943139101.885, "dur": 2.187, + "args": { + "External id": 4557251,"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": 1336753, "tid": 1381210, + "ts": 1696943139102.355, "dur": 1.320, + "args": { + "External id": 4557252,"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": 1336753, "tid": 1381210, + "ts": 1696943139102.956, "dur": 0.607, + "args": { + "External id": 4557253,"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": 1336753, "tid": 1381210, + "ts": 1696943139108.313, "dur": 36196.662, + "args": { + "External id": 4557254,"Record function id": 0, "Sequence number": 45295587, "Fwd thread id": 1, "Ev Idx": 5573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696943139109.688, "dur": 36187.053, + "args": { + "External id": 4557255,"Sequence number": 45295587, "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": 1336753, "tid": 1381210, "ts": 1696943139109.688, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1696943139142.299, "dur": 36.446, + "args": { + "External id": 4557256,"Record function id": 0, "Ev Idx": 5575 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1696943139186.954, "dur": 68.546, + "args": { + "External id": 4557257,"Record function id": 0, "Ev Idx": 5576 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1696943139261.356, "dur": 36027.880, + "args": { + "External id": 4557258,"Record function id": 0, "Ev Idx": 5577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696943139350.114, "dur": 6.911, + "args": { + "External id": 4557259,"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": 1336753, "tid": 1381210, + "ts": 1696943139366.064, "dur": 4.721, + "args": { + "External id": 4557260,"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": 1336753, "tid": 1381210, + "ts": 1696943139385.221, "dur": 35098.769, + "args": { + "External id": 4557261,"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": 1336753, "tid": 1381210, + "ts": 1696943139399.074, "dur": 35076.950, + "args": { + "External id": 4557262,"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": 1336753, "tid": 1381210, + "ts": 1696943139437.548, "dur": 13.327, + "args": { + "External id": 4557263,"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": 1336753, "tid": 1381210, + "ts": 1696943139457.523, "dur": 34982.569, + "args": { + "External id": 4557264,"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": 1336753, "tid": 1381210, + "ts": 1696943139460.250, "dur": 34979.162, + "args": { + "External id": 4557265,"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": 1336753, "tid": 1381210, + "ts": 1696943139464.131, "dur": 4.981, + "args": { + "External id": 4557266,"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": 1336753, "tid": 1381210, + "ts": 1696943139470.792, "dur": 34965.005, + "args": { + "External id": 4557267,"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": 1336753, "tid": 1381210, + "ts": 1696943174585.676, "dur": 10.420, + "args": { + "External id": 4557268,"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": 1336753, "tid": 1381210, + "ts": 1696943174590.148, "dur": 5.476, + "args": { + "External id": 4557269,"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": 1336753, "tid": 1381210, + "ts": 1696943174624.753, "dur": 340.259, + "args": { + "External id": 4557270,"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": 1336753, "tid": 1381210, + "ts": 1696943174651.713, "dur": 308.463, + "args": { + "External id": 4557271,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696943174662.182, "dur": 292.851, + "args": { + "External id": 4557272,"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": 1336753, "tid": 1381210, + "ts": 1696943175022.918, "dur": 4.337, + "args": { + "External id": 4557273,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696943175089.362, "dur": 7.185, + "args": { + "External id": 4557274,"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": 1336753, "tid": 1381210, + "ts": 1696943175140.298, "dur": 1.245, + "args": { + "External id": 4557275,"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": 1336753, "tid": 1381210, + "ts": 1696943175158.369, "dur": 1.545, + "args": { + "External id": 4557276,"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": 1336753, "tid": 1381210, + "ts": 1696943175171.322, "dur": 0.781, + "args": { + "External id": 4557277,"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": 1336753, "tid": 1381210, + "ts": 1696943175183.403, "dur": 1.224, + "args": { + "External id": 4557278,"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": 1336753, "tid": 1381210, + "ts": 1696943175193.829, "dur": 0.790, + "args": { + "External id": 4557279,"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": 1336753, "tid": 1381210, + "ts": 1696943175206.992, "dur": 1.770, + "args": { + "External id": 4557280,"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": 1336753, "tid": 1381210, + "ts": 1696943175218.512, "dur": 0.890, + "args": { + "External id": 4557281,"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": 1336753, "tid": 1381210, + "ts": 1696943175228.193, "dur": 1.069, + "args": { + "External id": 4557282,"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": 1336753, "tid": 1381210, + "ts": 1696943175321.146, "dur": 2156.712, + "args": { + "External id": 4557283,"Record function id": 0, "Ev Idx": 5602 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1696943175341.428, "dur": 481.142, + "args": { + "External id": 4557284,"Record function id": 0, "Ev Idx": 5603 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1696943175354.775, "dur": 357.739, + "args": { + "External id": 4557285,"Record function id": 0, "Ev Idx": 5604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1696943175442.176, "dur": 4.208, + "args": { + "External id": 4557286,"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": 1336753, "tid": 1381210, + "ts": 1696943175449.387, "dur": 0.808, + "args": { + "External id": 4557287,"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": 1336753, "tid": 1381210, + "ts": 1696943175451.777, "dur": 0.974, + "args": { + "External id": 4557288,"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": 1336753, "tid": 1381210, + "ts": 1696943175454.503, "dur": 2.643, + "args": { + "External id": 4557289,"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": 1336753, "tid": 1381210, + "ts": 1696943175458.822, "dur": 0.981, + "args": { + "External id": 4557290,"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": 1336753, "tid": 1381210, + "ts": 1696943175461.666, "dur": 1.153, + "args": { + "External id": 4557291,"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": 1336753, "tid": 1381210, + "ts": 1696943175465.756, "dur": 1.226, + "args": { + "External id": 4557292,"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": 1336753, "tid": 1381210, + "ts": 1696943175468.712, "dur": 1.772, + "args": { + "External id": 4557293,"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": 1336753, "tid": 1381210, + "ts": 1696943175471.933, "dur": 1.434, + "args": { + "External id": 4557294,"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": 1336753, "tid": 1381210, + "ts": 1696943175474.755, "dur": 1.183, + "args": { + "External id": 4557295,"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": 1336753, "tid": 1381210, + "ts": 1696943175494.484, "dur": 179.200, + "args": { + "External id": 4557296,"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": 1336753, "tid": 1381210, + "ts": 1696943175512.831, "dur": 156.194, + "args": { + "External id": 4557297,"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": 1336753, "tid": 1381210, + "ts": 1696943175548.179, "dur": 13.439, + "args": { + "External id": 4557298,"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": 1336753, "tid": 1381210, + "ts": 1696943175565.058, "dur": 74.821, + "args": { + "External id": 4557299,"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": 1336753, "tid": 1381210, + "ts": 1696943175567.866, "dur": 71.651, + "args": { + "External id": 4557300,"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": 1336753, "tid": 1381210, + "ts": 1696943175572.144, "dur": 8.451, + "args": { + "External id": 4557301,"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": 1336753, "tid": 1381210, + "ts": 1696943175582.653, "dur": 56.048, + "args": { + "External id": 4557302,"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": 1336753, "tid": 1381210, + "ts": 1696943175830.096, "dur": 1625.962, + "args": { + "External id": 4557303,"Sequence number": 45295586, "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": 1336753, "tid": 1381210, "ts": 1696943175830.096, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1696943175941.879, "dur": 146.238, + "args": { + "External id": 4557304,"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": 1336753, "tid": 1381210, + "ts": 1696943176132.611, "dur": 39.751, + "args": { + "External id": 4557305,"kernel_hash": "c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/5t/c5tnhs5xq5qc7yr3l7cgs4vzxtk3cliycxpzqbsxievrlofzpfhr.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": 1336753, "tid": 1381210, + "ts": 1696943176190.991, "dur": 51.080, + "args": { + "External id": 4557306,"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": 1336753, "tid": 1381210, + "ts": 1696943176253.091, "dur": 32.914, + "args": { + "External id": 4557307,"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": 1336753, "tid": 1381210, + "ts": 1696943176293.596, "dur": 45.929, + "args": { + "External id": 4557308,"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": 1336753, "tid": 1381210, + "ts": 1696943176346.603, "dur": 26.864, + "args": { + "External id": 4557309,"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": 1336753, "tid": 1381210, + "ts": 1696943176380.628, "dur": 42.686, + "args": { + "External id": 4557310,"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": 1336753, "tid": 1381210, + "ts": 1696943176446.185, "dur": 20.994, + "args": { + "External id": 4557311,"kernel_hash": "cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/mm/cmmtfvdkgvqhsz243szg36eql3ea4ycfjtkqpfgjhi44lbeji46k.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": 1336753, "tid": 1381210, + "ts": 1696943176484.231, "dur": 31.400, + "args": { + "External id": 4557312,"kernel_hash": "c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2", "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/4b/c4bvpuxlruf4ls6zaebh4ulq5kwzna7xpak4xntuufnkxt6y4wc2.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": 1336753, "tid": 1381210, + "ts": 1696943176577.162, "dur": 22.365, + "args": { + "External id": 4557313,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696943176614.644, "dur": 15.387, + "args": { + "External id": 4557314,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696943176640.252, "dur": 32.188, + "args": { + "External id": 4557315,"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": 1336753, "tid": 1381210, + "ts": 1696943176676.159, "dur": 35.105, + "args": { + "External id": 4557316,"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": 1336753, "tid": 1381210, + "ts": 1696943176742.172, "dur": 171.715, + "args": { + "External id": 4557317,"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": 1336753, "tid": 1381210, + "ts": 1696943176819.444, "dur": 6.048, + "args": { + "External id": 4557318,"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": 1336753, "tid": 1381210, + "ts": 1696943176827.428, "dur": 2.289, + "args": { + "External id": 4557319,"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": 1336753, "tid": 1381210, + "ts": 1696943176946.670, "dur": 26.174, + "args": { + "External id": 4557320,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696943177019.445, "dur": 20.903, + "args": { + "External id": 4557321,"kernel_hash": "cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t", "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/d3/cd3ye4lv3yv2y7l5dde5joralcg7ll6hlrrxvigczijvlwrp2l6t.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": 1336753, "tid": 1381210, + "ts": 1696943177052.025, "dur": 38.088, + "args": { + "External id": 4557322,"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": 1336753, "tid": 1381210, + "ts": 1696943177096.942, "dur": 34.537, + "args": { + "External id": 4557323,"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": 1336753, "tid": 1381210, + "ts": 1696943177139.896, "dur": 19.751, + "args": { + "External id": 4557324,"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": 1336753, "tid": 1381210, + "ts": 1696943177165.671, "dur": 29.291, + "args": { + "External id": 4557325,"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": 1336753, "tid": 1381210, + "ts": 1696943177200.580, "dur": 18.862, + "args": { + "External id": 4557326,"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": 1336753, "tid": 1381210, + "ts": 1696943177227.304, "dur": 29.638, + "args": { + "External id": 4557327,"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": 1336753, "tid": 1381210, + "ts": 1696943177273.158, "dur": 25.239, + "args": { + "External id": 4557328,"kernel_hash": "cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/as/cas6dq7e5rikp56ssrhbxwcqp4ttdyuwqorivviwplq7rgsqykgf.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": 1336753, "tid": 1381210, + "ts": 1696943177314.030, "dur": 25.403, + "args": { + "External id": 4557329,"kernel_hash": "cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od", "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/ny/cnyczubjxqoksn4kug4drlj6rdh2oloxs37rovzz3o7ct4qcv4od.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": 1336753, "tid": 1381210, + "ts": 1696943177351.863, "dur": 16.224, + "args": { + "External id": 4557330,"kernel_hash": "c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/2k/c2kpn4mfmx5wt5gmjhm7dpm4gulqcmz5mcm7dlheptufg56to5av.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": 1336753, "tid": 1381210, + "ts": 1696943177381.585, "dur": 13.851, + "args": { + "External id": 4557331,"kernel_hash": "cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/yf/cyfeqwmtr3blvks63uqsw3zds2osxyp6k5wrjhmcluio7cothlaw.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": 1336753, "tid": 1381210, + "ts": 1696943177407.495, "dur": 18.876, + "args": { + "External id": 4557332,"kernel_hash": "c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/25/c25b4nhnmm2ykwmscwd3eqlx5bkfkwuzdtym5ifpvjo2smy2yhw6.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": 1336753, "tid": 1381210, + "ts": 1696943177504.211, "dur": 14.849, + "args": { + "External id": 4557333,"Record function id": 0, "Ev Idx": 5652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943177507.360, "dur": 10.785, + "args": { + "External id": 4557334,"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": 1336753, "tid": 1381210, + "ts": 1696943177511.476, "dur": 5.819, + "args": { + "External id": 4557335,"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": 1336753, "tid": 1381210, + "ts": 1696943177513.066, "dur": 4.120, + "args": { + "External id": 4557336,"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": 1336753, "tid": 1381210, + "ts": 1696943177522.978, "dur": 22.465, + "args": { + "External id": 4557337,"Record function id": 0, "Ev Idx": 5656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943177524.204, "dur": 20.125, + "args": { + "External id": 4557338,"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": 1336753, "tid": 1381210, + "ts": 1696943177525.086, "dur": 18.234, + "args": { + "External id": 4557339,"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": 1336753, "tid": 1381210, + "ts": 1696943177540.914, "dur": 2.019, + "args": { + "External id": 4557340,"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": 1336753, "tid": 1381210, + "ts": 1696943177550.956, "dur": 5.993, + "args": { + "External id": 4557341,"Record function id": 0, "Ev Idx": 5660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943177552.789, "dur": 3.710, + "args": { + "External id": 4557342,"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": 1336753, "tid": 1381210, + "ts": 1696943177553.877, "dur": 2.093, + "args": { + "External id": 4557343,"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": 1336753, "tid": 1381210, + "ts": 1696943177554.880, "dur": 1.010, + "args": { + "External id": 4557344,"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": 1336753, "tid": 1381210, + "ts": 1696943177560.425, "dur": 4.954, + "args": { + "External id": 4557345,"Record function id": 0, "Ev Idx": 5664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943177562.039, "dur": 2.912, + "args": { + "External id": 4557346,"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": 1336753, "tid": 1381210, + "ts": 1696943177563.083, "dur": 1.430, + "args": { + "External id": 4557347,"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": 1336753, "tid": 1381210, + "ts": 1696943177563.671, "dur": 0.763, + "args": { + "External id": 4557348,"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": 1336753, "tid": 1381210, + "ts": 1696943177568.506, "dur": 4.218, + "args": { + "External id": 4557349,"Record function id": 0, "Ev Idx": 5668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943177569.993, "dur": 2.316, + "args": { + "External id": 4557350,"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": 1336753, "tid": 1381210, + "ts": 1696943177570.598, "dur": 1.318, + "args": { + "External id": 4557351,"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": 1336753, "tid": 1381210, + "ts": 1696943177570.904, "dur": 0.948, + "args": { + "External id": 4557352,"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": 1336753, "tid": 1381210, + "ts": 1696943177575.935, "dur": 5.081, + "args": { + "External id": 4557353,"Record function id": 0, "Ev Idx": 5672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943177577.163, "dur": 3.379, + "args": { + "External id": 4557354,"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": 1336753, "tid": 1381210, + "ts": 1696943177578.302, "dur": 1.791, + "args": { + "External id": 4557355,"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": 1336753, "tid": 1381210, + "ts": 1696943177579.090, "dur": 0.914, + "args": { + "External id": 4557356,"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": 1336753, "tid": 1381210, + "ts": 1696943177584.329, "dur": 5.725, + "args": { + "External id": 4557357,"Record function id": 0, "Ev Idx": 5676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943177585.483, "dur": 4.126, + "args": { + "External id": 4557358,"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": 1336753, "tid": 1381210, + "ts": 1696943177586.019, "dur": 3.151, + "args": { + "External id": 4557359,"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": 1336753, "tid": 1381210, + "ts": 1696943177586.369, "dur": 2.723, + "args": { + "External id": 4557360,"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": 1336753, "tid": 1381210, + "ts": 1696943177593.241, "dur": 4.848, + "args": { + "External id": 4557361,"Record function id": 0, "Ev Idx": 5680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943177594.821, "dur": 2.850, + "args": { + "External id": 4557362,"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": 1336753, "tid": 1381210, + "ts": 1696943177595.568, "dur": 1.669, + "args": { + "External id": 4557363,"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": 1336753, "tid": 1381210, + "ts": 1696943177596.224, "dur": 0.934, + "args": { + "External id": 4557364,"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": 1336753, "tid": 1381210, + "ts": 1696943177601.095, "dur": 3.770, + "args": { + "External id": 4557365,"Record function id": 0, "Ev Idx": 5684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943177602.170, "dur": 2.247, + "args": { + "External id": 4557366,"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": 1336753, "tid": 1381210, + "ts": 1696943177602.669, "dur": 1.307, + "args": { + "External id": 4557367,"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": 1336753, "tid": 1381210, + "ts": 1696943177603.144, "dur": 0.749, + "args": { + "External id": 4557368,"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": 1336753, "tid": 1381210, + "ts": 1696943177608.674, "dur": 38410.578, + "args": { + "External id": 4557369,"Record function id": 0, "Sequence number": 45295585, "Fwd thread id": 1, "Ev Idx": 5688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696943177610.260, "dur": 38368.012, + "args": { + "External id": 4557370,"Sequence number": 45295585, "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": 1336753, "tid": 1381210, "ts": 1696943177610.260, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1696943177638.491, "dur": 37.954, + "args": { + "External id": 4557371,"Record function id": 0, "Ev Idx": 5690 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1696943177683.907, "dur": 72.058, + "args": { + "External id": 4557372,"Record function id": 0, "Ev Idx": 5691 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1696943177761.612, "dur": 38208.976, + "args": { + "External id": 4557373,"Record function id": 0, "Ev Idx": 5692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696943177868.173, "dur": 6.987, + "args": { + "External id": 4557374,"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": 1336753, "tid": 1381210, + "ts": 1696943177888.191, "dur": 4.700, + "args": { + "External id": 4557375,"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": 1336753, "tid": 1381210, + "ts": 1696943177907.425, "dur": 37296.693, + "args": { + "External id": 4557376,"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": 1336753, "tid": 1381210, + "ts": 1696943177920.386, "dur": 37275.493, + "args": { + "External id": 4557377,"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": 1336753, "tid": 1381210, + "ts": 1696943177968.495, "dur": 13.213, + "args": { + "External id": 4557378,"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": 1336753, "tid": 1381210, + "ts": 1696943178024.610, "dur": 37134.130, + "args": { + "External id": 4557379,"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": 1336753, "tid": 1381210, + "ts": 1696943178027.150, "dur": 37131.004, + "args": { + "External id": 4557380,"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": 1336753, "tid": 1381210, + "ts": 1696943178032.112, "dur": 6.607, + "args": { + "External id": 4557381,"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": 1336753, "tid": 1381210, + "ts": 1696943178041.947, "dur": 37113.271, + "args": { + "External id": 4557382,"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": 1336753, "tid": 1381210, + "ts": 1696943215292.897, "dur": 7.902, + "args": { + "External id": 4557383,"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": 1336753, "tid": 1381210, + "ts": 1696943215295.322, "dur": 5.210, + "args": { + "External id": 4557384,"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": 1336753, "tid": 1381210, + "ts": 1696943215331.184, "dur": 354.448, + "args": { + "External id": 4557385,"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": 1336753, "tid": 1381210, + "ts": 1696943215357.165, "dur": 323.025, + "args": { + "External id": 4557386,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696943215367.160, "dur": 307.186, + "args": { + "External id": 4557387,"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": 1336753, "tid": 1381210, + "ts": 1696943215704.736, "dur": 2.476, + "args": { + "External id": 4557388,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696943215766.607, "dur": 6.825, + "args": { + "External id": 4557389,"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": 1336753, "tid": 1381210, + "ts": 1696943215818.499, "dur": 1.550, + "args": { + "External id": 4557390,"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": 1336753, "tid": 1381210, + "ts": 1696943215835.451, "dur": 1.060, + "args": { + "External id": 4557391,"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": 1336753, "tid": 1381210, + "ts": 1696943215850.040, "dur": 1.218, + "args": { + "External id": 4557392,"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": 1336753, "tid": 1381210, + "ts": 1696943215862.756, "dur": 1.524, + "args": { + "External id": 4557393,"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": 1336753, "tid": 1381210, + "ts": 1696943215874.069, "dur": 1.121, + "args": { + "External id": 4557394,"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": 1336753, "tid": 1381210, + "ts": 1696943215886.168, "dur": 0.829, + "args": { + "External id": 4557395,"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": 1336753, "tid": 1381210, + "ts": 1696943215899.656, "dur": 1.198, + "args": { + "External id": 4557396,"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": 1336753, "tid": 1381210, + "ts": 1696943215910.373, "dur": 0.903, + "args": { + "External id": 4557397,"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": 1336753, "tid": 1381210, + "ts": 1696943216036.805, "dur": 259.622, + "args": { + "External id": 4557398,"Record function id": 0, "Sequence number": 45295584, "Fwd thread id": 1, "Ev Idx": 5717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1696943216039.736, "dur": 248.831, + "args": { + "External id": 4557399,"Sequence number": 45295584, "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": 1336753, "tid": 1381210, "ts": 1696943216039.736, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 1336753, "tid": 1381210, + "ts": 1696943216151.621, "dur": 43.817, + "args": { + "External id": 4557400,"kernel_hash": "cfr73mqqwqpdrss7r6csecalgrfowe5r3r24yaeyivzpezfoy4fz", "grid": "grid(65536000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "65536000"], "kernel_file": "/tmp/torchinductor_cvm/fr/cfr73mqqwqpdrss7r6csecalgrfowe5r3r24yaeyivzpezfoy4fz.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": 1336753, "tid": 1381210, + "ts": 1696943216209.664, "dur": 26.536, + "args": { + "External id": 4557401,"kernel_hash": "cxedqnbrx2bvln4bf3pphdmthxjm6nsxqowbdddlxye4bt3yfnsg", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/xe/cxedqnbrx2bvln4bf3pphdmthxjm6nsxqowbdddlxye4bt3yfnsg.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": 1336753, "tid": 1381210, + "ts": 1696943216255.028, "dur": 19.469, + "args": { + "External id": 4557402,"kernel_hash": "c2xxuncnwkfhjvqk7hfnejnsljjkm6qo4ajwnumdr7vdpf4nk2iq", "grid": "grid(65536000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "65536000"], "kernel_file": "/tmp/torchinductor_cvm/2x/c2xxuncnwkfhjvqk7hfnejnsljjkm6qo4ajwnumdr7vdpf4nk2iq.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": 1336753, "tid": 1381210, + "ts": 1696943216305.506, "dur": 17.809, + "args": { + "External id": 4557403,"Record function id": 0, "Ev Idx": 5722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1696943216311.490, "dur": 10.874, + "args": { + "External id": 4557404,"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": 1336753, "tid": 1381210, + "ts": 1696943216315.396, "dur": 6.194, + "args": { + "External id": 4557405,"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": 1336753, "tid": 1381210, + "ts": 1696943216317.090, "dur": 4.389, + "args": { + "External id": 4557406,"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": 1336753, "tid": 1381210, + "ts": 1696943216345.572, "dur": 6608.673, + "args": { + "External id": 4557407,"Record function id": 0, "Ev Idx": 5726 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 1336753, "tid": 1381210, + "ts": 1696943216363.922, "dur": 42.919, + "args": { + "External id": 4557408,"Record function id": 0, "Ev Idx": 5727 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 1336753, "tid": 1381210, + "ts": 1696943216413.948, "dur": 304.131, + "args": { + "External id": 4557409,"Record function id": 0, "Ev Idx": 5728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 1336753, "tid": 1381210, + "ts": 1696943216726.304, "dur": 5956.185, + "args": { + "External id": 4557410,"Record function id": 0, "Ev Idx": 5729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1696943216846.219, "dur": 7.452, + "args": { + "External id": 4557411,"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": 1336753, "tid": 1381210, + "ts": 1696943216864.179, "dur": 5.794, + "args": { + "External id": 4557412,"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": 1336753, "tid": 1381210, + "ts": 1696943216890.889, "dur": 4501.298, + "args": { + "External id": 4557413,"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": 1336753, "tid": 1381210, + "ts": 1696943216909.541, "dur": 4469.357, + "args": { + "External id": 4557414,"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": 1336753, "tid": 1381210, + "ts": 1696943217291.293, "dur": 20.053, + "args": { + "External id": 4557415,"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": 1336753, "tid": 1381210, + "ts": 1696943217376.390, "dur": 3952.206, + "args": { + "External id": 4557416,"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": 1336753, "tid": 1381210, + "ts": 1696943217379.971, "dur": 3947.538, + "args": { + "External id": 4557417,"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": 1336753, "tid": 1381210, + "ts": 1696943217385.336, "dur": 14.455, + "args": { + "External id": 4557418,"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": 1336753, "tid": 1381210, + "ts": 1696943217402.821, "dur": 3919.379, + "args": { + "External id": 4557419,"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": 1336753, "tid": 1381210, + "ts": 1696943221522.862, "dur": 26.245, + "args": { + "External id": 4557420,"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": 1336753, "tid": 1381210, + "ts": 1696943221539.614, "dur": 8.918, + "args": { + "External id": 4557421,"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": 1336753, "tid": 1381210, + "ts": 1696943221580.040, "dur": 396.571, + "args": { + "External id": 4557422,"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": 1336753, "tid": 1381210, + "ts": 1696943221605.467, "dur": 366.298, + "args": { + "External id": 4557423,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 1336753, "tid": 1381210, + "ts": 1696943221620.165, "dur": 346.291, + "args": { + "External id": 4557424,"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": 1336753, "tid": 1381210, + "ts": 1696943222029.595, "dur": 3.193, + "args": { + "External id": 4557425,"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": ["", "", "0", "", "[]", "[]", "-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": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1381210, + "ts": 1696943222093.536, "dur": 7.531, + "args": { + "External id": 4557426,"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": 1336753, "tid": 1381210, + "ts": 1696943222143.965, "dur": 1.459, + "args": { + "External id": 4557427,"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": 1336753, "tid": 1381210, + "ts": 1696943222160.562, "dur": 1.147, + "args": { + "External id": 4557428,"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": 1336753, "tid": 1381210, + "ts": 1696943222174.348, "dur": 3.973, + "args": { + "External id": 4557429,"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": 1336753, "tid": 1381210, + "ts": 1696943222190.130, "dur": 1.474, + "args": { + "External id": 4557430,"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": 1336753, "tid": 1381210, + "ts": 1696943222201.793, "dur": 1.486, + "args": { + "External id": 4557431,"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": 1336753, "tid": 1381210, + "ts": 1696943222215.547, "dur": 1.202, + "args": { + "External id": 4557432,"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": 1336753, "tid": 1381210, + "ts": 1696943222226.777, "dur": 2.928, + "args": { + "External id": 4557433,"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": 1336753, "tid": 1381210, + "ts": 1696943222241.051, "dur": 1.545, + "args": { + "External id": 4557434,"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": 1336753, "tid": 1381210, + "ts": 1696943222252.707, "dur": 1.463, + "args": { + "External id": 4557435,"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": 1336753, "tid": 1381210, + "ts": 1696943222265.090, "dur": 1.486, + "args": { + "External id": 4557436,"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": 1336753, "tid": 1381210, + "ts": 1696943222276.666, "dur": 3.111, + "args": { + "External id": 4557437,"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": 1336753, "tid": 1381210, + "ts": 1696943222291.420, "dur": 1.406, + "args": { + "External id": 4557438,"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": 1336753, "tid": 1381210, + "ts": 1696943222301.966, "dur": 1.108, + "args": { + "External id": 4557439,"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": 1336753, "tid": 1381210, + "ts": 1696943222312.071, "dur": 1.279, + "args": { + "External id": 4557440,"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": 1336753, "tid": 1381210, + "ts": 1696943222323.152, "dur": 2.477, + "args": { + "External id": 4557441,"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": 1336753, "tid": 1381210, + "ts": 1696943222336.310, "dur": 1.523, + "args": { + "External id": 4557442,"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": 1336753, "tid": 1381210, + "ts": 1696943222347.730, "dur": 1.472, + "args": { + "External id": 4557443,"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": 1336753, "tid": 1381210, + "ts": 1696943222358.814, "dur": 1.724, + "args": { + "External id": 4557444,"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": 1336753, "tid": 1381210, + "ts": 1696943222370.362, "dur": 2.548, + "args": { + "External id": 4557445,"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": 1336753, "tid": 1381210, + "ts": 1696943222383.622, "dur": 1.341, + "args": { + "External id": 4557446,"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": 1336753, "tid": 1381210, + "ts": 1696943222396.557, "dur": 1.293, + "args": { + "External id": 4557447,"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": 1336753, "tid": 1381210, + "ts": 1696943222407.496, "dur": 1.391, + "args": { + "External id": 4557448,"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": 1336753, "tid": 1381210, + "ts": 1696943222419.066, "dur": 3.348, + "args": { + "External id": 4557449,"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": 1336753, "tid": 1381210, + "ts": 1696943222432.288, "dur": 1.673, + "args": { + "External id": 4557450,"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": 1336753, "tid": 1381210, + "ts": 1696943222443.634, "dur": 1.522, + "args": { + "External id": 4557451,"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": 1336753, "tid": 1381210, + "ts": 1696943222454.732, "dur": 1.302, + "args": { + "External id": 4557452,"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": 1336753, "tid": 1381210, + "ts": 1696943222466.133, "dur": 3.526, + "args": { + "External id": 4557453,"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": 1336753, "tid": 1381210, + "ts": 1696943222481.276, "dur": 1.575, + "args": { + "External id": 4557454,"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": 1336753, "tid": 1381210, + "ts": 1696943222493.091, "dur": 1.280, + "args": { + "External id": 4557455,"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": 1336753, "tid": 1381210, + "ts": 1696943222504.252, "dur": 1.127, + "args": { + "External id": 4557456,"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": 1336753, "tid": 1381210, + "ts": 1696943222515.335, "dur": 3.158, + "args": { + "External id": 4557457,"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": 1336753, "tid": 1381210, + "ts": 1696943222543.030, "dur": 2.582, + "args": { + "External id": 4557458,"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": 1336753, "tid": 1381210, + "ts": 1696943222559.028, "dur": 1.322, + "args": { + "External id": 4557459,"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": 1336753, "tid": 1381210, + "ts": 1696943222570.379, "dur": 1.622, + "args": { + "External id": 4557460,"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": 1336753, "tid": 1381210, + "ts": 1696943222582.068, "dur": 2.848, + "args": { + "External id": 4557461,"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": 1336753, "tid": 1381210, + "ts": 1696943222595.136, "dur": 1.164, + "args": { + "External id": 4557462,"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": 1336753, "tid": 1381210, + "ts": 1696943222605.534, "dur": 1.558, + "args": { + "External id": 4557463,"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": 1336753, "tid": 1381210, + "ts": 1696943222616.863, "dur": 1.153, + "args": { + "External id": 4557464,"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#188415", "pid": 1336753, "tid": 1336753, + "ts": 1696941146262.605, "dur": 2095676.624, + "args": { + "External id": 4546561,"Record function id": 0, "Ev Idx": 5784 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.zero_grad#AdamW.zero_grad", "pid": 1336753, "tid": 1336753, + "ts": 1696941146298.662, "dur": 716.977, + "args": { + "External id": 4546562,"Record function id": 0, "Ev Idx": 5785 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 1336753, "tid": 1336753, + "ts": 1696941147059.662, "dur": 2312.917, + "args": { + "External id": 4546563,"Record function id": 0, "Ev Idx": 5786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941148240.014, "dur": 8.408, + "args": { + "External id": 4546564,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 1336753, "tid": 1336753, + "ts": 1696941148269.106, "dur": 6.241, + "args": { + "External id": 4546565,"Sequence number": 45295584, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[16, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 5788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941148791.594, "dur": 2.500, + "args": { + "External id": 4546566,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 1336753, "tid": 1336753, + "ts": 1696941148804.325, "dur": 2.509, + "args": { + "External id": 4546567,"Sequence number": 45295584, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[16, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 5790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941149266.013, "dur": 2.144, + "args": { + "External id": 4546568,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::set_", "pid": 1336753, "tid": 1336753, + "ts": 1696941149272.591, "dur": 2.161, + "args": { + "External id": 4546569,"Sequence number": 45295584, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "0", "[16, 8192]", "[8192, 1]"], "Input type": ["long int", "", "Scalar", "ScalarList", "ScalarList"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[0], [], [], [], []], "Ev Idx": 5792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941150426.478, "dur": 16.022, + "args": { + "External id": 4546570,"Sequence number": 45295584, "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": 5793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941150436.336, "dur": 2.344, + "args": { + "External id": 4546571,"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": 5794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941150444.053, "dur": 4.040, + "args": { + "External id": 4546572,"Sequence number": 45295584, "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": 5795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941150446.024, "dur": 0.942, + "args": { + "External id": 4546573,"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": 5796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941150475.518, "dur": 615.594, + "args": { + "External id": 4546574,"Sequence number": 45295584, "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": 5797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941150482.376, "dur": 607.820, + "args": { + "External id": 4546575,"Sequence number": 45295584, "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": 5798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941150491.394, "dur": 9.758, + "args": { + "External id": 4546576,"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": 5799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941150503.752, "dur": 584.368, + "args": { + "External id": 4546577,"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": 5800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941150513.478, "dur": 0.615, + "args": { + "External id": 4546578,"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": 5801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941150516.243, "dur": 6.528, + "args": { + "External id": 4546579,"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": 5802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 1336753, "tid": 1336753, + "ts": 1696941150518.610, "dur": 3.996, + "args": { + "External id": 4546580,"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": 5803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941150521.625, "dur": 0.733, + "args": { + "External id": 4546581,"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": 5804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1696941150524.647, "dur": 273.448, + "args": { + "External id": 4546582,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 5805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1696941150544.164, "dur": 253.418, + "args": { + "External id": 4546583,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 5806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941150546.551, "dur": 17.236, + "args": { + "External id": 4546584,"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": 5807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941150548.993, "dur": 14.108, + "args": { + "External id": 4546585,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941150564.865, "dur": 232.022, + "args": { + "External id": 4546586,"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": 5809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941150800.701, "dur": 282.373, + "args": { + "External id": 4546587,"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": 5810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941151110.792, "dur": 625.791, + "args": { + "External id": 4546588,"Sequence number": 45295584, "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": 5811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941151112.881, "dur": 622.911, + "args": { + "External id": 4546589,"Sequence number": 45295584, "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": 5812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941151123.997, "dur": 10.912, + "args": { + "External id": 4546590,"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": 5813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941151135.983, "dur": 595.128, + "args": { + "External id": 4546591,"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": 5814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 1336753, "tid": 1336753, + "ts": 1696941151766.811, "dur": 53.656, + "args": { + "External id": 4546592,"Record function id": 0, "Concrete Inputs": ["0", "4096", "", "", "", "False"], "Input type": ["Scalar", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941151772.259, "dur": 5.821, + "args": { + "External id": 4546593,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 1336753, "tid": 1336753, + "ts": 1696941151780.645, "dur": 39.443, + "args": { + "External id": 4546594,"Record function id": 0, "Concrete Inputs": ["0", "4096", "1", ""], "Input type": ["Scalar", "Scalar", "Scalar", "long int"], "Input Strides": [[], [], [], [1]], "Input Dims": [[], [], [], [0]], "Ev Idx": 5817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941151784.890, "dur": 7.587, + "args": { + "External id": 4546595,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["long int", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 5818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::repeat", "pid": 1336753, "tid": 1336753, + "ts": 1696941151831.838, "dur": 78.768, + "args": { + "External id": 4546596,"Sequence number": 45295584, "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": 5819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 1336753, "tid": 1336753, + "ts": 1696941151839.470, "dur": 7.637, + "args": { + "External id": 4546597,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[4096], [], []], "Ev Idx": 5820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941151844.729, "dur": 2.038, + "args": { + "External id": 4546598,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "[4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 5821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941151848.067, "dur": 5.581, + "args": { + "External id": 4546599,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1336753, + "ts": 1696941151856.073, "dur": 3.289, + "args": { + "External id": 4546600,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[4096, 1]], "Input Dims": [[16, 4096]], "Ev Idx": 5823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 1336753, "tid": 1336753, + "ts": 1696941151861.387, "dur": 5.177, + "args": { + "External id": 4546601,"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": 5824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941151865.868, "dur": 0.524, + "args": { + "External id": 4546602,"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": 5825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 1336753, "tid": 1336753, + "ts": 1696941151867.353, "dur": 4.798, + "args": { + "External id": 4546603,"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": 5826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941151871.259, "dur": 0.805, + "args": { + "External id": 4546604,"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": 5827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941151873.739, "dur": 7.424, + "args": { + "External id": 4546605,"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": 5828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 1336753, "tid": 1336753, + "ts": 1696941151878.742, "dur": 2.322, + "args": { + "External id": 4546606,"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": 5829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941151880.365, "dur": 0.603, + "args": { + "External id": 4546607,"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": 5830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941151882.386, "dur": 27.360, + "args": { + "External id": 4546608,"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": 5831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941151919.143, "dur": 29.778, + "args": { + "External id": 4546609,"Sequence number": 45295584, "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": 5832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941151920.476, "dur": 28.257, + "args": { + "External id": 4546610,"Sequence number": 45295584, "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": 5833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941151925.937, "dur": 3.586, + "args": { + "External id": 4546611,"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": 5834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941151930.194, "dur": 17.998, + "args": { + "External id": 4546612,"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": 5835 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_pre_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941152103.179, "dur": 154.107, + "args": { + "External id": 4546613,"Record function id": 0, "Ev Idx": 5836 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 1336753, "tid": 1336753, + "ts": 1696941152185.889, "dur": 59.746, + "args": { + "External id": 4546614,"Record function id": 0, "Ev Idx": 5837 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941152265.386, "dur": 41.107, + "args": { + "External id": 4546615,"Record function id": 0, "Ev Idx": 5838 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941152314.895, "dur": 8821.471, + "args": { + "External id": 4546616,"Record function id": 0, "Ev Idx": 5839 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 1336753, "tid": 1336753, + "ts": 1696941152325.019, "dur": 1341.853, + "args": { + "External id": 4546617,"Record function id": 0, "Ev Idx": 5840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941152448.662, "dur": 7.725, + "args": { + "External id": 4546618,"Record function id": 0, "Concrete Inputs": ["[42076416]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941152474.565, "dur": 150.506, + "args": { + "External id": 4546619,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[42076416], [], []], "Ev Idx": 5842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152479.970, "dur": 1.885, + "args": { + "External id": 4546620,"Record function id": 0, "Concrete Inputs": ["", "[8192000]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941152488.459, "dur": 0.544, + "args": { + "External id": 4546621,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "8192000"], "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": 1336753, "tid": 1336753, + "ts": 1696941152489.740, "dur": 0.433, + "args": { + "External id": 4546622,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "8192256"], "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": 1336753, "tid": 1336753, + "ts": 1696941152491.102, "dur": 2.209, + "args": { + "External id": 4546623,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "8716544"], "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": 1336753, "tid": 1336753, + "ts": 1696941152498.639, "dur": 0.256, + "args": { + "External id": 4546624,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "9240832"], "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": 1336753, "tid": 1336753, + "ts": 1696941152499.590, "dur": 0.269, + "args": { + "External id": 4546625,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "9765120"], "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": 1336753, "tid": 1336753, + "ts": 1696941152500.423, "dur": 2.407, + "args": { + "External id": 4546626,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "10289408"], "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": 1336753, "tid": 1336753, + "ts": 1696941152506.125, "dur": 0.341, + "args": { + "External id": 4546627,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "10289664"], "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": 1336753, "tid": 1336753, + "ts": 1696941152507.248, "dur": 0.261, + "args": { + "External id": 4546628,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "11731456"], "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": 1336753, "tid": 1336753, + "ts": 1696941152512.645, "dur": 0.438, + "args": { + "External id": 4546629,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "13173248"], "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": 1336753, "tid": 1336753, + "ts": 1696941152513.671, "dur": 0.448, + "args": { + "External id": 4546630,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "14615040"], "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": 1336753, "tid": 1336753, + "ts": 1696941152514.986, "dur": 1.445, + "args": { + "External id": 4546631,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "14615296"], "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": 1336753, "tid": 1336753, + "ts": 1696941152521.865, "dur": 0.388, + "args": { + "External id": 4546632,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "15139584"], "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": 1336753, "tid": 1336753, + "ts": 1696941152522.838, "dur": 0.157, + "args": { + "External id": 4546633,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "15663872"], "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": 1336753, "tid": 1336753, + "ts": 1696941152523.756, "dur": 17.443, + "args": { + "External id": 4546634,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "16188160"], "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": 1336753, "tid": 1336753, + "ts": 1696941152546.695, "dur": 0.344, + "args": { + "External id": 4546635,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "16712448"], "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": 1336753, "tid": 1336753, + "ts": 1696941152547.736, "dur": 0.345, + "args": { + "External id": 4546636,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "16712704"], "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": 1336753, "tid": 1336753, + "ts": 1696941152553.757, "dur": 0.322, + "args": { + "External id": 4546637,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "18154496"], "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": 1336753, "tid": 1336753, + "ts": 1696941152554.743, "dur": 0.364, + "args": { + "External id": 4546638,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "19596288"], "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": 1336753, "tid": 1336753, + "ts": 1696941152555.809, "dur": 1.342, + "args": { + "External id": 4546639,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21038080"], "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": 1336753, "tid": 1336753, + "ts": 1696941152562.009, "dur": 0.490, + "args": { + "External id": 4546640,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "21038336"], "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": 1336753, "tid": 1336753, + "ts": 1696941152563.046, "dur": 0.328, + "args": { + "External id": 4546641,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "21562624"], "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": 1336753, "tid": 1336753, + "ts": 1696941152564.090, "dur": 2.267, + "args": { + "External id": 4546642,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "22086912"], "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": 1336753, "tid": 1336753, + "ts": 1696941152569.509, "dur": 0.146, + "args": { + "External id": 4546643,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "22611200"], "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": 1336753, "tid": 1336753, + "ts": 1696941152570.670, "dur": 0.166, + "args": { + "External id": 4546644,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "23135488"], "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": 1336753, "tid": 1336753, + "ts": 1696941152576.102, "dur": 0.347, + "args": { + "External id": 4546645,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "23135744"], "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": 1336753, "tid": 1336753, + "ts": 1696941152576.937, "dur": 0.733, + "args": { + "External id": 4546646,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24577536"], "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": 1336753, "tid": 1336753, + "ts": 1696941152578.554, "dur": 1.453, + "args": { + "External id": 4546647,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "26019328"], "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": 1336753, "tid": 1336753, + "ts": 1696941152583.185, "dur": 0.500, + "args": { + "External id": 4546648,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "27461120"], "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": 1336753, "tid": 1336753, + "ts": 1696941152584.291, "dur": 0.142, + "args": { + "External id": 4546649,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "27461376"], "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": 1336753, "tid": 1336753, + "ts": 1696941152585.112, "dur": 2.537, + "args": { + "External id": 4546650,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "27985664"], "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": 1336753, "tid": 1336753, + "ts": 1696941152591.218, "dur": 0.321, + "args": { + "External id": 4546651,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "28509952"], "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": 1336753, "tid": 1336753, + "ts": 1696941152592.195, "dur": 0.504, + "args": { + "External id": 4546652,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29034240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152596.997, "dur": 0.441, + "args": { + "External id": 4546653,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "29558528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152598.020, "dur": 0.354, + "args": { + "External id": 4546654,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "29558784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152599.126, "dur": 1.158, + "args": { + "External id": 4546655,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "31000576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152603.802, "dur": 0.142, + "args": { + "External id": 4546656,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "32442368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152604.525, "dur": 0.339, + "args": { + "External id": 4546657,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "33884160"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152605.416, "dur": 2.285, + "args": { + "External id": 4546658,"Record function id": 0, "Concrete Inputs": ["", "[8192000]", "[1]", "33884416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941152650.889, "dur": 84.737, + "args": { + "External id": 4546659,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 5882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941152811.091, "dur": 312.640, + "args": { + "External id": 4546660,"Record function id": 0, "Concrete Inputs": ["", "", "42076416", "8", "0", "15", ""], "Input type": ["TensorList", "", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 5883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941152829.302, "dur": 4.933, + "args": { + "External id": 4546661,"Record function id": 0, "Concrete Inputs": ["[336611328]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941152840.833, "dur": 13.867, + "args": { + "External id": 4546662,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "42076416"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[336611328], [], [], []], "Ev Idx": 5885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941152845.471, "dur": 8.791, + "args": { + "External id": 4546663,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "42076416", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[336611328], [], [], [], []], "Ev Idx": 5886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152851.033, "dur": 0.588, + "args": { + "External id": 4546664,"Record function id": 0, "Concrete Inputs": ["", "[42076416]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[336611328], [], [], []], "Ev Idx": 5887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941152863.099, "dur": 156.322, + "args": { + "External id": 4546665,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[42076416], [], []], "Ev Idx": 5888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152864.898, "dur": 0.498, + "args": { + "External id": 4546666,"Record function id": 0, "Concrete Inputs": ["", "[8192000]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941152866.573, "dur": 0.510, + "args": { + "External id": 4546667,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "8192000"], "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": 1336753, "tid": 1336753, + "ts": 1696941152870.273, "dur": 1.667, + "args": { + "External id": 4546668,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "8192256"], "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": 1336753, "tid": 1336753, + "ts": 1696941152872.695, "dur": 0.638, + "args": { + "External id": 4546669,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "8716544"], "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": 1336753, "tid": 1336753, + "ts": 1696941152875.975, "dur": 0.498, + "args": { + "External id": 4546670,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "9240832"], "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": 1336753, "tid": 1336753, + "ts": 1696941152876.977, "dur": 0.534, + "args": { + "External id": 4546671,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "9765120"], "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": 1336753, "tid": 1336753, + "ts": 1696941152878.336, "dur": 0.184, + "args": { + "External id": 4546672,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "10289408"], "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": 1336753, "tid": 1336753, + "ts": 1696941152882.168, "dur": 0.387, + "args": { + "External id": 4546673,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "10289664"], "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": 1336753, "tid": 1336753, + "ts": 1696941152883.126, "dur": 0.570, + "args": { + "External id": 4546674,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "11731456"], "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": 1336753, "tid": 1336753, + "ts": 1696941152884.336, "dur": 0.488, + "args": { + "External id": 4546675,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "13173248"], "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": 1336753, "tid": 1336753, + "ts": 1696941152888.282, "dur": 1.208, + "args": { + "External id": 4546676,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "14615040"], "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": 1336753, "tid": 1336753, + "ts": 1696941152890.506, "dur": 0.391, + "args": { + "External id": 4546677,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "14615296"], "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": 1336753, "tid": 1336753, + "ts": 1696941152893.489, "dur": 2.872, + "args": { + "External id": 4546678,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "15139584"], "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": 1336753, "tid": 1336753, + "ts": 1696941152897.002, "dur": 0.546, + "args": { + "External id": 4546679,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "15663872"], "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": 1336753, "tid": 1336753, + "ts": 1696941152898.129, "dur": 0.143, + "args": { + "External id": 4546680,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "16188160"], "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": 1336753, "tid": 1336753, + "ts": 1696941152903.458, "dur": 0.206, + "args": { + "External id": 4546681,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "16712448"], "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": 1336753, "tid": 1336753, + "ts": 1696941152904.309, "dur": 0.343, + "args": { + "External id": 4546682,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "16712704"], "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": 1336753, "tid": 1336753, + "ts": 1696941152905.397, "dur": 0.619, + "args": { + "External id": 4546683,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "18154496"], "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": 1336753, "tid": 1336753, + "ts": 1696941152911.207, "dur": 1.355, + "args": { + "External id": 4546684,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "19596288"], "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": 1336753, "tid": 1336753, + "ts": 1696941152913.541, "dur": 0.536, + "args": { + "External id": 4546685,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21038080"], "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": 1336753, "tid": 1336753, + "ts": 1696941152916.837, "dur": 2.274, + "args": { + "External id": 4546686,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "21038336"], "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": 1336753, "tid": 1336753, + "ts": 1696941152919.581, "dur": 0.277, + "args": { + "External id": 4546687,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "21562624"], "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": 1336753, "tid": 1336753, + "ts": 1696941152920.288, "dur": 0.356, + "args": { + "External id": 4546688,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "22086912"], "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": 1336753, "tid": 1336753, + "ts": 1696941152925.990, "dur": 0.155, + "args": { + "External id": 4546689,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "22611200"], "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": 1336753, "tid": 1336753, + "ts": 1696941152926.776, "dur": 0.177, + "args": { + "External id": 4546690,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "23135488"], "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": 1336753, "tid": 1336753, + "ts": 1696941152927.626, "dur": 0.177, + "args": { + "External id": 4546691,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "23135744"], "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": 1336753, "tid": 1336753, + "ts": 1696941152933.358, "dur": 1.566, + "args": { + "External id": 4546692,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24577536"], "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": 1336753, "tid": 1336753, + "ts": 1696941152935.666, "dur": 0.302, + "args": { + "External id": 4546693,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "26019328"], "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": 1336753, "tid": 1336753, + "ts": 1696941152938.738, "dur": 2.014, + "args": { + "External id": 4546694,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "27461120"], "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": 1336753, "tid": 1336753, + "ts": 1696941152941.255, "dur": 0.156, + "args": { + "External id": 4546695,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "27461376"], "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": 1336753, "tid": 1336753, + "ts": 1696941152942.042, "dur": 0.164, + "args": { + "External id": 4546696,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "27985664"], "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": 1336753, "tid": 1336753, + "ts": 1696941152947.859, "dur": 0.133, + "args": { + "External id": 4546697,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "28509952"], "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": 1336753, "tid": 1336753, + "ts": 1696941152948.420, "dur": 0.171, + "args": { + "External id": 4546698,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29034240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152949.188, "dur": 0.352, + "args": { + "External id": 4546699,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "29558528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152954.902, "dur": 1.415, + "args": { + "External id": 4546700,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "29558784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152956.740, "dur": 0.132, + "args": { + "External id": 4546701,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "31000576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152959.518, "dur": 2.367, + "args": { + "External id": 4546702,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "32442368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152962.394, "dur": 0.299, + "args": { + "External id": 4546703,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "33884160"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941152963.518, "dur": 0.350, + "args": { + "External id": 4546704,"Record function id": 0, "Concrete Inputs": ["", "[8192000]", "[1]", "33884416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941153044.640, "dur": 62.649, + "args": { + "External id": 4546705,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 5928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941153180.784, "dur": 368.406, + "args": { + "External id": 4546706,"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": 5929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941153216.520, "dur": 326.832, + "args": { + "External id": 4546707,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 5930, "In msg nelems": 42076416 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941153226.495, "dur": 293.809, + "args": { + "External id": 4546708,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[42076416]], "Ev Idx": 5931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941153579.424, "dur": 2.942, + "args": { + "External id": 4546709,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5932, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out", "pid": 1336753, "tid": 1336753, + "ts": 1696941153683.795, "dur": 7215.350, + "args": { + "External id": 4546710,"Record function id": 0, "Ev Idx": 5933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153907.661, "dur": 6.831, + "args": { + "External id": 4546711,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[336611328], []], "Ev Idx": 5934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153918.766, "dur": 1.251, + "args": { + "External id": 4546712,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[65536000], []], "Ev Idx": 5935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153921.986, "dur": 0.956, + "args": { + "External id": 4546713,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153924.985, "dur": 2.047, + "args": { + "External id": 4546714,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153928.732, "dur": 0.827, + "args": { + "External id": 4546715,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153930.940, "dur": 0.905, + "args": { + "External id": 4546716,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153935.235, "dur": 0.694, + "args": { + "External id": 4546717,"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": 1336753, "tid": 1336753, + "ts": 1696941153937.356, "dur": 1.862, + "args": { + "External id": 4546718,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153942.925, "dur": 0.755, + "args": { + "External id": 4546719,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153944.855, "dur": 0.823, + "args": { + "External id": 4546720,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153949.652, "dur": 0.592, + "args": { + "External id": 4546721,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153951.404, "dur": 1.975, + "args": { + "External id": 4546722,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153955.102, "dur": 0.643, + "args": { + "External id": 4546723,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153957.089, "dur": 0.919, + "args": { + "External id": 4546724,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153961.065, "dur": 0.665, + "args": { + "External id": 4546725,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153962.916, "dur": 1.691, + "args": { + "External id": 4546726,"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": 1336753, "tid": 1336753, + "ts": 1696941153968.076, "dur": 0.601, + "args": { + "External id": 4546727,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153970.243, "dur": 0.694, + "args": { + "External id": 4546728,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153974.744, "dur": 0.531, + "args": { + "External id": 4546729,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153976.702, "dur": 1.994, + "args": { + "External id": 4546730,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941153980.081, "dur": 50.168, + "args": { + "External id": 4546731,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154035.197, "dur": 1.133, + "args": { + "External id": 4546732,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154039.879, "dur": 0.555, + "args": { + "External id": 4546733,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154041.867, "dur": 1.699, + "args": { + "External id": 4546734,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154064.604, "dur": 0.705, + "args": { + "External id": 4546735,"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": 1336753, "tid": 1336753, + "ts": 1696941154066.914, "dur": 0.723, + "args": { + "External id": 4546736,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154071.129, "dur": 0.605, + "args": { + "External id": 4546737,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154073.288, "dur": 1.270, + "args": { + "External id": 4546738,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154076.240, "dur": 0.578, + "args": { + "External id": 4546739,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154078.247, "dur": 1.005, + "args": { + "External id": 4546740,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154082.498, "dur": 0.559, + "args": { + "External id": 4546741,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154084.486, "dur": 1.712, + "args": { + "External id": 4546742,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154090.594, "dur": 0.546, + "args": { + "External id": 4546743,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154092.738, "dur": 0.723, + "args": { + "External id": 4546744,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154097.026, "dur": 0.470, + "args": { + "External id": 4546745,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154099.056, "dur": 1.620, + "args": { + "External id": 4546746,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154102.185, "dur": 0.579, + "args": { + "External id": 4546747,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154103.976, "dur": 0.437, + "args": { + "External id": 4546748,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154107.736, "dur": 0.512, + "args": { + "External id": 4546749,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941154109.433, "dur": 1.685, + "args": { + "External id": 4546750,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[65536000], []], "Ev Idx": 5973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941154143.768, "dur": 6703.943, + "args": { + "External id": 4546751,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[42076416, 1], [], [], []], "Input Dims": [[8, 42076416], [], [], []], "Ev Idx": 5974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941154169.574, "dur": 6669.924, + "args": { + "External id": 4546752,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[42076416, 1], [], [], []], "Input Dims": [[8, 42076416], [], [], []], "Ev Idx": 5975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941154192.561, "dur": 6.115, + "args": { + "External id": 4546753,"Record function id": 0, "Concrete Inputs": ["[4290]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941154205.701, "dur": 6592.814, + "args": { + "External id": 4546754,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[4290], [], [], [], [], [], [], []], "Ev Idx": 5977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941154208.297, "dur": 6589.485, + "args": { + "External id": 4546755,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[4290], [], [], [], [], [], []], "Ev Idx": 5978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941154216.625, "dur": 5.460, + "args": { + "External id": 4546756,"Record function id": 0, "Concrete Inputs": ["[4290]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941154225.926, "dur": 6568.808, + "args": { + "External id": 4546757,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4290], [4290], []], "Ev Idx": 5980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941161220.974, "dur": 40.616, + "args": { + "External id": 4546758,"Record function id": 0, "Ev Idx": 5981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 1336753, "tid": 1336753, + "ts": 1696941161263.300, "dur": 222.081, + "args": { + "External id": 4546759,"Record function id": 0, "Ev Idx": 5982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941161306.388, "dur": 169.242, + "args": { + "External id": 4546760,"Sequence number": 45295584, "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": 5983 + } + }, + { + "ph": "s", "id": 228, "pid": 1336753, "tid": 1336753, "ts": 1696941161306.388, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941161382.302, "dur": 55.522, + "args": { + "External id": 4546761,"kernel_hash": "cepuvqida76mp3inhfyv5xcp3dgr5kc6gyyaupvhufqptth43nyf", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ep/cepuvqida76mp3inhfyv5xcp3dgr5kc6gyyaupvhufqptth43nyf.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": 5984 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941161563.698, "dur": 54.521, + "args": { + "External id": 4546762,"Record function id": 0, "Ev Idx": 5985 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 1336753, "tid": 1336753, + "ts": 1696941161630.157, "dur": 7476.279, + "args": { + "External id": 4546763,"Record function id": 0, "Ev Idx": 5986 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 1336753, "tid": 1336753, + "ts": 1696941161637.889, "dur": 808.313, + "args": { + "External id": 4546764,"Record function id": 0, "Ev Idx": 5987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941161713.062, "dur": 10.609, + "args": { + "External id": 4546765,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941161738.499, "dur": 42.613, + "args": { + "External id": 4546766,"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": 5989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161748.058, "dur": 2.060, + "args": { + "External id": 4546767,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941161751.929, "dur": 0.472, + "args": { + "External id": 4546768,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941161753.451, "dur": 2.589, + "args": { + "External id": 4546769,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161759.231, "dur": 0.379, + "args": { + "External id": 4546770,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161760.294, "dur": 0.298, + "args": { + "External id": 4546771,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161766.243, "dur": 0.187, + "args": { + "External id": 4546772,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161767.150, "dur": 0.178, + "args": { + "External id": 4546773,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161768.113, "dur": 1.417, + "args": { + "External id": 4546774,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161773.493, "dur": 0.556, + "args": { + "External id": 4546775,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941161791.739, "dur": 39.234, + "args": { + "External id": 4546776,"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": 5999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941161864.882, "dur": 114.497, + "args": { + "External id": 4546777,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 6000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941161876.270, "dur": 3.421, + "args": { + "External id": 4546778,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941161885.037, "dur": 12.090, + "args": { + "External id": 4546779,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941161889.245, "dur": 7.429, + "args": { + "External id": 4546780,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161895.117, "dur": 0.400, + "args": { + "External id": 4546781,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941161903.174, "dur": 31.612, + "args": { + "External id": 4546782,"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": 6005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161904.636, "dur": 0.480, + "args": { + "External id": 4546783,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941161909.518, "dur": 0.515, + "args": { + "External id": 4546784,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941161913.095, "dur": 0.256, + "args": { + "External id": 4546785,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161916.612, "dur": 0.197, + "args": { + "External id": 4546786,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161917.725, "dur": 3.656, + "args": { + "External id": 4546787,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161922.300, "dur": 0.350, + "args": { + "External id": 4546788,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161925.563, "dur": 0.668, + "args": { + "External id": 4546789,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161929.393, "dur": 0.167, + "args": { + "External id": 4546790,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941161930.162, "dur": 0.544, + "args": { + "External id": 4546791,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941161948.001, "dur": 22.492, + "args": { + "External id": 4546792,"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": 6015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941162069.936, "dur": 288.037, + "args": { + "External id": 4546793,"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": 6016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941162102.599, "dur": 250.835, + "args": { + "External id": 4546794,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 6017, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941162112.247, "dur": 236.020, + "args": { + "External id": 4546795,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941162379.013, "dur": 2.039, + "args": { + "External id": 4546796,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6019, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 1336753, "tid": 1336753, + "ts": 1696941162467.966, "dur": 6287.228, + "args": { + "External id": 4546797,"Record function id": 0, "Ev Idx": 6020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941162591.338, "dur": 7.113, + "args": { + "External id": 4546798,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941162602.171, "dur": 1.202, + "args": { + "External id": 4546799,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941162604.998, "dur": 1.029, + "args": { + "External id": 4546800,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941162607.516, "dur": 1.924, + "args": { + "External id": 4546801,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941162613.245, "dur": 1.117, + "args": { + "External id": 4546802,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941162615.637, "dur": 1.162, + "args": { + "External id": 4546803,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941162618.270, "dur": 1.230, + "args": { + "External id": 4546804,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941162622.934, "dur": 2.246, + "args": { + "External id": 4546805,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941162628.807, "dur": 0.698, + "args": { + "External id": 4546806,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941162630.776, "dur": 0.617, + "args": { + "External id": 4546807,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941162649.102, "dur": 6024.975, + "args": { + "External id": 4546808,"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": 6031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941162666.717, "dur": 5993.243, + "args": { + "External id": 4546809,"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": 6032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941162693.615, "dur": 13.090, + "args": { + "External id": 4546810,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941162711.071, "dur": 5889.581, + "args": { + "External id": 4546811,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941162715.751, "dur": 5883.637, + "args": { + "External id": 4546812,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941162721.860, "dur": 7.357, + "args": { + "External id": 4546813,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941162731.030, "dur": 5858.218, + "args": { + "External id": 4546814,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941168968.339, "dur": 97.333, + "args": { + "External id": 4546815,"Sequence number": 45295585, "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": 6038 + } + }, + { + "ph": "s", "id": 227, "pid": 1336753, "tid": 1336753, "ts": 1696941168968.339, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941169041.847, "dur": 17.055, + "args": { + "External id": 4546816,"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": 6039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941169050.669, "dur": 7.662, + "args": { + "External id": 4546817,"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": 6040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941169159.845, "dur": 114.925, + "args": { + "External id": 4546818,"Record function id": 0, "Ev Idx": 6041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941169277.382, "dur": 1668.571, + "args": { + "External id": 4546819,"Record function id": 0, "Ev Idx": 6042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941169336.463, "dur": 1589.385, + "args": { + "External id": 4546820,"Sequence number": 45295586, "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": 6043 + } + }, + { + "ph": "s", "id": 226, "pid": 1336753, "tid": 1336753, "ts": 1696941169336.463, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941169433.117, "dur": 64.148, + "args": { + "External id": 4546821,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 6044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941169515.488, "dur": 161.175, + "args": { + "External id": 4546822,"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": 6045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941169703.033, "dur": 73.527, + "args": { + "External id": 4546823,"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": 6046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941169788.641, "dur": 48.372, + "args": { + "External id": 4546824,"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": 6047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941169880.231, "dur": 43.722, + "args": { + "External id": 4546825,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941169953.826, "dur": 22.949, + "args": { + "External id": 4546826,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941170060.821, "dur": 195.899, + "args": { + "External id": 4546827,"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": 6050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941170136.883, "dur": 15.679, + "args": { + "External id": 4546828,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941170142.992, "dur": 8.355, + "args": { + "External id": 4546829,"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": 6052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941170155.690, "dur": 5.048, + "args": { + "External id": 4546830,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941170167.483, "dur": 1.978, + "args": { + "External id": 4546831,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941170173.142, "dur": 5.662, + "args": { + "External id": 4546832,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941170272.953, "dur": 79.931, + "args": { + "External id": 4546833,"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": 6056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941170398.948, "dur": 46.095, + "args": { + "External id": 4546834,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 6057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941170455.605, "dur": 63.757, + "args": { + "External id": 4546835,"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": 6058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941170566.726, "dur": 59.011, + "args": { + "External id": 4546836,"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": 6059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941170660.077, "dur": 39.259, + "args": { + "External id": 4546837,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 6060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941170707.770, "dur": 48.232, + "args": { + "External id": 4546838,"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": 6061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941170789.743, "dur": 27.756, + "args": { + "External id": 4546839,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 6062 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.0)", "pid": 1336753, "tid": 1336753, + "ts": 1696941171109.269, "dur": 116.808, + "args": { + "External id": 4546840,"Record function id": 0, "Ev Idx": 6063 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941171324.535, "dur": 63.591, + "args": { + "External id": 4546841,"Record function id": 0, "Ev Idx": 6064 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 1336753, "tid": 1336753, + "ts": 1696941171401.737, "dur": 16954.282, + "args": { + "External id": 4546842,"Record function id": 0, "Ev Idx": 6065 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 1336753, "tid": 1336753, + "ts": 1696941171414.632, "dur": 1333.346, + "args": { + "External id": 4546843,"Record function id": 0, "Ev Idx": 6066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941171519.043, "dur": 48.812, + "args": { + "External id": 4546844,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941171589.186, "dur": 56.455, + "args": { + "External id": 4546845,"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": 6068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171598.539, "dur": 5.220, + "args": { + "External id": 4546846,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941171606.078, "dur": 1.000, + "args": { + "External id": 4546847,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941171611.009, "dur": 0.523, + "args": { + "External id": 4546848,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171615.948, "dur": 0.395, + "args": { + "External id": 4546849,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171617.831, "dur": 1.678, + "args": { + "External id": 4546850,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171623.390, "dur": 0.493, + "args": { + "External id": 4546851,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171627.741, "dur": 0.795, + "args": { + "External id": 4546852,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171630.017, "dur": 0.553, + "args": { + "External id": 4546853,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171634.487, "dur": 3.221, + "args": { + "External id": 4546854,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941171661.193, "dur": 60.927, + "args": { + "External id": 4546855,"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": 6078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941171769.817, "dur": 163.736, + "args": { + "External id": 4546856,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 6079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941171788.082, "dur": 6.513, + "args": { + "External id": 4546857,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941171801.478, "dur": 12.436, + "args": { + "External id": 4546858,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941171806.588, "dur": 6.763, + "args": { + "External id": 4546859,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171810.787, "dur": 0.813, + "args": { + "External id": 4546860,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941171823.711, "dur": 43.628, + "args": { + "External id": 4546861,"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": 6084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171828.848, "dur": 0.710, + "args": { + "External id": 4546862,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941171831.204, "dur": 2.183, + "args": { + "External id": 4546863,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941171835.065, "dur": 2.554, + "args": { + "External id": 4546864,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171841.752, "dur": 0.465, + "args": { + "External id": 4546865,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171843.451, "dur": 0.960, + "args": { + "External id": 4546866,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171847.938, "dur": 0.254, + "args": { + "External id": 4546867,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171851.730, "dur": 0.428, + "args": { + "External id": 4546868,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171853.300, "dur": 0.694, + "args": { + "External id": 4546869,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941171860.631, "dur": 0.622, + "args": { + "External id": 4546870,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941171884.910, "dur": 35.374, + "args": { + "External id": 4546871,"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": 6094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941172097.007, "dur": 501.115, + "args": { + "External id": 4546872,"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": 6095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941172137.858, "dur": 451.641, + "args": { + "External id": 4546873,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 6096, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941172151.321, "dur": 427.220, + "args": { + "External id": 4546874,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941172636.818, "dur": 4.196, + "args": { + "External id": 4546875,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6098, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 1336753, "tid": 1336753, + "ts": 1696941172779.042, "dur": 15344.056, + "args": { + "External id": 4546876,"Record function id": 0, "Ev Idx": 6099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941172925.223, "dur": 9.094, + "args": { + "External id": 4546877,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941172939.561, "dur": 1.915, + "args": { + "External id": 4546878,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941172944.021, "dur": 1.795, + "args": { + "External id": 4546879,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941172948.485, "dur": 1.445, + "args": { + "External id": 4546880,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941172952.188, "dur": 1.458, + "args": { + "External id": 4546881,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941172958.648, "dur": 1.303, + "args": { + "External id": 4546882,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941172965.316, "dur": 1.474, + "args": { + "External id": 4546883,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941172970.070, "dur": 3.990, + "args": { + "External id": 4546884,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941172976.511, "dur": 1.413, + "args": { + "External id": 4546885,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941172982.859, "dur": 50.334, + "args": { + "External id": 4546886,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941173061.173, "dur": 14994.470, + "args": { + "External id": 4546887,"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": 6110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941173086.444, "dur": 14955.981, + "args": { + "External id": 4546888,"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": 6111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941173118.342, "dur": 17.499, + "args": { + "External id": 4546889,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941173141.309, "dur": 14827.134, + "args": { + "External id": 4546890,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941173144.731, "dur": 14822.404, + "args": { + "External id": 4546891,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941173151.459, "dur": 7.450, + "args": { + "External id": 4546892,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941173161.280, "dur": 14800.239, + "args": { + "External id": 4546893,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941188291.786, "dur": 37.147, + "args": { + "External id": 4546894,"Sequence number": 45295587, "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": 6117 + } + }, + { + "ph": "s", "id": 225, "pid": 1336753, "tid": 1336753, "ts": 1696941188291.786, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941188309.243, "dur": 14.526, + "args": { + "External id": 4546895,"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": 6118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941188317.075, "dur": 6.493, + "args": { + "External id": 4546896,"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": 6119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941188401.324, "dur": 80.665, + "args": { + "External id": 4546897,"Record function id": 0, "Ev Idx": 6120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941188483.783, "dur": 1137.555, + "args": { + "External id": 4546898,"Record function id": 0, "Ev Idx": 6121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941188543.652, "dur": 1063.316, + "args": { + "External id": 4546899,"Sequence number": 45295588, "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": 6122 + } + }, + { + "ph": "s", "id": 224, "pid": 1336753, "tid": 1336753, "ts": 1696941188543.652, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941188632.734, "dur": 50.545, + "args": { + "External id": 4546900,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 6123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941188699.761, "dur": 102.792, + "args": { + "External id": 4546901,"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": 6124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941188810.518, "dur": 38.872, + "args": { + "External id": 4546902,"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": 6125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941188855.622, "dur": 31.156, + "args": { + "External id": 4546903,"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": 6126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941188919.744, "dur": 28.709, + "args": { + "External id": 4546904,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941188963.932, "dur": 55.704, + "args": { + "External id": 4546905,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941189040.378, "dur": 136.791, + "args": { + "External id": 4546906,"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": 6129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941189092.961, "dur": 13.270, + "args": { + "External id": 4546907,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941189097.953, "dur": 7.513, + "args": { + "External id": 4546908,"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": 6131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941189110.891, "dur": 5.385, + "args": { + "External id": 4546909,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941189117.358, "dur": 2.905, + "args": { + "External id": 4546910,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941189122.363, "dur": 2.968, + "args": { + "External id": 4546911,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941189187.456, "dur": 51.271, + "args": { + "External id": 4546912,"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": 6135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941189271.199, "dur": 29.436, + "args": { + "External id": 4546913,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 6136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941189310.460, "dur": 41.179, + "args": { + "External id": 4546914,"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": 6137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941189357.657, "dur": 33.908, + "args": { + "External id": 4546915,"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": 6138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941189415.889, "dur": 26.174, + "args": { + "External id": 4546916,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 6139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941189446.803, "dur": 34.095, + "args": { + "External id": 4546917,"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": 6140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941189499.428, "dur": 22.838, + "args": { + "External id": 4546918,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 6141 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.1)", "pid": 1336753, "tid": 1336753, + "ts": 1696941189686.981, "dur": 80.232, + "args": { + "External id": 4546919,"Record function id": 0, "Ev Idx": 6142 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941189842.658, "dur": 46.675, + "args": { + "External id": 4546920,"Record function id": 0, "Ev Idx": 6143 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 1336753, "tid": 1336753, + "ts": 1696941189899.393, "dur": 18527.552, + "args": { + "External id": 4546921,"Record function id": 0, "Ev Idx": 6144 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 1336753, "tid": 1336753, + "ts": 1696941189911.097, "dur": 941.108, + "args": { + "External id": 4546922,"Record function id": 0, "Ev Idx": 6145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941190031.992, "dur": 9.716, + "args": { + "External id": 4546923,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941190060.377, "dur": 40.719, + "args": { + "External id": 4546924,"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": 6147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190065.327, "dur": 2.314, + "args": { + "External id": 4546925,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941190071.922, "dur": 0.543, + "args": { + "External id": 4546926,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941190075.892, "dur": 0.592, + "args": { + "External id": 4546927,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190077.143, "dur": 0.551, + "args": { + "External id": 4546928,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190080.983, "dur": 0.205, + "args": { + "External id": 4546929,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190084.154, "dur": 0.321, + "args": { + "External id": 4546930,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190085.420, "dur": 3.786, + "args": { + "External id": 4546931,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190092.655, "dur": 0.354, + "args": { + "External id": 4546932,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190093.584, "dur": 0.438, + "args": { + "External id": 4546933,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941190112.642, "dur": 47.913, + "args": { + "External id": 4546934,"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": 6157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941190196.457, "dur": 115.817, + "args": { + "External id": 4546935,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 6158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941190209.830, "dur": 3.989, + "args": { + "External id": 4546936,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941190218.799, "dur": 9.396, + "args": { + "External id": 4546937,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941190223.155, "dur": 4.609, + "args": { + "External id": 4546938,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190226.085, "dur": 0.545, + "args": { + "External id": 4546939,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941190234.457, "dur": 34.422, + "args": { + "External id": 4546940,"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": 6163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190238.186, "dur": 2.756, + "args": { + "External id": 4546941,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941190241.670, "dur": 0.402, + "args": { + "External id": 4546942,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941190242.753, "dur": 0.244, + "args": { + "External id": 4546943,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190248.648, "dur": 1.471, + "args": { + "External id": 4546944,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190250.849, "dur": 0.413, + "args": { + "External id": 4546945,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190254.227, "dur": 0.179, + "args": { + "External id": 4546946,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190257.253, "dur": 0.253, + "args": { + "External id": 4546947,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190258.101, "dur": 0.476, + "args": { + "External id": 4546948,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941190261.659, "dur": 2.647, + "args": { + "External id": 4546949,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941190279.378, "dur": 24.927, + "args": { + "External id": 4546950,"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": 6173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941190366.435, "dur": 381.551, + "args": { + "External id": 4546951,"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": 6174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941190401.832, "dur": 340.363, + "args": { + "External id": 4546952,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 6175, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941190413.293, "dur": 322.436, + "args": { + "External id": 4546953,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941190778.277, "dur": 2.395, + "args": { + "External id": 4546954,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6177, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 1336753, "tid": 1336753, + "ts": 1696941190874.199, "dur": 17266.698, + "args": { + "External id": 4546955,"Record function id": 0, "Ev Idx": 6178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941190975.953, "dur": 43.860, + "args": { + "External id": 4546956,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941191026.193, "dur": 1.832, + "args": { + "External id": 4546957,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941191030.155, "dur": 2.479, + "args": { + "External id": 4546958,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941191034.478, "dur": 1.090, + "args": { + "External id": 4546959,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941191037.374, "dur": 0.993, + "args": { + "External id": 4546960,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941191039.784, "dur": 0.905, + "args": { + "External id": 4546961,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941191044.203, "dur": 0.971, + "args": { + "External id": 4546962,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941191046.937, "dur": 2.393, + "args": { + "External id": 4546963,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941191050.665, "dur": 0.817, + "args": { + "External id": 4546964,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941191052.664, "dur": 0.747, + "args": { + "External id": 4546965,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941191076.622, "dur": 16988.895, + "args": { + "External id": 4546966,"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": 6189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941191092.544, "dur": 16957.890, + "args": { + "External id": 4546967,"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": 6190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941191117.067, "dur": 14.648, + "args": { + "External id": 4546968,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941191134.642, "dur": 16795.925, + "args": { + "External id": 4546969,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941191137.192, "dur": 16791.913, + "args": { + "External id": 4546970,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941191143.423, "dur": 5.981, + "args": { + "External id": 4546971,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941191151.034, "dur": 16770.975, + "args": { + "External id": 4546972,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941208346.125, "dur": 42.081, + "args": { + "External id": 4546973,"Sequence number": 45295589, "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": 6196 + } + }, + { + "ph": "s", "id": 223, "pid": 1336753, "tid": 1336753, "ts": 1696941208346.125, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941208369.066, "dur": 13.300, + "args": { + "External id": 4546974,"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": 6197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941208374.471, "dur": 7.433, + "args": { + "External id": 4546975,"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": 6198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941208482.798, "dur": 149.387, + "args": { + "External id": 4546976,"Record function id": 0, "Ev Idx": 6199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941208636.269, "dur": 1684.476, + "args": { + "External id": 4546977,"Record function id": 0, "Ev Idx": 6200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941208698.970, "dur": 1601.447, + "args": { + "External id": 4546978,"Sequence number": 45295590, "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": 6201 + } + }, + { + "ph": "s", "id": 222, "pid": 1336753, "tid": 1336753, "ts": 1696941208698.970, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941208801.655, "dur": 64.097, + "args": { + "External id": 4546979,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 6202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941208884.510, "dur": 198.977, + "args": { + "External id": 4546980,"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": 6203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941209107.699, "dur": 63.029, + "args": { + "External id": 4546981,"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": 6204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941209185.063, "dur": 47.240, + "args": { + "External id": 4546982,"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": 6205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941209273.197, "dur": 37.141, + "args": { + "External id": 4546983,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941209335.970, "dur": 23.455, + "args": { + "External id": 4546984,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941209385.645, "dur": 204.265, + "args": { + "External id": 4546985,"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": 6208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941209447.702, "dur": 17.373, + "args": { + "External id": 4546986,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941209456.488, "dur": 7.638, + "args": { + "External id": 4546987,"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": 6210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941209467.987, "dur": 7.621, + "args": { + "External id": 4546988,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941209477.424, "dur": 1.469, + "args": { + "External id": 4546989,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941209481.733, "dur": 5.930, + "args": { + "External id": 4546990,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941209607.132, "dur": 80.849, + "args": { + "External id": 4546991,"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": 6214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941209740.674, "dur": 46.526, + "args": { + "External id": 4546992,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 6215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941209801.202, "dur": 69.139, + "args": { + "External id": 4546993,"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": 6216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941209882.879, "dur": 52.153, + "args": { + "External id": 4546994,"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": 6217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941209962.446, "dur": 95.559, + "args": { + "External id": 4546995,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 6218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941210070.289, "dur": 55.469, + "args": { + "External id": 4546996,"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": 6219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941210163.290, "dur": 26.780, + "args": { + "External id": 4546997,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 6220 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.2)", "pid": 1336753, "tid": 1336753, + "ts": 1696941210403.485, "dur": 112.289, + "args": { + "External id": 4546998,"Record function id": 0, "Ev Idx": 6221 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941210648.759, "dur": 70.775, + "args": { + "External id": 4546999,"Record function id": 0, "Ev Idx": 6222 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 1336753, "tid": 1336753, + "ts": 1696941210735.855, "dur": 17208.615, + "args": { + "External id": 4547000,"Record function id": 0, "Ev Idx": 6223 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 1336753, "tid": 1336753, + "ts": 1696941210752.654, "dur": 1448.251, + "args": { + "External id": 4547001,"Record function id": 0, "Ev Idx": 6224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941210859.977, "dur": 12.606, + "args": { + "External id": 4547002,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941210891.407, "dur": 60.458, + "args": { + "External id": 4547003,"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": 6226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941210898.409, "dur": 2.897, + "args": { + "External id": 4547004,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941210909.603, "dur": 0.865, + "args": { + "External id": 4547005,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941210911.819, "dur": 0.746, + "args": { + "External id": 4547006,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941210920.083, "dur": 0.644, + "args": { + "External id": 4547007,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941210927.729, "dur": 0.529, + "args": { + "External id": 4547008,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941210929.503, "dur": 0.624, + "args": { + "External id": 4547009,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941210934.404, "dur": 4.237, + "args": { + "External id": 4547010,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941210940.300, "dur": 0.481, + "args": { + "External id": 4547011,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941210942.108, "dur": 0.532, + "args": { + "External id": 4547012,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941210969.389, "dur": 118.695, + "args": { + "External id": 4547013,"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": 6236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941211143.013, "dur": 200.706, + "args": { + "External id": 4547014,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 6237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941211163.151, "dur": 8.044, + "args": { + "External id": 4547015,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941211181.362, "dur": 16.722, + "args": { + "External id": 4547016,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941211188.458, "dur": 9.064, + "args": { + "External id": 4547017,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941211193.177, "dur": 1.827, + "args": { + "External id": 4547018,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941211211.946, "dur": 43.164, + "args": { + "External id": 4547019,"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": 6242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941211214.703, "dur": 3.142, + "args": { + "External id": 4547020,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941211219.305, "dur": 0.536, + "args": { + "External id": 4547021,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941211223.834, "dur": 0.555, + "args": { + "External id": 4547022,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941211228.199, "dur": 2.599, + "args": { + "External id": 4547023,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941211233.781, "dur": 0.613, + "args": { + "External id": 4547024,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941211235.603, "dur": 0.297, + "args": { + "External id": 4547025,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941211239.683, "dur": 0.296, + "args": { + "External id": 4547026,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941211244.227, "dur": 0.472, + "args": { + "External id": 4547027,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941211245.968, "dur": 2.953, + "args": { + "External id": 4547028,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941211288.071, "dur": 42.469, + "args": { + "External id": 4547029,"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": 6252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941211419.815, "dur": 621.920, + "args": { + "External id": 4547030,"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": 6253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941211461.576, "dur": 514.580, + "args": { + "External id": 4547031,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 6254, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941211480.610, "dur": 484.363, + "args": { + "External id": 4547032,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941212084.473, "dur": 6.404, + "args": { + "External id": 4547033,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6256, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 1336753, "tid": 1336753, + "ts": 1696941212231.518, "dur": 15469.607, + "args": { + "External id": 4547034,"Record function id": 0, "Ev Idx": 6257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941212366.527, "dur": 7.933, + "args": { + "External id": 4547035,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941212379.767, "dur": 2.648, + "args": { + "External id": 4547036,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941212385.021, "dur": 3.539, + "args": { + "External id": 4547037,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941212391.560, "dur": 1.108, + "args": { + "External id": 4547038,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941212394.930, "dur": 1.116, + "args": { + "External id": 4547039,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941212398.341, "dur": 1.363, + "args": { + "External id": 4547040,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941212404.869, "dur": 1.032, + "args": { + "External id": 4547041,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941212408.458, "dur": 3.220, + "args": { + "External id": 4547042,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941212414.114, "dur": 1.100, + "args": { + "External id": 4547043,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941212417.395, "dur": 1.107, + "args": { + "External id": 4547044,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941212446.285, "dur": 15193.025, + "args": { + "External id": 4547045,"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": 6268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941212466.311, "dur": 15161.193, + "args": { + "External id": 4547046,"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": 6269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941212496.439, "dur": 18.109, + "args": { + "External id": 4547047,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941212518.560, "dur": 15062.898, + "args": { + "External id": 4547048,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941212521.815, "dur": 15058.616, + "args": { + "External id": 4547049,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941212551.544, "dur": 10.015, + "args": { + "External id": 4547050,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941212564.281, "dur": 15010.756, + "args": { + "External id": 4547051,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941227860.387, "dur": 56.487, + "args": { + "External id": 4547052,"Sequence number": 45295591, "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": 6275 + } + }, + { + "ph": "s", "id": 221, "pid": 1336753, "tid": 1336753, "ts": 1696941227860.387, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941227900.986, "dur": 11.131, + "args": { + "External id": 4547053,"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": 6276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941227905.750, "dur": 6.157, + "args": { + "External id": 4547054,"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": 6277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941228020.692, "dur": 81.654, + "args": { + "External id": 4547055,"Record function id": 0, "Ev Idx": 6278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941228106.098, "dur": 1168.796, + "args": { + "External id": 4547056,"Record function id": 0, "Ev Idx": 6279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941228152.171, "dur": 1108.545, + "args": { + "External id": 4547057,"Sequence number": 45295592, "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": 6280 + } + }, + { + "ph": "s", "id": 220, "pid": 1336753, "tid": 1336753, "ts": 1696941228152.171, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941228227.444, "dur": 50.391, + "args": { + "External id": 4547058,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 6281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941228289.772, "dur": 109.161, + "args": { + "External id": 4547059,"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": 6282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941228412.354, "dur": 37.095, + "args": { + "External id": 4547060,"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": 6283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941228455.344, "dur": 30.005, + "args": { + "External id": 4547061,"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": 6284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941228515.423, "dur": 47.897, + "args": { + "External id": 4547062,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941228584.612, "dur": 17.305, + "args": { + "External id": 4547063,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941228622.432, "dur": 134.325, + "args": { + "External id": 4547064,"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": 6287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941228675.027, "dur": 11.287, + "args": { + "External id": 4547065,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941228680.387, "dur": 5.241, + "args": { + "External id": 4547066,"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": 6289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941228688.608, "dur": 5.503, + "args": { + "External id": 4547067,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941228695.701, "dur": 1.071, + "args": { + "External id": 4547068,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941228701.319, "dur": 4.200, + "args": { + "External id": 4547069,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941228767.729, "dur": 49.714, + "args": { + "External id": 4547070,"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": 6293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941228849.238, "dur": 30.659, + "args": { + "External id": 4547071,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 6294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941228890.324, "dur": 41.297, + "args": { + "External id": 4547072,"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": 6295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941228967.107, "dur": 74.713, + "args": { + "External id": 4547073,"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": 6296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941229075.487, "dur": 29.819, + "args": { + "External id": 4547074,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 6297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941229112.034, "dur": 37.873, + "args": { + "External id": 4547075,"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": 6298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941229166.888, "dur": 24.653, + "args": { + "External id": 4547076,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 6299 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.3)", "pid": 1336753, "tid": 1336753, + "ts": 1696941229339.266, "dur": 77.203, + "args": { + "External id": 4547077,"Record function id": 0, "Ev Idx": 6300 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941229491.069, "dur": 64.789, + "args": { + "External id": 4547078,"Record function id": 0, "Ev Idx": 6301 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 1336753, "tid": 1336753, + "ts": 1696941229567.682, "dur": 18838.405, + "args": { + "External id": 4547079,"Record function id": 0, "Ev Idx": 6302 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 1336753, "tid": 1336753, + "ts": 1696941229579.843, "dur": 917.316, + "args": { + "External id": 4547080,"Record function id": 0, "Ev Idx": 6303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941229669.122, "dur": 9.008, + "args": { + "External id": 4547081,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941229692.085, "dur": 44.275, + "args": { + "External id": 4547082,"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": 6305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229699.294, "dur": 2.395, + "args": { + "External id": 4547083,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941229705.838, "dur": 0.580, + "args": { + "External id": 4547084,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941229707.064, "dur": 0.536, + "args": { + "External id": 4547085,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229710.759, "dur": 0.328, + "args": { + "External id": 4547086,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229714.369, "dur": 0.206, + "args": { + "External id": 4547087,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229717.273, "dur": 0.427, + "args": { + "External id": 4547088,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229718.276, "dur": 4.127, + "args": { + "External id": 4547089,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229723.053, "dur": 0.362, + "args": { + "External id": 4547090,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229727.165, "dur": 0.370, + "args": { + "External id": 4547091,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941229748.824, "dur": 46.745, + "args": { + "External id": 4547092,"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": 6315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941229827.700, "dur": 115.010, + "args": { + "External id": 4547093,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 6316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941229840.557, "dur": 3.459, + "args": { + "External id": 4547094,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941229849.440, "dur": 11.150, + "args": { + "External id": 4547095,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941229853.849, "dur": 6.321, + "args": { + "External id": 4547096,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229858.586, "dur": 0.467, + "args": { + "External id": 4547097,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941229866.839, "dur": 30.478, + "args": { + "External id": 4547098,"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": 6321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229868.209, "dur": 0.970, + "args": { + "External id": 4547099,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941229872.912, "dur": 0.398, + "args": { + "External id": 4547100,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941229873.901, "dur": 0.607, + "args": { + "External id": 4547101,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229879.949, "dur": 1.496, + "args": { + "External id": 4547102,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229881.946, "dur": 0.328, + "args": { + "External id": 4547103,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229882.798, "dur": 0.339, + "args": { + "External id": 4547104,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229888.138, "dur": 0.358, + "args": { + "External id": 4547105,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229889.025, "dur": 0.325, + "args": { + "External id": 4547106,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941229889.867, "dur": 2.656, + "args": { + "External id": 4547107,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941229910.465, "dur": 24.291, + "args": { + "External id": 4547108,"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": 6331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941230037.170, "dur": 362.817, + "args": { + "External id": 4547109,"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": 6332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941230072.882, "dur": 321.994, + "args": { + "External id": 4547110,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 6333, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941230084.955, "dur": 301.495, + "args": { + "External id": 4547111,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941230424.920, "dur": 2.158, + "args": { + "External id": 4547112,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6335, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 1336753, "tid": 1336753, + "ts": 1696941230518.558, "dur": 17670.348, + "args": { + "External id": 4547113,"Record function id": 0, "Ev Idx": 6336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941230648.652, "dur": 6.952, + "args": { + "External id": 4547114,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941230658.976, "dur": 1.107, + "args": { + "External id": 4547115,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941230662.045, "dur": 2.141, + "args": { + "External id": 4547116,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941230666.218, "dur": 1.298, + "args": { + "External id": 4547117,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941230668.816, "dur": 1.419, + "args": { + "External id": 4547118,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941230671.451, "dur": 0.748, + "args": { + "External id": 4547119,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941230676.593, "dur": 0.756, + "args": { + "External id": 4547120,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941230680.876, "dur": 2.873, + "args": { + "External id": 4547121,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941230685.038, "dur": 0.782, + "args": { + "External id": 4547122,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941230687.128, "dur": 0.877, + "args": { + "External id": 4547123,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941230708.600, "dur": 17432.888, + "args": { + "External id": 4547124,"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": 6347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941230725.577, "dur": 17407.579, + "args": { + "External id": 4547125,"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": 6348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941230749.371, "dur": 14.180, + "args": { + "External id": 4547126,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941230766.505, "dur": 17328.788, + "args": { + "External id": 4547127,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941230769.323, "dur": 17325.216, + "args": { + "External id": 4547128,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941230775.191, "dur": 4.867, + "args": { + "External id": 4547129,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941230782.245, "dur": 17308.925, + "args": { + "External id": 4547130,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941248345.780, "dur": 34.510, + "args": { + "External id": 4547131,"Sequence number": 45295593, "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": 6354 + } + }, + { + "ph": "s", "id": 219, "pid": 1336753, "tid": 1336753, "ts": 1696941248345.780, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941248363.239, "dur": 12.280, + "args": { + "External id": 4547132,"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": 6355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941248370.148, "dur": 5.187, + "args": { + "External id": 4547133,"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": 6356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941248447.587, "dur": 96.514, + "args": { + "External id": 4547134,"Record function id": 0, "Ev Idx": 6357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941248546.822, "dur": 1108.578, + "args": { + "External id": 4547135,"Record function id": 0, "Ev Idx": 6358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941248590.857, "dur": 1050.635, + "args": { + "External id": 4547136,"Sequence number": 45295594, "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": 6359 + } + }, + { + "ph": "s", "id": 218, "pid": 1336753, "tid": 1336753, "ts": 1696941248590.857, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941248658.748, "dur": 44.365, + "args": { + "External id": 4547137,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 6360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941248715.250, "dur": 105.297, + "args": { + "External id": 4547138,"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": 6361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941248830.165, "dur": 38.464, + "args": { + "External id": 4547139,"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": 6362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941248878.263, "dur": 31.258, + "args": { + "External id": 4547140,"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": 6363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941248933.654, "dur": 27.818, + "args": { + "External id": 4547141,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941249021.830, "dur": 21.113, + "args": { + "External id": 4547142,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941249064.456, "dur": 133.850, + "args": { + "External id": 4547143,"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": 6366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941249114.823, "dur": 11.044, + "args": { + "External id": 4547144,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941249119.408, "dur": 5.734, + "args": { + "External id": 4547145,"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": 6368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941249128.337, "dur": 7.382, + "args": { + "External id": 4547146,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941249139.041, "dur": 0.991, + "args": { + "External id": 4547147,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941249142.432, "dur": 3.757, + "args": { + "External id": 4547148,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941249208.968, "dur": 49.879, + "args": { + "External id": 4547149,"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": 6372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941249291.068, "dur": 30.711, + "args": { + "External id": 4547150,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 6373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941249330.498, "dur": 41.677, + "args": { + "External id": 4547151,"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": 6374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941249380.523, "dur": 34.252, + "args": { + "External id": 4547152,"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": 6375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941249436.580, "dur": 29.099, + "args": { + "External id": 4547153,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 6376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941249471.298, "dur": 33.179, + "args": { + "External id": 4547154,"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": 6377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941249525.653, "dur": 35.433, + "args": { + "External id": 4547155,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 6378 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.4)", "pid": 1336753, "tid": 1336753, + "ts": 1696941249718.652, "dur": 76.363, + "args": { + "External id": 4547156,"Record function id": 0, "Ev Idx": 6379 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941249871.837, "dur": 48.519, + "args": { + "External id": 4547157,"Record function id": 0, "Ev Idx": 6380 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 1336753, "tid": 1336753, + "ts": 1696941249930.025, "dur": 18412.071, + "args": { + "External id": 4547158,"Record function id": 0, "Ev Idx": 6381 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 1336753, "tid": 1336753, + "ts": 1696941249941.547, "dur": 933.165, + "args": { + "External id": 4547159,"Record function id": 0, "Ev Idx": 6382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941250065.206, "dur": 9.487, + "args": { + "External id": 4547160,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941250089.414, "dur": 43.018, + "args": { + "External id": 4547161,"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": 6384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250096.784, "dur": 2.147, + "args": { + "External id": 4547162,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941250103.203, "dur": 0.247, + "args": { + "External id": 4547163,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941250106.574, "dur": 0.341, + "args": { + "External id": 4547164,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250107.523, "dur": 0.656, + "args": { + "External id": 4547165,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250111.567, "dur": 0.471, + "args": { + "External id": 4547166,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250114.785, "dur": 0.346, + "args": { + "External id": 4547167,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250115.862, "dur": 3.742, + "args": { + "External id": 4547168,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250120.141, "dur": 0.394, + "args": { + "External id": 4547169,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250123.927, "dur": 0.317, + "args": { + "External id": 4547170,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941250144.543, "dur": 47.511, + "args": { + "External id": 4547171,"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": 6394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941250225.980, "dur": 118.822, + "args": { + "External id": 4547172,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 6395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941250241.252, "dur": 4.146, + "args": { + "External id": 4547173,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941250250.596, "dur": 9.455, + "args": { + "External id": 4547174,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941250254.996, "dur": 4.659, + "args": { + "External id": 4547175,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250257.965, "dur": 0.603, + "args": { + "External id": 4547176,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941250266.170, "dur": 32.025, + "args": { + "External id": 4547177,"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": 6400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250269.346, "dur": 2.796, + "args": { + "External id": 4547178,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941250273.091, "dur": 0.410, + "args": { + "External id": 4547179,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941250274.224, "dur": 0.336, + "args": { + "External id": 4547180,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250278.658, "dur": 1.792, + "args": { + "External id": 4547181,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250281.118, "dur": 0.568, + "args": { + "External id": 4547182,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250282.426, "dur": 0.175, + "args": { + "External id": 4547183,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250286.758, "dur": 0.345, + "args": { + "External id": 4547184,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250287.909, "dur": 0.523, + "args": { + "External id": 4547185,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941250289.941, "dur": 2.501, + "args": { + "External id": 4547186,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941250312.592, "dur": 23.498, + "args": { + "External id": 4547187,"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": 6410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941250397.241, "dur": 377.281, + "args": { + "External id": 4547188,"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": 6411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941250433.625, "dur": 335.401, + "args": { + "External id": 4547189,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 6412, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941250445.894, "dur": 316.924, + "args": { + "External id": 4547190,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941250803.250, "dur": 2.262, + "args": { + "External id": 4547191,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6414, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 1336753, "tid": 1336753, + "ts": 1696941250894.364, "dur": 17241.030, + "args": { + "External id": 4547192,"Record function id": 0, "Ev Idx": 6415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941251034.910, "dur": 6.862, + "args": { + "External id": 4547193,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941251045.688, "dur": 1.279, + "args": { + "External id": 4547194,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941251049.545, "dur": 2.441, + "args": { + "External id": 4547195,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941251054.156, "dur": 1.105, + "args": { + "External id": 4547196,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941251057.205, "dur": 1.010, + "args": { + "External id": 4547197,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941251059.813, "dur": 1.220, + "args": { + "External id": 4547198,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941251065.507, "dur": 0.968, + "args": { + "External id": 4547199,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941251068.037, "dur": 2.720, + "args": { + "External id": 4547200,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941251072.369, "dur": 0.828, + "args": { + "External id": 4547201,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941251074.674, "dur": 0.574, + "args": { + "External id": 4547202,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941251096.829, "dur": 16985.626, + "args": { + "External id": 4547203,"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": 6426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941251120.719, "dur": 16954.484, + "args": { + "External id": 4547204,"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": 6427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941251142.693, "dur": 14.274, + "args": { + "External id": 4547205,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941251159.882, "dur": 16879.990, + "args": { + "External id": 4547206,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941251162.544, "dur": 16876.701, + "args": { + "External id": 4547207,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941251169.097, "dur": 5.273, + "args": { + "External id": 4547208,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941251175.870, "dur": 16860.085, + "args": { + "External id": 4547209,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941268286.008, "dur": 31.029, + "args": { + "External id": 4547210,"Sequence number": 45295595, "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": 6433 + } + }, + { + "ph": "s", "id": 217, "pid": 1336753, "tid": 1336753, "ts": 1696941268286.008, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941268303.243, "dur": 9.218, + "args": { + "External id": 4547211,"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": 6434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941268306.921, "dur": 5.287, + "args": { + "External id": 4547212,"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": 6435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941268383.220, "dur": 80.779, + "args": { + "External id": 4547213,"Record function id": 0, "Ev Idx": 6436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941268466.331, "dur": 1132.129, + "args": { + "External id": 4547214,"Record function id": 0, "Ev Idx": 6437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941268508.370, "dur": 1075.788, + "args": { + "External id": 4547215,"Sequence number": 45295596, "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": 6438 + } + }, + { + "ph": "s", "id": 216, "pid": 1336753, "tid": 1336753, "ts": 1696941268508.370, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941268591.130, "dur": 47.137, + "args": { + "External id": 4547216,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 6439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941268651.120, "dur": 106.843, + "args": { + "External id": 4547217,"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": 6440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941268769.040, "dur": 38.742, + "args": { + "External id": 4547218,"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": 6441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941268817.099, "dur": 30.679, + "args": { + "External id": 4547219,"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": 6442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941268873.450, "dur": 29.547, + "args": { + "External id": 4547220,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941268922.405, "dur": 18.284, + "args": { + "External id": 4547221,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941268965.236, "dur": 175.550, + "args": { + "External id": 4547222,"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": 6445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941269055.870, "dur": 12.412, + "args": { + "External id": 4547223,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941269061.320, "dur": 6.108, + "args": { + "External id": 4547224,"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": 6447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941269071.094, "dur": 5.500, + "args": { + "External id": 4547225,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941269078.392, "dur": 1.204, + "args": { + "External id": 4547226,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941269082.158, "dur": 5.724, + "args": { + "External id": 4547227,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941269151.814, "dur": 52.087, + "args": { + "External id": 4547228,"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": 6451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941269238.321, "dur": 34.994, + "args": { + "External id": 4547229,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 6452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941269282.532, "dur": 41.451, + "args": { + "External id": 4547230,"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": 6453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941269334.112, "dur": 34.752, + "args": { + "External id": 4547231,"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": 6454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941269388.991, "dur": 28.921, + "args": { + "External id": 4547232,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 6455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941269423.594, "dur": 33.656, + "args": { + "External id": 4547233,"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": 6456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941269478.979, "dur": 19.777, + "args": { + "External id": 4547234,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 6457 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.5)", "pid": 1336753, "tid": 1336753, + "ts": 1696941269663.797, "dur": 80.588, + "args": { + "External id": 4547235,"Record function id": 0, "Ev Idx": 6458 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941269819.401, "dur": 49.414, + "args": { + "External id": 4547236,"Record function id": 0, "Ev Idx": 6459 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 1336753, "tid": 1336753, + "ts": 1696941269879.243, "dur": 18260.056, + "args": { + "External id": 4547237,"Record function id": 0, "Ev Idx": 6460 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 1336753, "tid": 1336753, + "ts": 1696941269889.018, "dur": 936.974, + "args": { + "External id": 4547238,"Record function id": 0, "Ev Idx": 6461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941269972.423, "dur": 8.145, + "args": { + "External id": 4547239,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941270034.300, "dur": 43.684, + "args": { + "External id": 4547240,"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": 6463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270040.156, "dur": 2.482, + "args": { + "External id": 4547241,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941270047.859, "dur": 0.348, + "args": { + "External id": 4547242,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941270050.055, "dur": 0.472, + "args": { + "External id": 4547243,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270052.509, "dur": 0.321, + "args": { + "External id": 4547244,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270057.045, "dur": 0.706, + "args": { + "External id": 4547245,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270059.446, "dur": 0.394, + "args": { + "External id": 4547246,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270061.324, "dur": 3.809, + "args": { + "External id": 4547247,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270066.794, "dur": 0.490, + "args": { + "External id": 4547248,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270068.706, "dur": 0.146, + "args": { + "External id": 4547249,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941270091.532, "dur": 44.549, + "args": { + "External id": 4547250,"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": 6473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941270172.110, "dur": 122.012, + "args": { + "External id": 4547251,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 6474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941270186.802, "dur": 4.694, + "args": { + "External id": 4547252,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941270196.664, "dur": 10.485, + "args": { + "External id": 4547253,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941270200.972, "dur": 5.754, + "args": { + "External id": 4547254,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270204.819, "dur": 0.674, + "args": { + "External id": 4547255,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941270214.619, "dur": 36.022, + "args": { + "External id": 4547256,"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": 6479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270217.299, "dur": 2.093, + "args": { + "External id": 4547257,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941270221.482, "dur": 0.599, + "args": { + "External id": 4547258,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941270223.721, "dur": 0.760, + "args": { + "External id": 4547259,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270228.898, "dur": 2.127, + "args": { + "External id": 4547260,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270232.708, "dur": 0.568, + "args": { + "External id": 4547261,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270234.738, "dur": 0.593, + "args": { + "External id": 4547262,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270238.943, "dur": 0.323, + "args": { + "External id": 4547263,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270241.183, "dur": 0.506, + "args": { + "External id": 4547264,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941270243.030, "dur": 2.277, + "args": { + "External id": 4547265,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941270261.740, "dur": 24.061, + "args": { + "External id": 4547266,"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": 6489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941270348.321, "dur": 377.811, + "args": { + "External id": 4547267,"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": 6490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941270382.997, "dur": 337.329, + "args": { + "External id": 4547268,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 6491, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941270395.135, "dur": 319.278, + "args": { + "External id": 4547269,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941270753.563, "dur": 2.452, + "args": { + "External id": 4547270,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6493, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 1336753, "tid": 1336753, + "ts": 1696941270846.343, "dur": 17046.549, + "args": { + "External id": 4547271,"Record function id": 0, "Ev Idx": 6494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941270943.093, "dur": 6.422, + "args": { + "External id": 4547272,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941270953.501, "dur": 1.282, + "args": { + "External id": 4547273,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941270956.612, "dur": 2.916, + "args": { + "External id": 4547274,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941270961.552, "dur": 1.063, + "args": { + "External id": 4547275,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941270964.540, "dur": 0.962, + "args": { + "External id": 4547276,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941270967.545, "dur": 0.918, + "args": { + "External id": 4547277,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941270971.966, "dur": 0.979, + "args": { + "External id": 4547278,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941270974.595, "dur": 2.346, + "args": { + "External id": 4547279,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941270978.745, "dur": 0.862, + "args": { + "External id": 4547280,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941271032.709, "dur": 2.206, + "args": { + "External id": 4547281,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941271059.366, "dur": 16778.740, + "args": { + "External id": 4547282,"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": 6505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941271076.013, "dur": 16753.979, + "args": { + "External id": 4547283,"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": 6506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941271101.359, "dur": 14.149, + "args": { + "External id": 4547284,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941271118.185, "dur": 16676.687, + "args": { + "External id": 4547285,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941271121.338, "dur": 16672.811, + "args": { + "External id": 4547286,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941271127.758, "dur": 5.911, + "args": { + "External id": 4547287,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941271135.621, "dur": 16655.165, + "args": { + "External id": 4547288,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941288081.728, "dur": 30.414, + "args": { + "External id": 4547289,"Sequence number": 45295597, "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": 6512 + } + }, + { + "ph": "s", "id": 215, "pid": 1336753, "tid": 1336753, "ts": 1696941288081.728, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941288097.859, "dur": 9.521, + "args": { + "External id": 4547290,"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": 6513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941288101.821, "dur": 5.205, + "args": { + "External id": 4547291,"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": 6514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941288182.703, "dur": 80.348, + "args": { + "External id": 4547292,"Record function id": 0, "Ev Idx": 6515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941288264.706, "dur": 1108.447, + "args": { + "External id": 4547293,"Record function id": 0, "Ev Idx": 6516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941288306.621, "dur": 1052.591, + "args": { + "External id": 4547294,"Sequence number": 45295598, "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": 6517 + } + }, + { + "ph": "s", "id": 214, "pid": 1336753, "tid": 1336753, "ts": 1696941288306.621, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941288373.706, "dur": 46.589, + "args": { + "External id": 4547295,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 6518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941288433.013, "dur": 114.198, + "args": { + "External id": 4547296,"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": 6519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941288562.304, "dur": 42.497, + "args": { + "External id": 4547297,"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": 6520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941288613.456, "dur": 30.946, + "args": { + "External id": 4547298,"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": 6521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941288672.218, "dur": 27.551, + "args": { + "External id": 4547299,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941288718.233, "dur": 16.301, + "args": { + "External id": 4547300,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941288754.111, "dur": 131.671, + "args": { + "External id": 4547301,"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": 6524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941288803.521, "dur": 13.079, + "args": { + "External id": 4547302,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941288808.977, "dur": 6.855, + "args": { + "External id": 4547303,"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": 6526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941288820.103, "dur": 5.678, + "args": { + "External id": 4547304,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941288827.300, "dur": 0.910, + "args": { + "External id": 4547305,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941288831.326, "dur": 4.410, + "args": { + "External id": 4547306,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941288896.281, "dur": 44.619, + "args": { + "External id": 4547307,"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": 6530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941288973.747, "dur": 72.145, + "args": { + "External id": 4547308,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 6531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941289058.752, "dur": 47.823, + "args": { + "External id": 4547309,"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": 6532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941289114.910, "dur": 34.440, + "args": { + "External id": 4547310,"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": 6533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941289175.315, "dur": 30.425, + "args": { + "External id": 4547311,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 6534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941289210.834, "dur": 33.435, + "args": { + "External id": 4547312,"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": 6535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941289264.775, "dur": 19.438, + "args": { + "External id": 4547313,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 6536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.6)", "pid": 1336753, "tid": 1336753, + "ts": 1696941289434.972, "dur": 79.109, + "args": { + "External id": 4547314,"Record function id": 0, "Ev Idx": 6537 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941289610.264, "dur": 48.373, + "args": { + "External id": 4547315,"Record function id": 0, "Ev Idx": 6538 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 1336753, "tid": 1336753, + "ts": 1696941289669.753, "dur": 18113.113, + "args": { + "External id": 4547316,"Record function id": 0, "Ev Idx": 6539 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 1336753, "tid": 1336753, + "ts": 1696941289677.963, "dur": 937.021, + "args": { + "External id": 4547317,"Record function id": 0, "Ev Idx": 6540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941289761.069, "dur": 9.345, + "args": { + "External id": 4547318,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941289784.676, "dur": 44.451, + "args": { + "External id": 4547319,"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": 6542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941289790.737, "dur": 2.058, + "args": { + "External id": 4547320,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941289797.674, "dur": 0.398, + "args": { + "External id": 4547321,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941289800.070, "dur": 0.408, + "args": { + "External id": 4547322,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941289802.123, "dur": 0.659, + "args": { + "External id": 4547323,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941289807.112, "dur": 0.483, + "args": { + "External id": 4547324,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941289809.892, "dur": 0.654, + "args": { + "External id": 4547325,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941289812.915, "dur": 3.666, + "args": { + "External id": 4547326,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941289818.507, "dur": 0.376, + "args": { + "External id": 4547327,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941289821.111, "dur": 0.156, + "args": { + "External id": 4547328,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941289841.628, "dur": 41.378, + "args": { + "External id": 4547329,"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": 6552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941289917.973, "dur": 167.809, + "args": { + "External id": 4547330,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 6553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941289931.932, "dur": 3.759, + "args": { + "External id": 4547331,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941289941.070, "dur": 11.091, + "args": { + "External id": 4547332,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941289945.878, "dur": 5.845, + "args": { + "External id": 4547333,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941289949.798, "dur": 0.694, + "args": { + "External id": 4547334,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941289959.154, "dur": 74.999, + "args": { + "External id": 4547335,"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": 6558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941289961.524, "dur": 2.469, + "args": { + "External id": 4547336,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941289965.746, "dur": 0.358, + "args": { + "External id": 4547337,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941289967.770, "dur": 0.586, + "args": { + "External id": 4547338,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941289972.628, "dur": 1.934, + "args": { + "External id": 4547339,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941289975.782, "dur": 0.389, + "args": { + "External id": 4547340,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941289977.664, "dur": 0.339, + "args": { + "External id": 4547341,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941290019.122, "dur": 0.521, + "args": { + "External id": 4547342,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941290021.993, "dur": 0.454, + "args": { + "External id": 4547343,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941290024.426, "dur": 2.722, + "args": { + "External id": 4547344,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941290049.639, "dur": 27.747, + "args": { + "External id": 4547345,"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": 6568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941290141.661, "dur": 355.282, + "args": { + "External id": 4547346,"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": 6569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941290176.302, "dur": 315.586, + "args": { + "External id": 4547347,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 6570, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941290188.510, "dur": 298.206, + "args": { + "External id": 4547348,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941290523.274, "dur": 2.410, + "args": { + "External id": 4547349,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6572, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 1336753, "tid": 1336753, + "ts": 1696941290637.077, "dur": 16936.682, + "args": { + "External id": 4547350,"Record function id": 0, "Ev Idx": 6573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941290747.390, "dur": 6.878, + "args": { + "External id": 4547351,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941290758.394, "dur": 1.459, + "args": { + "External id": 4547352,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941290761.762, "dur": 3.035, + "args": { + "External id": 4547353,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941290769.463, "dur": 0.989, + "args": { + "External id": 4547354,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941290771.882, "dur": 0.884, + "args": { + "External id": 4547355,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941290774.476, "dur": 1.067, + "args": { + "External id": 4547356,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941290777.075, "dur": 1.079, + "args": { + "External id": 4547357,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941290782.075, "dur": 2.585, + "args": { + "External id": 4547358,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941290786.221, "dur": 0.915, + "args": { + "External id": 4547359,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941290788.534, "dur": 1.020, + "args": { + "External id": 4547360,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941290809.410, "dur": 16704.002, + "args": { + "External id": 4547361,"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": 6584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941290825.674, "dur": 16680.849, + "args": { + "External id": 4547362,"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": 6585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941290845.456, "dur": 15.618, + "args": { + "External id": 4547363,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941290866.710, "dur": 16604.478, + "args": { + "External id": 4547364,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941290869.394, "dur": 16601.216, + "args": { + "External id": 4547365,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941290875.700, "dur": 4.750, + "args": { + "External id": 4547366,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941290882.218, "dur": 16585.561, + "args": { + "External id": 4547367,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941307727.001, "dur": 30.856, + "args": { + "External id": 4547368,"Sequence number": 45295599, "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": 6591 + } + }, + { + "ph": "s", "id": 213, "pid": 1336753, "tid": 1336753, "ts": 1696941307727.001, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941307744.933, "dur": 8.349, + "args": { + "External id": 4547369,"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": 6592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941307748.345, "dur": 4.670, + "args": { + "External id": 4547370,"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": 6593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941307824.135, "dur": 79.795, + "args": { + "External id": 4547371,"Record function id": 0, "Ev Idx": 6594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941307905.687, "dur": 1139.093, + "args": { + "External id": 4547372,"Record function id": 0, "Ev Idx": 6595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941307947.661, "dur": 1081.704, + "args": { + "External id": 4547373,"Sequence number": 45295600, "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": 6596 + } + }, + { + "ph": "s", "id": 212, "pid": 1336753, "tid": 1336753, "ts": 1696941307947.661, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941308051.143, "dur": 46.785, + "args": { + "External id": 4547374,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 6597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941308111.039, "dur": 104.121, + "args": { + "External id": 4547375,"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": 6598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941308224.352, "dur": 38.639, + "args": { + "External id": 4547376,"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": 6599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941308273.020, "dur": 30.808, + "args": { + "External id": 4547377,"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": 6600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941308330.099, "dur": 27.656, + "args": { + "External id": 4547378,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941308375.052, "dur": 15.952, + "args": { + "External id": 4547379,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941308411.431, "dur": 156.496, + "args": { + "External id": 4547380,"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": 6603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941308463.298, "dur": 10.578, + "args": { + "External id": 4547381,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941308468.101, "dur": 4.841, + "args": { + "External id": 4547382,"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": 6605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941308476.581, "dur": 7.127, + "args": { + "External id": 4547383,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941308492.184, "dur": 1.159, + "args": { + "External id": 4547384,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941308495.792, "dur": 4.251, + "args": { + "External id": 4547385,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941308580.894, "dur": 52.532, + "args": { + "External id": 4547386,"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": 6609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941308666.272, "dur": 29.348, + "args": { + "External id": 4547387,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 6610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941308704.672, "dur": 40.924, + "args": { + "External id": 4547388,"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": 6611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941308753.676, "dur": 35.271, + "args": { + "External id": 4547389,"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": 6612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941308809.776, "dur": 28.959, + "args": { + "External id": 4547390,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 6613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941308844.232, "dur": 33.581, + "args": { + "External id": 4547391,"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": 6614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941308900.764, "dur": 20.489, + "args": { + "External id": 4547392,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 6615 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.7)", "pid": 1336753, "tid": 1336753, + "ts": 1696941309113.008, "dur": 82.433, + "args": { + "External id": 4547393,"Record function id": 0, "Ev Idx": 6616 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941309271.523, "dur": 47.398, + "args": { + "External id": 4547394,"Record function id": 0, "Ev Idx": 6617 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 1336753, "tid": 1336753, + "ts": 1696941309328.074, "dur": 17999.177, + "args": { + "External id": 4547395,"Record function id": 0, "Ev Idx": 6618 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 1336753, "tid": 1336753, + "ts": 1696941309336.388, "dur": 969.224, + "args": { + "External id": 4547396,"Record function id": 0, "Ev Idx": 6619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941309418.486, "dur": 8.273, + "args": { + "External id": 4547397,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941309441.729, "dur": 40.992, + "args": { + "External id": 4547398,"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": 6621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309447.203, "dur": 2.180, + "args": { + "External id": 4547399,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941309455.007, "dur": 0.359, + "args": { + "External id": 4547400,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941309456.751, "dur": 0.553, + "args": { + "External id": 4547401,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309459.116, "dur": 0.533, + "args": { + "External id": 4547402,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309462.962, "dur": 0.614, + "args": { + "External id": 4547403,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309464.979, "dur": 0.556, + "args": { + "External id": 4547404,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309466.950, "dur": 4.889, + "args": { + "External id": 4547405,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309473.517, "dur": 0.479, + "args": { + "External id": 4547406,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309475.135, "dur": 0.363, + "args": { + "External id": 4547407,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941309495.556, "dur": 60.052, + "args": { + "External id": 4547408,"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": 6631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941309593.318, "dur": 122.829, + "args": { + "External id": 4547409,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 6632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941309606.482, "dur": 5.091, + "args": { + "External id": 4547410,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941309618.016, "dur": 11.547, + "args": { + "External id": 4547411,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941309622.647, "dur": 6.514, + "args": { + "External id": 4547412,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309626.773, "dur": 0.738, + "args": { + "External id": 4547413,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941309636.145, "dur": 35.573, + "args": { + "External id": 4547414,"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": 6637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309638.833, "dur": 2.747, + "args": { + "External id": 4547415,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941309642.836, "dur": 0.550, + "args": { + "External id": 4547416,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941309644.936, "dur": 0.497, + "args": { + "External id": 4547417,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309648.738, "dur": 2.930, + "args": { + "External id": 4547418,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309652.730, "dur": 0.456, + "args": { + "External id": 4547419,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309654.414, "dur": 0.524, + "args": { + "External id": 4547420,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309656.696, "dur": 4.483, + "args": { + "External id": 4547421,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309662.083, "dur": 0.750, + "args": { + "External id": 4547422,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941309663.822, "dur": 2.570, + "args": { + "External id": 4547423,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941309683.343, "dur": 24.736, + "args": { + "External id": 4547424,"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": 6647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941309769.235, "dur": 431.189, + "args": { + "External id": 4547425,"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": 6648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941309801.722, "dur": 393.236, + "args": { + "External id": 4547426,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 6649, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941309813.089, "dur": 374.734, + "args": { + "External id": 4547427,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941310229.864, "dur": 2.480, + "args": { + "External id": 4547428,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6651, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 1336753, "tid": 1336753, + "ts": 1696941310326.220, "dur": 16814.149, + "args": { + "External id": 4547429,"Record function id": 0, "Ev Idx": 6652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941310428.464, "dur": 6.665, + "args": { + "External id": 4547430,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941310439.098, "dur": 1.151, + "args": { + "External id": 4547431,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941310442.214, "dur": 3.354, + "args": { + "External id": 4547432,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941310447.438, "dur": 1.121, + "args": { + "External id": 4547433,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941310449.931, "dur": 0.933, + "args": { + "External id": 4547434,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941310452.374, "dur": 1.195, + "args": { + "External id": 4547435,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941310457.140, "dur": 1.081, + "args": { + "External id": 4547436,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941310459.694, "dur": 2.836, + "args": { + "External id": 4547437,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941310464.004, "dur": 0.873, + "args": { + "External id": 4547438,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941310466.143, "dur": 1.089, + "args": { + "External id": 4547439,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941310498.810, "dur": 16594.780, + "args": { + "External id": 4547440,"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": 6663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941310515.586, "dur": 16571.543, + "args": { + "External id": 4547441,"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": 6664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941310552.576, "dur": 16.052, + "args": { + "External id": 4547442,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941310572.098, "dur": 16481.263, + "args": { + "External id": 4547443,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941310574.690, "dur": 16478.156, + "args": { + "External id": 4547444,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941310580.421, "dur": 5.435, + "args": { + "External id": 4547445,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941310587.417, "dur": 16462.710, + "args": { + "External id": 4547446,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941327276.843, "dur": 27.133, + "args": { + "External id": 4547447,"Sequence number": 45295601, "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": 6670 + } + }, + { + "ph": "s", "id": 211, "pid": 1336753, "tid": 1336753, "ts": 1696941327276.843, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941327292.280, "dur": 7.351, + "args": { + "External id": 4547448,"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": 6671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941327295.246, "dur": 4.172, + "args": { + "External id": 4547449,"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": 6672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941327368.115, "dur": 74.352, + "args": { + "External id": 4547450,"Record function id": 0, "Ev Idx": 6673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941327444.042, "dur": 1109.393, + "args": { + "External id": 4547451,"Record function id": 0, "Ev Idx": 6674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941327483.098, "dur": 1041.198, + "args": { + "External id": 4547452,"Sequence number": 45295602, "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": 6675 + } + }, + { + "ph": "s", "id": 210, "pid": 1336753, "tid": 1336753, "ts": 1696941327483.098, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941327563.356, "dur": 44.495, + "args": { + "External id": 4547453,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 6676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941327622.387, "dur": 105.531, + "args": { + "External id": 4547454,"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": 6677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941327738.275, "dur": 39.100, + "args": { + "External id": 4547455,"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": 6678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941327788.442, "dur": 32.378, + "args": { + "External id": 4547456,"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": 6679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941327846.489, "dur": 28.042, + "args": { + "External id": 4547457,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941327894.490, "dur": 16.514, + "args": { + "External id": 4547458,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941327930.765, "dur": 175.060, + "args": { + "External id": 4547459,"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": 6682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941327979.002, "dur": 49.843, + "args": { + "External id": 4547460,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941328021.010, "dur": 6.625, + "args": { + "External id": 4547461,"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": 6684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941328031.629, "dur": 8.313, + "args": { + "External id": 4547462,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941328041.035, "dur": 1.076, + "args": { + "External id": 4547463,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941328044.585, "dur": 5.023, + "args": { + "External id": 4547464,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941328116.925, "dur": 48.691, + "args": { + "External id": 4547465,"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": 6688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941328197.538, "dur": 29.153, + "args": { + "External id": 4547466,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 6689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941328236.848, "dur": 41.612, + "args": { + "External id": 4547467,"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": 6690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941328287.660, "dur": 34.755, + "args": { + "External id": 4547468,"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": 6691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941328346.938, "dur": 28.824, + "args": { + "External id": 4547469,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 6692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941328381.316, "dur": 33.827, + "args": { + "External id": 4547470,"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": 6693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941328434.670, "dur": 17.986, + "args": { + "External id": 4547471,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 6694 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.8)", "pid": 1336753, "tid": 1336753, + "ts": 1696941328619.099, "dur": 77.446, + "args": { + "External id": 4547472,"Record function id": 0, "Ev Idx": 6695 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941328776.596, "dur": 49.632, + "args": { + "External id": 4547473,"Record function id": 0, "Ev Idx": 6696 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 1336753, "tid": 1336753, + "ts": 1696941328836.078, "dur": 17924.258, + "args": { + "External id": 4547474,"Record function id": 0, "Ev Idx": 6697 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 1336753, "tid": 1336753, + "ts": 1696941328844.839, "dur": 870.943, + "args": { + "External id": 4547475,"Record function id": 0, "Ev Idx": 6698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941328927.304, "dur": 8.216, + "args": { + "External id": 4547476,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941328949.128, "dur": 78.651, + "args": { + "External id": 4547477,"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": 6700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941328954.837, "dur": 2.363, + "args": { + "External id": 4547478,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941328961.656, "dur": 0.518, + "args": { + "External id": 4547479,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941328963.394, "dur": 0.714, + "args": { + "External id": 4547480,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941328965.178, "dur": 0.417, + "args": { + "External id": 4547481,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941328969.224, "dur": 0.591, + "args": { + "External id": 4547482,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941328971.485, "dur": 0.448, + "args": { + "External id": 4547483,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941328973.681, "dur": 4.292, + "args": { + "External id": 4547484,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941328978.961, "dur": 0.742, + "args": { + "External id": 4547485,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941329018.211, "dur": 0.893, + "args": { + "External id": 4547486,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941329041.878, "dur": 45.549, + "args": { + "External id": 4547487,"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": 6710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941329125.474, "dur": 128.101, + "args": { + "External id": 4547488,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 6711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941329138.928, "dur": 5.108, + "args": { + "External id": 4547489,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941329149.387, "dur": 10.363, + "args": { + "External id": 4547490,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941329153.768, "dur": 5.590, + "args": { + "External id": 4547491,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941329157.550, "dur": 0.630, + "args": { + "External id": 4547492,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941329167.267, "dur": 34.514, + "args": { + "External id": 4547493,"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": 6716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941329169.230, "dur": 3.215, + "args": { + "External id": 4547494,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941329176.833, "dur": 0.678, + "args": { + "External id": 4547495,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941329178.760, "dur": 0.472, + "args": { + "External id": 4547496,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941329182.817, "dur": 2.405, + "args": { + "External id": 4547497,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941329186.325, "dur": 0.451, + "args": { + "External id": 4547498,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941329187.764, "dur": 2.680, + "args": { + "External id": 4547499,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941329191.302, "dur": 0.388, + "args": { + "External id": 4547500,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941329192.902, "dur": 0.385, + "args": { + "External id": 4547501,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941329196.580, "dur": 0.363, + "args": { + "External id": 4547502,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941329221.106, "dur": 24.604, + "args": { + "External id": 4547503,"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": 6726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941329308.029, "dur": 307.866, + "args": { + "External id": 4547504,"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": 6727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941329340.967, "dur": 270.000, + "args": { + "External id": 4547505,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 6728, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941329355.345, "dur": 249.791, + "args": { + "External id": 4547506,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941329643.808, "dur": 2.291, + "args": { + "External id": 4547507,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6730, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 1336753, "tid": 1336753, + "ts": 1696941329735.547, "dur": 16829.071, + "args": { + "External id": 4547508,"Record function id": 0, "Ev Idx": 6731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941329833.674, "dur": 6.395, + "args": { + "External id": 4547509,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941329843.727, "dur": 1.611, + "args": { + "External id": 4547510,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941329847.553, "dur": 3.821, + "args": { + "External id": 4547511,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941329853.501, "dur": 1.395, + "args": { + "External id": 4547512,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941329856.442, "dur": 1.153, + "args": { + "External id": 4547513,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941329858.972, "dur": 1.013, + "args": { + "External id": 4547514,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941329863.807, "dur": 0.835, + "args": { + "External id": 4547515,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941329866.093, "dur": 3.089, + "args": { + "External id": 4547516,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941329870.485, "dur": 1.080, + "args": { + "External id": 4547517,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941329872.810, "dur": 0.948, + "args": { + "External id": 4547518,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941329893.328, "dur": 16614.810, + "args": { + "External id": 4547519,"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": 6742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941329908.517, "dur": 16593.389, + "args": { + "External id": 4547520,"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": 6743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941329928.696, "dur": 14.768, + "args": { + "External id": 4547521,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941329946.614, "dur": 16522.322, + "args": { + "External id": 4547522,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941329949.333, "dur": 16518.936, + "args": { + "External id": 4547523,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941329955.674, "dur": 7.161, + "args": { + "External id": 4547524,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941329964.635, "dur": 16500.994, + "args": { + "External id": 4547525,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941346707.604, "dur": 27.499, + "args": { + "External id": 4547526,"Sequence number": 45295603, "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": 6749 + } + }, + { + "ph": "s", "id": 209, "pid": 1336753, "tid": 1336753, "ts": 1696941346707.604, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941346723.110, "dur": 7.506, + "args": { + "External id": 4547527,"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": 6750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941346726.115, "dur": 4.295, + "args": { + "External id": 4547528,"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": 6751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941346800.307, "dur": 77.214, + "args": { + "External id": 4547529,"Record function id": 0, "Ev Idx": 6752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941346879.510, "dur": 1099.394, + "args": { + "External id": 4547530,"Record function id": 0, "Ev Idx": 6753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941346920.353, "dur": 1046.038, + "args": { + "External id": 4547531,"Sequence number": 45295604, "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": 6754 + } + }, + { + "ph": "s", "id": 208, "pid": 1336753, "tid": 1336753, "ts": 1696941346920.353, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941347019.428, "dur": 49.172, + "args": { + "External id": 4547532,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 6755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941347087.344, "dur": 101.985, + "args": { + "External id": 4547533,"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": 6756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941347199.204, "dur": 38.459, + "args": { + "External id": 4547534,"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": 6757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941347244.656, "dur": 29.968, + "args": { + "External id": 4547535,"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": 6758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941347300.879, "dur": 28.753, + "args": { + "External id": 4547536,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941347347.684, "dur": 14.972, + "args": { + "External id": 4547537,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941347382.834, "dur": 134.627, + "args": { + "External id": 4547538,"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": 6761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941347433.166, "dur": 11.519, + "args": { + "External id": 4547539,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941347438.732, "dur": 5.235, + "args": { + "External id": 4547540,"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": 6763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941347447.654, "dur": 6.145, + "args": { + "External id": 4547541,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941347455.028, "dur": 1.300, + "args": { + "External id": 4547542,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941347458.829, "dur": 6.373, + "args": { + "External id": 4547543,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941347544.200, "dur": 51.027, + "args": { + "External id": 4547544,"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": 6767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941347627.530, "dur": 29.987, + "args": { + "External id": 4547545,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 6768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941347674.353, "dur": 41.601, + "args": { + "External id": 4547546,"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": 6769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941347724.214, "dur": 35.262, + "args": { + "External id": 4547547,"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": 6770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941347784.563, "dur": 31.017, + "args": { + "External id": 4547548,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 6771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941347822.083, "dur": 34.050, + "args": { + "External id": 4547549,"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": 6772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941347876.135, "dur": 19.512, + "args": { + "External id": 4547550,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 6773 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.9)", "pid": 1336753, "tid": 1336753, + "ts": 1696941348080.817, "dur": 77.291, + "args": { + "External id": 4547551,"Record function id": 0, "Ev Idx": 6774 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941348234.864, "dur": 46.316, + "args": { + "External id": 4547552,"Record function id": 0, "Ev Idx": 6775 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 1336753, "tid": 1336753, + "ts": 1696941348290.253, "dur": 18080.586, + "args": { + "External id": 4547553,"Record function id": 0, "Ev Idx": 6776 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 1336753, "tid": 1336753, + "ts": 1696941348300.044, "dur": 992.713, + "args": { + "External id": 4547554,"Record function id": 0, "Ev Idx": 6777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941348386.502, "dur": 8.711, + "args": { + "External id": 4547555,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941348410.221, "dur": 44.171, + "args": { + "External id": 4547556,"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": 6779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348415.228, "dur": 2.080, + "args": { + "External id": 4547557,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941348422.761, "dur": 0.953, + "args": { + "External id": 4547558,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941348425.508, "dur": 0.908, + "args": { + "External id": 4547559,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348428.040, "dur": 1.014, + "args": { + "External id": 4547560,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348432.879, "dur": 0.424, + "args": { + "External id": 4547561,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348435.254, "dur": 0.613, + "args": { + "External id": 4547562,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348437.628, "dur": 4.481, + "args": { + "External id": 4547563,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348444.403, "dur": 0.553, + "args": { + "External id": 4547564,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348446.487, "dur": 0.576, + "args": { + "External id": 4547565,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941348467.810, "dur": 40.061, + "args": { + "External id": 4547566,"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": 6789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941348559.163, "dur": 130.545, + "args": { + "External id": 4547567,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 6790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941348573.493, "dur": 5.722, + "args": { + "External id": 4547568,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941348584.940, "dur": 11.643, + "args": { + "External id": 4547569,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941348589.406, "dur": 6.745, + "args": { + "External id": 4547570,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348593.682, "dur": 0.989, + "args": { + "External id": 4547571,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941348603.973, "dur": 37.366, + "args": { + "External id": 4547572,"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": 6795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348606.618, "dur": 2.637, + "args": { + "External id": 4547573,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941348610.968, "dur": 0.545, + "args": { + "External id": 4547574,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941348613.095, "dur": 0.855, + "args": { + "External id": 4547575,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348617.884, "dur": 2.497, + "args": { + "External id": 4547576,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348621.928, "dur": 0.396, + "args": { + "External id": 4547577,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348624.275, "dur": 0.330, + "args": { + "External id": 4547578,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348628.347, "dur": 0.377, + "args": { + "External id": 4547579,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348630.398, "dur": 0.333, + "args": { + "External id": 4547580,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941348632.427, "dur": 2.695, + "args": { + "External id": 4547581,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941348653.817, "dur": 27.256, + "args": { + "External id": 4547582,"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": 6805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941348742.767, "dur": 445.001, + "args": { + "External id": 4547583,"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": 6806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941348775.740, "dur": 406.295, + "args": { + "External id": 4547584,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 6807, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941348818.458, "dur": 357.171, + "args": { + "External id": 4547585,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941349215.988, "dur": 2.521, + "args": { + "External id": 4547586,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6809, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 1336753, "tid": 1336753, + "ts": 1696941349313.458, "dur": 16835.820, + "args": { + "External id": 4547587,"Record function id": 0, "Ev Idx": 6810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941349416.478, "dur": 6.631, + "args": { + "External id": 4547588,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941349426.412, "dur": 1.571, + "args": { + "External id": 4547589,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941349429.755, "dur": 3.997, + "args": { + "External id": 4547590,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941349435.540, "dur": 1.081, + "args": { + "External id": 4547591,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941349437.808, "dur": 1.094, + "args": { + "External id": 4547592,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941349441.276, "dur": 1.108, + "args": { + "External id": 4547593,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941349446.681, "dur": 1.127, + "args": { + "External id": 4547594,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941349449.494, "dur": 3.268, + "args": { + "External id": 4547595,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941349454.092, "dur": 1.269, + "args": { + "External id": 4547596,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941349456.806, "dur": 1.114, + "args": { + "External id": 4547597,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941349479.557, "dur": 16614.844, + "args": { + "External id": 4547598,"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": 6821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941349495.629, "dur": 16589.123, + "args": { + "External id": 4547599,"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": 6822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941349514.957, "dur": 32.750, + "args": { + "External id": 4547600,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941349551.813, "dur": 16492.365, + "args": { + "External id": 4547601,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941349554.424, "dur": 16488.871, + "args": { + "External id": 4547602,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941349561.442, "dur": 7.088, + "args": { + "External id": 4547603,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941349570.195, "dur": 16469.000, + "args": { + "External id": 4547604,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941366305.484, "dur": 39.724, + "args": { + "External id": 4547605,"Sequence number": 45295605, "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": 6828 + } + }, + { + "ph": "s", "id": 207, "pid": 1336753, "tid": 1336753, "ts": 1696941366305.484, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941366330.365, "dur": 10.282, + "args": { + "External id": 4547606,"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": 6829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941366334.726, "dur": 5.687, + "args": { + "External id": 4547607,"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": 6830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941366414.084, "dur": 77.756, + "args": { + "External id": 4547608,"Record function id": 0, "Ev Idx": 6831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941366493.274, "dur": 1122.612, + "args": { + "External id": 4547609,"Record function id": 0, "Ev Idx": 6832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941366549.022, "dur": 1051.764, + "args": { + "External id": 4547610,"Sequence number": 45295606, "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": 6833 + } + }, + { + "ph": "s", "id": 206, "pid": 1336753, "tid": 1336753, "ts": 1696941366549.022, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941366617.980, "dur": 44.496, + "args": { + "External id": 4547611,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 6834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941366676.464, "dur": 104.248, + "args": { + "External id": 4547612,"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": 6835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941366790.717, "dur": 38.386, + "args": { + "External id": 4547613,"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": 6836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941366837.269, "dur": 30.593, + "args": { + "External id": 4547614,"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": 6837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941366894.912, "dur": 26.266, + "args": { + "External id": 4547615,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941366939.179, "dur": 18.041, + "args": { + "External id": 4547616,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941366976.571, "dur": 181.524, + "args": { + "External id": 4547617,"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": 6840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941367071.711, "dur": 12.131, + "args": { + "External id": 4547618,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941367077.045, "dur": 6.064, + "args": { + "External id": 4547619,"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": 6842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941367086.769, "dur": 6.194, + "args": { + "External id": 4547620,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941367094.394, "dur": 1.127, + "args": { + "External id": 4547621,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941367097.934, "dur": 7.148, + "args": { + "External id": 4547622,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941367169.774, "dur": 50.657, + "args": { + "External id": 4547623,"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": 6846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941367252.970, "dur": 30.972, + "args": { + "External id": 4547624,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 6847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941367293.419, "dur": 42.047, + "args": { + "External id": 4547625,"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": 6848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941367346.772, "dur": 34.831, + "args": { + "External id": 4547626,"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": 6849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941367401.271, "dur": 30.431, + "args": { + "External id": 4547627,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 6850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941367437.633, "dur": 32.782, + "args": { + "External id": 4547628,"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": 6851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941367492.860, "dur": 18.485, + "args": { + "External id": 4547629,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 6852 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.10)", "pid": 1336753, "tid": 1336753, + "ts": 1696941367681.364, "dur": 76.181, + "args": { + "External id": 4547630,"Record function id": 0, "Ev Idx": 6853 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941367832.336, "dur": 46.838, + "args": { + "External id": 4547631,"Record function id": 0, "Ev Idx": 6854 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 1336753, "tid": 1336753, + "ts": 1696941367888.633, "dur": 17949.537, + "args": { + "External id": 4547632,"Record function id": 0, "Ev Idx": 6855 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 1336753, "tid": 1336753, + "ts": 1696941367897.852, "dur": 943.014, + "args": { + "External id": 4547633,"Record function id": 0, "Ev Idx": 6856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941367980.155, "dur": 45.998, + "args": { + "External id": 4547634,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941368043.693, "dur": 44.517, + "args": { + "External id": 4547635,"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": 6858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368049.813, "dur": 2.264, + "args": { + "External id": 4547636,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941368057.687, "dur": 0.622, + "args": { + "External id": 4547637,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941368059.980, "dur": 0.718, + "args": { + "External id": 4547638,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368062.419, "dur": 0.693, + "args": { + "External id": 4547639,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368066.698, "dur": 0.662, + "args": { + "External id": 4547640,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368068.984, "dur": 0.521, + "args": { + "External id": 4547641,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368071.091, "dur": 5.067, + "args": { + "External id": 4547642,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368077.796, "dur": 0.500, + "args": { + "External id": 4547643,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368079.708, "dur": 0.738, + "args": { + "External id": 4547644,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941368104.043, "dur": 47.047, + "args": { + "External id": 4547645,"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": 6868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941368185.229, "dur": 121.838, + "args": { + "External id": 4547646,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 6869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941368198.828, "dur": 5.514, + "args": { + "External id": 4547647,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941368209.422, "dur": 10.673, + "args": { + "External id": 4547648,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941368213.914, "dur": 5.655, + "args": { + "External id": 4547649,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368217.629, "dur": 0.662, + "args": { + "External id": 4547650,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941368227.420, "dur": 33.941, + "args": { + "External id": 4547651,"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": 6874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368230.297, "dur": 0.672, + "args": { + "External id": 4547652,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941368232.686, "dur": 2.488, + "args": { + "External id": 4547653,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941368236.840, "dur": 0.653, + "args": { + "External id": 4547654,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368239.002, "dur": 2.454, + "args": { + "External id": 4547655,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368245.604, "dur": 0.386, + "args": { + "External id": 4547656,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368247.536, "dur": 0.350, + "args": { + "External id": 4547657,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368249.877, "dur": 0.325, + "args": { + "External id": 4547658,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368254.171, "dur": 0.360, + "args": { + "External id": 4547659,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941368256.037, "dur": 0.316, + "args": { + "External id": 4547660,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941368274.370, "dur": 24.345, + "args": { + "External id": 4547661,"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": 6884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941368359.182, "dur": 382.285, + "args": { + "External id": 4547662,"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": 6885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941368391.982, "dur": 344.275, + "args": { + "External id": 4547663,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 6886, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941368404.508, "dur": 325.809, + "args": { + "External id": 4547664,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941368769.469, "dur": 2.293, + "args": { + "External id": 4547665,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6888, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 1336753, "tid": 1336753, + "ts": 1696941368862.161, "dur": 16772.213, + "args": { + "External id": 4547666,"Record function id": 0, "Ev Idx": 6889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941368961.745, "dur": 6.706, + "args": { + "External id": 4547667,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941368971.996, "dur": 1.482, + "args": { + "External id": 4547668,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941368975.297, "dur": 3.027, + "args": { + "External id": 4547669,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941368979.977, "dur": 36.074, + "args": { + "External id": 4547670,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941369020.389, "dur": 1.320, + "args": { + "External id": 4547671,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941369023.022, "dur": 1.057, + "args": { + "External id": 4547672,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941369028.012, "dur": 1.258, + "args": { + "External id": 4547673,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941369030.969, "dur": 2.548, + "args": { + "External id": 4547674,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941369035.265, "dur": 1.021, + "args": { + "External id": 4547675,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941369037.945, "dur": 0.698, + "args": { + "External id": 4547676,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941369060.227, "dur": 16536.657, + "args": { + "External id": 4547677,"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": 6900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941369077.202, "dur": 16512.990, + "args": { + "External id": 4547678,"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": 6901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941369101.551, "dur": 14.948, + "args": { + "External id": 4547679,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941369119.490, "dur": 16436.699, + "args": { + "External id": 4547680,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941369122.054, "dur": 16433.564, + "args": { + "External id": 4547681,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941369128.470, "dur": 7.302, + "args": { + "External id": 4547682,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941369137.275, "dur": 16415.337, + "args": { + "External id": 4547683,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941385777.130, "dur": 36.918, + "args": { + "External id": 4547684,"Sequence number": 45295607, "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": 6907 + } + }, + { + "ph": "s", "id": 205, "pid": 1336753, "tid": 1336753, "ts": 1696941385777.130, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941385802.084, "dur": 7.562, + "args": { + "External id": 4547685,"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": 6908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941385805.459, "dur": 4.010, + "args": { + "External id": 4547686,"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": 6909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941385879.318, "dur": 79.752, + "args": { + "External id": 4547687,"Record function id": 0, "Ev Idx": 6910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941385960.779, "dur": 1126.809, + "args": { + "External id": 4547688,"Record function id": 0, "Ev Idx": 6911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941386035.387, "dur": 1037.802, + "args": { + "External id": 4547689,"Sequence number": 45295608, "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": 6912 + } + }, + { + "ph": "s", "id": 204, "pid": 1336753, "tid": 1336753, "ts": 1696941386035.387, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941386106.326, "dur": 45.614, + "args": { + "External id": 4547690,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 6913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941386165.840, "dur": 103.558, + "args": { + "External id": 4547691,"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": 6914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941386280.430, "dur": 37.995, + "args": { + "External id": 4547692,"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": 6915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941386326.479, "dur": 30.588, + "args": { + "External id": 4547693,"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": 6916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941386384.611, "dur": 28.003, + "args": { + "External id": 4547694,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941386430.883, "dur": 16.759, + "args": { + "External id": 4547695,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941386467.228, "dur": 150.099, + "args": { + "External id": 4547696,"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": 6919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941386516.139, "dur": 25.396, + "args": { + "External id": 4547697,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941386521.005, "dur": 19.315, + "args": { + "External id": 4547698,"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": 6921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941386545.549, "dur": 6.693, + "args": { + "External id": 4547699,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941386553.571, "dur": 1.054, + "args": { + "External id": 4547700,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941386557.483, "dur": 7.239, + "args": { + "External id": 4547701,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941386627.906, "dur": 50.670, + "args": { + "External id": 4547702,"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": 6925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941386709.420, "dur": 32.732, + "args": { + "External id": 4547703,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 6926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941386753.600, "dur": 41.276, + "args": { + "External id": 4547704,"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": 6927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941386802.760, "dur": 34.361, + "args": { + "External id": 4547705,"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": 6928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941386860.387, "dur": 28.497, + "args": { + "External id": 4547706,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 6929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941386894.457, "dur": 34.284, + "args": { + "External id": 4547707,"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": 6930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941386948.886, "dur": 18.499, + "args": { + "External id": 4547708,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 6931 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.11)", "pid": 1336753, "tid": 1336753, + "ts": 1696941387154.132, "dur": 79.529, + "args": { + "External id": 4547709,"Record function id": 0, "Ev Idx": 6932 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941387309.821, "dur": 48.070, + "args": { + "External id": 4547710,"Record function id": 0, "Ev Idx": 6933 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 1336753, "tid": 1336753, + "ts": 1696941387368.146, "dur": 18042.606, + "args": { + "External id": 4547711,"Record function id": 0, "Ev Idx": 6934 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 1336753, "tid": 1336753, + "ts": 1696941387377.427, "dur": 947.265, + "args": { + "External id": 4547712,"Record function id": 0, "Ev Idx": 6935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941387460.367, "dur": 8.120, + "args": { + "External id": 4547713,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941387485.181, "dur": 58.884, + "args": { + "External id": 4547714,"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": 6937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387490.718, "dur": 2.323, + "args": { + "External id": 4547715,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941387497.613, "dur": 0.454, + "args": { + "External id": 4547716,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941387500.141, "dur": 0.406, + "args": { + "External id": 4547717,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387502.261, "dur": 2.402, + "args": { + "External id": 4547718,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387506.422, "dur": 0.654, + "args": { + "External id": 4547719,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387508.600, "dur": 0.533, + "args": { + "External id": 4547720,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387513.186, "dur": 2.418, + "args": { + "External id": 4547721,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387517.153, "dur": 0.460, + "args": { + "External id": 4547722,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387519.478, "dur": 0.555, + "args": { + "External id": 4547723,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941387558.706, "dur": 45.281, + "args": { + "External id": 4547724,"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": 6947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941387639.673, "dur": 125.286, + "args": { + "External id": 4547725,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 6948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941387653.488, "dur": 4.846, + "args": { + "External id": 4547726,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941387663.558, "dur": 13.274, + "args": { + "External id": 4547727,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941387668.037, "dur": 8.388, + "args": { + "External id": 4547728,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387672.041, "dur": 3.009, + "args": { + "External id": 4547729,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941387684.671, "dur": 33.601, + "args": { + "External id": 4547730,"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": 6953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387687.417, "dur": 0.759, + "args": { + "External id": 4547731,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941387689.745, "dur": 0.730, + "args": { + "External id": 4547732,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941387692.590, "dur": 0.563, + "args": { + "External id": 4547733,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387697.130, "dur": 1.877, + "args": { + "External id": 4547734,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387700.354, "dur": 0.334, + "args": { + "External id": 4547735,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387702.324, "dur": 2.812, + "args": { + "External id": 4547736,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387706.596, "dur": 0.178, + "args": { + "External id": 4547737,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387708.227, "dur": 0.505, + "args": { + "External id": 4547738,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941387712.602, "dur": 0.456, + "args": { + "External id": 4547739,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941387730.505, "dur": 25.880, + "args": { + "External id": 4547740,"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": 6963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941387817.973, "dur": 405.931, + "args": { + "External id": 4547741,"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": 6964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941387852.751, "dur": 366.141, + "args": { + "External id": 4547742,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 6965, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941387862.895, "dur": 346.768, + "args": { + "External id": 4547743,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941388253.488, "dur": 2.545, + "args": { + "External id": 4547744,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6967, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 1336753, "tid": 1336753, + "ts": 1696941388345.775, "dur": 16856.731, + "args": { + "External id": 4547745,"Record function id": 0, "Ev Idx": 6968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941388446.584, "dur": 6.433, + "args": { + "External id": 4547746,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941388456.127, "dur": 1.531, + "args": { + "External id": 4547747,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941388459.259, "dur": 2.244, + "args": { + "External id": 4547748,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941388463.171, "dur": 0.952, + "args": { + "External id": 4547749,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941388465.506, "dur": 0.958, + "args": { + "External id": 4547750,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941388467.613, "dur": 0.975, + "args": { + "External id": 4547751,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941388472.098, "dur": 0.860, + "args": { + "External id": 4547752,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941388474.419, "dur": 3.148, + "args": { + "External id": 4547753,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941388479.192, "dur": 0.752, + "args": { + "External id": 4547754,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941388481.962, "dur": 0.878, + "args": { + "External id": 4547755,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941388503.049, "dur": 16663.008, + "args": { + "External id": 4547756,"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": 6979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941388519.108, "dur": 16639.768, + "args": { + "External id": 4547757,"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": 6980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941388561.288, "dur": 14.346, + "args": { + "External id": 4547758,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941388578.811, "dur": 16546.548, + "args": { + "External id": 4547759,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941388581.419, "dur": 16543.363, + "args": { + "External id": 4547760,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941388588.368, "dur": 6.289, + "args": { + "External id": 4547761,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941388596.651, "dur": 16525.424, + "args": { + "External id": 4547762,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941405348.846, "dur": 36.655, + "args": { + "External id": 4547763,"Sequence number": 45295609, "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": 6986 + } + }, + { + "ph": "s", "id": 203, "pid": 1336753, "tid": 1336753, "ts": 1696941405348.846, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941405373.210, "dur": 7.798, + "args": { + "External id": 4547764,"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": 6987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941405376.681, "dur": 4.129, + "args": { + "External id": 4547765,"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": 6988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941405451.837, "dur": 96.351, + "args": { + "External id": 4547766,"Record function id": 0, "Ev Idx": 6989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941405551.692, "dur": 1099.020, + "args": { + "External id": 4547767,"Record function id": 0, "Ev Idx": 6990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941405596.774, "dur": 1040.158, + "args": { + "External id": 4547768,"Sequence number": 45295610, "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": 6991 + } + }, + { + "ph": "s", "id": 202, "pid": 1336753, "tid": 1336753, "ts": 1696941405596.774, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941405663.968, "dur": 44.092, + "args": { + "External id": 4547769,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 6992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941405721.705, "dur": 101.197, + "args": { + "External id": 4547770,"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": 6993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941405832.013, "dur": 37.806, + "args": { + "External id": 4547771,"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": 6994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941405877.742, "dur": 31.687, + "args": { + "External id": 4547772,"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": 6995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941405935.468, "dur": 26.233, + "args": { + "External id": 4547773,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941405979.145, "dur": 60.697, + "args": { + "External id": 4547774,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 6997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941406061.437, "dur": 135.573, + "args": { + "External id": 4547775,"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": 6998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941406113.287, "dur": 11.850, + "args": { + "External id": 4547776,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941406118.787, "dur": 5.522, + "args": { + "External id": 4547777,"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": 7000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941406128.007, "dur": 6.516, + "args": { + "External id": 4547778,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941406135.817, "dur": 0.833, + "args": { + "External id": 4547779,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941406139.460, "dur": 5.901, + "args": { + "External id": 4547780,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941406207.193, "dur": 48.184, + "args": { + "External id": 4547781,"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": 7004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941406286.718, "dur": 29.328, + "args": { + "External id": 4547782,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 7005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941406325.614, "dur": 40.891, + "args": { + "External id": 4547783,"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": 7006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941406374.907, "dur": 35.049, + "args": { + "External id": 4547784,"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": 7007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941406437.082, "dur": 32.376, + "args": { + "External id": 4547785,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 7008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941406477.786, "dur": 34.524, + "args": { + "External id": 4547786,"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": 7009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941406545.871, "dur": 21.789, + "args": { + "External id": 4547787,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 7010 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.12)", "pid": 1336753, "tid": 1336753, + "ts": 1696941406713.762, "dur": 79.123, + "args": { + "External id": 4547788,"Record function id": 0, "Ev Idx": 7011 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941406867.766, "dur": 45.296, + "args": { + "External id": 4547789,"Record function id": 0, "Ev Idx": 7012 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 1336753, "tid": 1336753, + "ts": 1696941406922.621, "dur": 17982.703, + "args": { + "External id": 4547790,"Record function id": 0, "Ev Idx": 7013 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 1336753, "tid": 1336753, + "ts": 1696941406929.858, "dur": 933.536, + "args": { + "External id": 4547791,"Record function id": 0, "Ev Idx": 7014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941407049.408, "dur": 9.244, + "args": { + "External id": 4547792,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941407074.438, "dur": 41.302, + "args": { + "External id": 4547793,"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": 7016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407080.447, "dur": 2.049, + "args": { + "External id": 4547794,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941407087.725, "dur": 0.429, + "args": { + "External id": 4547795,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941407090.230, "dur": 0.635, + "args": { + "External id": 4547796,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407093.098, "dur": 0.367, + "args": { + "External id": 4547797,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407097.000, "dur": 0.504, + "args": { + "External id": 4547798,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407099.044, "dur": 0.161, + "args": { + "External id": 4547799,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407100.697, "dur": 4.169, + "args": { + "External id": 4547800,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407106.426, "dur": 0.279, + "args": { + "External id": 4547801,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407108.103, "dur": 0.377, + "args": { + "External id": 4547802,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941407128.269, "dur": 43.153, + "args": { + "External id": 4547803,"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": 7026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941407205.837, "dur": 123.510, + "args": { + "External id": 4547804,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 7027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941407219.468, "dur": 3.781, + "args": { + "External id": 4547805,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941407228.180, "dur": 10.556, + "args": { + "External id": 4547806,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941407232.544, "dur": 5.750, + "args": { + "External id": 4547807,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407236.657, "dur": 0.492, + "args": { + "External id": 4547808,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941407246.115, "dur": 33.973, + "args": { + "External id": 4547809,"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": 7032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407248.633, "dur": 2.836, + "args": { + "External id": 4547810,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941407253.159, "dur": 0.543, + "args": { + "External id": 4547811,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941407255.026, "dur": 0.551, + "args": { + "External id": 4547812,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407259.623, "dur": 2.048, + "args": { + "External id": 4547813,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407263.381, "dur": 0.324, + "args": { + "External id": 4547814,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407265.461, "dur": 0.164, + "args": { + "External id": 4547815,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407269.024, "dur": 0.313, + "args": { + "External id": 4547816,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407270.748, "dur": 0.375, + "args": { + "External id": 4547817,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941407272.386, "dur": 2.462, + "args": { + "External id": 4547818,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941407295.092, "dur": 25.541, + "args": { + "External id": 4547819,"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": 7042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941407380.959, "dur": 384.530, + "args": { + "External id": 4547820,"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": 7043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941407415.638, "dur": 344.685, + "args": { + "External id": 4547821,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 7044, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941407425.760, "dur": 328.392, + "args": { + "External id": 4547822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941407793.018, "dur": 2.373, + "args": { + "External id": 4547823,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7046, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 1336753, "tid": 1336753, + "ts": 1696941407885.113, "dur": 16817.187, + "args": { + "External id": 4547824,"Record function id": 0, "Ev Idx": 7047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941408022.044, "dur": 6.874, + "args": { + "External id": 4547825,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941408033.871, "dur": 1.145, + "args": { + "External id": 4547826,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941408036.853, "dur": 3.478, + "args": { + "External id": 4547827,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941408042.094, "dur": 1.017, + "args": { + "External id": 4547828,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941408044.324, "dur": 1.170, + "args": { + "External id": 4547829,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941408049.260, "dur": 1.024, + "args": { + "External id": 4547830,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941408052.084, "dur": 0.812, + "args": { + "External id": 4547831,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941408054.487, "dur": 2.253, + "args": { + "External id": 4547832,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941408058.125, "dur": 0.818, + "args": { + "External id": 4547833,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941408062.874, "dur": 0.859, + "args": { + "External id": 4547834,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941408083.858, "dur": 16580.297, + "args": { + "External id": 4547835,"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": 7058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941408101.167, "dur": 16556.518, + "args": { + "External id": 4547836,"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": 7059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941408128.011, "dur": 13.853, + "args": { + "External id": 4547837,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941408144.806, "dur": 16479.095, + "args": { + "External id": 4547838,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941408147.306, "dur": 16476.122, + "args": { + "External id": 4547839,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941408153.576, "dur": 6.318, + "args": { + "External id": 4547840,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941408161.336, "dur": 16459.545, + "args": { + "External id": 4547841,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941424841.811, "dur": 38.044, + "args": { + "External id": 4547842,"Sequence number": 45295611, "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": 7065 + } + }, + { + "ph": "s", "id": 201, "pid": 1336753, "tid": 1336753, "ts": 1696941424841.811, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941424867.563, "dur": 7.737, + "args": { + "External id": 4547843,"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": 7066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941424871.126, "dur": 3.965, + "args": { + "External id": 4547844,"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": 7067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941424947.819, "dur": 106.820, + "args": { + "External id": 4547845,"Record function id": 0, "Ev Idx": 7068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941425057.766, "dur": 1102.646, + "args": { + "External id": 4547846,"Record function id": 0, "Ev Idx": 7069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941425100.767, "dur": 1046.046, + "args": { + "External id": 4547847,"Sequence number": 45295612, "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": 7070 + } + }, + { + "ph": "s", "id": 200, "pid": 1336753, "tid": 1336753, "ts": 1696941425100.767, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941425170.963, "dur": 44.856, + "args": { + "External id": 4547848,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 7071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941425229.577, "dur": 103.606, + "args": { + "External id": 4547849,"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": 7072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941425342.577, "dur": 38.980, + "args": { + "External id": 4547850,"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": 7073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941425390.097, "dur": 30.343, + "args": { + "External id": 4547851,"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": 7074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941425443.936, "dur": 28.859, + "args": { + "External id": 4547852,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941425493.916, "dur": 15.516, + "args": { + "External id": 4547853,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941425543.585, "dur": 133.731, + "args": { + "External id": 4547854,"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": 7077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941425596.424, "dur": 11.779, + "args": { + "External id": 4547855,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941425601.841, "dur": 5.509, + "args": { + "External id": 4547856,"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": 7079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941425611.063, "dur": 6.083, + "args": { + "External id": 4547857,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941425618.514, "dur": 0.833, + "args": { + "External id": 4547858,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941425621.877, "dur": 4.538, + "args": { + "External id": 4547859,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941425688.312, "dur": 50.065, + "args": { + "External id": 4547860,"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": 7083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941425768.399, "dur": 30.372, + "args": { + "External id": 4547861,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 7084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941425808.706, "dur": 40.318, + "args": { + "External id": 4547862,"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": 7085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941425858.257, "dur": 35.142, + "args": { + "External id": 4547863,"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": 7086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941425918.569, "dur": 28.000, + "args": { + "External id": 4547864,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 7087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941425952.082, "dur": 69.700, + "args": { + "External id": 4547865,"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": 7088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941426049.199, "dur": 22.740, + "args": { + "External id": 4547866,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 7089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.13)", "pid": 1336753, "tid": 1336753, + "ts": 1696941426225.090, "dur": 76.331, + "args": { + "External id": 4547867,"Record function id": 0, "Ev Idx": 7090 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941426377.535, "dur": 47.734, + "args": { + "External id": 4547868,"Record function id": 0, "Ev Idx": 7091 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 1336753, "tid": 1336753, + "ts": 1696941426435.147, "dur": 18150.828, + "args": { + "External id": 4547869,"Record function id": 0, "Ev Idx": 7092 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 1336753, "tid": 1336753, + "ts": 1696941426444.905, "dur": 975.543, + "args": { + "External id": 4547870,"Record function id": 0, "Ev Idx": 7093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941426523.419, "dur": 24.171, + "args": { + "External id": 4547871,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941426564.386, "dur": 52.258, + "args": { + "External id": 4547872,"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": 7095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426575.388, "dur": 1.893, + "args": { + "External id": 4547873,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941426582.724, "dur": 0.537, + "args": { + "External id": 4547874,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941426584.852, "dur": 0.444, + "args": { + "External id": 4547875,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426587.126, "dur": 3.133, + "args": { + "External id": 4547876,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426591.925, "dur": 0.379, + "args": { + "External id": 4547877,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426596.678, "dur": 0.561, + "args": { + "External id": 4547878,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426600.974, "dur": 1.980, + "args": { + "External id": 4547879,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426604.396, "dur": 0.494, + "args": { + "External id": 4547880,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426606.774, "dur": 2.726, + "args": { + "External id": 4547881,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941426628.794, "dur": 43.531, + "args": { + "External id": 4547882,"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": 7105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941426707.170, "dur": 116.226, + "args": { + "External id": 4547883,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 7106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941426719.102, "dur": 4.010, + "args": { + "External id": 4547884,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941426728.643, "dur": 10.602, + "args": { + "External id": 4547885,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941426732.986, "dur": 5.814, + "args": { + "External id": 4547886,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426736.787, "dur": 0.756, + "args": { + "External id": 4547887,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941426746.407, "dur": 31.975, + "args": { + "External id": 4547888,"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": 7111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426749.012, "dur": 0.264, + "args": { + "External id": 4547889,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941426751.102, "dur": 0.617, + "args": { + "External id": 4547890,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941426753.212, "dur": 2.400, + "args": { + "External id": 4547891,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426756.857, "dur": 2.241, + "args": { + "External id": 4547892,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426760.542, "dur": 0.338, + "args": { + "External id": 4547893,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426764.723, "dur": 0.346, + "args": { + "External id": 4547894,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426766.863, "dur": 0.316, + "args": { + "External id": 4547895,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426768.452, "dur": 0.352, + "args": { + "External id": 4547896,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941426772.212, "dur": 0.605, + "args": { + "External id": 4547897,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941426789.971, "dur": 25.580, + "args": { + "External id": 4547898,"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": 7121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941426876.040, "dur": 439.598, + "args": { + "External id": 4547899,"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": 7122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941426911.955, "dur": 397.964, + "args": { + "External id": 4547900,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 7123, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941426922.062, "dur": 381.319, + "args": { + "External id": 4547901,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941427344.454, "dur": 2.509, + "args": { + "External id": 4547902,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7125, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 1336753, "tid": 1336753, + "ts": 1696941427442.505, "dur": 16910.667, + "args": { + "External id": 4547903,"Record function id": 0, "Ev Idx": 7126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941427564.997, "dur": 6.997, + "args": { + "External id": 4547904,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941427575.573, "dur": 1.236, + "args": { + "External id": 4547905,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941427578.887, "dur": 2.754, + "args": { + "External id": 4547906,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941427583.532, "dur": 1.347, + "args": { + "External id": 4547907,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941427586.322, "dur": 1.050, + "args": { + "External id": 4547908,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941427588.605, "dur": 0.988, + "args": { + "External id": 4547909,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941427593.283, "dur": 1.333, + "args": { + "External id": 4547910,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941427596.186, "dur": 2.660, + "args": { + "External id": 4547911,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941427600.330, "dur": 0.762, + "args": { + "External id": 4547912,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941427603.178, "dur": 1.020, + "args": { + "External id": 4547913,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941427627.130, "dur": 16679.189, + "args": { + "External id": 4547914,"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": 7137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941427643.905, "dur": 16654.174, + "args": { + "External id": 4547915,"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": 7138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941427669.904, "dur": 15.165, + "args": { + "External id": 4547916,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941427687.949, "dur": 16572.290, + "args": { + "External id": 4547917,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941427690.771, "dur": 16568.475, + "args": { + "External id": 4547918,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941427697.750, "dur": 5.746, + "args": { + "External id": 4547919,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941427705.310, "dur": 16550.483, + "args": { + "External id": 4547920,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941444505.891, "dur": 52.013, + "args": { + "External id": 4547921,"Sequence number": 45295613, "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": 7144 + } + }, + { + "ph": "s", "id": 199, "pid": 1336753, "tid": 1336753, "ts": 1696941444505.891, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941444543.004, "dur": 9.807, + "args": { + "External id": 4547922,"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": 7145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941444546.733, "dur": 5.658, + "args": { + "External id": 4547923,"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": 7146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941444629.872, "dur": 79.277, + "args": { + "External id": 4547924,"Record function id": 0, "Ev Idx": 7147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941444710.720, "dur": 1127.342, + "args": { + "External id": 4547925,"Record function id": 0, "Ev Idx": 7148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941444753.924, "dur": 1070.252, + "args": { + "External id": 4547926,"Sequence number": 45295614, "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": 7149 + } + }, + { + "ph": "s", "id": 198, "pid": 1336753, "tid": 1336753, "ts": 1696941444753.924, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941444823.550, "dur": 46.034, + "args": { + "External id": 4547927,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 7150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941444882.360, "dur": 136.809, + "args": { + "External id": 4547928,"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": 7151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941445033.543, "dur": 43.794, + "args": { + "External id": 4547929,"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": 7152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941445087.403, "dur": 32.233, + "args": { + "External id": 4547930,"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": 7153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941445149.376, "dur": 29.842, + "args": { + "External id": 4547931,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941445198.662, "dur": 17.148, + "args": { + "External id": 4547932,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941445236.219, "dur": 138.175, + "args": { + "External id": 4547933,"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": 7156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941445292.101, "dur": 11.806, + "args": { + "External id": 4547934,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941445297.585, "dur": 5.616, + "args": { + "External id": 4547935,"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": 7158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941445306.643, "dur": 6.547, + "args": { + "External id": 4547936,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941445314.439, "dur": 1.401, + "args": { + "External id": 4547937,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941445318.748, "dur": 5.276, + "args": { + "External id": 4547938,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941445384.954, "dur": 45.764, + "args": { + "External id": 4547939,"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": 7162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941445466.367, "dur": 30.588, + "args": { + "External id": 4547940,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 7163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941445507.388, "dur": 58.801, + "args": { + "External id": 4547941,"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": 7164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941445578.241, "dur": 37.768, + "args": { + "External id": 4547942,"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": 7165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941445638.674, "dur": 30.661, + "args": { + "External id": 4547943,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 7166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941445674.559, "dur": 33.131, + "args": { + "External id": 4547944,"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": 7167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941445731.417, "dur": 19.790, + "args": { + "External id": 4547945,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 7168 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.14)", "pid": 1336753, "tid": 1336753, + "ts": 1696941445902.574, "dur": 76.370, + "args": { + "External id": 4547946,"Record function id": 0, "Ev Idx": 7169 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941446100.390, "dur": 50.116, + "args": { + "External id": 4547947,"Record function id": 0, "Ev Idx": 7170 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 1336753, "tid": 1336753, + "ts": 1696941446161.397, "dur": 18079.938, + "args": { + "External id": 4547948,"Record function id": 0, "Ev Idx": 7171 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 1336753, "tid": 1336753, + "ts": 1696941446169.040, "dur": 958.337, + "args": { + "External id": 4547949,"Record function id": 0, "Ev Idx": 7172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941446252.959, "dur": 9.406, + "args": { + "External id": 4547950,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941446277.016, "dur": 38.836, + "args": { + "External id": 4547951,"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": 7174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446283.090, "dur": 2.250, + "args": { + "External id": 4547952,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941446290.173, "dur": 0.407, + "args": { + "External id": 4547953,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941446292.205, "dur": 0.427, + "args": { + "External id": 4547954,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446294.359, "dur": 0.242, + "args": { + "External id": 4547955,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446298.190, "dur": 0.424, + "args": { + "External id": 4547956,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446300.325, "dur": 0.370, + "args": { + "External id": 4547957,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446302.272, "dur": 3.441, + "args": { + "External id": 4547958,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446307.495, "dur": 0.230, + "args": { + "External id": 4547959,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446308.973, "dur": 0.286, + "args": { + "External id": 4547960,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941446327.872, "dur": 44.420, + "args": { + "External id": 4547961,"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": 7184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941446405.827, "dur": 146.661, + "args": { + "External id": 4547962,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 7185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941446416.387, "dur": 3.933, + "args": { + "External id": 4547963,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941446425.026, "dur": 11.220, + "args": { + "External id": 4547964,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941446429.871, "dur": 5.982, + "args": { + "External id": 4547965,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446433.804, "dur": 0.837, + "args": { + "External id": 4547966,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941446443.506, "dur": 35.291, + "args": { + "External id": 4547967,"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": 7190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446446.045, "dur": 2.808, + "args": { + "External id": 4547968,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941446450.652, "dur": 0.275, + "args": { + "External id": 4547969,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941446452.688, "dur": 0.230, + "args": { + "External id": 4547970,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446457.055, "dur": 2.613, + "args": { + "External id": 4547971,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446461.087, "dur": 0.151, + "args": { + "External id": 4547972,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446462.685, "dur": 0.466, + "args": { + "External id": 4547973,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446466.529, "dur": 0.464, + "args": { + "External id": 4547974,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446468.453, "dur": 0.238, + "args": { + "External id": 4547975,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941446470.446, "dur": 2.445, + "args": { + "External id": 4547976,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941446500.870, "dur": 41.890, + "args": { + "External id": 4547977,"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": 7200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941446608.593, "dur": 363.807, + "args": { + "External id": 4547978,"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": 7201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941446644.222, "dur": 323.421, + "args": { + "External id": 4547979,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 7202, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941446656.313, "dur": 305.217, + "args": { + "External id": 4547980,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941447049.890, "dur": 3.638, + "args": { + "External id": 4547981,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7204, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 1336753, "tid": 1336753, + "ts": 1696941447148.958, "dur": 16871.620, + "args": { + "External id": 4547982,"Record function id": 0, "Ev Idx": 7205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941447253.877, "dur": 6.665, + "args": { + "External id": 4547983,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941447264.065, "dur": 1.406, + "args": { + "External id": 4547984,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941447267.203, "dur": 2.112, + "args": { + "External id": 4547985,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941447271.321, "dur": 1.053, + "args": { + "External id": 4547986,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941447273.725, "dur": 1.018, + "args": { + "External id": 4547987,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941447275.964, "dur": 1.238, + "args": { + "External id": 4547988,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941447280.828, "dur": 1.093, + "args": { + "External id": 4547989,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941447283.442, "dur": 2.626, + "args": { + "External id": 4547990,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941447287.516, "dur": 0.945, + "args": { + "External id": 4547991,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941447289.968, "dur": 0.808, + "args": { + "External id": 4547992,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941447311.627, "dur": 16633.982, + "args": { + "External id": 4547993,"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": 7216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941447329.058, "dur": 16608.657, + "args": { + "External id": 4547994,"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": 7217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941447351.680, "dur": 15.154, + "args": { + "External id": 4547995,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941447369.914, "dur": 16529.407, + "args": { + "External id": 4547996,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941447372.690, "dur": 16525.963, + "args": { + "External id": 4547997,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941447379.717, "dur": 5.150, + "args": { + "External id": 4547998,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941447386.420, "dur": 16508.591, + "args": { + "External id": 4547999,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941464175.489, "dur": 39.931, + "args": { + "External id": 4548000,"Sequence number": 45295615, "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": 7223 + } + }, + { + "ph": "s", "id": 197, "pid": 1336753, "tid": 1336753, "ts": 1696941464175.489, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941464200.449, "dur": 10.238, + "args": { + "External id": 4548001,"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": 7224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941464204.486, "dur": 5.974, + "args": { + "External id": 4548002,"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": 7225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941464282.866, "dur": 80.345, + "args": { + "External id": 4548003,"Record function id": 0, "Ev Idx": 7226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941464364.929, "dur": 1120.595, + "args": { + "External id": 4548004,"Record function id": 0, "Ev Idx": 7227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941464411.840, "dur": 1059.637, + "args": { + "External id": 4548005,"Sequence number": 45295616, "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": 7228 + } + }, + { + "ph": "s", "id": 196, "pid": 1336753, "tid": 1336753, "ts": 1696941464411.840, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941464483.450, "dur": 60.550, + "args": { + "External id": 4548006,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 7229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941464559.441, "dur": 105.117, + "args": { + "External id": 4548007,"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": 7230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941464674.955, "dur": 39.429, + "args": { + "External id": 4548008,"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": 7231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941464722.987, "dur": 30.665, + "args": { + "External id": 4548009,"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": 7232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941464781.391, "dur": 30.688, + "args": { + "External id": 4548010,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941464831.306, "dur": 15.241, + "args": { + "External id": 4548011,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941464866.444, "dur": 173.705, + "args": { + "External id": 4548012,"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": 7235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941464916.097, "dur": 12.861, + "args": { + "External id": 4548013,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941464922.312, "dur": 5.731, + "args": { + "External id": 4548014,"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": 7237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941464931.652, "dur": 7.624, + "args": { + "External id": 4548015,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941464940.545, "dur": 1.571, + "args": { + "External id": 4548016,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941464944.581, "dur": 4.863, + "args": { + "External id": 4548017,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941465053.037, "dur": 52.720, + "args": { + "External id": 4548018,"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": 7241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941465138.032, "dur": 30.996, + "args": { + "External id": 4548019,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 7242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941465179.202, "dur": 41.207, + "args": { + "External id": 4548020,"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": 7243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941465229.408, "dur": 35.307, + "args": { + "External id": 4548021,"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": 7244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941465289.178, "dur": 27.566, + "args": { + "External id": 4548022,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 7245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941465322.105, "dur": 34.333, + "args": { + "External id": 4548023,"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": 7246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941465375.779, "dur": 18.995, + "args": { + "External id": 4548024,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 7247 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.15)", "pid": 1336753, "tid": 1336753, + "ts": 1696941465568.271, "dur": 84.166, + "args": { + "External id": 4548025,"Record function id": 0, "Ev Idx": 7248 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941465731.318, "dur": 47.586, + "args": { + "External id": 4548026,"Record function id": 0, "Ev Idx": 7249 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 1336753, "tid": 1336753, + "ts": 1696941465788.920, "dur": 18075.509, + "args": { + "External id": 4548027,"Record function id": 0, "Ev Idx": 7250 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 1336753, "tid": 1336753, + "ts": 1696941465798.503, "dur": 946.430, + "args": { + "External id": 4548028,"Record function id": 0, "Ev Idx": 7251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941465883.634, "dur": 8.851, + "args": { + "External id": 4548029,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941465906.229, "dur": 39.783, + "args": { + "External id": 4548030,"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": 7253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941465912.330, "dur": 2.226, + "args": { + "External id": 4548031,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941465919.528, "dur": 0.237, + "args": { + "External id": 4548032,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941465921.540, "dur": 0.188, + "args": { + "External id": 4548033,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941465923.607, "dur": 0.483, + "args": { + "External id": 4548034,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941465928.166, "dur": 0.211, + "args": { + "External id": 4548035,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941465930.500, "dur": 0.157, + "args": { + "External id": 4548036,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941465932.121, "dur": 3.212, + "args": { + "External id": 4548037,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941465936.745, "dur": 0.312, + "args": { + "External id": 4548038,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941465938.493, "dur": 0.269, + "args": { + "External id": 4548039,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941465962.312, "dur": 81.487, + "args": { + "External id": 4548040,"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": 7263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941466082.202, "dur": 123.386, + "args": { + "External id": 4548041,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 7264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941466094.603, "dur": 7.249, + "args": { + "External id": 4548042,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941466107.446, "dur": 11.006, + "args": { + "External id": 4548043,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941466111.982, "dur": 6.079, + "args": { + "External id": 4548044,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941466115.897, "dur": 0.685, + "args": { + "External id": 4548045,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941466125.986, "dur": 32.411, + "args": { + "External id": 4548046,"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": 7269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941466128.700, "dur": 0.827, + "args": { + "External id": 4548047,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941466131.158, "dur": 2.721, + "args": { + "External id": 4548048,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941466135.827, "dur": 0.282, + "args": { + "External id": 4548049,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941466138.277, "dur": 1.638, + "args": { + "External id": 4548050,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941466143.353, "dur": 0.453, + "args": { + "External id": 4548051,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941466145.316, "dur": 0.172, + "args": { + "External id": 4548052,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941466148.072, "dur": 0.265, + "args": { + "External id": 4548053,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941466151.820, "dur": 0.270, + "args": { + "External id": 4548054,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941466153.499, "dur": 0.162, + "args": { + "External id": 4548055,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941466170.434, "dur": 26.784, + "args": { + "External id": 4548056,"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": 7279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941466261.326, "dur": 381.781, + "args": { + "External id": 4548057,"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": 7280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941466296.658, "dur": 341.068, + "args": { + "External id": 4548058,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 7281, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941466306.885, "dur": 324.489, + "args": { + "External id": 4548059,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941466671.162, "dur": 2.837, + "args": { + "External id": 4548060,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7283, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 1336753, "tid": 1336753, + "ts": 1696941466766.837, "dur": 16886.394, + "args": { + "External id": 4548061,"Record function id": 0, "Ev Idx": 7284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941466874.555, "dur": 6.284, + "args": { + "External id": 4548062,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941466884.021, "dur": 1.255, + "args": { + "External id": 4548063,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941466887.266, "dur": 2.786, + "args": { + "External id": 4548064,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941466891.688, "dur": 0.748, + "args": { + "External id": 4548065,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941466893.867, "dur": 1.061, + "args": { + "External id": 4548066,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941466896.378, "dur": 0.876, + "args": { + "External id": 4548067,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941466901.106, "dur": 0.995, + "args": { + "External id": 4548068,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941466903.750, "dur": 1.970, + "args": { + "External id": 4548069,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941466907.290, "dur": 0.746, + "args": { + "External id": 4548070,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941466909.959, "dur": 0.777, + "args": { + "External id": 4548071,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941466932.319, "dur": 16678.546, + "args": { + "External id": 4548072,"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": 7295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941466949.376, "dur": 16654.856, + "args": { + "External id": 4548073,"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": 7296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941466975.786, "dur": 49.799, + "args": { + "External id": 4548074,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941467029.956, "dur": 16540.291, + "args": { + "External id": 4548075,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941467032.510, "dur": 16537.002, + "args": { + "External id": 4548076,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941467039.374, "dur": 6.172, + "args": { + "External id": 4548077,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941467047.433, "dur": 16519.004, + "args": { + "External id": 4548078,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941483801.697, "dur": 36.540, + "args": { + "External id": 4548079,"Sequence number": 45295617, "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": 7302 + } + }, + { + "ph": "s", "id": 195, "pid": 1336753, "tid": 1336753, "ts": 1696941483801.697, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941483825.346, "dur": 8.009, + "args": { + "External id": 4548080,"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": 7303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941483828.853, "dur": 4.274, + "args": { + "External id": 4548081,"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": 7304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941483905.309, "dur": 104.782, + "args": { + "External id": 4548082,"Record function id": 0, "Ev Idx": 7305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941484013.243, "dur": 1150.065, + "args": { + "External id": 4548083,"Record function id": 0, "Ev Idx": 7306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941484060.309, "dur": 1088.247, + "args": { + "External id": 4548084,"Sequence number": 45295618, "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": 7307 + } + }, + { + "ph": "s", "id": 194, "pid": 1336753, "tid": 1336753, "ts": 1696941484060.309, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941484129.092, "dur": 43.560, + "args": { + "External id": 4548085,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 7308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941484186.244, "dur": 104.806, + "args": { + "External id": 4548086,"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": 7309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941484301.442, "dur": 37.616, + "args": { + "External id": 4548087,"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": 7310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941484347.758, "dur": 31.533, + "args": { + "External id": 4548088,"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": 7311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941484409.888, "dur": 28.216, + "args": { + "External id": 4548089,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941484454.680, "dur": 15.779, + "args": { + "External id": 4548090,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941484489.115, "dur": 156.089, + "args": { + "External id": 4548091,"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": 7314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941484554.915, "dur": 13.317, + "args": { + "External id": 4548092,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941484560.650, "dur": 6.660, + "args": { + "External id": 4548093,"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": 7316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941484571.105, "dur": 6.634, + "args": { + "External id": 4548094,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941484579.085, "dur": 1.355, + "args": { + "External id": 4548095,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941484583.060, "dur": 7.992, + "args": { + "External id": 4548096,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941484683.102, "dur": 52.502, + "args": { + "External id": 4548097,"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": 7320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941484773.879, "dur": 31.742, + "args": { + "External id": 4548098,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 7321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941484815.911, "dur": 42.350, + "args": { + "External id": 4548099,"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": 7322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941484866.863, "dur": 35.274, + "args": { + "External id": 4548100,"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": 7323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941484923.442, "dur": 27.288, + "args": { + "External id": 4548101,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 7324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941484956.082, "dur": 68.410, + "args": { + "External id": 4548102,"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": 7325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941485051.365, "dur": 22.680, + "args": { + "External id": 4548103,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 7326 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.16)", "pid": 1336753, "tid": 1336753, + "ts": 1696941485228.970, "dur": 76.046, + "args": { + "External id": 4548104,"Record function id": 0, "Ev Idx": 7327 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941485379.013, "dur": 45.373, + "args": { + "External id": 4548105,"Record function id": 0, "Ev Idx": 7328 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 1336753, "tid": 1336753, + "ts": 1696941485434.229, "dur": 18172.041, + "args": { + "External id": 4548106,"Record function id": 0, "Ev Idx": 7329 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 1336753, "tid": 1336753, + "ts": 1696941485443.070, "dur": 930.904, + "args": { + "External id": 4548107,"Record function id": 0, "Ev Idx": 7330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941485545.508, "dur": 9.474, + "args": { + "External id": 4548108,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941485571.124, "dur": 39.366, + "args": { + "External id": 4548109,"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": 7332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485577.242, "dur": 2.246, + "args": { + "External id": 4548110,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941485584.440, "dur": 0.606, + "args": { + "External id": 4548111,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941485586.773, "dur": 0.625, + "args": { + "External id": 4548112,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485589.308, "dur": 0.375, + "args": { + "External id": 4548113,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485593.040, "dur": 0.516, + "args": { + "External id": 4548114,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485595.468, "dur": 0.381, + "args": { + "External id": 4548115,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485597.783, "dur": 2.497, + "args": { + "External id": 4548116,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485601.808, "dur": 0.320, + "args": { + "External id": 4548117,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485603.922, "dur": 0.148, + "args": { + "External id": 4548118,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941485622.981, "dur": 44.556, + "args": { + "External id": 4548119,"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": 7342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941485703.189, "dur": 116.857, + "args": { + "External id": 4548120,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 7343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941485714.527, "dur": 4.360, + "args": { + "External id": 4548121,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941485724.281, "dur": 10.703, + "args": { + "External id": 4548122,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941485729.009, "dur": 5.562, + "args": { + "External id": 4548123,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485732.767, "dur": 0.617, + "args": { + "External id": 4548124,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941485742.214, "dur": 31.807, + "args": { + "External id": 4548125,"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": 7348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485744.223, "dur": 2.852, + "args": { + "External id": 4548126,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941485748.829, "dur": 0.478, + "args": { + "External id": 4548127,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941485750.807, "dur": 0.355, + "args": { + "External id": 4548128,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485754.515, "dur": 1.951, + "args": { + "External id": 4548129,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485757.811, "dur": 0.344, + "args": { + "External id": 4548130,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485760.106, "dur": 0.286, + "args": { + "External id": 4548131,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485763.377, "dur": 0.251, + "args": { + "External id": 4548132,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485764.965, "dur": 0.355, + "args": { + "External id": 4548133,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941485766.962, "dur": 2.699, + "args": { + "External id": 4548134,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941485787.272, "dur": 24.813, + "args": { + "External id": 4548135,"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": 7358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941485872.606, "dur": 400.877, + "args": { + "External id": 4548136,"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": 7359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941485907.620, "dur": 359.781, + "args": { + "External id": 4548137,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 7360, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941485917.977, "dur": 342.956, + "args": { + "External id": 4548138,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941486303.087, "dur": 2.311, + "args": { + "External id": 4548139,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7362, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 1336753, "tid": 1336753, + "ts": 1696941486393.826, "dur": 16998.140, + "args": { + "External id": 4548140,"Record function id": 0, "Ev Idx": 7363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941486496.495, "dur": 6.372, + "args": { + "External id": 4548141,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941486506.039, "dur": 1.415, + "args": { + "External id": 4548142,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941486509.103, "dur": 3.394, + "args": { + "External id": 4548143,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941486514.207, "dur": 1.269, + "args": { + "External id": 4548144,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941486516.855, "dur": 0.933, + "args": { + "External id": 4548145,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941486519.021, "dur": 1.248, + "args": { + "External id": 4548146,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941486524.147, "dur": 0.850, + "args": { + "External id": 4548147,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941486543.198, "dur": 2.707, + "args": { + "External id": 4548148,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941486549.305, "dur": 0.720, + "args": { + "External id": 4548149,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941486551.606, "dur": 0.949, + "args": { + "External id": 4548150,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941486574.918, "dur": 16778.906, + "args": { + "External id": 4548151,"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": 7374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941486591.631, "dur": 16755.600, + "args": { + "External id": 4548152,"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": 7375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941486623.140, "dur": 15.062, + "args": { + "External id": 4548153,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941486640.972, "dur": 16672.532, + "args": { + "External id": 4548154,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941486643.531, "dur": 16669.394, + "args": { + "External id": 4548155,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941486649.944, "dur": 5.918, + "args": { + "External id": 4548156,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941486657.499, "dur": 16652.458, + "args": { + "External id": 4548157,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941503542.272, "dur": 36.787, + "args": { + "External id": 4548158,"Sequence number": 45295619, "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": 7381 + } + }, + { + "ph": "s", "id": 193, "pid": 1336753, "tid": 1336753, "ts": 1696941503542.272, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941503566.579, "dur": 7.798, + "args": { + "External id": 4548159,"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": 7382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941503569.919, "dur": 4.166, + "args": { + "External id": 4548160,"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": 7383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941503647.917, "dur": 75.914, + "args": { + "External id": 4548161,"Record function id": 0, "Ev Idx": 7384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941503725.573, "dur": 1104.382, + "args": { + "External id": 4548162,"Record function id": 0, "Ev Idx": 7385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941503771.120, "dur": 1045.527, + "args": { + "External id": 4548163,"Sequence number": 45295620, "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": 7386 + } + }, + { + "ph": "s", "id": 192, "pid": 1336753, "tid": 1336753, "ts": 1696941503771.120, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941503838.726, "dur": 46.985, + "args": { + "External id": 4548164,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 7387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941503898.835, "dur": 129.326, + "args": { + "External id": 4548165,"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": 7388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941504042.467, "dur": 43.810, + "args": { + "External id": 4548166,"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": 7389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941504096.025, "dur": 31.161, + "args": { + "External id": 4548167,"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": 7390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941504154.389, "dur": 29.118, + "args": { + "External id": 4548168,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941504202.737, "dur": 15.857, + "args": { + "External id": 4548169,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941504239.590, "dur": 133.282, + "args": { + "External id": 4548170,"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": 7393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941504289.905, "dur": 12.736, + "args": { + "External id": 4548171,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941504296.027, "dur": 5.837, + "args": { + "External id": 4548172,"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": 7395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941504305.482, "dur": 6.916, + "args": { + "External id": 4548173,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941504313.759, "dur": 1.614, + "args": { + "External id": 4548174,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941504317.599, "dur": 4.824, + "args": { + "External id": 4548175,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941504383.261, "dur": 46.228, + "args": { + "External id": 4548176,"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": 7399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941504461.605, "dur": 29.332, + "args": { + "External id": 4548177,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 7400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941504500.939, "dur": 58.167, + "args": { + "External id": 4548178,"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": 7401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941504570.942, "dur": 38.306, + "args": { + "External id": 4548179,"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": 7402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941504634.398, "dur": 29.444, + "args": { + "External id": 4548180,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 7403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941504669.958, "dur": 34.176, + "args": { + "External id": 4548181,"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": 7404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941504723.791, "dur": 19.356, + "args": { + "External id": 4548182,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 7405 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.17)", "pid": 1336753, "tid": 1336753, + "ts": 1696941504893.209, "dur": 79.949, + "args": { + "External id": 4548183,"Record function id": 0, "Ev Idx": 7406 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941505092.105, "dur": 49.529, + "args": { + "External id": 4548184,"Record function id": 0, "Ev Idx": 7407 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 1336753, "tid": 1336753, + "ts": 1696941505152.396, "dur": 18289.877, + "args": { + "External id": 4548185,"Record function id": 0, "Ev Idx": 7408 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 1336753, "tid": 1336753, + "ts": 1696941505160.263, "dur": 925.071, + "args": { + "External id": 4548186,"Record function id": 0, "Ev Idx": 7409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941505243.674, "dur": 8.976, + "args": { + "External id": 4548187,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941505266.716, "dur": 40.794, + "args": { + "External id": 4548188,"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": 7411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505273.180, "dur": 2.420, + "args": { + "External id": 4548189,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941505280.510, "dur": 0.460, + "args": { + "External id": 4548190,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941505282.762, "dur": 0.336, + "args": { + "External id": 4548191,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505284.632, "dur": 0.748, + "args": { + "External id": 4548192,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505288.911, "dur": 0.298, + "args": { + "External id": 4548193,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505290.913, "dur": 0.296, + "args": { + "External id": 4548194,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505292.879, "dur": 3.341, + "args": { + "External id": 4548195,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505298.255, "dur": 0.184, + "args": { + "External id": 4548196,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505300.249, "dur": 0.338, + "args": { + "External id": 4548197,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941505320.935, "dur": 43.207, + "args": { + "External id": 4548198,"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": 7421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941505396.375, "dur": 121.282, + "args": { + "External id": 4548199,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 7422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941505411.479, "dur": 5.842, + "args": { + "External id": 4548200,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941505422.840, "dur": 10.393, + "args": { + "External id": 4548201,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941505427.097, "dur": 5.705, + "args": { + "External id": 4548202,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505431.163, "dur": 0.460, + "args": { + "External id": 4548203,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941505440.250, "dur": 33.132, + "args": { + "External id": 4548204,"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": 7427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505443.399, "dur": 0.602, + "args": { + "External id": 4548205,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941505445.594, "dur": 2.863, + "args": { + "External id": 4548206,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941505450.115, "dur": 0.626, + "args": { + "External id": 4548207,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505452.518, "dur": 1.842, + "args": { + "External id": 4548208,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505458.524, "dur": 0.504, + "args": { + "External id": 4548209,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505460.523, "dur": 0.270, + "args": { + "External id": 4548210,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505462.435, "dur": 0.155, + "args": { + "External id": 4548211,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505466.620, "dur": 0.382, + "args": { + "External id": 4548212,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941505468.619, "dur": 0.156, + "args": { + "External id": 4548213,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941505484.954, "dur": 25.244, + "args": { + "External id": 4548214,"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": 7437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941505590.042, "dur": 360.188, + "args": { + "External id": 4548215,"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": 7438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941505624.593, "dur": 320.229, + "args": { + "External id": 4548216,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 7439, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941505634.804, "dur": 304.378, + "args": { + "External id": 4548217,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941505975.520, "dur": 2.251, + "args": { + "External id": 4548218,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7441, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 1336753, "tid": 1336753, + "ts": 1696941506106.648, "dur": 17136.953, + "args": { + "External id": 4548219,"Record function id": 0, "Ev Idx": 7442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941506210.908, "dur": 6.687, + "args": { + "External id": 4548220,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941506220.911, "dur": 1.431, + "args": { + "External id": 4548221,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941506224.001, "dur": 3.206, + "args": { + "External id": 4548222,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941506228.782, "dur": 0.942, + "args": { + "External id": 4548223,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941506230.891, "dur": 0.945, + "args": { + "External id": 4548224,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941506233.082, "dur": 0.757, + "args": { + "External id": 4548225,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941506237.750, "dur": 1.035, + "args": { + "External id": 4548226,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941506240.295, "dur": 1.645, + "args": { + "External id": 4548227,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941506243.350, "dur": 0.953, + "args": { + "External id": 4548228,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941506246.140, "dur": 0.815, + "args": { + "External id": 4548229,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941506267.932, "dur": 16939.264, + "args": { + "External id": 4548230,"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": 7453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941506284.406, "dur": 16916.414, + "args": { + "External id": 4548231,"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": 7454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941506310.285, "dur": 15.576, + "args": { + "External id": 4548232,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941506328.674, "dur": 16838.298, + "args": { + "External id": 4548233,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941506331.022, "dur": 16835.355, + "args": { + "External id": 4548234,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941506338.213, "dur": 5.184, + "args": { + "External id": 4548235,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941506344.944, "dur": 16818.248, + "args": { + "External id": 4548236,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941523381.342, "dur": 36.221, + "args": { + "External id": 4548237,"Sequence number": 45295621, "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": 7460 + } + }, + { + "ph": "s", "id": 191, "pid": 1336753, "tid": 1336753, "ts": 1696941523381.342, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941523404.779, "dur": 7.852, + "args": { + "External id": 4548238,"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": 7461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941523408.386, "dur": 4.028, + "args": { + "External id": 4548239,"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": 7462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941523482.373, "dur": 91.247, + "args": { + "External id": 4548240,"Record function id": 0, "Ev Idx": 7463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941523585.983, "dur": 1097.778, + "args": { + "External id": 4548241,"Record function id": 0, "Ev Idx": 7464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941523632.148, "dur": 1038.092, + "args": { + "External id": 4548242,"Sequence number": 45295622, "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": 7465 + } + }, + { + "ph": "s", "id": 190, "pid": 1336753, "tid": 1336753, "ts": 1696941523632.148, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941523705.621, "dur": 46.371, + "args": { + "External id": 4548243,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 7466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941523766.980, "dur": 100.845, + "args": { + "External id": 4548244,"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": 7467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941523877.334, "dur": 37.294, + "args": { + "External id": 4548245,"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": 7468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941523920.393, "dur": 31.663, + "args": { + "External id": 4548246,"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": 7469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941523979.645, "dur": 61.872, + "args": { + "External id": 4548247,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941524063.868, "dur": 19.917, + "args": { + "External id": 4548248,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941524101.911, "dur": 133.943, + "args": { + "External id": 4548249,"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": 7472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941524150.994, "dur": 12.051, + "args": { + "External id": 4548250,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941524156.108, "dur": 6.182, + "args": { + "External id": 4548251,"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": 7474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941524165.840, "dur": 7.302, + "args": { + "External id": 4548252,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941524174.647, "dur": 3.486, + "args": { + "External id": 4548253,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941524180.461, "dur": 4.401, + "args": { + "External id": 4548254,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941524246.042, "dur": 49.033, + "args": { + "External id": 4548255,"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": 7478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941524325.291, "dur": 28.182, + "args": { + "External id": 4548256,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 7479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941524363.360, "dur": 40.946, + "args": { + "External id": 4548257,"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": 7480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941524411.056, "dur": 34.796, + "args": { + "External id": 4548258,"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": 7481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941524472.471, "dur": 28.436, + "args": { + "External id": 4548259,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 7482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941524506.249, "dur": 50.739, + "args": { + "External id": 4548260,"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": 7483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941524579.637, "dur": 22.765, + "args": { + "External id": 4548261,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 7484 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.18)", "pid": 1336753, "tid": 1336753, + "ts": 1696941524747.924, "dur": 76.465, + "args": { + "External id": 4548262,"Record function id": 0, "Ev Idx": 7485 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941524900.927, "dur": 49.615, + "args": { + "External id": 4548263,"Record function id": 0, "Ev Idx": 7486 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 1336753, "tid": 1336753, + "ts": 1696941524960.110, "dur": 18275.671, + "args": { + "External id": 4548264,"Record function id": 0, "Ev Idx": 7487 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 1336753, "tid": 1336753, + "ts": 1696941524968.199, "dur": 992.159, + "args": { + "External id": 4548265,"Record function id": 0, "Ev Idx": 7488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941525091.559, "dur": 9.538, + "args": { + "External id": 4548266,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941525115.892, "dur": 40.530, + "args": { + "External id": 4548267,"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": 7490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525121.843, "dur": 2.148, + "args": { + "External id": 4548268,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941525129.101, "dur": 0.410, + "args": { + "External id": 4548269,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941525130.963, "dur": 0.518, + "args": { + "External id": 4548270,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525133.314, "dur": 0.524, + "args": { + "External id": 4548271,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525138.145, "dur": 0.427, + "args": { + "External id": 4548272,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525140.260, "dur": 0.409, + "args": { + "External id": 4548273,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525142.600, "dur": 3.556, + "args": { + "External id": 4548274,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525147.615, "dur": 0.180, + "args": { + "External id": 4548275,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525149.689, "dur": 0.322, + "args": { + "External id": 4548276,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941525168.619, "dur": 43.380, + "args": { + "External id": 4548277,"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": 7500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941525246.343, "dur": 119.887, + "args": { + "External id": 4548278,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 7501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941525256.917, "dur": 3.851, + "args": { + "External id": 4548279,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941525266.084, "dur": 10.351, + "args": { + "External id": 4548280,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941525270.424, "dur": 5.585, + "args": { + "External id": 4548281,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525274.430, "dur": 0.550, + "args": { + "External id": 4548282,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941525283.708, "dur": 35.832, + "args": { + "External id": 4548283,"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": 7506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525286.189, "dur": 2.586, + "args": { + "External id": 4548284,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941525290.468, "dur": 0.552, + "args": { + "External id": 4548285,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941525293.118, "dur": 0.373, + "args": { + "External id": 4548286,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525297.188, "dur": 2.026, + "args": { + "External id": 4548287,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525300.735, "dur": 0.527, + "args": { + "External id": 4548288,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525303.131, "dur": 0.428, + "args": { + "External id": 4548289,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525307.712, "dur": 0.375, + "args": { + "External id": 4548290,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525310.808, "dur": 0.197, + "args": { + "External id": 4548291,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941525312.640, "dur": 2.426, + "args": { + "External id": 4548292,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941525333.152, "dur": 24.981, + "args": { + "External id": 4548293,"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": 7516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941525418.015, "dur": 437.939, + "args": { + "External id": 4548294,"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": 7517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941525453.901, "dur": 396.806, + "args": { + "External id": 4548295,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 7518, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941525464.054, "dur": 379.988, + "args": { + "External id": 4548296,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941525885.178, "dur": 2.860, + "args": { + "External id": 4548297,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7520, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 1336753, "tid": 1336753, + "ts": 1696941526017.484, "dur": 17002.851, + "args": { + "External id": 4548298,"Record function id": 0, "Ev Idx": 7521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941526131.270, "dur": 6.800, + "args": { + "External id": 4548299,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941526157.248, "dur": 1.363, + "args": { + "External id": 4548300,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941526160.392, "dur": 3.057, + "args": { + "External id": 4548301,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941526167.515, "dur": 0.898, + "args": { + "External id": 4548302,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941526169.819, "dur": 0.813, + "args": { + "External id": 4548303,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941526171.749, "dur": 0.772, + "args": { + "External id": 4548304,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941526174.081, "dur": 0.974, + "args": { + "External id": 4548305,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941526178.625, "dur": 1.940, + "args": { + "External id": 4548306,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941526181.996, "dur": 0.839, + "args": { + "External id": 4548307,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941526184.549, "dur": 0.617, + "args": { + "External id": 4548308,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941526205.884, "dur": 16748.583, + "args": { + "External id": 4548309,"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": 7532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941526222.947, "dur": 16724.964, + "args": { + "External id": 4548310,"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": 7533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941526242.116, "dur": 15.567, + "args": { + "External id": 4548311,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941526263.637, "dur": 16651.162, + "args": { + "External id": 4548312,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941526266.148, "dur": 16648.141, + "args": { + "External id": 4548313,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941526272.610, "dur": 5.518, + "args": { + "External id": 4548314,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941526279.600, "dur": 16631.771, + "args": { + "External id": 4548315,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941543170.878, "dur": 38.954, + "args": { + "External id": 4548316,"Sequence number": 45295623, "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": 7539 + } + }, + { + "ph": "s", "id": 189, "pid": 1336753, "tid": 1336753, "ts": 1696941543170.878, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941543196.970, "dur": 7.792, + "args": { + "External id": 4548317,"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": 7540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941543200.341, "dur": 4.160, + "args": { + "External id": 4548318,"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": 7541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941543278.185, "dur": 76.943, + "args": { + "External id": 4548319,"Record function id": 0, "Ev Idx": 7542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941543356.561, "dur": 1096.656, + "args": { + "External id": 4548320,"Record function id": 0, "Ev Idx": 7543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941543396.799, "dur": 1042.280, + "args": { + "External id": 4548321,"Sequence number": 45295624, "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": 7544 + } + }, + { + "ph": "s", "id": 188, "pid": 1336753, "tid": 1336753, "ts": 1696941543396.799, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941543469.532, "dur": 43.294, + "args": { + "External id": 4548322,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 7545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941543525.385, "dur": 121.454, + "args": { + "External id": 4548323,"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": 7546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941543659.791, "dur": 36.364, + "args": { + "External id": 4548324,"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": 7547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941543704.876, "dur": 29.600, + "args": { + "External id": 4548325,"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": 7548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941543759.816, "dur": 28.825, + "args": { + "External id": 4548326,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941543808.645, "dur": 15.516, + "args": { + "External id": 4548327,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941543842.762, "dur": 129.231, + "args": { + "External id": 4548328,"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": 7551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941543892.466, "dur": 11.796, + "args": { + "External id": 4548329,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941543897.834, "dur": 5.684, + "args": { + "External id": 4548330,"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": 7553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941543907.012, "dur": 6.768, + "args": { + "External id": 4548331,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941543915.381, "dur": 1.387, + "args": { + "External id": 4548332,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941543918.996, "dur": 4.213, + "args": { + "External id": 4548333,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941544018.229, "dur": 54.110, + "args": { + "External id": 4548334,"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": 7557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941544106.189, "dur": 31.658, + "args": { + "External id": 4548335,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 7558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941544148.216, "dur": 40.289, + "args": { + "External id": 4548336,"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": 7559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941544197.304, "dur": 34.385, + "args": { + "External id": 4548337,"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": 7560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941544256.372, "dur": 29.513, + "args": { + "External id": 4548338,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 7561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941544291.642, "dur": 33.648, + "args": { + "External id": 4548339,"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": 7562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941544347.027, "dur": 18.963, + "args": { + "External id": 4548340,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 7563 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.19)", "pid": 1336753, "tid": 1336753, + "ts": 1696941544516.415, "dur": 90.799, + "args": { + "External id": 4548341,"Record function id": 0, "Ev Idx": 7564 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941544684.719, "dur": 49.702, + "args": { + "External id": 4548342,"Record function id": 0, "Ev Idx": 7565 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.20)", "pid": 1336753, "tid": 1336753, + "ts": 1696941544744.718, "dur": 18113.527, + "args": { + "External id": 4548343,"Record function id": 0, "Ev Idx": 7566 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 1336753, "tid": 1336753, + "ts": 1696941544755.761, "dur": 962.623, + "args": { + "External id": 4548344,"Record function id": 0, "Ev Idx": 7567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941544839.247, "dur": 8.858, + "args": { + "External id": 4548345,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941544862.489, "dur": 41.038, + "args": { + "External id": 4548346,"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": 7569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941544868.196, "dur": 2.278, + "args": { + "External id": 4548347,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941544875.545, "dur": 0.465, + "args": { + "External id": 4548348,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941544877.315, "dur": 0.387, + "args": { + "External id": 4548349,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941544879.492, "dur": 0.532, + "args": { + "External id": 4548350,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941544883.387, "dur": 0.604, + "args": { + "External id": 4548351,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941544885.430, "dur": 0.595, + "args": { + "External id": 4548352,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941544887.882, "dur": 4.292, + "args": { + "External id": 4548353,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941544893.847, "dur": 0.518, + "args": { + "External id": 4548354,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941544896.038, "dur": 0.149, + "args": { + "External id": 4548355,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941544917.308, "dur": 41.626, + "args": { + "External id": 4548356,"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": 7579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941545029.690, "dur": 129.242, + "args": { + "External id": 4548357,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 7580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941545041.599, "dur": 6.145, + "args": { + "External id": 4548358,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941545054.089, "dur": 11.288, + "args": { + "External id": 4548359,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941545058.500, "dur": 6.464, + "args": { + "External id": 4548360,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941545062.857, "dur": 0.641, + "args": { + "External id": 4548361,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941545073.611, "dur": 37.220, + "args": { + "External id": 4548362,"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": 7585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941545076.331, "dur": 2.728, + "args": { + "External id": 4548363,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941545080.936, "dur": 0.662, + "args": { + "External id": 4548364,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941545087.072, "dur": 0.165, + "args": { + "External id": 4548365,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941545091.230, "dur": 1.668, + "args": { + "External id": 4548366,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941545094.498, "dur": 0.486, + "args": { + "External id": 4548367,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941545096.241, "dur": 2.564, + "args": { + "External id": 4548368,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941545100.472, "dur": 0.225, + "args": { + "External id": 4548369,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941545101.957, "dur": 0.186, + "args": { + "External id": 4548370,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941545106.015, "dur": 0.150, + "args": { + "External id": 4548371,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941545122.976, "dur": 27.842, + "args": { + "External id": 4548372,"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": 7595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941545213.918, "dur": 399.875, + "args": { + "External id": 4548373,"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": 7596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941545248.017, "dur": 359.905, + "args": { + "External id": 4548374,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 7597, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941545258.371, "dur": 341.346, + "args": { + "External id": 4548375,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941545642.182, "dur": 2.331, + "args": { + "External id": 4548376,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7599, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 1336753, "tid": 1336753, + "ts": 1696941545741.317, "dur": 16891.710, + "args": { + "External id": 4548377,"Record function id": 0, "Ev Idx": 7600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941545847.218, "dur": 6.877, + "args": { + "External id": 4548378,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941545857.309, "dur": 0.947, + "args": { + "External id": 4548379,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941545859.751, "dur": 2.780, + "args": { + "External id": 4548380,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941545864.372, "dur": 0.790, + "args": { + "External id": 4548381,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941545866.740, "dur": 0.806, + "args": { + "External id": 4548382,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941545868.779, "dur": 0.765, + "args": { + "External id": 4548383,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941545873.783, "dur": 0.813, + "args": { + "External id": 4548384,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941545876.199, "dur": 1.825, + "args": { + "External id": 4548385,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941545879.743, "dur": 0.715, + "args": { + "External id": 4548386,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941545881.949, "dur": 0.605, + "args": { + "External id": 4548387,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941545903.247, "dur": 16679.260, + "args": { + "External id": 4548388,"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": 7611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941545919.954, "dur": 16652.994, + "args": { + "External id": 4548389,"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": 7612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941545944.115, "dur": 14.747, + "args": { + "External id": 4548390,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941545961.950, "dur": 16561.887, + "args": { + "External id": 4548391,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941545964.432, "dur": 16558.427, + "args": { + "External id": 4548392,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941545970.932, "dur": 5.293, + "args": { + "External id": 4548393,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941545978.153, "dur": 16540.942, + "args": { + "External id": 4548394,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941562788.137, "dur": 43.906, + "args": { + "External id": 4548395,"Sequence number": 45295625, "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": 7618 + } + }, + { + "ph": "s", "id": 187, "pid": 1336753, "tid": 1336753, "ts": 1696941562788.137, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941562816.533, "dur": 10.318, + "args": { + "External id": 4548396,"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": 7619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941562821.423, "dur": 5.231, + "args": { + "External id": 4548397,"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": 7620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941562901.242, "dur": 75.046, + "args": { + "External id": 4548398,"Record function id": 0, "Ev Idx": 7621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941562977.708, "dur": 1122.140, + "args": { + "External id": 4548399,"Record function id": 0, "Ev Idx": 7622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941563051.363, "dur": 1034.527, + "args": { + "External id": 4548400,"Sequence number": 45295626, "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": 7623 + } + }, + { + "ph": "s", "id": 186, "pid": 1336753, "tid": 1336753, "ts": 1696941563051.363, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941563123.400, "dur": 45.674, + "args": { + "External id": 4548401,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 7624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941563182.387, "dur": 105.019, + "args": { + "External id": 4548402,"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": 7625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941563300.682, "dur": 37.263, + "args": { + "External id": 4548403,"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": 7626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941563344.633, "dur": 29.566, + "args": { + "External id": 4548404,"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": 7627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941563403.187, "dur": 25.879, + "args": { + "External id": 4548405,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941563445.513, "dur": 17.008, + "args": { + "External id": 4548406,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941563480.777, "dur": 153.016, + "args": { + "External id": 4548407,"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": 7630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941563545.690, "dur": 12.479, + "args": { + "External id": 4548408,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941563550.890, "dur": 6.473, + "args": { + "External id": 4548409,"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": 7632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941563561.287, "dur": 6.431, + "args": { + "External id": 4548410,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941563569.228, "dur": 1.582, + "args": { + "External id": 4548411,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941563575.930, "dur": 4.172, + "args": { + "External id": 4548412,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941563645.149, "dur": 50.065, + "args": { + "External id": 4548413,"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": 7636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941563728.565, "dur": 30.115, + "args": { + "External id": 4548414,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 7637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941563767.964, "dur": 40.693, + "args": { + "External id": 4548415,"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": 7638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941563814.950, "dur": 34.112, + "args": { + "External id": 4548416,"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": 7639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941563872.935, "dur": 29.191, + "args": { + "External id": 4548417,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 7640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941563907.503, "dur": 33.199, + "args": { + "External id": 4548418,"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": 7641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941563958.102, "dur": 18.699, + "args": { + "External id": 4548419,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 7642 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.20)", "pid": 1336753, "tid": 1336753, + "ts": 1696941564167.350, "dur": 76.480, + "args": { + "External id": 4548420,"Record function id": 0, "Ev Idx": 7643 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941564318.361, "dur": 48.742, + "args": { + "External id": 4548421,"Record function id": 0, "Ev Idx": 7644 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.21)", "pid": 1336753, "tid": 1336753, + "ts": 1696941564376.440, "dur": 18095.764, + "args": { + "External id": 4548422,"Record function id": 0, "Ev Idx": 7645 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 1336753, "tid": 1336753, + "ts": 1696941564384.443, "dur": 951.439, + "args": { + "External id": 4548423,"Record function id": 0, "Ev Idx": 7646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941564466.738, "dur": 9.240, + "args": { + "External id": 4548424,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941564490.008, "dur": 55.226, + "args": { + "External id": 4548425,"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": 7648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564495.902, "dur": 1.878, + "args": { + "External id": 4548426,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941564502.570, "dur": 0.230, + "args": { + "External id": 4548427,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941564504.533, "dur": 0.469, + "args": { + "External id": 4548428,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564506.703, "dur": 0.477, + "args": { + "External id": 4548429,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564510.764, "dur": 0.501, + "args": { + "External id": 4548430,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564512.732, "dur": 0.673, + "args": { + "External id": 4548431,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564515.333, "dur": 3.389, + "args": { + "External id": 4548432,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564519.919, "dur": 0.367, + "args": { + "External id": 4548433,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564521.833, "dur": 0.387, + "args": { + "External id": 4548434,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941564559.609, "dur": 45.645, + "args": { + "External id": 4548435,"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": 7658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941564640.386, "dur": 124.422, + "args": { + "External id": 4548436,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 7659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941564651.706, "dur": 4.849, + "args": { + "External id": 4548437,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941564661.974, "dur": 10.295, + "args": { + "External id": 4548438,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941564666.118, "dur": 5.724, + "args": { + "External id": 4548439,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564670.054, "dur": 0.557, + "args": { + "External id": 4548440,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941564680.284, "dur": 34.552, + "args": { + "External id": 4548441,"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": 7664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564682.851, "dur": 2.674, + "args": { + "External id": 4548442,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941564687.684, "dur": 0.293, + "args": { + "External id": 4548443,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941564689.957, "dur": 0.457, + "args": { + "External id": 4548444,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564693.833, "dur": 1.850, + "args": { + "External id": 4548445,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564697.924, "dur": 0.283, + "args": { + "External id": 4548446,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564699.908, "dur": 0.547, + "args": { + "External id": 4548447,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564703.799, "dur": 0.514, + "args": { + "External id": 4548448,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564705.590, "dur": 0.318, + "args": { + "External id": 4548449,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941564707.736, "dur": 2.278, + "args": { + "External id": 4548450,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941564731.228, "dur": 26.064, + "args": { + "External id": 4548451,"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": 7674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941564831.310, "dur": 403.206, + "args": { + "External id": 4548452,"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": 7675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941564865.849, "dur": 363.282, + "args": { + "External id": 4548453,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 7676, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941564876.514, "dur": 346.248, + "args": { + "External id": 4548454,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941565260.725, "dur": 2.361, + "args": { + "External id": 4548455,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7678, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 1336753, "tid": 1336753, + "ts": 1696941565357.971, "dur": 16913.331, + "args": { + "External id": 4548456,"Record function id": 0, "Ev Idx": 7679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941565459.664, "dur": 6.569, + "args": { + "External id": 4548457,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941565469.371, "dur": 1.363, + "args": { + "External id": 4548458,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941565472.268, "dur": 2.453, + "args": { + "External id": 4548459,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941565476.868, "dur": 0.888, + "args": { + "External id": 4548460,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941565479.056, "dur": 0.987, + "args": { + "External id": 4548461,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941565484.348, "dur": 0.880, + "args": { + "External id": 4548462,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941565487.431, "dur": 0.978, + "args": { + "External id": 4548463,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941565490.138, "dur": 2.370, + "args": { + "External id": 4548464,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941565494.331, "dur": 0.658, + "args": { + "External id": 4548465,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941565499.276, "dur": 0.746, + "args": { + "External id": 4548466,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941565518.741, "dur": 16713.135, + "args": { + "External id": 4548467,"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": 7690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941565553.488, "dur": 16671.724, + "args": { + "External id": 4548468,"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": 7691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941565576.637, "dur": 14.773, + "args": { + "External id": 4548469,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941565594.720, "dur": 16596.450, + "args": { + "External id": 4548470,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941565597.232, "dur": 16593.387, + "args": { + "External id": 4548471,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941565604.153, "dur": 8.051, + "args": { + "External id": 4548472,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941565613.772, "dur": 16573.781, + "args": { + "External id": 4548473,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941582408.821, "dur": 36.433, + "args": { + "External id": 4548474,"Sequence number": 45295627, "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": 7697 + } + }, + { + "ph": "s", "id": 185, "pid": 1336753, "tid": 1336753, "ts": 1696941582408.821, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941582432.230, "dur": 7.824, + "args": { + "External id": 4548475,"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": 7698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941582435.663, "dur": 4.193, + "args": { + "External id": 4548476,"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": 7699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941582513.894, "dur": 87.358, + "args": { + "External id": 4548477,"Record function id": 0, "Ev Idx": 7700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941582604.259, "dur": 1098.426, + "args": { + "External id": 4548478,"Record function id": 0, "Ev Idx": 7701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941582645.069, "dur": 1044.012, + "args": { + "External id": 4548479,"Sequence number": 45295628, "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": 7702 + } + }, + { + "ph": "s", "id": 184, "pid": 1336753, "tid": 1336753, "ts": 1696941582645.069, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941582713.570, "dur": 45.508, + "args": { + "External id": 4548480,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 7703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941582771.672, "dur": 101.290, + "args": { + "External id": 4548481,"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": 7704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941582883.103, "dur": 39.501, + "args": { + "External id": 4548482,"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": 7705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941582930.622, "dur": 31.432, + "args": { + "External id": 4548483,"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": 7706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941583023.788, "dur": 32.307, + "args": { + "External id": 4548484,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941583077.525, "dur": 15.905, + "args": { + "External id": 4548485,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941583113.111, "dur": 131.814, + "args": { + "External id": 4548486,"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": 7709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941583164.288, "dur": 12.769, + "args": { + "External id": 4548487,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941583169.999, "dur": 6.266, + "args": { + "External id": 4548488,"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": 7711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941583179.865, "dur": 5.227, + "args": { + "External id": 4548489,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941583186.641, "dur": 1.415, + "args": { + "External id": 4548490,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941583190.370, "dur": 4.526, + "args": { + "External id": 4548491,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941583255.284, "dur": 53.291, + "args": { + "External id": 4548492,"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": 7715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941583338.117, "dur": 30.768, + "args": { + "External id": 4548493,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 7716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941583377.846, "dur": 41.546, + "args": { + "External id": 4548494,"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": 7717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941583428.385, "dur": 34.109, + "args": { + "External id": 4548495,"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": 7718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941583486.717, "dur": 27.702, + "args": { + "External id": 4548496,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 7719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941583519.909, "dur": 53.365, + "args": { + "External id": 4548497,"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": 7720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941583597.364, "dur": 20.731, + "args": { + "External id": 4548498,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 7721 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.21)", "pid": 1336753, "tid": 1336753, + "ts": 1696941583765.531, "dur": 77.746, + "args": { + "External id": 4548499,"Record function id": 0, "Ev Idx": 7722 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941583920.292, "dur": 47.165, + "args": { + "External id": 4548500,"Record function id": 0, "Ev Idx": 7723 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.22)", "pid": 1336753, "tid": 1336753, + "ts": 1696941583977.680, "dur": 18128.250, + "args": { + "External id": 4548501,"Record function id": 0, "Ev Idx": 7724 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 1336753, "tid": 1336753, + "ts": 1696941584027.126, "dur": 900.106, + "args": { + "External id": 4548502,"Record function id": 0, "Ev Idx": 7725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941584112.182, "dur": 9.404, + "args": { + "External id": 4548503,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941584136.326, "dur": 40.394, + "args": { + "External id": 4548504,"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": 7727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584142.530, "dur": 2.268, + "args": { + "External id": 4548505,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941584149.809, "dur": 0.315, + "args": { + "External id": 4548506,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941584152.035, "dur": 0.290, + "args": { + "External id": 4548507,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584153.926, "dur": 0.351, + "args": { + "External id": 4548508,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584157.978, "dur": 0.566, + "args": { + "External id": 4548509,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584160.303, "dur": 0.200, + "args": { + "External id": 4548510,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584162.070, "dur": 3.810, + "args": { + "External id": 4548511,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584167.544, "dur": 0.190, + "args": { + "External id": 4548512,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584169.180, "dur": 0.371, + "args": { + "External id": 4548513,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941584189.912, "dur": 41.715, + "args": { + "External id": 4548514,"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": 7737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941584265.157, "dur": 121.742, + "args": { + "External id": 4548515,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 7738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941584275.624, "dur": 4.342, + "args": { + "External id": 4548516,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941584285.315, "dur": 10.466, + "args": { + "External id": 4548517,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941584289.684, "dur": 5.656, + "args": { + "External id": 4548518,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584293.766, "dur": 0.478, + "args": { + "External id": 4548519,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941584303.237, "dur": 35.702, + "args": { + "External id": 4548520,"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": 7743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584305.430, "dur": 2.595, + "args": { + "External id": 4548521,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941584309.753, "dur": 0.462, + "args": { + "External id": 4548522,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941584312.252, "dur": 0.361, + "args": { + "External id": 4548523,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584316.757, "dur": 1.691, + "args": { + "External id": 4548524,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584320.024, "dur": 0.395, + "args": { + "External id": 4548525,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584322.016, "dur": 0.173, + "args": { + "External id": 4548526,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584324.560, "dur": 0.326, + "args": { + "External id": 4548527,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584326.422, "dur": 0.375, + "args": { + "External id": 4548528,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941584331.642, "dur": 2.506, + "args": { + "External id": 4548529,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941584353.577, "dur": 25.119, + "args": { + "External id": 4548530,"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": 7753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941584440.836, "dur": 391.618, + "args": { + "External id": 4548531,"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": 7754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941584473.641, "dur": 353.467, + "args": { + "External id": 4548532,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 7755, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941584483.496, "dur": 337.108, + "args": { + "External id": 4548533,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941584857.718, "dur": 2.340, + "args": { + "External id": 4548534,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7757, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 1336753, "tid": 1336753, + "ts": 1696941584948.723, "dur": 16923.373, + "args": { + "External id": 4548535,"Record function id": 0, "Ev Idx": 7758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941585086.714, "dur": 6.889, + "args": { + "External id": 4548536,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941585096.902, "dur": 1.159, + "args": { + "External id": 4548537,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941585099.951, "dur": 2.954, + "args": { + "External id": 4548538,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941585104.728, "dur": 0.686, + "args": { + "External id": 4548539,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941585106.721, "dur": 1.000, + "args": { + "External id": 4548540,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941585111.106, "dur": 0.860, + "args": { + "External id": 4548541,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941585113.745, "dur": 0.573, + "args": { + "External id": 4548542,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941585116.072, "dur": 2.134, + "args": { + "External id": 4548543,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941585119.775, "dur": 0.914, + "args": { + "External id": 4548544,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941585124.280, "dur": 0.660, + "args": { + "External id": 4548545,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941585144.852, "dur": 16689.372, + "args": { + "External id": 4548546,"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": 7769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941585168.621, "dur": 16659.168, + "args": { + "External id": 4548547,"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": 7770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941585187.176, "dur": 15.088, + "args": { + "External id": 4548548,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941585205.036, "dur": 16590.412, + "args": { + "External id": 4548549,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941585207.567, "dur": 16587.276, + "args": { + "External id": 4548550,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941585213.858, "dur": 7.297, + "args": { + "External id": 4548551,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941585223.322, "dur": 16568.641, + "args": { + "External id": 4548552,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941602038.298, "dur": 38.802, + "args": { + "External id": 4548553,"Sequence number": 45295629, "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": 7776 + } + }, + { + "ph": "s", "id": 183, "pid": 1336753, "tid": 1336753, "ts": 1696941602038.298, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941602063.969, "dur": 8.077, + "args": { + "External id": 4548554,"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": 7777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941602067.505, "dur": 4.206, + "args": { + "External id": 4548555,"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": 7778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941602148.421, "dur": 76.502, + "args": { + "External id": 4548556,"Record function id": 0, "Ev Idx": 7779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941602226.780, "dur": 1092.343, + "args": { + "External id": 4548557,"Record function id": 0, "Ev Idx": 7780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941602264.288, "dur": 1040.520, + "args": { + "External id": 4548558,"Sequence number": 45295630, "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": 7781 + } + }, + { + "ph": "s", "id": 182, "pid": 1336753, "tid": 1336753, "ts": 1696941602264.288, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941602329.505, "dur": 44.377, + "args": { + "External id": 4548559,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 7782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941602386.348, "dur": 101.966, + "args": { + "External id": 4548560,"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": 7783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941602497.747, "dur": 53.739, + "args": { + "External id": 4548561,"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": 7784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941602562.930, "dur": 35.985, + "args": { + "External id": 4548562,"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": 7785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941602626.374, "dur": 26.920, + "args": { + "External id": 4548563,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941602671.786, "dur": 16.968, + "args": { + "External id": 4548564,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941602709.421, "dur": 129.477, + "args": { + "External id": 4548565,"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": 7788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941602758.770, "dur": 11.830, + "args": { + "External id": 4548566,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941602764.386, "dur": 5.543, + "args": { + "External id": 4548567,"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": 7790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941602773.795, "dur": 5.533, + "args": { + "External id": 4548568,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941602780.688, "dur": 1.248, + "args": { + "External id": 4548569,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941602784.247, "dur": 4.516, + "args": { + "External id": 4548570,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941602849.709, "dur": 44.293, + "args": { + "External id": 4548571,"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": 7794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941602924.109, "dur": 30.003, + "args": { + "External id": 4548572,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 7795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941602962.876, "dur": 82.037, + "args": { + "External id": 4548573,"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": 7796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941603058.279, "dur": 37.779, + "args": { + "External id": 4548574,"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": 7797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941603122.212, "dur": 30.318, + "args": { + "External id": 4548575,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 7798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941603158.095, "dur": 33.407, + "args": { + "External id": 4548576,"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": 7799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941603212.320, "dur": 18.844, + "args": { + "External id": 4548577,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 7800 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.22)", "pid": 1336753, "tid": 1336753, + "ts": 1696941603381.640, "dur": 72.432, + "args": { + "External id": 4548578,"Record function id": 0, "Ev Idx": 7801 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941603545.884, "dur": 49.904, + "args": { + "External id": 4548579,"Record function id": 0, "Ev Idx": 7802 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.23)", "pid": 1336753, "tid": 1336753, + "ts": 1696941603606.379, "dur": 18597.204, + "args": { + "External id": 4548580,"Record function id": 0, "Ev Idx": 7803 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 1336753, "tid": 1336753, + "ts": 1696941603614.936, "dur": 955.401, + "args": { + "External id": 4548581,"Record function id": 0, "Ev Idx": 7804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941603696.099, "dur": 9.751, + "args": { + "External id": 4548582,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941603720.942, "dur": 39.815, + "args": { + "External id": 4548583,"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": 7806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603726.850, "dur": 2.291, + "args": { + "External id": 4548584,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941603733.981, "dur": 0.425, + "args": { + "External id": 4548585,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941603736.073, "dur": 0.293, + "args": { + "External id": 4548586,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603738.267, "dur": 0.407, + "args": { + "External id": 4548587,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603742.323, "dur": 0.190, + "args": { + "External id": 4548588,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603743.938, "dur": 0.498, + "args": { + "External id": 4548589,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603746.081, "dur": 3.818, + "args": { + "External id": 4548590,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603751.500, "dur": 0.367, + "args": { + "External id": 4548591,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603753.266, "dur": 0.465, + "args": { + "External id": 4548592,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941603773.072, "dur": 42.215, + "args": { + "External id": 4548593,"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": 7816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941603848.966, "dur": 186.498, + "args": { + "External id": 4548594,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 7817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941603859.014, "dur": 4.004, + "args": { + "External id": 4548595,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941603868.149, "dur": 9.535, + "args": { + "External id": 4548596,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941603872.462, "dur": 4.822, + "args": { + "External id": 4548597,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603875.624, "dur": 0.505, + "args": { + "External id": 4548598,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941603884.735, "dur": 28.834, + "args": { + "External id": 4548599,"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": 7822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603886.718, "dur": 2.801, + "args": { + "External id": 4548600,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941603890.581, "dur": 0.541, + "args": { + "External id": 4548601,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941603892.223, "dur": 0.214, + "args": { + "External id": 4548602,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603896.517, "dur": 1.579, + "args": { + "External id": 4548603,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603899.340, "dur": 0.337, + "args": { + "External id": 4548604,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603900.859, "dur": 0.363, + "args": { + "External id": 4548605,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603904.379, "dur": 0.167, + "args": { + "External id": 4548606,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603905.566, "dur": 0.347, + "args": { + "External id": 4548607,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941603906.859, "dur": 2.349, + "args": { + "External id": 4548608,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941603961.828, "dur": 63.015, + "args": { + "External id": 4548609,"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": 7832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941604091.343, "dur": 368.644, + "args": { + "External id": 4548610,"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": 7833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941604123.088, "dur": 332.673, + "args": { + "External id": 4548611,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 7834, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941604135.099, "dur": 315.149, + "args": { + "External id": 4548612,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941604482.298, "dur": 2.321, + "args": { + "External id": 4548613,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7836, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 1336753, "tid": 1336753, + "ts": 1696941604594.000, "dur": 17363.742, + "args": { + "External id": 4548614,"Record function id": 0, "Ev Idx": 7837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941604699.671, "dur": 7.176, + "args": { + "External id": 4548615,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941604710.422, "dur": 1.657, + "args": { + "External id": 4548616,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941604713.754, "dur": 2.321, + "args": { + "External id": 4548617,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941604717.859, "dur": 0.700, + "args": { + "External id": 4548618,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941604720.053, "dur": 0.896, + "args": { + "External id": 4548619,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941604724.433, "dur": 0.976, + "args": { + "External id": 4548620,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941604727.074, "dur": 1.471, + "args": { + "External id": 4548621,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941604730.169, "dur": 2.036, + "args": { + "External id": 4548622,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941604733.643, "dur": 0.826, + "args": { + "External id": 4548623,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941604737.975, "dur": 0.732, + "args": { + "External id": 4548624,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941604757.105, "dur": 17161.941, + "args": { + "External id": 4548625,"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": 7848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941604773.532, "dur": 17138.775, + "args": { + "External id": 4548626,"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": 7849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941604797.949, "dur": 15.828, + "args": { + "External id": 4548627,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941604816.880, "dur": 17062.167, + "args": { + "External id": 4548628,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941604819.362, "dur": 17059.175, + "args": { + "External id": 4548629,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941604825.091, "dur": 6.705, + "args": { + "External id": 4548630,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941604833.371, "dur": 17041.924, + "args": { + "External id": 4548631,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941622135.928, "dur": 39.052, + "args": { + "External id": 4548632,"Sequence number": 45295631, "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": 7855 + } + }, + { + "ph": "s", "id": 181, "pid": 1336753, "tid": 1336753, "ts": 1696941622135.928, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941622161.716, "dur": 8.165, + "args": { + "External id": 4548633,"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": 7856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941622164.999, "dur": 4.463, + "args": { + "External id": 4548634,"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": 7857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941622245.504, "dur": 77.948, + "args": { + "External id": 4548635,"Record function id": 0, "Ev Idx": 7858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941622325.077, "dur": 1099.068, + "args": { + "External id": 4548636,"Record function id": 0, "Ev Idx": 7859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941622366.724, "dur": 1043.408, + "args": { + "External id": 4548637,"Sequence number": 45295632, "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": 7860 + } + }, + { + "ph": "s", "id": 180, "pid": 1336753, "tid": 1336753, "ts": 1696941622366.724, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941622436.796, "dur": 43.733, + "args": { + "External id": 4548638,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 7861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941622493.368, "dur": 117.090, + "args": { + "External id": 4548639,"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": 7862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941622623.462, "dur": 40.896, + "args": { + "External id": 4548640,"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": 7863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941622673.775, "dur": 30.874, + "args": { + "External id": 4548641,"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": 7864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941622732.241, "dur": 29.141, + "args": { + "External id": 4548642,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941622779.197, "dur": 15.147, + "args": { + "External id": 4548643,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941622813.552, "dur": 129.042, + "args": { + "External id": 4548644,"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": 7867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941622862.603, "dur": 12.388, + "args": { + "External id": 4548645,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941622868.083, "dur": 5.995, + "args": { + "External id": 4548646,"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": 7869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941622877.583, "dur": 6.523, + "args": { + "External id": 4548647,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941622885.268, "dur": 1.456, + "args": { + "External id": 4548648,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941622889.028, "dur": 4.120, + "args": { + "External id": 4548649,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941622952.316, "dur": 85.214, + "args": { + "External id": 4548650,"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": 7873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941623072.945, "dur": 30.745, + "args": { + "External id": 4548651,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 7874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941623113.287, "dur": 44.878, + "args": { + "External id": 4548652,"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": 7875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941623167.989, "dur": 35.815, + "args": { + "External id": 4548653,"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": 7876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941623228.245, "dur": 26.325, + "args": { + "External id": 4548654,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 7877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941623260.048, "dur": 34.625, + "args": { + "External id": 4548655,"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": 7878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941623314.775, "dur": 19.848, + "args": { + "External id": 4548656,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 7879 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.23)", "pid": 1336753, "tid": 1336753, + "ts": 1696941623487.964, "dur": 91.021, + "args": { + "External id": 4548657,"Record function id": 0, "Ev Idx": 7880 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941623658.489, "dur": 53.397, + "args": { + "External id": 4548658,"Record function id": 0, "Ev Idx": 7881 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.24)", "pid": 1336753, "tid": 1336753, + "ts": 1696941623721.521, "dur": 17947.812, + "args": { + "External id": 4548659,"Record function id": 0, "Ev Idx": 7882 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 1336753, "tid": 1336753, + "ts": 1696941623732.225, "dur": 980.215, + "args": { + "External id": 4548660,"Record function id": 0, "Ev Idx": 7883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941623813.626, "dur": 11.697, + "args": { + "External id": 4548661,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941623839.198, "dur": 33.884, + "args": { + "External id": 4548662,"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": 7885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941623844.541, "dur": 2.007, + "args": { + "External id": 4548663,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941623850.451, "dur": 0.274, + "args": { + "External id": 4548664,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941623851.526, "dur": 0.210, + "args": { + "External id": 4548665,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941623853.078, "dur": 0.340, + "args": { + "External id": 4548666,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941623856.729, "dur": 0.428, + "args": { + "External id": 4548667,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941623858.113, "dur": 0.596, + "args": { + "External id": 4548668,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941623859.998, "dur": 4.257, + "args": { + "External id": 4548669,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941623865.159, "dur": 0.511, + "args": { + "External id": 4548670,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941623866.991, "dur": 0.522, + "args": { + "External id": 4548671,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941623885.270, "dur": 44.899, + "args": { + "External id": 4548672,"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": 7895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941623963.092, "dur": 159.491, + "args": { + "External id": 4548673,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 7896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941623973.798, "dur": 4.696, + "args": { + "External id": 4548674,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941624020.616, "dur": 11.803, + "args": { + "External id": 4548675,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941624025.152, "dur": 6.856, + "args": { + "External id": 4548676,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941624029.456, "dur": 0.819, + "args": { + "External id": 4548677,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941624041.565, "dur": 31.557, + "args": { + "External id": 4548678,"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": 7901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941624044.234, "dur": 3.107, + "args": { + "External id": 4548679,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941624048.996, "dur": 0.351, + "args": { + "External id": 4548680,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941624050.586, "dur": 0.468, + "args": { + "External id": 4548681,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941624054.585, "dur": 1.649, + "args": { + "External id": 4548682,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941624057.363, "dur": 0.509, + "args": { + "External id": 4548683,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941624059.027, "dur": 0.446, + "args": { + "External id": 4548684,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941624062.744, "dur": 0.390, + "args": { + "External id": 4548685,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941624064.329, "dur": 0.567, + "args": { + "External id": 4548686,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941624066.292, "dur": 2.486, + "args": { + "External id": 4548687,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941624086.104, "dur": 28.287, + "args": { + "External id": 4548688,"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": 7911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941624176.593, "dur": 432.444, + "args": { + "External id": 4548689,"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": 7912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941624214.304, "dur": 389.185, + "args": { + "External id": 4548690,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 7913, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941624224.002, "dur": 373.059, + "args": { + "External id": 4548691,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941624636.382, "dur": 2.530, + "args": { + "External id": 4548692,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7915, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 1336753, "tid": 1336753, + "ts": 1696941624733.170, "dur": 16722.844, + "args": { + "External id": 4548693,"Record function id": 0, "Ev Idx": 7916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941624837.112, "dur": 6.917, + "args": { + "External id": 4548694,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941624852.528, "dur": 1.836, + "args": { + "External id": 4548695,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941624856.132, "dur": 2.320, + "args": { + "External id": 4548696,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941624862.610, "dur": 0.898, + "args": { + "External id": 4548697,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941624864.662, "dur": 1.014, + "args": { + "External id": 4548698,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941624867.031, "dur": 0.796, + "args": { + "External id": 4548699,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941624869.371, "dur": 0.948, + "args": { + "External id": 4548700,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941624873.595, "dur": 2.212, + "args": { + "External id": 4548701,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941624877.103, "dur": 0.706, + "args": { + "External id": 4548702,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941624879.357, "dur": 0.795, + "args": { + "External id": 4548703,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941624899.967, "dur": 16518.224, + "args": { + "External id": 4548704,"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": 7927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941624915.503, "dur": 16495.708, + "args": { + "External id": 4548705,"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": 7928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941624934.712, "dur": 14.592, + "args": { + "External id": 4548706,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941624954.586, "dur": 16422.228, + "args": { + "External id": 4548707,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941624956.945, "dur": 16419.225, + "args": { + "External id": 4548708,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941624962.871, "dur": 6.695, + "args": { + "External id": 4548709,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941624971.123, "dur": 16401.983, + "args": { + "External id": 4548710,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941641608.550, "dur": 35.634, + "args": { + "External id": 4548711,"Sequence number": 45295633, "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": 7934 + } + }, + { + "ph": "s", "id": 179, "pid": 1336753, "tid": 1336753, "ts": 1696941641608.550, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941641631.168, "dur": 7.820, + "args": { + "External id": 4548712,"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": 7935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941641634.459, "dur": 4.219, + "args": { + "External id": 4548713,"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": 7936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941641710.316, "dur": 80.332, + "args": { + "External id": 4548714,"Record function id": 0, "Ev Idx": 7937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941641792.353, "dur": 1086.366, + "args": { + "External id": 4548715,"Record function id": 0, "Ev Idx": 7938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941641829.757, "dur": 1034.892, + "args": { + "External id": 4548716,"Sequence number": 45295634, "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": 7939 + } + }, + { + "ph": "s", "id": 178, "pid": 1336753, "tid": 1336753, "ts": 1696941641829.757, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941641898.244, "dur": 41.782, + "args": { + "External id": 4548717,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 7940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941641952.928, "dur": 130.974, + "args": { + "External id": 4548718,"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": 7941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941642097.682, "dur": 39.464, + "args": { + "External id": 4548719,"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": 7942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941642146.042, "dur": 30.046, + "args": { + "External id": 4548720,"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": 7943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941642201.664, "dur": 25.902, + "args": { + "External id": 4548721,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941642248.738, "dur": 16.374, + "args": { + "External id": 4548722,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 7945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941642284.341, "dur": 128.043, + "args": { + "External id": 4548723,"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": 7946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941642333.132, "dur": 11.150, + "args": { + "External id": 4548724,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941642338.230, "dur": 5.399, + "args": { + "External id": 4548725,"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": 7948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941642346.775, "dur": 5.666, + "args": { + "External id": 4548726,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941642353.497, "dur": 1.566, + "args": { + "External id": 4548727,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941642357.394, "dur": 3.967, + "args": { + "External id": 4548728,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941642422.486, "dur": 45.538, + "args": { + "External id": 4548729,"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": 7952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941642499.714, "dur": 46.787, + "args": { + "External id": 4548730,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 7953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941642558.891, "dur": 47.286, + "args": { + "External id": 4548731,"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": 7954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941642614.978, "dur": 34.795, + "args": { + "External id": 4548732,"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": 7955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941642682.070, "dur": 32.818, + "args": { + "External id": 4548733,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 7956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941642723.144, "dur": 33.356, + "args": { + "External id": 4548734,"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": 7957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941642776.459, "dur": 19.399, + "args": { + "External id": 4548735,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 7958 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.24)", "pid": 1336753, "tid": 1336753, + "ts": 1696941642942.939, "dur": 116.628, + "args": { + "External id": 4548736,"Record function id": 0, "Ev Idx": 7959 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941643139.667, "dur": 49.800, + "args": { + "External id": 4548737,"Record function id": 0, "Ev Idx": 7960 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.25)", "pid": 1336753, "tid": 1336753, + "ts": 1696941643199.117, "dur": 18014.920, + "args": { + "External id": 4548738,"Record function id": 0, "Ev Idx": 7961 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 1336753, "tid": 1336753, + "ts": 1696941643206.830, "dur": 912.489, + "args": { + "External id": 4548739,"Record function id": 0, "Ev Idx": 7962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941643292.986, "dur": 8.925, + "args": { + "External id": 4548740,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941643316.773, "dur": 34.623, + "args": { + "External id": 4548741,"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": 7964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643321.845, "dur": 2.234, + "args": { + "External id": 4548742,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941643328.833, "dur": 0.519, + "args": { + "External id": 4548743,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941643330.754, "dur": 0.464, + "args": { + "External id": 4548744,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643332.154, "dur": 0.227, + "args": { + "External id": 4548745,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643335.442, "dur": 0.205, + "args": { + "External id": 4548746,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643336.963, "dur": 0.212, + "args": { + "External id": 4548747,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643338.234, "dur": 4.247, + "args": { + "External id": 4548748,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643343.538, "dur": 0.186, + "args": { + "External id": 4548749,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643345.010, "dur": 0.480, + "args": { + "External id": 4548750,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941643363.278, "dur": 41.731, + "args": { + "External id": 4548751,"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": 7974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941643438.734, "dur": 132.653, + "args": { + "External id": 4548752,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 7975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941643449.316, "dur": 3.921, + "args": { + "External id": 4548753,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941643458.102, "dur": 9.601, + "args": { + "External id": 4548754,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941643462.445, "dur": 4.860, + "args": { + "External id": 4548755,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643465.623, "dur": 0.447, + "args": { + "External id": 4548756,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941643474.356, "dur": 28.565, + "args": { + "External id": 4548757,"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": 7980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643476.507, "dur": 2.626, + "args": { + "External id": 4548758,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941643480.642, "dur": 0.571, + "args": { + "External id": 4548759,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941643482.242, "dur": 0.300, + "args": { + "External id": 4548760,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643486.133, "dur": 1.632, + "args": { + "External id": 4548761,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643488.882, "dur": 0.373, + "args": { + "External id": 4548762,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643490.304, "dur": 0.181, + "args": { + "External id": 4548763,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643493.397, "dur": 0.197, + "args": { + "External id": 4548764,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643494.670, "dur": 0.325, + "args": { + "External id": 4548765,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941643496.210, "dur": 2.375, + "args": { + "External id": 4548766,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941643519.426, "dur": 43.082, + "args": { + "External id": 4548767,"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": 7990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941643625.588, "dur": 390.688, + "args": { + "External id": 4548768,"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": 7991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941643656.896, "dur": 321.493, + "args": { + "External id": 4548769,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 7992, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941643666.977, "dur": 306.282, + "args": { + "External id": 4548770,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941644044.473, "dur": 3.490, + "args": { + "External id": 4548771,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7994, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.25)", "pid": 1336753, "tid": 1336753, + "ts": 1696941644139.985, "dur": 16875.438, + "args": { + "External id": 4548772,"Record function id": 0, "Ev Idx": 7995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941644241.993, "dur": 6.803, + "args": { + "External id": 4548773,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941644252.149, "dur": 1.147, + "args": { + "External id": 4548774,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941644255.032, "dur": 3.287, + "args": { + "External id": 4548775,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941644260.222, "dur": 0.937, + "args": { + "External id": 4548776,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941644262.510, "dur": 0.838, + "args": { + "External id": 4548777,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941644264.628, "dur": 0.821, + "args": { + "External id": 4548778,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941644269.390, "dur": 0.667, + "args": { + "External id": 4548779,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 8002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941644271.733, "dur": 2.165, + "args": { + "External id": 4548780,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941644275.380, "dur": 0.861, + "args": { + "External id": 4548781,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941644277.677, "dur": 0.644, + "args": { + "External id": 4548782,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941644298.727, "dur": 16656.340, + "args": { + "External id": 4548783,"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": 8006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941644315.438, "dur": 16632.682, + "args": { + "External id": 4548784,"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": 8007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941644340.395, "dur": 13.575, + "args": { + "External id": 4548785,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941644356.776, "dur": 16559.672, + "args": { + "External id": 4548786,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 8009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941644359.271, "dur": 16556.631, + "args": { + "External id": 4548787,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 8010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941644365.463, "dur": 6.357, + "args": { + "External id": 4548788,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941644373.487, "dur": 16539.449, + "args": { + "External id": 4548789,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 8012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941661153.813, "dur": 36.037, + "args": { + "External id": 4548790,"Sequence number": 45295635, "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": 8013 + } + }, + { + "ph": "s", "id": 177, "pid": 1336753, "tid": 1336753, "ts": 1696941661153.813, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941661177.128, "dur": 7.737, + "args": { + "External id": 4548791,"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": 8014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941661180.449, "dur": 4.175, + "args": { + "External id": 4548792,"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": 8015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941661254.001, "dur": 77.273, + "args": { + "External id": 4548793,"Record function id": 0, "Ev Idx": 8016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941661332.887, "dur": 1085.771, + "args": { + "External id": 4548794,"Record function id": 0, "Ev Idx": 8017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941661374.612, "dur": 1029.711, + "args": { + "External id": 4548795,"Sequence number": 45295636, "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": 8018 + } + }, + { + "ph": "s", "id": 176, "pid": 1336753, "tid": 1336753, "ts": 1696941661374.612, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941661439.846, "dur": 43.669, + "args": { + "External id": 4548796,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 8019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941661496.149, "dur": 116.563, + "args": { + "External id": 4548797,"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": 8020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941661625.286, "dur": 39.391, + "args": { + "External id": 4548798,"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": 8021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941661672.849, "dur": 30.178, + "args": { + "External id": 4548799,"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": 8022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941661729.080, "dur": 28.441, + "args": { + "External id": 4548800,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 8023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941661775.468, "dur": 15.948, + "args": { + "External id": 4548801,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 8024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941661811.442, "dur": 125.653, + "args": { + "External id": 4548802,"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": 8025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941661859.324, "dur": 11.252, + "args": { + "External id": 4548803,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941661864.319, "dur": 5.467, + "args": { + "External id": 4548804,"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": 8027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941661873.239, "dur": 5.991, + "args": { + "External id": 4548805,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941661880.322, "dur": 1.160, + "args": { + "External id": 4548806,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941661883.866, "dur": 4.293, + "args": { + "External id": 4548807,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941661946.728, "dur": 91.372, + "args": { + "External id": 4548808,"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": 8031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941662073.043, "dur": 30.640, + "args": { + "External id": 4548809,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 8032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941662112.539, "dur": 45.163, + "args": { + "External id": 4548810,"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": 8033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941662166.850, "dur": 36.038, + "args": { + "External id": 4548811,"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": 8034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941662226.480, "dur": 27.236, + "args": { + "External id": 4548812,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 8035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941662258.943, "dur": 33.750, + "args": { + "External id": 4548813,"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": 8036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941662312.210, "dur": 19.193, + "args": { + "External id": 4548814,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 8037 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.25)", "pid": 1336753, "tid": 1336753, + "ts": 1696941662481.319, "dur": 94.783, + "args": { + "External id": 4548815,"Record function id": 0, "Ev Idx": 8038 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941662655.376, "dur": 48.279, + "args": { + "External id": 4548816,"Record function id": 0, "Ev Idx": 8039 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.26)", "pid": 1336753, "tid": 1336753, + "ts": 1696941662713.558, "dur": 18067.942, + "args": { + "External id": 4548817,"Record function id": 0, "Ev Idx": 8040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.26)", "pid": 1336753, "tid": 1336753, + "ts": 1696941662721.814, "dur": 907.678, + "args": { + "External id": 4548818,"Record function id": 0, "Ev Idx": 8041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941662804.577, "dur": 8.853, + "args": { + "External id": 4548819,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941662827.923, "dur": 33.980, + "args": { + "External id": 4548820,"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": 8043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941662833.580, "dur": 2.110, + "args": { + "External id": 4548821,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941662840.500, "dur": 0.268, + "args": { + "External id": 4548822,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941662841.761, "dur": 0.294, + "args": { + "External id": 4548823,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941662843.222, "dur": 0.383, + "args": { + "External id": 4548824,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941662846.868, "dur": 0.259, + "args": { + "External id": 4548825,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941662848.181, "dur": 0.212, + "args": { + "External id": 4548826,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941662849.808, "dur": 3.314, + "args": { + "External id": 4548827,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941662853.938, "dur": 0.306, + "args": { + "External id": 4548828,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941662855.377, "dur": 0.278, + "args": { + "External id": 4548829,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941662874.385, "dur": 41.013, + "args": { + "External id": 4548830,"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": 8053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941662948.351, "dur": 159.417, + "args": { + "External id": 4548831,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 8054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941662958.289, "dur": 4.419, + "args": { + "External id": 4548832,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941662967.923, "dur": 9.917, + "args": { + "External id": 4548833,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 8056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941662972.249, "dur": 5.165, + "args": { + "External id": 4548834,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 8057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941662975.549, "dur": 0.519, + "args": { + "External id": 4548835,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 8058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941663022.369, "dur": 33.673, + "args": { + "External id": 4548836,"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": 8059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941663024.685, "dur": 2.933, + "args": { + "External id": 4548837,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941663029.300, "dur": 0.366, + "args": { + "External id": 4548838,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941663034.605, "dur": 0.331, + "args": { + "External id": 4548839,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941663038.552, "dur": 1.226, + "args": { + "External id": 4548840,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941663041.282, "dur": 0.320, + "args": { + "External id": 4548841,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941663042.525, "dur": 2.972, + "args": { + "External id": 4548842,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941663046.818, "dur": 0.321, + "args": { + "External id": 4548843,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941663047.872, "dur": 0.238, + "args": { + "External id": 4548844,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941663051.348, "dur": 0.390, + "args": { + "External id": 4548845,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941663071.551, "dur": 28.487, + "args": { + "External id": 4548846,"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": 8069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941663160.353, "dur": 354.688, + "args": { + "External id": 4548847,"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": 8070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941663193.122, "dur": 317.391, + "args": { + "External id": 4548848,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 8071, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941663202.897, "dur": 301.927, + "args": { + "External id": 4548849,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 8072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941663555.255, "dur": 3.222, + "args": { + "External id": 4548850,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8073, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.26)", "pid": 1336753, "tid": 1336753, + "ts": 1696941663650.370, "dur": 16921.980, + "args": { + "External id": 4548851,"Record function id": 0, "Ev Idx": 8074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941663754.831, "dur": 6.789, + "args": { + "External id": 4548852,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 8075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941663764.747, "dur": 1.142, + "args": { + "External id": 4548853,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 8076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941663774.333, "dur": 2.052, + "args": { + "External id": 4548854,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941663780.337, "dur": 0.773, + "args": { + "External id": 4548855,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941663782.382, "dur": 0.636, + "args": { + "External id": 4548856,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941663784.183, "dur": 0.601, + "args": { + "External id": 4548857,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941663786.388, "dur": 0.572, + "args": { + "External id": 4548858,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 8081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941663790.195, "dur": 2.083, + "args": { + "External id": 4548859,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941663793.632, "dur": 0.816, + "args": { + "External id": 4548860,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941663795.682, "dur": 0.539, + "args": { + "External id": 4548861,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941663816.371, "dur": 16703.419, + "args": { + "External id": 4548862,"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": 8085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941663832.101, "dur": 16681.046, + "args": { + "External id": 4548863,"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": 8086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941663850.490, "dur": 14.716, + "args": { + "External id": 4548864,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941663870.458, "dur": 16608.879, + "args": { + "External id": 4548865,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 8088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941663872.895, "dur": 16605.823, + "args": { + "External id": 4548866,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 8089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941663878.998, "dur": 6.304, + "args": { + "External id": 4548867,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941663887.054, "dur": 16588.557, + "args": { + "External id": 4548868,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 8091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941680720.772, "dur": 35.993, + "args": { + "External id": 4548869,"Sequence number": 45295637, "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": 8092 + } + }, + { + "ph": "s", "id": 175, "pid": 1336753, "tid": 1336753, "ts": 1696941680720.772, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941680743.409, "dur": 8.287, + "args": { + "External id": 4548870,"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": 8093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941680747.173, "dur": 4.248, + "args": { + "External id": 4548871,"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": 8094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941680821.480, "dur": 77.070, + "args": { + "External id": 4548872,"Record function id": 0, "Ev Idx": 8095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941680899.957, "dur": 1142.771, + "args": { + "External id": 4548873,"Record function id": 0, "Ev Idx": 8096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941680939.516, "dur": 1087.466, + "args": { + "External id": 4548874,"Sequence number": 45295638, "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": 8097 + } + }, + { + "ph": "s", "id": 174, "pid": 1336753, "tid": 1336753, "ts": 1696941680939.516, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941681057.557, "dur": 45.927, + "args": { + "External id": 4548875,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 8098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941681119.626, "dur": 103.501, + "args": { + "External id": 4548876,"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": 8099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941681232.035, "dur": 38.177, + "args": { + "External id": 4548877,"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": 8100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941681279.396, "dur": 30.185, + "args": { + "External id": 4548878,"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": 8101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941681333.822, "dur": 29.705, + "args": { + "External id": 4548879,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 8102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941681384.929, "dur": 17.518, + "args": { + "External id": 4548880,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 8103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941681419.561, "dur": 145.532, + "args": { + "External id": 4548881,"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": 8104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941681468.915, "dur": 11.651, + "args": { + "External id": 4548882,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941681474.269, "dur": 5.589, + "args": { + "External id": 4548883,"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": 8106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941681483.290, "dur": 5.783, + "args": { + "External id": 4548884,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941681490.538, "dur": 1.691, + "args": { + "External id": 4548885,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941681494.690, "dur": 3.225, + "args": { + "External id": 4548886,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941681577.833, "dur": 51.309, + "args": { + "External id": 4548887,"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": 8110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941681662.563, "dur": 29.386, + "args": { + "External id": 4548888,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 8111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941681700.278, "dur": 41.688, + "args": { + "External id": 4548889,"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": 8112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941681750.740, "dur": 33.880, + "args": { + "External id": 4548890,"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": 8113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941681806.855, "dur": 30.503, + "args": { + "External id": 4548891,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 8114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941681843.398, "dur": 34.302, + "args": { + "External id": 4548892,"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": 8115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941681899.280, "dur": 19.054, + "args": { + "External id": 4548893,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 8116 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.26)", "pid": 1336753, "tid": 1336753, + "ts": 1696941682109.000, "dur": 76.136, + "args": { + "External id": 4548894,"Record function id": 0, "Ev Idx": 8117 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1696941682259.748, "dur": 46.795, + "args": { + "External id": 4548895,"Record function id": 0, "Ev Idx": 8118 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.27)", "pid": 1336753, "tid": 1336753, + "ts": 1696941682315.942, "dur": 18068.033, + "args": { + "External id": 4548896,"Record function id": 0, "Ev Idx": 8119 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.27)", "pid": 1336753, "tid": 1336753, + "ts": 1696941682325.275, "dur": 939.757, + "args": { + "External id": 4548897,"Record function id": 0, "Ev Idx": 8120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941682409.446, "dur": 9.352, + "args": { + "External id": 4548898,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941682432.849, "dur": 34.398, + "args": { + "External id": 4548899,"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": 8122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682438.495, "dur": 2.276, + "args": { + "External id": 4548900,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941682445.317, "dur": 0.456, + "args": { + "External id": 4548901,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941682446.841, "dur": 0.687, + "args": { + "External id": 4548902,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682448.582, "dur": 0.696, + "args": { + "External id": 4548903,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682452.173, "dur": 0.718, + "args": { + "External id": 4548904,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682454.207, "dur": 0.457, + "args": { + "External id": 4548905,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682455.470, "dur": 2.561, + "args": { + "External id": 4548906,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682458.943, "dur": 0.446, + "args": { + "External id": 4548907,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682460.148, "dur": 0.637, + "args": { + "External id": 4548908,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941682479.424, "dur": 42.640, + "args": { + "External id": 4548909,"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": 8132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336753, "tid": 1336753, + "ts": 1696941682573.568, "dur": 125.194, + "args": { + "External id": 4548910,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "0", "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": 8133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941682585.046, "dur": 5.996, + "args": { + "External id": 4548911,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336753, "tid": 1336753, + "ts": 1696941682596.401, "dur": 10.571, + "args": { + "External id": 4548912,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 8135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941682600.780, "dur": 5.759, + "args": { + "External id": 4548913,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "6423040", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 8136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682604.196, "dur": 0.818, + "args": { + "External id": 4548914,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 8137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336753, "tid": 1336753, + "ts": 1696941682614.090, "dur": 31.245, + "args": { + "External id": 4548915,"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": 8138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682616.274, "dur": 2.761, + "args": { + "External id": 4548916,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "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": 1336753, "tid": 1336753, + "ts": 1696941682620.278, "dur": 0.651, + "args": { + "External id": 4548917,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "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": 1336753, "tid": 1336753, + "ts": 1696941682622.137, "dur": 0.641, + "args": { + "External id": 4548918,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682626.483, "dur": 0.448, + "args": { + "External id": 4548919,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682628.168, "dur": 0.683, + "args": { + "External id": 4548920,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682630.120, "dur": 0.562, + "args": { + "External id": 4548921,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682634.172, "dur": 0.556, + "args": { + "External id": 4548922,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682636.164, "dur": 0.656, + "args": { + "External id": 4548923,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941682638.210, "dur": 2.495, + "args": { + "External id": 4548924,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941682662.183, "dur": 28.352, + "args": { + "External id": 4548925,"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": 8148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336753, "tid": 1336753, + "ts": 1696941682751.955, "dur": 411.540, + "args": { + "External id": 4548926,"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": 8149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941682782.313, "dur": 375.693, + "args": { + "External id": 4548927,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 0, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 8150, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336753, "tid": 1336753, + "ts": 1696941682792.223, "dur": 359.477, + "args": { + "External id": 4548928,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 8151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696941683189.734, "dur": 2.505, + "args": { + "External id": 4548929,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8152, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.27)", "pid": 1336753, "tid": 1336753, + "ts": 1696941683285.597, "dur": 16898.755, + "args": { + "External id": 4548930,"Record function id": 0, "Ev Idx": 8153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941683401.989, "dur": 7.068, + "args": { + "External id": 4548931,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 8154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941683412.540, "dur": 1.177, + "args": { + "External id": 4548932,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 8155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941683415.275, "dur": 1.739, + "args": { + "External id": 4548933,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941683420.849, "dur": 1.378, + "args": { + "External id": 4548934,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941683423.581, "dur": 1.365, + "args": { + "External id": 4548935,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941683426.056, "dur": 1.282, + "args": { + "External id": 4548936,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941683429.055, "dur": 1.005, + "args": { + "External id": 4548937,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 8160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941683433.788, "dur": 2.105, + "args": { + "External id": 4548938,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941683437.430, "dur": 1.136, + "args": { + "External id": 4548939,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941683439.823, "dur": 1.066, + "args": { + "External id": 4548940,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941683461.058, "dur": 16686.048, + "args": { + "External id": 4548941,"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": 8164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941683477.227, "dur": 16663.099, + "args": { + "External id": 4548942,"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": 8165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941683496.206, "dur": 13.880, + "args": { + "External id": 4548943,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941683515.621, "dur": 16589.126, + "args": { + "External id": 4548944,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 8167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941683518.584, "dur": 16585.557, + "args": { + "External id": 4548945,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 8168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941683524.986, "dur": 21.804, + "args": { + "External id": 4548946,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941683549.011, "dur": 16552.171, + "args": { + "External id": 4548947,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 8170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941700321.914, "dur": 38.151, + "args": { + "External id": 4548948,"Sequence number": 45295639, "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": 8171 + } + }, + { + "ph": "s", "id": 173, "pid": 1336753, "tid": 1336753, "ts": 1696941700321.914, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941700346.763, "dur": 7.990, + "args": { + "External id": 4548949,"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": 8172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941700350.149, "dur": 4.403, + "args": { + "External id": 4548950,"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": 8173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941700423.012, "dur": 77.245, + "args": { + "External id": 4548951,"Record function id": 0, "Ev Idx": 8174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1696941700501.877, "dur": 1098.902, + "args": { + "External id": 4548952,"Record function id": 0, "Ev Idx": 8175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941700555.588, "dur": 1031.443, + "args": { + "External id": 4548953,"Sequence number": 45295640, "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": 8176 + } + }, + { + "ph": "s", "id": 172, "pid": 1336753, "tid": 1336753, "ts": 1696941700555.588, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941700628.077, "dur": 46.434, + "args": { + "External id": 4548954,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 8177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941700688.507, "dur": 103.757, + "args": { + "External id": 4548955,"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": 8178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941700801.639, "dur": 37.524, + "args": { + "External id": 4548956,"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": 8179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941700847.843, "dur": 31.172, + "args": { + "External id": 4548957,"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": 8180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941700901.682, "dur": 27.473, + "args": { + "External id": 4548958,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 8181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941700949.630, "dur": 15.402, + "args": { + "External id": 4548959,"kernel_hash": "cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554", "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/ex/cex6azrfnirqh3jognpirazamj4oyxhnk3mxs7t2vmitx2fbo554.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": 8182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941701019.475, "dur": 135.453, + "args": { + "External id": 4548960,"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": 8183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941701073.689, "dur": 12.124, + "args": { + "External id": 4548961,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941701078.884, "dur": 6.014, + "args": { + "External id": 4548962,"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": 8185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941701088.520, "dur": 5.155, + "args": { + "External id": 4548963,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941701094.894, "dur": 1.805, + "args": { + "External id": 4548964,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941701098.995, "dur": 2.895, + "args": { + "External id": 4548965,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941701166.551, "dur": 48.899, + "args": { + "External id": 4548966,"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": 8189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336753, "tid": 1336753, + "ts": 1696941701249.659, "dur": 30.408, + "args": { + "External id": 4548967,"kernel_hash": "cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/w7/cw7dgbt4tjenpklhtvob3eghj7bbox7g2wxbo732slxqx2vrsyd5.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": 8190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941701288.240, "dur": 39.978, + "args": { + "External id": 4548968,"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": 8191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941701337.966, "dur": 34.332, + "args": { + "External id": 4548969,"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": 8192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941701393.912, "dur": 27.829, + "args": { + "External id": 4548970,"kernel_hash": "czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/zh/czh4pfojeoszm3aid3si2yxrotnl4lfradxhc2mhjrcx6kyggzha.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": 8193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941701428.290, "dur": 34.971, + "args": { + "External id": 4548971,"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": 8194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336753, "tid": 1336753, + "ts": 1696941701484.535, "dur": 18.034, + "args": { + "External id": 4548972,"kernel_hash": "cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/nz/cnzai7gm7fkymyw2bih55vxu3i63al2yxbe4zf3zad5ca4tx2gz4.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": 8195 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.27)", "pid": 1336753, "tid": 1336753, + "ts": 1696941701666.242, "dur": 33.212, + "args": { + "External id": 4548973,"Record function id": 0, "Ev Idx": 8196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941701846.339, "dur": 342.406, + "args": { + "External id": 4548974,"Sequence number": 45295641, "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": 8197 + } + }, + { + "ph": "s", "id": 171, "pid": 1336753, "tid": 1336753, "ts": 1696941701846.339, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941701877.435, "dur": 8.256, + "args": { + "External id": 4548975,"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": 8198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941701879.390, "dur": 6.049, + "args": { + "External id": 4548976,"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": 8199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941701896.096, "dur": 11.653, + "args": { + "External id": 4548977,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941701899.358, "dur": 7.835, + "args": { + "External id": 4548978,"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": 8201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941701917.769, "dur": 5.562, + "args": { + "External id": 4548979,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941702165.601, "dur": 7.986, + "args": { + "External id": 4548980,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941702168.948, "dur": 4.262, + "args": { + "External id": 4548981,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941702220.265, "dur": 132.315, + "args": { + "External id": 4548982,"Sequence number": 45295642, "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": 8205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941702222.694, "dur": 14.749, + "args": { + "External id": 4548983,"Sequence number": 45295642, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8206 + } + }, + { + "ph": "s", "id": 170, "pid": 1336753, "tid": 1336753, "ts": 1696941702222.694, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941702228.137, "dur": 7.578, + "args": { + "External id": 4548984,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941702233.191, "dur": 2.186, + "args": { + "External id": 4548985,"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": 8208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941702239.862, "dur": 112.397, + "args": { + "External id": 4548986,"Sequence number": 45295643, "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": 8209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941702242.457, "dur": 4.777, + "args": { + "External id": 4548987,"Sequence number": 45295643, "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": 8210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941702243.597, "dur": 3.484, + "args": { + "External id": 4548988,"Sequence number": 45295643, "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": 8211 + } + }, + { + "ph": "s", "id": 169, "pid": 1336753, "tid": 1336753, "ts": 1696941702243.597, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941702251.701, "dur": 92.058, + "args": { + "External id": 4548989,"Sequence number": 45295644, "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": 8212 + } + }, + { + "ph": "s", "id": 168, "pid": 1336753, "tid": 1336753, "ts": 1696941702251.701, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941702346.976, "dur": 4.285, + "args": { + "External id": 4548990,"Sequence number": 45295645, "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": 8213 + } + }, + { + "ph": "s", "id": 167, "pid": 1336753, "tid": 1336753, "ts": 1696941702346.976, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941702363.017, "dur": 70.169, + "args": { + "External id": 4548991,"Sequence number": 45295646, "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": 8214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941702363.880, "dur": 8.518, + "args": { + "External id": 4548992,"Sequence number": 45295646, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8215 + } + }, + { + "ph": "s", "id": 166, "pid": 1336753, "tid": 1336753, "ts": 1696941702363.880, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941702365.961, "dur": 5.444, + "args": { + "External id": 4548993,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941702370.171, "dur": 1.069, + "args": { + "External id": 4548994,"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": 8217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941702373.156, "dur": 59.808, + "args": { + "External id": 4548995,"Sequence number": 45295647, "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": 8218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941702374.075, "dur": 6.465, + "args": { + "External id": 4548996,"Sequence number": 45295647, "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": 8219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941702375.303, "dur": 5.078, + "args": { + "External id": 4548997,"Sequence number": 45295647, "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": 8220 + } + }, + { + "ph": "s", "id": 165, "pid": 1336753, "tid": 1336753, "ts": 1696941702375.303, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941702381.050, "dur": 43.715, + "args": { + "External id": 4548998,"Sequence number": 45295648, "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": 8221 + } + }, + { + "ph": "s", "id": 164, "pid": 1336753, "tid": 1336753, "ts": 1696941702381.050, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941702426.528, "dur": 6.088, + "args": { + "External id": 4548999,"Sequence number": 45295649, "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": 8222 + } + }, + { + "ph": "s", "id": 163, "pid": 1336753, "tid": 1336753, "ts": 1696941702426.528, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941702441.499, "dur": 66.295, + "args": { + "External id": 4549000,"Sequence number": 45295650, "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": 8223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941702442.219, "dur": 6.196, + "args": { + "External id": 4549001,"Sequence number": 45295650, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8224 + } + }, + { + "ph": "s", "id": 162, "pid": 1336753, "tid": 1336753, "ts": 1696941702442.219, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941702444.441, "dur": 2.474, + "args": { + "External id": 4549002,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941702445.785, "dur": 0.976, + "args": { + "External id": 4549003,"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": 8226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941702451.225, "dur": 56.224, + "args": { + "External id": 4549004,"Sequence number": 45295651, "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": 8227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941702452.710, "dur": 5.394, + "args": { + "External id": 4549005,"Sequence number": 45295651, "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": 8228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941702453.545, "dur": 4.402, + "args": { + "External id": 4549006,"Sequence number": 45295651, "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": 8229 + } + }, + { + "ph": "s", "id": 161, "pid": 1336753, "tid": 1336753, "ts": 1696941702453.545, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941702458.693, "dur": 39.983, + "args": { + "External id": 4549007,"Sequence number": 45295652, "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": 8230 + } + }, + { + "ph": "s", "id": 160, "pid": 1336753, "tid": 1336753, "ts": 1696941702458.693, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941702500.244, "dur": 6.841, + "args": { + "External id": 4549008,"Sequence number": 45295653, "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": 8231 + } + }, + { + "ph": "s", "id": 159, "pid": 1336753, "tid": 1336753, "ts": 1696941702500.244, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941702548.712, "dur": 4.977, + "args": { + "External id": 4549009,"Sequence number": 45295654, "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": 8232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941702549.745, "dur": 3.729, + "args": { + "External id": 4549010,"Sequence number": 45295654, "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": 8233 + } + }, + { + "ph": "s", "id": 158, "pid": 1336753, "tid": 1336753, "ts": 1696941702549.745, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941702562.040, "dur": 3.728, + "args": { + "External id": 4549011,"Sequence number": 45295655, "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": 8234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941702563.330, "dur": 2.310, + "args": { + "External id": 4549012,"Sequence number": 45295655, "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": 8235 + } + }, + { + "ph": "s", "id": 157, "pid": 1336753, "tid": 1336753, "ts": 1696941702563.330, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941702572.496, "dur": 5.374, + "args": { + "External id": 4549013,"Sequence number": 45295656, "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": 8236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941702573.559, "dur": 4.178, + "args": { + "External id": 4549014,"Sequence number": 45295656, "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": 8237 + } + }, + { + "ph": "s", "id": 156, "pid": 1336753, "tid": 1336753, "ts": 1696941702573.559, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941702615.973, "dur": 189.279, + "args": { + "External id": 4549015,"Sequence number": 45295657, "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": 8238 + } + }, + { + "ph": "s", "id": 155, "pid": 1336753, "tid": 1336753, "ts": 1696941702615.973, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941702639.372, "dur": 9.855, + "args": { + "External id": 4549016,"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": 8239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941702642.875, "dur": 5.888, + "args": { + "External id": 4549017,"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": 8240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941702818.590, "dur": 113.441, + "args": { + "External id": 4549018,"Sequence number": 45295658, "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": 8241 + } + }, + { + "ph": "s", "id": 154, "pid": 1336753, "tid": 1336753, "ts": 1696941702818.590, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941702833.382, "dur": 7.124, + "args": { + "External id": 4549019,"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": 8242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941702835.822, "dur": 4.222, + "args": { + "External id": 4549020,"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": 8243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 1336753, "tid": 1336753, + "ts": 1696941702960.084, "dur": 251.391, + "args": { + "External id": 4549021,"Sequence number": 45295659, "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": 8244 + } + }, + { + "ph": "s", "id": 153, "pid": 1336753, "tid": 1336753, "ts": 1696941702960.084, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941703037.557, "dur": 142.476, + "args": { + "External id": 4549022,"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": 8245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941703094.418, "dur": 9.815, + "args": { + "External id": 4549023,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941703097.443, "dur": 5.985, + "args": { + "External id": 4549024,"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": 8247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941703106.825, "dur": 4.804, + "args": { + "External id": 4549025,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941703113.112, "dur": 2.025, + "args": { + "External id": 4549026,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941703119.548, "dur": 3.234, + "args": { + "External id": 4549027,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1336753, + "ts": 1696941703194.095, "dur": 5.669, + "args": { + "External id": 4549028,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 8251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941703217.451, "dur": 6.779, + "args": { + "External id": 4549029,"Sequence number": 45295660, "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": 8252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941703219.270, "dur": 4.798, + "args": { + "External id": 4549030,"Sequence number": 45295660, "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": 8253 + } + }, + { + "ph": "s", "id": 152, "pid": 1336753, "tid": 1336753, "ts": 1696941703219.270, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941703242.530, "dur": 124.142, + "args": { + "External id": 4549031,"Sequence number": 45295661, "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": 8254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941703245.962, "dur": 9.728, + "args": { + "External id": 4549032,"Sequence number": 45295661, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8255 + } + }, + { + "ph": "s", "id": 151, "pid": 1336753, "tid": 1336753, "ts": 1696941703245.962, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941703249.707, "dur": 4.820, + "args": { + "External id": 4549033,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941703252.399, "dur": 1.812, + "args": { + "External id": 4549034,"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": 8257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941703257.044, "dur": 109.294, + "args": { + "External id": 4549035,"Sequence number": 45295662, "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": 8258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941703258.730, "dur": 10.000, + "args": { + "External id": 4549036,"Sequence number": 45295662, "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": 8259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941703262.064, "dur": 6.447, + "args": { + "External id": 4549037,"Sequence number": 45295662, "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": 8260 + } + }, + { + "ph": "s", "id": 150, "pid": 1336753, "tid": 1336753, "ts": 1696941703262.064, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941703269.695, "dur": 87.098, + "args": { + "External id": 4549038,"Sequence number": 45295663, "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": 8261 + } + }, + { + "ph": "s", "id": 149, "pid": 1336753, "tid": 1336753, "ts": 1696941703269.695, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941703359.713, "dur": 5.902, + "args": { + "External id": 4549039,"Sequence number": 45295664, "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": 8262 + } + }, + { + "ph": "s", "id": 148, "pid": 1336753, "tid": 1336753, "ts": 1696941703359.713, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941703403.430, "dur": 259.076, + "args": { + "External id": 4549040,"Sequence number": 45295665, "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": 8263 + } + }, + { + "ph": "s", "id": 147, "pid": 1336753, "tid": 1336753, "ts": 1696941703403.430, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941703426.224, "dur": 2.737, + "args": { + "External id": 4549041,"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": 8264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941703427.177, "dur": 1.628, + "args": { + "External id": 4549042,"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": 8265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941703434.635, "dur": 3.312, + "args": { + "External id": 4549043,"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": 8266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941703435.919, "dur": 1.914, + "args": { + "External id": 4549044,"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": 8267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941703436.511, "dur": 1.206, + "args": { + "External id": 4549045,"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": 8268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941703446.115, "dur": 8.937, + "args": { + "External id": 4549046,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941703450.468, "dur": 4.249, + "args": { + "External id": 4549047,"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": 8270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941703461.288, "dur": 3.523, + "args": { + "External id": 4549048,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941703467.993, "dur": 3.031, + "args": { + "External id": 4549049,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941703635.660, "dur": 4.143, + "args": { + "External id": 4549050,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941703636.671, "dur": 2.929, + "args": { + "External id": 4549051,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941703642.671, "dur": 2.460, + "args": { + "External id": 4549052,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941703643.820, "dur": 1.203, + "args": { + "External id": 4549053,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941703684.795, "dur": 102.755, + "args": { + "External id": 4549054,"Sequence number": 45295666, "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": 8277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941703686.212, "dur": 8.852, + "args": { + "External id": 4549055,"Sequence number": 45295666, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8278 + } + }, + { + "ph": "s", "id": 146, "pid": 1336753, "tid": 1336753, "ts": 1696941703686.212, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941703688.984, "dur": 4.418, + "args": { + "External id": 4549056,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941703691.301, "dur": 1.710, + "args": { + "External id": 4549057,"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": 8280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941703696.023, "dur": 91.199, + "args": { + "External id": 4549058,"Sequence number": 45295667, "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": 8281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941703699.747, "dur": 3.766, + "args": { + "External id": 4549059,"Sequence number": 45295667, "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": 8282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941703700.423, "dur": 2.928, + "args": { + "External id": 4549060,"Sequence number": 45295667, "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": 8283 + } + }, + { + "ph": "s", "id": 145, "pid": 1336753, "tid": 1336753, "ts": 1696941703700.423, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941703704.401, "dur": 76.459, + "args": { + "External id": 4549061,"Sequence number": 45295668, "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": 8284 + } + }, + { + "ph": "s", "id": 144, "pid": 1336753, "tid": 1336753, "ts": 1696941703704.401, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941703783.053, "dur": 3.566, + "args": { + "External id": 4549062,"Sequence number": 45295669, "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": 8285 + } + }, + { + "ph": "s", "id": 143, "pid": 1336753, "tid": 1336753, "ts": 1696941703783.053, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941703796.826, "dur": 72.480, + "args": { + "External id": 4549063,"Sequence number": 45295670, "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": 8286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941703800.141, "dur": 5.569, + "args": { + "External id": 4549064,"Sequence number": 45295670, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8287 + } + }, + { + "ph": "s", "id": 142, "pid": 1336753, "tid": 1336753, "ts": 1696941703800.141, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941703802.302, "dur": 2.317, + "args": { + "External id": 4549065,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941703803.716, "dur": 0.749, + "args": { + "External id": 4549066,"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": 8289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941703806.663, "dur": 62.378, + "args": { + "External id": 4549067,"Sequence number": 45295671, "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": 8290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941703807.437, "dur": 8.967, + "args": { + "External id": 4549068,"Sequence number": 45295671, "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": 8291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941703810.731, "dur": 5.505, + "args": { + "External id": 4549069,"Sequence number": 45295671, "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": 8292 + } + }, + { + "ph": "s", "id": 141, "pid": 1336753, "tid": 1336753, "ts": 1696941703810.731, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941703817.065, "dur": 45.627, + "args": { + "External id": 4549070,"Sequence number": 45295672, "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": 8293 + } + }, + { + "ph": "s", "id": 140, "pid": 1336753, "tid": 1336753, "ts": 1696941703817.065, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941703864.454, "dur": 4.272, + "args": { + "External id": 4549071,"Sequence number": 45295673, "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": 8294 + } + }, + { + "ph": "s", "id": 139, "pid": 1336753, "tid": 1336753, "ts": 1696941703864.454, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941703892.704, "dur": 206.818, + "args": { + "External id": 4549072,"Sequence number": 45295674, "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": 8295 + } + }, + { + "ph": "s", "id": 138, "pid": 1336753, "tid": 1336753, "ts": 1696941703892.704, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941703937.814, "dur": 4.381, + "args": { + "External id": 4549073,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941703979.533, "dur": 103.983, + "args": { + "External id": 4549074,"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": 8297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941703980.274, "dur": 43.439, + "args": { + "External id": 4549075,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 8298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941704018.493, "dur": 4.127, + "args": { + "External id": 4549076,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 8299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941704020.334, "dur": 1.725, + "args": { + "External id": 4549077,"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": 8300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941704024.446, "dur": 58.705, + "args": { + "External id": 4549078,"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": 8301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941704028.320, "dur": 2.568, + "args": { + "External id": 4549079,"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": 8302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941704029.245, "dur": 1.543, + "args": { + "External id": 4549080,"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": 8303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941704031.646, "dur": 47.370, + "args": { + "External id": 4549081,"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": 8304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941704081.048, "dur": 1.297, + "args": { + "External id": 4549082,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1696941704110.396, "dur": 30.790, + "args": { + "External id": 4549083,"Sequence number": 45295675, "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": 8306 + } + }, + { + "ph": "s", "id": 137, "pid": 1336753, "tid": 1336753, "ts": 1696941704110.396, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941704179.164, "dur": 190.907, + "args": { + "External id": 4549084,"Sequence number": 45295676, "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": 8307 + } + }, + { + "ph": "s", "id": 136, "pid": 1336753, "tid": 1336753, "ts": 1696941704179.164, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941704199.074, "dur": 5.105, + "args": { + "External id": 4549085,"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": 8308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941704202.189, "dur": 1.861, + "args": { + "External id": 4549086,"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": 8309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941704212.308, "dur": 7.885, + "args": { + "External id": 4549087,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941704214.984, "dur": 4.802, + "args": { + "External id": 4549088,"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": 8311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941704226.301, "dur": 4.286, + "args": { + "External id": 4549089,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941704354.209, "dur": 3.689, + "args": { + "External id": 4549090,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941704355.761, "dur": 1.948, + "args": { + "External id": 4549091,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941704390.237, "dur": 88.484, + "args": { + "External id": 4549092,"Sequence number": 45295677, "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": 8315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941704391.638, "dur": 10.802, + "args": { + "External id": 4549093,"Sequence number": 45295677, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8316 + } + }, + { + "ph": "s", "id": 135, "pid": 1336753, "tid": 1336753, "ts": 1696941704391.638, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941704397.618, "dur": 3.727, + "args": { + "External id": 4549094,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941704399.578, "dur": 1.592, + "args": { + "External id": 4549095,"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": 8318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941704403.540, "dur": 74.843, + "args": { + "External id": 4549096,"Sequence number": 45295678, "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": 8319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941704404.887, "dur": 5.900, + "args": { + "External id": 4549097,"Sequence number": 45295678, "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": 8320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941704407.914, "dur": 2.742, + "args": { + "External id": 4549098,"Sequence number": 45295678, "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": 8321 + } + }, + { + "ph": "s", "id": 134, "pid": 1336753, "tid": 1336753, "ts": 1696941704407.914, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941704411.636, "dur": 60.687, + "args": { + "External id": 4549099,"Sequence number": 45295679, "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": 8322 + } + }, + { + "ph": "s", "id": 133, "pid": 1336753, "tid": 1336753, "ts": 1696941704411.636, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941704474.306, "dur": 3.606, + "args": { + "External id": 4549100,"Sequence number": 45295680, "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": 8323 + } + }, + { + "ph": "s", "id": 132, "pid": 1336753, "tid": 1336753, "ts": 1696941704474.306, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941704487.660, "dur": 91.509, + "args": { + "External id": 4549101,"Sequence number": 45295681, "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": 8324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941704488.352, "dur": 11.554, + "args": { + "External id": 4549102,"Sequence number": 45295681, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8325 + } + }, + { + "ph": "s", "id": 131, "pid": 1336753, "tid": 1336753, "ts": 1696941704488.352, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941704495.414, "dur": 3.409, + "args": { + "External id": 4549103,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941704497.666, "dur": 0.901, + "args": { + "External id": 4549104,"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": 8327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941704500.888, "dur": 78.034, + "args": { + "External id": 4549105,"Sequence number": 45295682, "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": 8328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941704502.069, "dur": 5.930, + "args": { + "External id": 4549106,"Sequence number": 45295682, "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": 8329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941704502.769, "dur": 5.066, + "args": { + "External id": 4549107,"Sequence number": 45295682, "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": 8330 + } + }, + { + "ph": "s", "id": 130, "pid": 1336753, "tid": 1336753, "ts": 1696941704502.769, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941704508.679, "dur": 64.010, + "args": { + "External id": 4549108,"Sequence number": 45295683, "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": 8331 + } + }, + { + "ph": "s", "id": 129, "pid": 1336753, "tid": 1336753, "ts": 1696941704508.679, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941704575.208, "dur": 3.248, + "args": { + "External id": 4549109,"Sequence number": 45295684, "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": 8332 + } + }, + { + "ph": "s", "id": 128, "pid": 1336753, "tid": 1336753, "ts": 1696941704575.208, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941704589.038, "dur": 67.156, + "args": { + "External id": 4549110,"Sequence number": 45295685, "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": 8333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941704589.829, "dur": 10.292, + "args": { + "External id": 4549111,"Sequence number": 45295685, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8334 + } + }, + { + "ph": "s", "id": 127, "pid": 1336753, "tid": 1336753, "ts": 1696941704589.829, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941704591.755, "dur": 7.252, + "args": { + "External id": 4549112,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941704595.608, "dur": 3.160, + "args": { + "External id": 4549113,"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": 8336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941704600.745, "dur": 55.138, + "args": { + "External id": 4549114,"Sequence number": 45295686, "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": 8337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941704601.757, "dur": 5.014, + "args": { + "External id": 4549115,"Sequence number": 45295686, "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": 8338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941704602.668, "dur": 3.977, + "args": { + "External id": 4549116,"Sequence number": 45295686, "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": 8339 + } + }, + { + "ph": "s", "id": 126, "pid": 1336753, "tid": 1336753, "ts": 1696941704602.668, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941704609.341, "dur": 40.119, + "args": { + "External id": 4549117,"Sequence number": 45295687, "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": 8340 + } + }, + { + "ph": "s", "id": 125, "pid": 1336753, "tid": 1336753, "ts": 1696941704609.341, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941704650.926, "dur": 4.612, + "args": { + "External id": 4549118,"Sequence number": 45295688, "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": 8341 + } + }, + { + "ph": "s", "id": 124, "pid": 1336753, "tid": 1336753, "ts": 1696941704650.926, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941704672.027, "dur": 4.629, + "args": { + "External id": 4549119,"Sequence number": 45295689, "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": 8342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941704673.181, "dur": 3.356, + "args": { + "External id": 4549120,"Sequence number": 45295689, "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": 8343 + } + }, + { + "ph": "s", "id": 123, "pid": 1336753, "tid": 1336753, "ts": 1696941704673.181, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941704711.970, "dur": 7.730, + "args": { + "External id": 4549121,"Sequence number": 45295690, "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": 8344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941704715.778, "dur": 3.810, + "args": { + "External id": 4549122,"Sequence number": 45295690, "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": 8345 + } + }, + { + "ph": "s", "id": 122, "pid": 1336753, "tid": 1336753, "ts": 1696941704715.778, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941704724.044, "dur": 5.062, + "args": { + "External id": 4549123,"Sequence number": 45295691, "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": 8346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941704725.102, "dur": 3.848, + "args": { + "External id": 4549124,"Sequence number": 45295691, "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": 8347 + } + }, + { + "ph": "s", "id": 121, "pid": 1336753, "tid": 1336753, "ts": 1696941704725.102, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941704759.122, "dur": 162.706, + "args": { + "External id": 4549125,"Sequence number": 45295692, "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": 8348 + } + }, + { + "ph": "s", "id": 120, "pid": 1336753, "tid": 1336753, "ts": 1696941704759.122, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941704778.172, "dur": 8.907, + "args": { + "External id": 4549126,"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": 8349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941704781.276, "dur": 5.392, + "args": { + "External id": 4549127,"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": 8350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941704936.556, "dur": 164.535, + "args": { + "External id": 4549128,"Sequence number": 45295693, "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": 8351 + } + }, + { + "ph": "s", "id": 119, "pid": 1336753, "tid": 1336753, "ts": 1696941704936.556, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941704950.034, "dur": 7.057, + "args": { + "External id": 4549129,"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": 8352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941704952.140, "dur": 4.542, + "args": { + "External id": 4549130,"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": 8353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 1336753, "tid": 1336753, + "ts": 1696941705130.354, "dur": 183.770, + "args": { + "External id": 4549131,"Sequence number": 45295694, "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": 8354 + } + }, + { + "ph": "s", "id": 118, "pid": 1336753, "tid": 1336753, "ts": 1696941705130.354, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941705160.081, "dur": 129.071, + "args": { + "External id": 4549132,"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": 8355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941705209.298, "dur": 8.549, + "args": { + "External id": 4549133,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941705212.078, "dur": 5.300, + "args": { + "External id": 4549134,"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": 8357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941705220.809, "dur": 4.820, + "args": { + "External id": 4549135,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941705226.565, "dur": 3.497, + "args": { + "External id": 4549136,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941705232.656, "dur": 3.226, + "args": { + "External id": 4549137,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1336753, + "ts": 1696941705300.260, "dur": 4.693, + "args": { + "External id": 4549138,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 8361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941705319.130, "dur": 6.893, + "args": { + "External id": 4549139,"Sequence number": 45295695, "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": 8362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941705320.384, "dur": 5.489, + "args": { + "External id": 4549140,"Sequence number": 45295695, "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": 8363 + } + }, + { + "ph": "s", "id": 117, "pid": 1336753, "tid": 1336753, "ts": 1696941705320.384, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941705341.443, "dur": 106.137, + "args": { + "External id": 4549141,"Sequence number": 45295696, "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": 8364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941705342.906, "dur": 8.438, + "args": { + "External id": 4549142,"Sequence number": 45295696, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8365 + } + }, + { + "ph": "s", "id": 116, "pid": 1336753, "tid": 1336753, "ts": 1696941705342.906, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941705346.235, "dur": 3.812, + "args": { + "External id": 4549143,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941705348.284, "dur": 1.527, + "args": { + "External id": 4549144,"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": 8367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941705352.413, "dur": 94.883, + "args": { + "External id": 4549145,"Sequence number": 45295697, "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": 8368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941705356.205, "dur": 5.230, + "args": { + "External id": 4549146,"Sequence number": 45295697, "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": 8369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941705356.651, "dur": 4.614, + "args": { + "External id": 4549147,"Sequence number": 45295697, "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": 8370 + } + }, + { + "ph": "s", "id": 115, "pid": 1336753, "tid": 1336753, "ts": 1696941705356.651, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941705362.254, "dur": 77.215, + "args": { + "External id": 4549148,"Sequence number": 45295698, "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": 8371 + } + }, + { + "ph": "s", "id": 114, "pid": 1336753, "tid": 1336753, "ts": 1696941705362.254, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941705441.392, "dur": 5.286, + "args": { + "External id": 4549149,"Sequence number": 45295699, "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": 8372 + } + }, + { + "ph": "s", "id": 113, "pid": 1336753, "tid": 1336753, "ts": 1696941705441.392, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941705481.255, "dur": 235.719, + "args": { + "External id": 4549150,"Sequence number": 45295700, "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": 8373 + } + }, + { + "ph": "s", "id": 112, "pid": 1336753, "tid": 1336753, "ts": 1696941705481.255, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941705501.354, "dur": 2.244, + "args": { + "External id": 4549151,"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": 8374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941705501.968, "dur": 1.499, + "args": { + "External id": 4549152,"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": 8375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941705507.397, "dur": 5.670, + "args": { + "External id": 4549153,"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": 8376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941705508.294, "dur": 4.666, + "args": { + "External id": 4549154,"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": 8377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941705511.680, "dur": 1.174, + "args": { + "External id": 4549155,"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": 8378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941705520.015, "dur": 24.665, + "args": { + "External id": 4549156,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941705521.950, "dur": 22.022, + "args": { + "External id": 4549157,"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": 8380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941705552.461, "dur": 4.099, + "args": { + "External id": 4549158,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941705560.218, "dur": 3.449, + "args": { + "External id": 4549159,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941705689.951, "dur": 3.782, + "args": { + "External id": 4549160,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941705690.971, "dur": 2.607, + "args": { + "External id": 4549161,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941705698.773, "dur": 2.705, + "args": { + "External id": 4549162,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941705700.029, "dur": 1.350, + "args": { + "External id": 4549163,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941705737.351, "dur": 97.646, + "args": { + "External id": 4549164,"Sequence number": 45295701, "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": 8387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941705738.441, "dur": 8.246, + "args": { + "External id": 4549165,"Sequence number": 45295701, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8388 + } + }, + { + "ph": "s", "id": 111, "pid": 1336753, "tid": 1336753, "ts": 1696941705738.441, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941705741.546, "dur": 3.915, + "args": { + "External id": 4549166,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941705743.508, "dur": 1.678, + "args": { + "External id": 4549167,"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": 8390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941705749.542, "dur": 85.136, + "args": { + "External id": 4549168,"Sequence number": 45295702, "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": 8391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941705750.823, "dur": 3.284, + "args": { + "External id": 4549169,"Sequence number": 45295702, "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": 8392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941705751.561, "dur": 2.398, + "args": { + "External id": 4549170,"Sequence number": 45295702, "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": 8393 + } + }, + { + "ph": "s", "id": 110, "pid": 1336753, "tid": 1336753, "ts": 1696941705751.561, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941705754.763, "dur": 72.176, + "args": { + "External id": 4549171,"Sequence number": 45295703, "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": 8394 + } + }, + { + "ph": "s", "id": 109, "pid": 1336753, "tid": 1336753, "ts": 1696941705754.763, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941705828.840, "dur": 5.281, + "args": { + "External id": 4549172,"Sequence number": 45295704, "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": 8395 + } + }, + { + "ph": "s", "id": 108, "pid": 1336753, "tid": 1336753, "ts": 1696941705828.840, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941705843.052, "dur": 68.044, + "args": { + "External id": 4549173,"Sequence number": 45295705, "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": 8396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941705843.595, "dur": 5.472, + "args": { + "External id": 4549174,"Sequence number": 45295705, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8397 + } + }, + { + "ph": "s", "id": 107, "pid": 1336753, "tid": 1336753, "ts": 1696941705843.595, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941705845.200, "dur": 2.518, + "args": { + "External id": 4549175,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941705846.736, "dur": 0.840, + "args": { + "External id": 4549176,"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": 8399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941705849.663, "dur": 61.230, + "args": { + "External id": 4549177,"Sequence number": 45295706, "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": 8400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941705852.980, "dur": 6.385, + "args": { + "External id": 4549178,"Sequence number": 45295706, "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": 8401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941705853.412, "dur": 5.789, + "args": { + "External id": 4549179,"Sequence number": 45295706, "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": 8402 + } + }, + { + "ph": "s", "id": 106, "pid": 1336753, "tid": 1336753, "ts": 1696941705853.412, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941705859.927, "dur": 44.198, + "args": { + "External id": 4549180,"Sequence number": 45295707, "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": 8403 + } + }, + { + "ph": "s", "id": 105, "pid": 1336753, "tid": 1336753, "ts": 1696941705859.927, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941705905.580, "dur": 4.956, + "args": { + "External id": 4549181,"Sequence number": 45295708, "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": 8404 + } + }, + { + "ph": "s", "id": 104, "pid": 1336753, "tid": 1336753, "ts": 1696941705905.580, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941705934.018, "dur": 195.131, + "args": { + "External id": 4549182,"Sequence number": 45295709, "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": 8405 + } + }, + { + "ph": "s", "id": 103, "pid": 1336753, "tid": 1336753, "ts": 1696941705934.018, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941705970.487, "dur": 4.286, + "args": { + "External id": 4549183,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941706048.566, "dur": 65.336, + "args": { + "External id": 4549184,"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": 8407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941706049.586, "dur": 7.385, + "args": { + "External id": 4549185,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 8408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941706051.051, "dur": 4.609, + "args": { + "External id": 4549186,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 8409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941706053.191, "dur": 2.134, + "args": { + "External id": 4549187,"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": 8410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941706059.875, "dur": 53.688, + "args": { + "External id": 4549188,"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": 8411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941706060.993, "dur": 2.493, + "args": { + "External id": 4549189,"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": 8412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941706061.780, "dur": 1.553, + "args": { + "External id": 4549190,"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": 8413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941706064.185, "dur": 45.527, + "args": { + "External id": 4549191,"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": 8414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941706111.555, "dur": 1.255, + "args": { + "External id": 4549192,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1696941706138.561, "dur": 27.675, + "args": { + "External id": 4549193,"Sequence number": 45295710, "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": 8416 + } + }, + { + "ph": "s", "id": 102, "pid": 1336753, "tid": 1336753, "ts": 1696941706138.561, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941706203.920, "dur": 186.208, + "args": { + "External id": 4549194,"Sequence number": 45295711, "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": 8417 + } + }, + { + "ph": "s", "id": 101, "pid": 1336753, "tid": 1336753, "ts": 1696941706203.920, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941706224.905, "dur": 2.776, + "args": { + "External id": 4549195,"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": 8418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941706225.714, "dur": 1.842, + "args": { + "External id": 4549196,"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": 8419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941706236.060, "dur": 7.081, + "args": { + "External id": 4549197,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941706238.314, "dur": 4.415, + "args": { + "External id": 4549198,"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": 8421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941706249.538, "dur": 3.760, + "args": { + "External id": 4549199,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941706372.457, "dur": 3.472, + "args": { + "External id": 4549200,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941706373.514, "dur": 2.188, + "args": { + "External id": 4549201,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941706410.279, "dur": 83.797, + "args": { + "External id": 4549202,"Sequence number": 45295712, "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": 8425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941706411.068, "dur": 6.975, + "args": { + "External id": 4549203,"Sequence number": 45295712, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8426 + } + }, + { + "ph": "s", "id": 100, "pid": 1336753, "tid": 1336753, "ts": 1696941706411.068, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941706413.411, "dur": 3.443, + "args": { + "External id": 4549204,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941706415.321, "dur": 1.349, + "args": { + "External id": 4549205,"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": 8428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941706418.845, "dur": 74.815, + "args": { + "External id": 4549206,"Sequence number": 45295713, "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": 8429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941706422.421, "dur": 3.873, + "args": { + "External id": 4549207,"Sequence number": 45295713, "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": 8430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941706422.841, "dur": 3.307, + "args": { + "External id": 4549208,"Sequence number": 45295713, "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": 8431 + } + }, + { + "ph": "s", "id": 99, "pid": 1336753, "tid": 1336753, "ts": 1696941706422.841, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941706426.918, "dur": 59.210, + "args": { + "External id": 4549209,"Sequence number": 45295714, "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": 8432 + } + }, + { + "ph": "s", "id": 98, "pid": 1336753, "tid": 1336753, "ts": 1696941706426.918, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941706488.071, "dur": 5.105, + "args": { + "External id": 4549210,"Sequence number": 45295715, "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": 8433 + } + }, + { + "ph": "s", "id": 97, "pid": 1336753, "tid": 1336753, "ts": 1696941706488.071, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941706501.386, "dur": 87.645, + "args": { + "External id": 4549211,"Sequence number": 45295716, "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": 8434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941706504.575, "dur": 6.833, + "args": { + "External id": 4549212,"Sequence number": 45295716, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8435 + } + }, + { + "ph": "s", "id": 96, "pid": 1336753, "tid": 1336753, "ts": 1696941706504.575, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941706507.113, "dur": 3.162, + "args": { + "External id": 4549213,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941706508.941, "dur": 0.996, + "args": { + "External id": 4549214,"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": 8437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941706511.990, "dur": 76.737, + "args": { + "External id": 4549215,"Sequence number": 45295717, "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": 8438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941706512.821, "dur": 4.891, + "args": { + "External id": 4549216,"Sequence number": 45295717, "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": 8439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941706515.604, "dur": 1.970, + "args": { + "External id": 4549217,"Sequence number": 45295717, "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": 8440 + } + }, + { + "ph": "s", "id": 95, "pid": 1336753, "tid": 1336753, "ts": 1696941706515.604, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941706518.341, "dur": 63.790, + "args": { + "External id": 4549218,"Sequence number": 45295718, "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": 8441 + } + }, + { + "ph": "s", "id": 94, "pid": 1336753, "tid": 1336753, "ts": 1696941706518.341, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941706585.236, "dur": 2.983, + "args": { + "External id": 4549219,"Sequence number": 45295719, "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": 8442 + } + }, + { + "ph": "s", "id": 93, "pid": 1336753, "tid": 1336753, "ts": 1696941706585.236, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941706597.150, "dur": 62.692, + "args": { + "External id": 4549220,"Sequence number": 45295720, "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": 8443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941706597.900, "dur": 9.022, + "args": { + "External id": 4549221,"Sequence number": 45295720, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8444 + } + }, + { + "ph": "s", "id": 92, "pid": 1336753, "tid": 1336753, "ts": 1696941706597.900, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941706601.579, "dur": 4.180, + "args": { + "External id": 4549222,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941706603.010, "dur": 2.533, + "args": { + "External id": 4549223,"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": 8446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941706607.543, "dur": 52.076, + "args": { + "External id": 4549224,"Sequence number": 45295721, "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": 8447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941706608.743, "dur": 6.490, + "args": { + "External id": 4549225,"Sequence number": 45295721, "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": 8448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941706611.585, "dur": 3.513, + "args": { + "External id": 4549226,"Sequence number": 45295721, "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": 8449 + } + }, + { + "ph": "s", "id": 91, "pid": 1336753, "tid": 1336753, "ts": 1696941706611.585, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941706615.672, "dur": 38.171, + "args": { + "External id": 4549227,"Sequence number": 45295722, "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": 8450 + } + }, + { + "ph": "s", "id": 90, "pid": 1336753, "tid": 1336753, "ts": 1696941706615.672, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941706655.264, "dur": 4.018, + "args": { + "External id": 4549228,"Sequence number": 45295723, "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": 8451 + } + }, + { + "ph": "s", "id": 89, "pid": 1336753, "tid": 1336753, "ts": 1696941706655.264, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941706676.133, "dur": 4.913, + "args": { + "External id": 4549229,"Sequence number": 45295724, "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": 8452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941706676.695, "dur": 4.187, + "args": { + "External id": 4549230,"Sequence number": 45295724, "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": 8453 + } + }, + { + "ph": "s", "id": 88, "pid": 1336753, "tid": 1336753, "ts": 1696941706676.695, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941706687.733, "dur": 3.068, + "args": { + "External id": 4549231,"Sequence number": 45295725, "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": 8454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941706688.524, "dur": 2.144, + "args": { + "External id": 4549232,"Sequence number": 45295725, "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": 8455 + } + }, + { + "ph": "s", "id": 87, "pid": 1336753, "tid": 1336753, "ts": 1696941706688.524, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941706694.906, "dur": 2.733, + "args": { + "External id": 4549233,"Sequence number": 45295726, "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": 8456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941706695.783, "dur": 1.729, + "args": { + "External id": 4549234,"Sequence number": 45295726, "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": 8457 + } + }, + { + "ph": "s", "id": 86, "pid": 1336753, "tid": 1336753, "ts": 1696941706695.783, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941706726.380, "dur": 156.019, + "args": { + "External id": 4549235,"Sequence number": 45295727, "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": 8458 + } + }, + { + "ph": "s", "id": 85, "pid": 1336753, "tid": 1336753, "ts": 1696941706726.380, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941706746.633, "dur": 10.825, + "args": { + "External id": 4549236,"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": 8459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941706749.663, "dur": 7.205, + "args": { + "External id": 4549237,"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": 8460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941706893.759, "dur": 145.057, + "args": { + "External id": 4549238,"Sequence number": 45295728, "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": 8461 + } + }, + { + "ph": "s", "id": 84, "pid": 1336753, "tid": 1336753, "ts": 1696941706893.759, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941706907.505, "dur": 6.096, + "args": { + "External id": 4549239,"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": 8462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941706909.609, "dur": 3.581, + "args": { + "External id": 4549240,"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": 8463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 1336753, "tid": 1336753, + "ts": 1696941707070.589, "dur": 183.921, + "args": { + "External id": 4549241,"Sequence number": 45295729, "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": 8464 + } + }, + { + "ph": "s", "id": 83, "pid": 1336753, "tid": 1336753, "ts": 1696941707070.589, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941707098.039, "dur": 130.205, + "args": { + "External id": 4549242,"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": 8465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941707146.413, "dur": 8.480, + "args": { + "External id": 4549243,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941707148.967, "dur": 5.484, + "args": { + "External id": 4549244,"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": 8467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941707157.439, "dur": 5.257, + "args": { + "External id": 4549245,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941707164.040, "dur": 1.903, + "args": { + "External id": 4549246,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941707168.268, "dur": 3.316, + "args": { + "External id": 4549247,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1336753, + "ts": 1696941707240.298, "dur": 4.928, + "args": { + "External id": 4549248,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 8471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941707259.716, "dur": 5.924, + "args": { + "External id": 4549249,"Sequence number": 45295730, "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": 8472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941707261.124, "dur": 4.345, + "args": { + "External id": 4549250,"Sequence number": 45295730, "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": 8473 + } + }, + { + "ph": "s", "id": 82, "pid": 1336753, "tid": 1336753, "ts": 1696941707261.124, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941707276.609, "dur": 112.274, + "args": { + "External id": 4549251,"Sequence number": 45295731, "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": 8474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941707277.964, "dur": 12.684, + "args": { + "External id": 4549252,"Sequence number": 45295731, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8475 + } + }, + { + "ph": "s", "id": 81, "pid": 1336753, "tid": 1336753, "ts": 1696941707277.964, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941707282.907, "dur": 6.498, + "args": { + "External id": 4549253,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941707287.460, "dur": 1.698, + "args": { + "External id": 4549254,"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": 8477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941707291.880, "dur": 96.676, + "args": { + "External id": 4549255,"Sequence number": 45295732, "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": 8478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941707293.388, "dur": 4.373, + "args": { + "External id": 4549256,"Sequence number": 45295732, "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": 8479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941707294.494, "dur": 3.084, + "args": { + "External id": 4549257,"Sequence number": 45295732, "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": 8480 + } + }, + { + "ph": "s", "id": 80, "pid": 1336753, "tid": 1336753, "ts": 1696941707294.494, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941707298.597, "dur": 80.444, + "args": { + "External id": 4549258,"Sequence number": 45295733, "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": 8481 + } + }, + { + "ph": "s", "id": 79, "pid": 1336753, "tid": 1336753, "ts": 1696941707298.597, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941707381.403, "dur": 6.422, + "args": { + "External id": 4549259,"Sequence number": 45295734, "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": 8482 + } + }, + { + "ph": "s", "id": 78, "pid": 1336753, "tid": 1336753, "ts": 1696941707381.403, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941707423.639, "dur": 226.687, + "args": { + "External id": 4549260,"Sequence number": 45295735, "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": 8483 + } + }, + { + "ph": "s", "id": 77, "pid": 1336753, "tid": 1336753, "ts": 1696941707423.639, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941707441.274, "dur": 2.892, + "args": { + "External id": 4549261,"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": 8484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941707442.214, "dur": 1.702, + "args": { + "External id": 4549262,"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": 8485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941707447.600, "dur": 5.753, + "args": { + "External id": 4549263,"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": 8486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941707451.260, "dur": 1.986, + "args": { + "External id": 4549264,"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": 8487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941707451.766, "dur": 1.369, + "args": { + "External id": 4549265,"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": 8488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941707460.487, "dur": 5.598, + "args": { + "External id": 4549266,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941707462.077, "dur": 3.686, + "args": { + "External id": 4549267,"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": 8490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941707472.354, "dur": 3.629, + "args": { + "External id": 4549268,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941707479.416, "dur": 3.799, + "args": { + "External id": 4549269,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941707626.426, "dur": 4.247, + "args": { + "External id": 4549270,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941707627.453, "dur": 2.924, + "args": { + "External id": 4549271,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941707633.376, "dur": 2.390, + "args": { + "External id": 4549272,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941707634.546, "dur": 1.110, + "args": { + "External id": 4549273,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941707668.627, "dur": 109.135, + "args": { + "External id": 4549274,"Sequence number": 45295736, "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": 8497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941707678.700, "dur": 9.330, + "args": { + "External id": 4549275,"Sequence number": 45295736, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8498 + } + }, + { + "ph": "s", "id": 76, "pid": 1336753, "tid": 1336753, "ts": 1696941707678.700, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941707683.495, "dur": 3.405, + "args": { + "External id": 4549276,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941707685.301, "dur": 1.291, + "args": { + "External id": 4549277,"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": 8500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941707688.747, "dur": 88.680, + "args": { + "External id": 4549278,"Sequence number": 45295737, "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": 8501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941707690.353, "dur": 7.064, + "args": { + "External id": 4549279,"Sequence number": 45295737, "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": 8502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941707690.785, "dur": 6.458, + "args": { + "External id": 4549280,"Sequence number": 45295737, "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": 8503 + } + }, + { + "ph": "s", "id": 75, "pid": 1336753, "tid": 1336753, "ts": 1696941707690.785, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941707698.269, "dur": 68.383, + "args": { + "External id": 4549281,"Sequence number": 45295738, "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": 8504 + } + }, + { + "ph": "s", "id": 74, "pid": 1336753, "tid": 1336753, "ts": 1696941707698.269, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941707768.592, "dur": 8.253, + "args": { + "External id": 4549282,"Sequence number": 45295739, "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": 8505 + } + }, + { + "ph": "s", "id": 73, "pid": 1336753, "tid": 1336753, "ts": 1696941707768.592, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941707785.590, "dur": 67.474, + "args": { + "External id": 4549283,"Sequence number": 45295740, "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": 8506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941707786.459, "dur": 7.815, + "args": { + "External id": 4549284,"Sequence number": 45295740, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8507 + } + }, + { + "ph": "s", "id": 72, "pid": 1336753, "tid": 1336753, "ts": 1696941707786.459, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941707787.736, "dur": 5.511, + "args": { + "External id": 4549285,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941707792.018, "dur": 1.071, + "args": { + "External id": 4549286,"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": 8509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941707794.806, "dur": 58.035, + "args": { + "External id": 4549287,"Sequence number": 45295741, "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": 8510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941707795.490, "dur": 4.439, + "args": { + "External id": 4549288,"Sequence number": 45295741, "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": 8511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941707796.512, "dur": 3.256, + "args": { + "External id": 4549289,"Sequence number": 45295741, "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": 8512 + } + }, + { + "ph": "s", "id": 71, "pid": 1336753, "tid": 1336753, "ts": 1696941707796.512, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941707802.761, "dur": 45.471, + "args": { + "External id": 4549290,"Sequence number": 45295742, "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": 8513 + } + }, + { + "ph": "s", "id": 70, "pid": 1336753, "tid": 1336753, "ts": 1696941707802.761, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941707850.285, "dur": 2.187, + "args": { + "External id": 4549291,"Sequence number": 45295743, "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": 8514 + } + }, + { + "ph": "s", "id": 69, "pid": 1336753, "tid": 1336753, "ts": 1696941707850.285, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941707873.007, "dur": 210.195, + "args": { + "External id": 4549292,"Sequence number": 45295744, "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": 8515 + } + }, + { + "ph": "s", "id": 68, "pid": 1336753, "tid": 1336753, "ts": 1696941707873.007, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941707909.220, "dur": 4.444, + "args": { + "External id": 4549293,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941707948.377, "dur": 119.144, + "args": { + "External id": 4549294,"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": 8517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941707949.268, "dur": 4.854, + "args": { + "External id": 4549295,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 8518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941707950.322, "dur": 2.672, + "args": { + "External id": 4549296,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 8519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941707951.985, "dur": 0.810, + "args": { + "External id": 4549297,"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": 8520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941707954.874, "dur": 112.227, + "args": { + "External id": 4549298,"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": 8521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941707956.292, "dur": 2.117, + "args": { + "External id": 4549299,"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": 8522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941707957.012, "dur": 1.254, + "args": { + "External id": 4549300,"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": 8523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941707961.082, "dur": 100.021, + "args": { + "External id": 4549301,"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": 8524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941708064.713, "dur": 1.614, + "args": { + "External id": 4549302,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1696941708092.957, "dur": 26.810, + "args": { + "External id": 4549303,"Sequence number": 45295745, "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": 8526 + } + }, + { + "ph": "s", "id": 67, "pid": 1336753, "tid": 1336753, "ts": 1696941708092.957, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941708157.911, "dur": 197.208, + "args": { + "External id": 4549304,"Sequence number": 45295746, "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": 8527 + } + }, + { + "ph": "s", "id": 66, "pid": 1336753, "tid": 1336753, "ts": 1696941708157.911, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941708176.105, "dur": 3.912, + "args": { + "External id": 4549305,"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": 8528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941708177.522, "dur": 2.318, + "args": { + "External id": 4549306,"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": 8529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941708191.038, "dur": 10.185, + "args": { + "External id": 4549307,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941708196.261, "dur": 4.559, + "args": { + "External id": 4549308,"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": 8531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941708210.728, "dur": 6.552, + "args": { + "External id": 4549309,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941708341.606, "dur": 3.859, + "args": { + "External id": 4549310,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941708343.196, "dur": 1.961, + "args": { + "External id": 4549311,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941708374.595, "dur": 89.610, + "args": { + "External id": 4549312,"Sequence number": 45295747, "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": 8535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941708375.796, "dur": 9.374, + "args": { + "External id": 4549313,"Sequence number": 45295747, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8536 + } + }, + { + "ph": "s", "id": 65, "pid": 1336753, "tid": 1336753, "ts": 1696941708375.796, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941708378.264, "dur": 5.566, + "args": { + "External id": 4549314,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941708382.345, "dur": 1.300, + "args": { + "External id": 4549315,"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": 8538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941708386.034, "dur": 77.859, + "args": { + "External id": 4549316,"Sequence number": 45295748, "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": 8539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941708387.241, "dur": 3.905, + "args": { + "External id": 4549317,"Sequence number": 45295748, "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": 8540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941708388.073, "dur": 2.938, + "args": { + "External id": 4549318,"Sequence number": 45295748, "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": 8541 + } + }, + { + "ph": "s", "id": 64, "pid": 1336753, "tid": 1336753, "ts": 1696941708388.073, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941708394.628, "dur": 63.594, + "args": { + "External id": 4549319,"Sequence number": 45295749, "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": 8542 + } + }, + { + "ph": "s", "id": 63, "pid": 1336753, "tid": 1336753, "ts": 1696941708394.628, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941708460.449, "dur": 2.867, + "args": { + "External id": 4549320,"Sequence number": 45295750, "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": 8543 + } + }, + { + "ph": "s", "id": 62, "pid": 1336753, "tid": 1336753, "ts": 1696941708460.449, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941708472.471, "dur": 86.712, + "args": { + "External id": 4549321,"Sequence number": 45295751, "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": 8544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941708472.939, "dur": 9.856, + "args": { + "External id": 4549322,"Sequence number": 45295751, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8545 + } + }, + { + "ph": "s", "id": 61, "pid": 1336753, "tid": 1336753, "ts": 1696941708472.939, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941708475.120, "dur": 6.354, + "args": { + "External id": 4549323,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941708478.686, "dur": 2.580, + "args": { + "External id": 4549324,"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": 8547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941708483.548, "dur": 75.408, + "args": { + "External id": 4549325,"Sequence number": 45295752, "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": 8548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941708484.599, "dur": 3.445, + "args": { + "External id": 4549326,"Sequence number": 45295752, "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": 8549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941708485.526, "dur": 2.367, + "args": { + "External id": 4549327,"Sequence number": 45295752, "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": 8550 + } + }, + { + "ph": "s", "id": 60, "pid": 1336753, "tid": 1336753, "ts": 1696941708485.526, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941708488.957, "dur": 59.422, + "args": { + "External id": 4549328,"Sequence number": 45295753, "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": 8551 + } + }, + { + "ph": "s", "id": 59, "pid": 1336753, "tid": 1336753, "ts": 1696941708488.957, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941708551.019, "dur": 7.363, + "args": { + "External id": 4549329,"Sequence number": 45295754, "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": 8552 + } + }, + { + "ph": "s", "id": 58, "pid": 1336753, "tid": 1336753, "ts": 1696941708551.019, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941708568.797, "dur": 64.721, + "args": { + "External id": 4549330,"Sequence number": 45295755, "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": 8553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941708569.411, "dur": 6.051, + "args": { + "External id": 4549331,"Sequence number": 45295755, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8554 + } + }, + { + "ph": "s", "id": 57, "pid": 1336753, "tid": 1336753, "ts": 1696941708569.411, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941708570.784, "dur": 3.350, + "args": { + "External id": 4549332,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941708572.651, "dur": 0.940, + "args": { + "External id": 4549333,"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": 8556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941708578.447, "dur": 54.899, + "args": { + "External id": 4549334,"Sequence number": 45295756, "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": 8557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941708579.147, "dur": 3.897, + "args": { + "External id": 4549335,"Sequence number": 45295756, "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": 8558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941708579.905, "dur": 2.989, + "args": { + "External id": 4549336,"Sequence number": 45295756, "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": 8559 + } + }, + { + "ph": "s", "id": 56, "pid": 1336753, "tid": 1336753, "ts": 1696941708579.905, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941708583.548, "dur": 43.893, + "args": { + "External id": 4549337,"Sequence number": 45295757, "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": 8560 + } + }, + { + "ph": "s", "id": 55, "pid": 1336753, "tid": 1336753, "ts": 1696941708583.548, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941708629.441, "dur": 3.581, + "args": { + "External id": 4549338,"Sequence number": 45295758, "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": 8561 + } + }, + { + "ph": "s", "id": 54, "pid": 1336753, "tid": 1336753, "ts": 1696941708629.441, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941708650.010, "dur": 3.959, + "args": { + "External id": 4549339,"Sequence number": 45295759, "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": 8562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941708651.048, "dur": 2.786, + "args": { + "External id": 4549340,"Sequence number": 45295759, "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": 8563 + } + }, + { + "ph": "s", "id": 53, "pid": 1336753, "tid": 1336753, "ts": 1696941708651.048, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941708660.289, "dur": 3.741, + "args": { + "External id": 4549341,"Sequence number": 45295760, "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": 8564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941708661.662, "dur": 2.241, + "args": { + "External id": 4549342,"Sequence number": 45295760, "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": 8565 + } + }, + { + "ph": "s", "id": 52, "pid": 1336753, "tid": 1336753, "ts": 1696941708661.662, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941708670.509, "dur": 5.282, + "args": { + "External id": 4549343,"Sequence number": 45295761, "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": 8566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941708671.675, "dur": 3.963, + "args": { + "External id": 4549344,"Sequence number": 45295761, "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": 8567 + } + }, + { + "ph": "s", "id": 51, "pid": 1336753, "tid": 1336753, "ts": 1696941708671.675, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941708704.986, "dur": 151.263, + "args": { + "External id": 4549345,"Sequence number": 45295762, "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": 8568 + } + }, + { + "ph": "s", "id": 50, "pid": 1336753, "tid": 1336753, "ts": 1696941708704.986, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941708722.715, "dur": 8.911, + "args": { + "External id": 4549346,"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": 8569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941708726.014, "dur": 5.074, + "args": { + "External id": 4549347,"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": 8570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941708867.194, "dur": 107.599, + "args": { + "External id": 4549348,"Sequence number": 45295763, "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": 8571 + } + }, + { + "ph": "s", "id": 49, "pid": 1336753, "tid": 1336753, "ts": 1696941708867.194, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941708880.458, "dur": 7.187, + "args": { + "External id": 4549349,"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": 8572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941708883.078, "dur": 4.073, + "args": { + "External id": 4549350,"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": 8573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 1336753, "tid": 1336753, + "ts": 1696941709037.688, "dur": 186.767, + "args": { + "External id": 4549351,"Sequence number": 45295764, "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": 8574 + } + }, + { + "ph": "s", "id": 48, "pid": 1336753, "tid": 1336753, "ts": 1696941709037.688, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941709067.246, "dur": 130.660, + "args": { + "External id": 4549352,"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": 8575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941709118.070, "dur": 9.384, + "args": { + "External id": 4549353,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941709121.008, "dur": 5.974, + "args": { + "External id": 4549354,"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": 8577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941709130.085, "dur": 5.322, + "args": { + "External id": 4549355,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941709136.410, "dur": 3.578, + "args": { + "External id": 4549356,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941709142.385, "dur": 3.207, + "args": { + "External id": 4549357,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336753, "tid": 1336753, + "ts": 1696941709209.525, "dur": 4.582, + "args": { + "External id": 4549358,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 8581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941709229.824, "dur": 5.509, + "args": { + "External id": 4549359,"Sequence number": 45295765, "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": 8582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941709231.252, "dur": 3.942, + "args": { + "External id": 4549360,"Sequence number": 45295765, "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": 8583 + } + }, + { + "ph": "s", "id": 47, "pid": 1336753, "tid": 1336753, "ts": 1696941709231.252, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941709247.902, "dur": 101.317, + "args": { + "External id": 4549361,"Sequence number": 45295766, "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": 8584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941709251.560, "dur": 8.010, + "args": { + "External id": 4549362,"Sequence number": 45295766, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8585 + } + }, + { + "ph": "s", "id": 46, "pid": 1336753, "tid": 1336753, "ts": 1696941709251.560, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941709254.171, "dur": 4.156, + "args": { + "External id": 4549363,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941709256.595, "dur": 1.490, + "args": { + "External id": 4549364,"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": 8587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941709260.986, "dur": 87.865, + "args": { + "External id": 4549365,"Sequence number": 45295767, "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": 8588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941709262.707, "dur": 5.640, + "args": { + "External id": 4549366,"Sequence number": 45295767, "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": 8589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941709265.813, "dur": 2.356, + "args": { + "External id": 4549367,"Sequence number": 45295767, "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": 8590 + } + }, + { + "ph": "s", "id": 45, "pid": 1336753, "tid": 1336753, "ts": 1696941709265.813, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941709269.145, "dur": 73.374, + "args": { + "External id": 4549368,"Sequence number": 45295768, "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": 8591 + } + }, + { + "ph": "s", "id": 44, "pid": 1336753, "tid": 1336753, "ts": 1696941709269.145, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941709344.587, "dur": 3.610, + "args": { + "External id": 4549369,"Sequence number": 45295769, "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": 8592 + } + }, + { + "ph": "s", "id": 43, "pid": 1336753, "tid": 1336753, "ts": 1696941709344.587, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941709380.541, "dur": 230.075, + "args": { + "External id": 4549370,"Sequence number": 45295770, "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": 8593 + } + }, + { + "ph": "s", "id": 42, "pid": 1336753, "tid": 1336753, "ts": 1696941709380.541, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941709400.515, "dur": 2.983, + "args": { + "External id": 4549371,"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": 8594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941709401.192, "dur": 2.089, + "args": { + "External id": 4549372,"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": 8595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 1336753, "tid": 1336753, + "ts": 1696941709407.228, "dur": 3.029, + "args": { + "External id": 4549373,"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": 8596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941709408.069, "dur": 2.080, + "args": { + "External id": 4549374,"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": 8597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941709408.998, "dur": 1.045, + "args": { + "External id": 4549375,"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": 8598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941709417.243, "dur": 8.812, + "args": { + "External id": 4549376,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941709421.612, "dur": 4.136, + "args": { + "External id": 4549377,"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": 8600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941709432.049, "dur": 3.464, + "args": { + "External id": 4549378,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941709439.169, "dur": 4.674, + "args": { + "External id": 4549379,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941709585.888, "dur": 4.359, + "args": { + "External id": 4549380,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941709587.256, "dur": 2.750, + "args": { + "External id": 4549381,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941709592.737, "dur": 2.558, + "args": { + "External id": 4549382,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941709594.257, "dur": 0.923, + "args": { + "External id": 4549383,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941709629.399, "dur": 95.664, + "args": { + "External id": 4549384,"Sequence number": 45295771, "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": 8607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941709630.344, "dur": 8.887, + "args": { + "External id": 4549385,"Sequence number": 45295771, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8608 + } + }, + { + "ph": "s", "id": 41, "pid": 1336753, "tid": 1336753, "ts": 1696941709630.344, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941709632.846, "dur": 5.125, + "args": { + "External id": 4549386,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941709634.479, "dur": 3.159, + "args": { + "External id": 4549387,"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": 8610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941709640.415, "dur": 84.378, + "args": { + "External id": 4549388,"Sequence number": 45295772, "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": 8611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941709641.887, "dur": 5.907, + "args": { + "External id": 4549389,"Sequence number": 45295772, "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": 8612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941709644.997, "dur": 2.645, + "args": { + "External id": 4549390,"Sequence number": 45295772, "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": 8613 + } + }, + { + "ph": "s", "id": 40, "pid": 1336753, "tid": 1336753, "ts": 1696941709644.997, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941709648.602, "dur": 68.690, + "args": { + "External id": 4549391,"Sequence number": 45295773, "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": 8614 + } + }, + { + "ph": "s", "id": 39, "pid": 1336753, "tid": 1336753, "ts": 1696941709648.602, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941709719.201, "dur": 4.925, + "args": { + "External id": 4549392,"Sequence number": 45295774, "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": 8615 + } + }, + { + "ph": "s", "id": 38, "pid": 1336753, "tid": 1336753, "ts": 1696941709719.201, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941709733.158, "dur": 70.369, + "args": { + "External id": 4549393,"Sequence number": 45295775, "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": 8616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941709733.875, "dur": 9.292, + "args": { + "External id": 4549394,"Sequence number": 45295775, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8617 + } + }, + { + "ph": "s", "id": 37, "pid": 1336753, "tid": 1336753, "ts": 1696941709733.875, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941709739.206, "dur": 2.754, + "args": { + "External id": 4549395,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941709740.574, "dur": 1.187, + "args": { + "External id": 4549396,"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": 8619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941709743.700, "dur": 59.525, + "args": { + "External id": 4549397,"Sequence number": 45295776, "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": 8620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941709744.901, "dur": 6.432, + "args": { + "External id": 4549398,"Sequence number": 45295776, "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": 8621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941709747.722, "dur": 3.459, + "args": { + "External id": 4549399,"Sequence number": 45295776, "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": 8622 + } + }, + { + "ph": "s", "id": 36, "pid": 1336753, "tid": 1336753, "ts": 1696941709747.722, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941709752.126, "dur": 46.755, + "args": { + "External id": 4549400,"Sequence number": 45295777, "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": 8623 + } + }, + { + "ph": "s", "id": 35, "pid": 1336753, "tid": 1336753, "ts": 1696941709752.126, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941709800.691, "dur": 2.147, + "args": { + "External id": 4549401,"Sequence number": 45295778, "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": 8624 + } + }, + { + "ph": "s", "id": 34, "pid": 1336753, "tid": 1336753, "ts": 1696941709800.691, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941709822.279, "dur": 138.895, + "args": { + "External id": 4549402,"Sequence number": 45295779, "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": 8625 + } + }, + { + "ph": "s", "id": 33, "pid": 1336753, "tid": 1336753, "ts": 1696941709822.279, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941709859.692, "dur": 4.303, + "args": { + "External id": 4549403,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941709894.549, "dur": 56.969, + "args": { + "External id": 4549404,"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": 8627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941709895.347, "dur": 6.288, + "args": { + "External id": 4549405,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 8628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941709896.199, "dur": 4.623, + "args": { + "External id": 4549406,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 8629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941709898.104, "dur": 2.507, + "args": { + "External id": 4549407,"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": 8630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941709902.286, "dur": 48.995, + "args": { + "External id": 4549408,"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": 8631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1696941709903.402, "dur": 5.445, + "args": { + "External id": 4549409,"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": 8632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941709906.858, "dur": 1.843, + "args": { + "External id": 4549410,"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": 8633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941709909.327, "dur": 38.776, + "args": { + "External id": 4549411,"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": 8634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1696941709949.759, "dur": 0.883, + "args": { + "External id": 4549412,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1696941709968.854, "dur": 61.284, + "args": { + "External id": 4549413,"Sequence number": 45295780, "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": 8636 + } + }, + { + "ph": "s", "id": 32, "pid": 1336753, "tid": 1336753, "ts": 1696941709968.854, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 1336753, "tid": 1336753, + "ts": 1696941710051.351, "dur": 47.157, + "args": { + "External id": 4549414,"Sequence number": 45295781, "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": 8637 + } + }, + { + "ph": "s", "id": 31, "pid": 1336753, "tid": 1336753, "ts": 1696941710051.351, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 1336753, "tid": 1336753, + "ts": 1696941710062.126, "dur": 31.653, + "args": { + "External id": 4549415,"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": 8638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941710095.324, "dur": 1.325, + "args": { + "External id": 4549416,"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": 8639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336753, "tid": 1336753, + "ts": 1696941710138.764, "dur": 51.858, + "args": { + "External id": 4549417,"Record function id": 0, "Ev Idx": 8640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 1336753, "tid": 1336753, + "ts": 1696941710192.038, "dur": 204.981, + "args": { + "External id": 4549418,"Record function id": 0, "Ev Idx": 8641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941710231.253, "dur": 157.724, + "args": { + "External id": 4549419,"Sequence number": 45295782, "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": 8642 + } + }, + { + "ph": "s", "id": 30, "pid": 1336753, "tid": 1336753, "ts": 1696941710231.253, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1696941710303.445, "dur": 45.373, + "args": { + "External id": 4549420,"kernel_hash": "cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/ml/cmljljlwjilefo6ueuqn5gaz5uvsdhhmauseg2vxhp3egffs57dc.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": 8643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1696941710488.259, "dur": 56.287, + "args": { + "External id": 4549421,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 8644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941710491.011, "dur": 5.223, + "args": { + "External id": 4549422,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941710499.616, "dur": 44.598, + "args": { + "External id": 4549423,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 8646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941710502.787, "dur": 40.454, + "args": { + "External id": 4549424,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 8647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1696941710551.412, "dur": 22.995, + "args": { + "External id": 4549425,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 8648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941710552.460, "dur": 3.316, + "args": { + "External id": 4549426,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941710558.956, "dur": 15.179, + "args": { + "External id": 4549427,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 8650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941710559.721, "dur": 14.029, + "args": { + "External id": 4549428,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 8651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1696941710577.885, "dur": 16.423, + "args": { + "External id": 4549429,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 8652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941710578.612, "dur": 2.774, + "args": { + "External id": 4549430,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941710582.303, "dur": 11.743, + "args": { + "External id": 4549431,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 8654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941710582.896, "dur": 10.778, + "args": { + "External id": 4549432,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 8655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941710603.180, "dur": 0.694, + "args": { + "External id": 4549433,"Sequence number": 45295783, "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": 8656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 1336753, "tid": 1336753, + "ts": 1696941710612.202, "dur": 11.626, + "args": { + "External id": 4549434,"Sequence number": 45295783, "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": 8657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710619.819, "dur": 2.040, + "args": { + "External id": 4549435,"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": 8658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941710629.926, "dur": 6.888, + "args": { + "External id": 4549436,"Sequence number": 45295783, "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": 8659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710634.213, "dur": 0.995, + "args": { + "External id": 4549437,"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": 8660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941710638.055, "dur": 3.684, + "args": { + "External id": 4549438,"Sequence number": 45295783, "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": 8661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710640.231, "dur": 0.734, + "args": { + "External id": 4549439,"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": 8662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941710643.180, "dur": 3.401, + "args": { + "External id": 4549440,"Sequence number": 45295783, "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": 8663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710645.048, "dur": 0.978, + "args": { + "External id": 4549441,"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": 8664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941710649.784, "dur": 3.119, + "args": { + "External id": 4549442,"Sequence number": 45295783, "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": 8665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710651.798, "dur": 0.561, + "args": { + "External id": 4549443,"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": 8666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941710653.813, "dur": 3.653, + "args": { + "External id": 4549444,"Sequence number": 45295783, "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": 8667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710655.973, "dur": 0.746, + "args": { + "External id": 4549445,"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": 8668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941710658.743, "dur": 3.263, + "args": { + "External id": 4549446,"Sequence number": 45295783, "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": 8669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710660.764, "dur": 0.736, + "args": { + "External id": 4549447,"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": 8670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941710667.025, "dur": 4.957, + "args": { + "External id": 4549448,"Sequence number": 45295783, "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": 8671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710670.601, "dur": 0.562, + "args": { + "External id": 4549449,"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": 8672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941710676.468, "dur": 3.519, + "args": { + "External id": 4549450,"Sequence number": 45295783, "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": 8673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710678.375, "dur": 1.029, + "args": { + "External id": 4549451,"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": 8674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1696941710685.310, "dur": 7.131, + "args": { + "External id": 4549452,"Sequence number": 45295783, "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": 8675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710690.413, "dur": 0.912, + "args": { + "External id": 4549453,"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": 8676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941710693.635, "dur": 3.332, + "args": { + "External id": 4549454,"Sequence number": 45295783, "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": 8677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710695.719, "dur": 0.693, + "args": { + "External id": 4549455,"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": 8678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941710699.564, "dur": 8.583, + "args": { + "External id": 4549456,"Sequence number": 45295783, "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": 8679 + } + }, + { + "ph": "s", "id": 29, "pid": 1336753, "tid": 1336753, "ts": 1696941710699.564, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710705.514, "dur": 1.027, + "args": { + "External id": 4549457,"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": 8680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941710709.176, "dur": 5.511, + "args": { + "External id": 4549458,"Sequence number": 45295784, "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": 8681 + } + }, + { + "ph": "s", "id": 28, "pid": 1336753, "tid": 1336753, "ts": 1696941710709.176, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710713.035, "dur": 0.915, + "args": { + "External id": 4549459,"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": 8682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1696941710715.723, "dur": 8.175, + "args": { + "External id": 4549460,"Sequence number": 45295785, "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": 8683 + } + }, + { + "ph": "s", "id": 27, "pid": 1336753, "tid": 1336753, "ts": 1696941710715.723, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710722.261, "dur": 0.791, + "args": { + "External id": 4549461,"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": 8684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941710724.816, "dur": 7.086, + "args": { + "External id": 4549462,"Sequence number": 45295786, "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": 8685 + } + }, + { + "ph": "s", "id": 26, "pid": 1336753, "tid": 1336753, "ts": 1696941710724.816, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710728.395, "dur": 2.760, + "args": { + "External id": 4549463,"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": 8686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1696941710736.135, "dur": 39.415, + "args": { + "External id": 4549464,"Sequence number": 45295787, "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": 8687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1696941710738.242, "dur": 37.004, + "args": { + "External id": 4549465,"Sequence number": 45295787, "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": 8688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941710741.170, "dur": 6.622, + "args": { + "External id": 4549466,"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": 8689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941710743.395, "dur": 3.664, + "args": { + "External id": 4549467,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941710749.360, "dur": 25.373, + "args": { + "External id": 4549468,"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": 8691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941710802.945, "dur": 4.953, + "args": { + "External id": 4549469,"Sequence number": 45295787, "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": 8692 + } + }, + { + "ph": "s", "id": 25, "pid": 1336753, "tid": 1336753, "ts": 1696941710802.945, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941710810.136, "dur": 2.053, + "args": { + "External id": 4549470,"Sequence number": 45295788, "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": 8693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941710841.278, "dur": 72766.240, + "args": { + "External id": 4549471,"Sequence number": 45295788, "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": 8694 + } + }, + { + "ph": "s", "id": 24, "pid": 1336753, "tid": 1336753, "ts": 1696941710841.278, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1696941710855.371, "dur": 28.547, + "args": { + "External id": 4549472,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1696941710856.082, "dur": 27.635, + "args": { + "External id": 4549473,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941710857.122, "dur": 7.583, + "args": { + "External id": 4549474,"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": 8697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941710858.356, "dur": 5.903, + "args": { + "External id": 4549475,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941710865.432, "dur": 17.612, + "args": { + "External id": 4549476,"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": 8699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941710901.931, "dur": 25.462, + "args": { + "External id": 4549477,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941710903.323, "dur": 6.643, + "args": { + "External id": 4549478,"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": 8701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710905.739, "dur": 3.876, + "args": { + "External id": 4549479,"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": 8702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941710910.846, "dur": 16.347, + "args": { + "External id": 4549480,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 8703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941710911.886, "dur": 14.899, + "args": { + "External id": 4549481,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941710930.916, "dur": 31.576, + "args": { + "External id": 4549482,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 8705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941710931.732, "dur": 7.680, + "args": { + "External id": 4549483,"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": 8706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941710935.645, "dur": 3.517, + "args": { + "External id": 4549484,"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": 8707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941710949.497, "dur": 12.733, + "args": { + "External id": 4549485,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941710950.100, "dur": 11.849, + "args": { + "External id": 4549486,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[32000, 2048], []], "Ev Idx": 8709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1696941710966.232, "dur": 52.738, + "args": { + "External id": 4549487,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 8710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941710967.502, "dur": 5.195, + "args": { + "External id": 4549488,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941710973.279, "dur": 45.378, + "args": { + "External id": 4549489,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 8712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941710973.952, "dur": 43.381, + "args": { + "External id": 4549490,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 8713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336753, "tid": 1336753, + "ts": 1696941711030.854, "dur": 32.594, + "args": { + "External id": 4549491,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 8714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941711067.547, "dur": 63.000, + "args": { + "External id": 4549492,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 8715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941711072.023, "dur": 58.124, + "args": { + "External id": 4549493,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941711077.987, "dur": 1.564, + "args": { + "External id": 4549494,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941711081.456, "dur": 27.200, + "args": { + "External id": 4549495,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941711083.079, "dur": 25.375, + "args": { + "External id": 4549496,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 8719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941711087.879, "dur": 3.766, + "args": { + "External id": 4549497,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941711092.389, "dur": 15.574, + "args": { + "External id": 4549498,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 8721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336753, "tid": 1336753, + "ts": 1696941711135.475, "dur": 66333.744, + "args": { + "External id": 4549499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 8722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336753, "tid": 1336753, + "ts": 1696941711138.037, "dur": 66329.034, + "args": { + "External id": 4549500,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 8723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941777488.122, "dur": 12.999, + "args": { + "External id": 4549501,"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": 8724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941777496.507, "dur": 1.741, + "args": { + "External id": 4549502,"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": 8725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941777506.973, "dur": 143.725, + "args": { + "External id": 4549503,"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": 8726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941777508.774, "dur": 14.505, + "args": { + "External id": 4549504,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941777514.368, "dur": 8.003, + "args": { + "External id": 4549505,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941777521.142, "dur": 0.965, + "args": { + "External id": 4549506,"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": 8729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941777525.243, "dur": 124.492, + "args": { + "External id": 4549507,"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": 8730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941777537.748, "dur": 110.812, + "args": { + "External id": 4549508,"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": 8731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941777655.863, "dur": 5.706, + "args": { + "External id": 4549509,"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": 8732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941777658.313, "dur": 1.049, + "args": { + "External id": 4549510,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941777672.224, "dur": 4.447, + "args": { + "External id": 4549511,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941777691.574, "dur": 8.441, + "args": { + "External id": 4549512,"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": 8735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941777694.340, "dur": 5.409, + "args": { + "External id": 4549513,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941777854.687, "dur": 303.111, + "args": { + "External id": 4549514,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941777860.188, "dur": 2.246, + "args": { + "External id": 4549515,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941777864.922, "dur": 292.146, + "args": { + "External id": 4549516,"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": 8739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941777867.559, "dur": 0.539, + "args": { + "External id": 4549517,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941777873.384, "dur": 31.788, + "args": { + "External id": 4549518,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941777907.719, "dur": 7.313, + "args": { + "External id": 4549519,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941777913.385, "dur": 1.121, + "args": { + "External id": 4549520,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941777917.420, "dur": 28.826, + "args": { + "External id": 4549521,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941777918.478, "dur": 1.632, + "args": { + "External id": 4549522,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941777922.088, "dur": 23.882, + "args": { + "External id": 4549523,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941777927.274, "dur": 3.324, + "args": { + "External id": 4549524,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941777949.117, "dur": 27.482, + "args": { + "External id": 4549525,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941777979.497, "dur": 66.180, + "args": { + "External id": 4549526,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941778050.320, "dur": 19.187, + "args": { + "External id": 4549527,"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": 8750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941778074.226, "dur": 17.937, + "args": { + "External id": 4549528,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941778095.276, "dur": 27.317, + "args": { + "External id": 4549529,"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": 8752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941778098.213, "dur": 2.070, + "args": { + "External id": 4549530,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941778102.966, "dur": 1.049, + "args": { + "External id": 4549531,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941778124.867, "dur": 16.132, + "args": { + "External id": 4549532,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941778143.480, "dur": 12.491, + "args": { + "External id": 4549533,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941778168.720, "dur": 2.718, + "args": { + "External id": 4549534,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941778179.572, "dur": 4.289, + "args": { + "External id": 4549535,"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": 8758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941778181.918, "dur": 0.766, + "args": { + "External id": 4549536,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941778275.960, "dur": 83.052, + "args": { + "External id": 4549537,"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": 8760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941778365.244, "dur": 4.918, + "args": { + "External id": 4549538,"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": 8761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941778368.086, "dur": 0.860, + "args": { + "External id": 4549539,"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": 8762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941778371.954, "dur": 34.047, + "args": { + "External id": 4549540,"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": 8763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941778411.492, "dur": 8.819, + "args": { + "External id": 4549541,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941778415.870, "dur": 3.676, + "args": { + "External id": 4549542,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941778417.899, "dur": 1.425, + "args": { + "External id": 4549543,"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": 8766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941778424.708, "dur": 51.547, + "args": { + "External id": 4549544,"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": 8767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941778426.184, "dur": 49.298, + "args": { + "External id": 4549545,"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": 8768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941778481.941, "dur": 18.798, + "args": { + "External id": 4549546,"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": 8769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941778506.994, "dur": 6.416, + "args": { + "External id": 4549547,"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": 8770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941778511.779, "dur": 0.752, + "args": { + "External id": 4549548,"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": 8771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941778517.909, "dur": 72.369, + "args": { + "External id": 4549549,"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": 8772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941778519.001, "dur": 3.630, + "args": { + "External id": 4549550,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941778519.988, "dur": 2.069, + "args": { + "External id": 4549551,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941778521.059, "dur": 0.834, + "args": { + "External id": 4549552,"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": 8775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941778523.550, "dur": 66.185, + "args": { + "External id": 4549553,"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": 8776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941778524.570, "dur": 64.319, + "args": { + "External id": 4549554,"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": 8777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941778598.703, "dur": 5.139, + "args": { + "External id": 4549555,"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": 8778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941778601.443, "dur": 0.899, + "args": { + "External id": 4549556,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941778610.832, "dur": 1.925, + "args": { + "External id": 4549557,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941778621.603, "dur": 10.225, + "args": { + "External id": 4549558,"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": 8781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941778623.948, "dur": 7.586, + "args": { + "External id": 4549559,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941778733.715, "dur": 203.380, + "args": { + "External id": 4549560,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941778736.090, "dur": 2.350, + "args": { + "External id": 4549561,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941778740.059, "dur": 196.477, + "args": { + "External id": 4549562,"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": 8785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941778741.989, "dur": 0.290, + "args": { + "External id": 4549563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941778743.364, "dur": 25.699, + "args": { + "External id": 4549564,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941778770.767, "dur": 3.850, + "args": { + "External id": 4549565,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941778773.073, "dur": 0.956, + "args": { + "External id": 4549566,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941778776.010, "dur": 30.473, + "args": { + "External id": 4549567,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941778777.180, "dur": 1.945, + "args": { + "External id": 4549568,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941778783.630, "dur": 22.437, + "args": { + "External id": 4549569,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941778788.830, "dur": 2.896, + "args": { + "External id": 4549570,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941778808.277, "dur": 22.215, + "args": { + "External id": 4549571,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941778832.154, "dur": 15.827, + "args": { + "External id": 4549572,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941778850.967, "dur": 15.305, + "args": { + "External id": 4549573,"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": 8796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941778867.735, "dur": 13.854, + "args": { + "External id": 4549574,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941778883.616, "dur": 23.718, + "args": { + "External id": 4549575,"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": 8798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941778885.966, "dur": 1.622, + "args": { + "External id": 4549576,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941778891.976, "dur": 0.850, + "args": { + "External id": 4549577,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941778908.807, "dur": 13.757, + "args": { + "External id": 4549578,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941778923.732, "dur": 11.527, + "args": { + "External id": 4549579,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941778944.150, "dur": 1.941, + "args": { + "External id": 4549580,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941778955.304, "dur": 3.410, + "args": { + "External id": 4549581,"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": 8804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941778957.539, "dur": 0.359, + "args": { + "External id": 4549582,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941779082.538, "dur": 60.101, + "args": { + "External id": 4549583,"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": 8806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941779148.191, "dur": 8.412, + "args": { + "External id": 4549584,"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": 8807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941779153.298, "dur": 1.682, + "args": { + "External id": 4549585,"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": 8808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941779158.161, "dur": 32.235, + "args": { + "External id": 4549586,"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": 8809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941779195.146, "dur": 5.230, + "args": { + "External id": 4549587,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941779196.598, "dur": 3.066, + "args": { + "External id": 4549588,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941779198.437, "dur": 1.018, + "args": { + "External id": 4549589,"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": 8812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941779203.075, "dur": 43.794, + "args": { + "External id": 4549590,"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": 8813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941779204.267, "dur": 41.893, + "args": { + "External id": 4549591,"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": 8814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941779253.633, "dur": 17.754, + "args": { + "External id": 4549592,"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": 8815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941779277.215, "dur": 3.782, + "args": { + "External id": 4549593,"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": 8816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941779279.295, "dur": 0.839, + "args": { + "External id": 4549594,"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": 8817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941779285.307, "dur": 53.479, + "args": { + "External id": 4549595,"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": 8818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941779286.142, "dur": 7.905, + "args": { + "External id": 4549596,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941779286.880, "dur": 6.562, + "args": { + "External id": 4549597,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941779290.549, "dur": 2.715, + "args": { + "External id": 4549598,"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": 8821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941779294.780, "dur": 43.499, + "args": { + "External id": 4549599,"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": 8822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941779295.515, "dur": 42.107, + "args": { + "External id": 4549600,"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": 8823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941779342.373, "dur": 4.260, + "args": { + "External id": 4549601,"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": 8824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941779344.391, "dur": 1.026, + "args": { + "External id": 4549602,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941779352.665, "dur": 1.621, + "args": { + "External id": 4549603,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941779362.415, "dur": 8.171, + "args": { + "External id": 4549604,"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": 8827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941779366.613, "dur": 3.731, + "args": { + "External id": 4549605,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941779464.494, "dur": 291.225, + "args": { + "External id": 4549606,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941779466.844, "dur": 2.312, + "args": { + "External id": 4549607,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941779470.557, "dur": 284.584, + "args": { + "External id": 4549608,"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": 8831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941779471.616, "dur": 0.361, + "args": { + "External id": 4549609,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941779475.270, "dur": 24.161, + "args": { + "External id": 4549610,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941779501.374, "dur": 3.230, + "args": { + "External id": 4549611,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941779503.516, "dur": 0.829, + "args": { + "External id": 4549612,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941779505.561, "dur": 46.270, + "args": { + "External id": 4549613,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941779506.753, "dur": 3.712, + "args": { + "External id": 4549614,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941779514.016, "dur": 37.245, + "args": { + "External id": 4549615,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941779516.610, "dur": 2.586, + "args": { + "External id": 4549616,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941779554.075, "dur": 34.094, + "args": { + "External id": 4549617,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941779589.871, "dur": 45.378, + "args": { + "External id": 4549618,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941779637.893, "dur": 28.757, + "args": { + "External id": 4549619,"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": 8842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941779668.096, "dur": 26.930, + "args": { + "External id": 4549620,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941779696.903, "dur": 27.971, + "args": { + "External id": 4549621,"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": 8844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941779698.928, "dur": 1.731, + "args": { + "External id": 4549622,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941779704.652, "dur": 0.888, + "args": { + "External id": 4549623,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941779726.161, "dur": 14.297, + "args": { + "External id": 4549624,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941779741.761, "dur": 12.303, + "args": { + "External id": 4549625,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941779763.970, "dur": 2.134, + "args": { + "External id": 4549626,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941779775.941, "dur": 3.554, + "args": { + "External id": 4549627,"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": 8850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941779778.088, "dur": 0.558, + "args": { + "External id": 4549628,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941779852.294, "dur": 59.031, + "args": { + "External id": 4549629,"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": 8852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941779916.306, "dur": 7.437, + "args": { + "External id": 4549630,"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": 8853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941779921.606, "dur": 1.135, + "args": { + "External id": 4549631,"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": 8854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941779925.105, "dur": 25.843, + "args": { + "External id": 4549632,"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": 8855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941780029.777, "dur": 10.827, + "args": { + "External id": 4549633,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941780032.513, "dur": 6.888, + "args": { + "External id": 4549634,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941780035.237, "dur": 3.604, + "args": { + "External id": 4549635,"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": 8858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941780044.280, "dur": 55.879, + "args": { + "External id": 4549636,"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": 8859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941780048.174, "dur": 50.955, + "args": { + "External id": 4549637,"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": 8860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941780104.766, "dur": 18.261, + "args": { + "External id": 4549638,"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": 8861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941780130.019, "dur": 4.314, + "args": { + "External id": 4549639,"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": 8862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941780132.633, "dur": 0.797, + "args": { + "External id": 4549640,"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": 8863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941780138.843, "dur": 53.513, + "args": { + "External id": 4549641,"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": 8864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941780139.794, "dur": 5.898, + "args": { + "External id": 4549642,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941780140.563, "dur": 4.535, + "args": { + "External id": 4549643,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941780144.230, "dur": 0.529, + "args": { + "External id": 4549644,"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": 8867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941780146.369, "dur": 45.439, + "args": { + "External id": 4549645,"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": 8868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941780147.018, "dur": 44.177, + "args": { + "External id": 4549646,"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": 8869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941780196.192, "dur": 4.133, + "args": { + "External id": 4549647,"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": 8870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941780198.392, "dur": 0.674, + "args": { + "External id": 4549648,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941780207.251, "dur": 1.569, + "args": { + "External id": 4549649,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941780219.103, "dur": 6.822, + "args": { + "External id": 4549650,"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": 8873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941780221.000, "dur": 4.703, + "args": { + "External id": 4549651,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941780321.834, "dur": 194.963, + "args": { + "External id": 4549652,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941780324.080, "dur": 2.519, + "args": { + "External id": 4549653,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941780330.899, "dur": 185.355, + "args": { + "External id": 4549654,"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": 8877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941780332.161, "dur": 0.345, + "args": { + "External id": 4549655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941780335.795, "dur": 23.216, + "args": { + "External id": 4549656,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941780360.769, "dur": 4.871, + "args": { + "External id": 4549657,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941780362.571, "dur": 2.734, + "args": { + "External id": 4549658,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941780366.708, "dur": 22.549, + "args": { + "External id": 4549659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941780367.744, "dur": 1.348, + "args": { + "External id": 4549660,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941780370.280, "dur": 18.664, + "args": { + "External id": 4549661,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941780372.944, "dur": 2.843, + "args": { + "External id": 4549662,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941780390.768, "dur": 22.097, + "args": { + "External id": 4549663,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941780414.416, "dur": 15.140, + "args": { + "External id": 4549664,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941780432.411, "dur": 14.824, + "args": { + "External id": 4549665,"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": 8888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941780451.372, "dur": 13.148, + "args": { + "External id": 4549666,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941780466.252, "dur": 22.333, + "args": { + "External id": 4549667,"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": 8890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941780468.012, "dur": 1.677, + "args": { + "External id": 4549668,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941780471.762, "dur": 2.408, + "args": { + "External id": 4549669,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941780489.997, "dur": 12.940, + "args": { + "External id": 4549670,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941780504.021, "dur": 11.072, + "args": { + "External id": 4549671,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941780541.562, "dur": 2.744, + "args": { + "External id": 4549672,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941780555.300, "dur": 3.981, + "args": { + "External id": 4549673,"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": 8896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941780557.662, "dur": 0.626, + "args": { + "External id": 4549674,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941780631.539, "dur": 53.656, + "args": { + "External id": 4549675,"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": 8898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941780689.969, "dur": 5.101, + "args": { + "External id": 4549676,"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": 8899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941780692.950, "dur": 1.068, + "args": { + "External id": 4549677,"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": 8900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941780696.746, "dur": 27.221, + "args": { + "External id": 4549678,"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": 8901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941780729.185, "dur": 8.177, + "args": { + "External id": 4549679,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941780730.721, "dur": 5.959, + "args": { + "External id": 4549680,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941780734.998, "dur": 1.466, + "args": { + "External id": 4549681,"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": 8904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941780739.844, "dur": 40.286, + "args": { + "External id": 4549682,"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": 8905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941780740.694, "dur": 38.782, + "args": { + "External id": 4549683,"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": 8906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941780783.812, "dur": 15.663, + "args": { + "External id": 4549684,"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": 8907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941780804.436, "dur": 3.599, + "args": { + "External id": 4549685,"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": 8908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941780806.473, "dur": 0.779, + "args": { + "External id": 4549686,"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": 8909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941780814.235, "dur": 47.902, + "args": { + "External id": 4549687,"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": 8910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941780815.423, "dur": 3.686, + "args": { + "External id": 4549688,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941780816.184, "dur": 2.423, + "args": { + "External id": 4549689,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941780817.311, "dur": 1.176, + "args": { + "External id": 4549690,"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": 8913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941780819.634, "dur": 42.035, + "args": { + "External id": 4549691,"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": 8914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941780820.069, "dur": 40.896, + "args": { + "External id": 4549692,"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": 8915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941780865.902, "dur": 4.000, + "args": { + "External id": 4549693,"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": 8916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941780868.086, "dur": 0.780, + "args": { + "External id": 4549694,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941780878.130, "dur": 1.614, + "args": { + "External id": 4549695,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941780887.218, "dur": 6.133, + "args": { + "External id": 4549696,"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": 8919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941780889.046, "dur": 4.083, + "args": { + "External id": 4549697,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941780972.141, "dur": 246.131, + "args": { + "External id": 4549698,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941780976.319, "dur": 1.935, + "args": { + "External id": 4549699,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941780979.938, "dur": 237.793, + "args": { + "External id": 4549700,"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": 8923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941781017.962, "dur": 0.403, + "args": { + "External id": 4549701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941781019.836, "dur": 25.407, + "args": { + "External id": 4549702,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941781047.141, "dur": 6.295, + "args": { + "External id": 4549703,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941781051.802, "dur": 1.313, + "args": { + "External id": 4549704,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941781054.454, "dur": 22.606, + "args": { + "External id": 4549705,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941781055.659, "dur": 2.056, + "args": { + "External id": 4549706,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941781058.920, "dur": 17.880, + "args": { + "External id": 4549707,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941781061.568, "dur": 2.773, + "args": { + "External id": 4549708,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941781078.367, "dur": 22.224, + "args": { + "External id": 4549709,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941781102.021, "dur": 23.253, + "args": { + "External id": 4549710,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941781128.134, "dur": 17.037, + "args": { + "External id": 4549711,"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": 8934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941781149.191, "dur": 14.032, + "args": { + "External id": 4549712,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941781165.084, "dur": 21.474, + "args": { + "External id": 4549713,"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": 8936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941781166.858, "dur": 1.903, + "args": { + "External id": 4549714,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941781170.979, "dur": 0.921, + "args": { + "External id": 4549715,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941781187.731, "dur": 12.987, + "args": { + "External id": 4549716,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941781201.834, "dur": 12.497, + "args": { + "External id": 4549717,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941781225.989, "dur": 2.203, + "args": { + "External id": 4549718,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941781237.148, "dur": 3.624, + "args": { + "External id": 4549719,"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": 8942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941781239.723, "dur": 0.288, + "args": { + "External id": 4549720,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941781305.213, "dur": 54.246, + "args": { + "External id": 4549721,"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": 8944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941781364.004, "dur": 4.293, + "args": { + "External id": 4549722,"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": 8945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941781366.500, "dur": 0.839, + "args": { + "External id": 4549723,"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": 8946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941781369.811, "dur": 24.384, + "args": { + "External id": 4549724,"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": 8947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941781398.977, "dur": 7.455, + "args": { + "External id": 4549725,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941781402.767, "dur": 3.047, + "args": { + "External id": 4549726,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941781404.629, "dur": 1.017, + "args": { + "External id": 4549727,"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": 8950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941781409.301, "dur": 39.746, + "args": { + "External id": 4549728,"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": 8951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941781410.765, "dur": 37.729, + "args": { + "External id": 4549729,"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": 8952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941781452.641, "dur": 15.085, + "args": { + "External id": 4549730,"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": 8953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941781472.514, "dur": 6.316, + "args": { + "External id": 4549731,"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": 8954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941781477.011, "dur": 1.035, + "args": { + "External id": 4549732,"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": 8955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941781482.532, "dur": 64.163, + "args": { + "External id": 4549733,"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": 8956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941781483.490, "dur": 3.944, + "args": { + "External id": 4549734,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941781484.488, "dur": 2.431, + "args": { + "External id": 4549735,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941781485.879, "dur": 0.907, + "args": { + "External id": 4549736,"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": 8959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941781487.943, "dur": 58.203, + "args": { + "External id": 4549737,"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": 8960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941781488.703, "dur": 56.452, + "args": { + "External id": 4549738,"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": 8961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941781554.449, "dur": 5.145, + "args": { + "External id": 4549739,"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": 8962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941781557.142, "dur": 1.260, + "args": { + "External id": 4549740,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941781576.566, "dur": 1.638, + "args": { + "External id": 4549741,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941781585.943, "dur": 8.295, + "args": { + "External id": 4549742,"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": 8965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941781587.584, "dur": 6.343, + "args": { + "External id": 4549743,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941781685.746, "dur": 199.123, + "args": { + "External id": 4549744,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941781687.590, "dur": 2.100, + "args": { + "External id": 4549745,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941781691.506, "dur": 192.966, + "args": { + "External id": 4549746,"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": 8969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941781703.005, "dur": 0.243, + "args": { + "External id": 4549747,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941781707.377, "dur": 22.698, + "args": { + "External id": 4549748,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941781731.929, "dur": 4.809, + "args": { + "External id": 4549749,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941781733.945, "dur": 2.498, + "args": { + "External id": 4549750,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941781737.659, "dur": 24.648, + "args": { + "External id": 4549751,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941781741.376, "dur": 1.455, + "args": { + "External id": 4549752,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941781743.850, "dur": 18.220, + "args": { + "External id": 4549753,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941781746.256, "dur": 2.709, + "args": { + "External id": 4549754,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941781763.813, "dur": 20.971, + "args": { + "External id": 4549755,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941781786.070, "dur": 14.432, + "args": { + "External id": 4549756,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941781802.956, "dur": 14.598, + "args": { + "External id": 4549757,"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": 8980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941781818.828, "dur": 13.106, + "args": { + "External id": 4549758,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941781833.921, "dur": 23.206, + "args": { + "External id": 4549759,"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": 8982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941781835.960, "dur": 1.814, + "args": { + "External id": 4549760,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941781841.934, "dur": 1.208, + "args": { + "External id": 4549761,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941781858.660, "dur": 13.045, + "args": { + "External id": 4549762,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941781872.538, "dur": 10.911, + "args": { + "External id": 4549763,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941781890.712, "dur": 1.637, + "args": { + "External id": 4549764,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941781899.797, "dur": 3.817, + "args": { + "External id": 4549765,"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": 8988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941781902.218, "dur": 0.647, + "args": { + "External id": 4549766,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941781963.857, "dur": 91.310, + "args": { + "External id": 4549767,"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": 8990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941782061.944, "dur": 12.748, + "args": { + "External id": 4549768,"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": 8991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941782067.219, "dur": 5.955, + "args": { + "External id": 4549769,"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": 8992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941782076.014, "dur": 26.808, + "args": { + "External id": 4549770,"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": 8993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941782108.084, "dur": 5.455, + "args": { + "External id": 4549771,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941782109.625, "dur": 3.174, + "args": { + "External id": 4549772,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941782111.638, "dur": 0.947, + "args": { + "External id": 4549773,"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": 8996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941782116.514, "dur": 45.456, + "args": { + "External id": 4549774,"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": 8997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941782120.193, "dur": 41.130, + "args": { + "External id": 4549775,"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": 8998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941782165.647, "dur": 16.089, + "args": { + "External id": 4549776,"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": 8999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941782187.204, "dur": 3.858, + "args": { + "External id": 4549777,"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": 9000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941782189.496, "dur": 0.811, + "args": { + "External id": 4549778,"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": 9001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941782194.867, "dur": 49.771, + "args": { + "External id": 4549779,"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": 9002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941782195.941, "dur": 6.090, + "args": { + "External id": 4549780,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941782196.874, "dur": 4.617, + "args": { + "External id": 4549781,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941782200.641, "dur": 0.765, + "args": { + "External id": 4549782,"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": 9005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941782202.677, "dur": 41.540, + "args": { + "External id": 4549783,"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": 9006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941782203.388, "dur": 40.185, + "args": { + "External id": 4549784,"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": 9007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941782248.404, "dur": 3.719, + "args": { + "External id": 4549785,"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": 9008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941782250.354, "dur": 0.759, + "args": { + "External id": 4549786,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941782258.204, "dur": 1.377, + "args": { + "External id": 4549787,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941782267.039, "dur": 8.730, + "args": { + "External id": 4549788,"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": 9011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941782271.199, "dur": 4.328, + "args": { + "External id": 4549789,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941782353.541, "dur": 209.994, + "args": { + "External id": 4549790,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941782355.734, "dur": 4.119, + "args": { + "External id": 4549791,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941782360.966, "dur": 202.056, + "args": { + "External id": 4549792,"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": 9015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941782362.193, "dur": 0.267, + "args": { + "External id": 4549793,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941782363.939, "dur": 21.144, + "args": { + "External id": 4549794,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941782386.552, "dur": 6.333, + "args": { + "External id": 4549795,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941782391.352, "dur": 1.164, + "args": { + "External id": 4549796,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941782393.792, "dur": 23.259, + "args": { + "External id": 4549797,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941782397.005, "dur": 1.728, + "args": { + "External id": 4549798,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941782399.745, "dur": 17.080, + "args": { + "External id": 4549799,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941782402.186, "dur": 2.382, + "args": { + "External id": 4549800,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941782418.370, "dur": 21.927, + "args": { + "External id": 4549801,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941782441.526, "dur": 13.736, + "args": { + "External id": 4549802,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941782457.471, "dur": 14.503, + "args": { + "External id": 4549803,"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": 9026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941782473.141, "dur": 12.597, + "args": { + "External id": 4549804,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941782487.351, "dur": 23.861, + "args": { + "External id": 4549805,"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": 9028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941782489.034, "dur": 1.624, + "args": { + "External id": 4549806,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941782494.495, "dur": 2.682, + "args": { + "External id": 4549807,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941782512.355, "dur": 13.137, + "args": { + "External id": 4549808,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941782541.368, "dur": 20.148, + "args": { + "External id": 4549809,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941782570.836, "dur": 2.640, + "args": { + "External id": 4549810,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941782581.952, "dur": 3.770, + "args": { + "External id": 4549811,"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": 9034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941782584.116, "dur": 0.641, + "args": { + "External id": 4549812,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941782649.456, "dur": 54.485, + "args": { + "External id": 4549813,"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": 9036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941782710.643, "dur": 4.725, + "args": { + "External id": 4549814,"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": 9037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941782713.173, "dur": 1.056, + "args": { + "External id": 4549815,"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": 9038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941782717.001, "dur": 24.953, + "args": { + "External id": 4549816,"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": 9039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941782745.799, "dur": 5.467, + "args": { + "External id": 4549817,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941782747.485, "dur": 3.250, + "args": { + "External id": 4549818,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941782749.121, "dur": 1.426, + "args": { + "External id": 4549819,"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": 9042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941782756.319, "dur": 40.078, + "args": { + "External id": 4549820,"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": 9043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941782757.526, "dur": 38.238, + "args": { + "External id": 4549821,"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": 9044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941782799.640, "dur": 15.048, + "args": { + "External id": 4549822,"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": 9045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941782819.578, "dur": 4.063, + "args": { + "External id": 4549823,"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": 9046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941782821.836, "dur": 1.140, + "args": { + "External id": 4549824,"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": 9047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941782826.828, "dur": 49.701, + "args": { + "External id": 4549825,"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": 9048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941782827.744, "dur": 5.759, + "args": { + "External id": 4549826,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941782830.986, "dur": 1.981, + "args": { + "External id": 4549827,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941782831.991, "dur": 0.867, + "args": { + "External id": 4549828,"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": 9051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941782834.087, "dur": 42.079, + "args": { + "External id": 4549829,"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": 9052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941782834.601, "dur": 40.975, + "args": { + "External id": 4549830,"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": 9053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941782880.025, "dur": 3.662, + "args": { + "External id": 4549831,"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": 9054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941782881.920, "dur": 0.760, + "args": { + "External id": 4549832,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941782890.891, "dur": 1.389, + "args": { + "External id": 4549833,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941782899.096, "dur": 6.096, + "args": { + "External id": 4549834,"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": 9057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941782900.979, "dur": 3.999, + "args": { + "External id": 4549835,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941783018.349, "dur": 204.569, + "args": { + "External id": 4549836,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941783023.792, "dur": 3.380, + "args": { + "External id": 4549837,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941783028.851, "dur": 193.552, + "args": { + "External id": 4549838,"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": 9061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941783032.605, "dur": 0.489, + "args": { + "External id": 4549839,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941783034.280, "dur": 26.320, + "args": { + "External id": 4549840,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941783062.359, "dur": 5.645, + "args": { + "External id": 4549841,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783066.445, "dur": 1.047, + "args": { + "External id": 4549842,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941783068.961, "dur": 24.137, + "args": { + "External id": 4549843,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941783070.341, "dur": 1.944, + "args": { + "External id": 4549844,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941783073.528, "dur": 19.333, + "args": { + "External id": 4549845,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783076.190, "dur": 2.754, + "args": { + "External id": 4549846,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941783094.456, "dur": 21.313, + "args": { + "External id": 4549847,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783117.397, "dur": 17.099, + "args": { + "External id": 4549848,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941783139.460, "dur": 14.783, + "args": { + "External id": 4549849,"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": 9072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783155.662, "dur": 13.828, + "args": { + "External id": 4549850,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941783171.438, "dur": 20.755, + "args": { + "External id": 4549851,"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": 9074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783173.122, "dur": 1.862, + "args": { + "External id": 4549852,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783177.397, "dur": 0.861, + "args": { + "External id": 4549853,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783193.597, "dur": 12.657, + "args": { + "External id": 4549854,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783209.713, "dur": 11.669, + "args": { + "External id": 4549855,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941783230.667, "dur": 2.013, + "args": { + "External id": 4549856,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941783241.653, "dur": 3.308, + "args": { + "External id": 4549857,"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": 9080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783243.775, "dur": 0.375, + "args": { + "External id": 4549858,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941783310.635, "dur": 54.882, + "args": { + "External id": 4549859,"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": 9082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941783369.963, "dur": 4.978, + "args": { + "External id": 4549860,"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": 9083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783372.476, "dur": 1.414, + "args": { + "External id": 4549861,"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": 9084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783376.118, "dur": 23.444, + "args": { + "External id": 4549862,"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": 9085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941783403.746, "dur": 7.879, + "args": { + "External id": 4549863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941783407.739, "dur": 3.281, + "args": { + "External id": 4549864,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783409.586, "dur": 1.240, + "args": { + "External id": 4549865,"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": 9088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941783413.941, "dur": 38.872, + "args": { + "External id": 4549866,"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": 9089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941783414.821, "dur": 37.307, + "args": { + "External id": 4549867,"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": 9090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783456.103, "dur": 15.713, + "args": { + "External id": 4549868,"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": 9091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941783476.070, "dur": 26.617, + "args": { + "External id": 4549869,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941783478.481, "dur": 23.849, + "args": { + "External id": 4549870,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783483.166, "dur": 2.789, + "args": { + "External id": 4549871,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941783510.774, "dur": 45.824, + "args": { + "External id": 4549872,"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": 9095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941783512.714, "dur": 43.636, + "args": { + "External id": 4549873,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], [], []], "Ev Idx": 9096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783517.662, "dur": 4.033, + "args": { + "External id": 4549874,"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": 9097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783522.728, "dur": 32.837, + "args": { + "External id": 4549875,"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": 9098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941783572.915, "dur": 5.581, + "args": { + "External id": 4549876,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941783574.955, "dur": 3.287, + "args": { + "External id": 4549877,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941783579.473, "dur": 1.373, + "args": { + "External id": 4549878,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941783580.333, "dur": 0.442, + "args": { + "External id": 4549879,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783626.497, "dur": 23.663, + "args": { + "External id": 4549880,"Sequence number": 45295789, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9103 + } + }, + { + "ph": "s", "id": 23, "pid": 1336753, "tid": 1336753, "ts": 1696941783626.497, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941783656.508, "dur": 6.830, + "args": { + "External id": 4549881,"Sequence number": 45295790, "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": 9104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783660.612, "dur": 1.320, + "args": { + "External id": 4549882,"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": 9105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1696941783665.681, "dur": 6.265, + "args": { + "External id": 4549883,"Sequence number": 45295790, "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": 9106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783669.892, "dur": 0.796, + "args": { + "External id": 4549884,"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": 9107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941783673.130, "dur": 5.124, + "args": { + "External id": 4549885,"Sequence number": 45295790, "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": 9108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783676.441, "dur": 1.231, + "args": { + "External id": 4549886,"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": 9109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941783682.775, "dur": 6.244, + "args": { + "External id": 4549887,"Sequence number": 45295790, "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": 9110 + } + }, + { + "ph": "s", "id": 22, "pid": 1336753, "tid": 1336753, "ts": 1696941783682.775, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783686.407, "dur": 1.072, + "args": { + "External id": 4549888,"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": 9111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941783690.082, "dur": 5.622, + "args": { + "External id": 4549889,"Sequence number": 45295791, "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": 9112 + } + }, + { + "ph": "s", "id": 21, "pid": 1336753, "tid": 1336753, "ts": 1696941783690.082, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783694.118, "dur": 0.833, + "args": { + "External id": 4549890,"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": 9113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1696941783698.908, "dur": 5.836, + "args": { + "External id": 4549891,"Sequence number": 45295792, "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": 9114 + } + }, + { + "ph": "s", "id": 20, "pid": 1336753, "tid": 1336753, "ts": 1696941783698.908, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783702.828, "dur": 1.076, + "args": { + "External id": 4549892,"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": 9115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941783705.839, "dur": 4.431, + "args": { + "External id": 4549893,"Sequence number": 45295793, "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": 9116 + } + }, + { + "ph": "s", "id": 19, "pid": 1336753, "tid": 1336753, "ts": 1696941783705.839, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783708.724, "dur": 0.773, + "args": { + "External id": 4549894,"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": 9117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1696941783714.557, "dur": 33.905, + "args": { + "External id": 4549895,"Sequence number": 45295794, "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": 9118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1696941783716.090, "dur": 32.110, + "args": { + "External id": 4549896,"Sequence number": 45295794, "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": 9119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941783718.800, "dur": 9.416, + "args": { + "External id": 4549897,"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": 9120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941783723.834, "dur": 3.844, + "args": { + "External id": 4549898,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783729.137, "dur": 18.492, + "args": { + "External id": 4549899,"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": 9122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941783777.868, "dur": 4.141, + "args": { + "External id": 4549900,"Sequence number": 45295794, "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": 9123 + } + }, + { + "ph": "s", "id": 18, "pid": 1336753, "tid": 1336753, "ts": 1696941783777.868, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941783784.338, "dur": 1.125, + "args": { + "External id": 4549901,"Sequence number": 45295795, "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": 9124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941783817.690, "dur": 42037.298, + "args": { + "External id": 4549902,"Sequence number": 45295795, "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": 9125 + } + }, + { + "ph": "s", "id": 17, "pid": 1336753, "tid": 1336753, "ts": 1696941783817.690, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1696941783831.342, "dur": 27.825, + "args": { + "External id": 4549903,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1696941783831.898, "dur": 27.063, + "args": { + "External id": 4549904,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941783833.683, "dur": 7.401, + "args": { + "External id": 4549905,"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": 9128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941783837.219, "dur": 3.485, + "args": { + "External id": 4549906,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783841.867, "dur": 16.528, + "args": { + "External id": 4549907,"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": 9130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941783873.633, "dur": 28.574, + "args": { + "External id": 4549908,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941783875.077, "dur": 6.301, + "args": { + "External id": 4549909,"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": 9132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783877.062, "dur": 3.993, + "args": { + "External id": 4549910,"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": 9133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783882.442, "dur": 19.518, + "args": { + "External id": 4549911,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783883.891, "dur": 17.708, + "args": { + "External id": 4549912,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941783905.800, "dur": 19.837, + "args": { + "External id": 4549913,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941783906.486, "dur": 5.321, + "args": { + "External id": 4549914,"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": 9137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941783908.032, "dur": 3.512, + "args": { + "External id": 4549915,"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": 9138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783912.344, "dur": 13.078, + "args": { + "External id": 4549916,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783913.004, "dur": 12.068, + "args": { + "External id": 4549917,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[32000, 2048], []], "Ev Idx": 9140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1696941783933.552, "dur": 17.970, + "args": { + "External id": 4549918,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 9141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941783935.632, "dur": 2.730, + "args": { + "External id": 4549919,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783939.090, "dur": 12.174, + "args": { + "External id": 4549920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 9143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941783939.882, "dur": 11.091, + "args": { + "External id": 4549921,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336753, "tid": 1336753, + "ts": 1696941783956.297, "dur": 23.422, + "args": { + "External id": 4549922,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941783982.111, "dur": 113.412, + "args": { + "External id": 4549923,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941784036.820, "dur": 57.999, + "args": { + "External id": 4549924,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941784044.423, "dur": 3.129, + "args": { + "External id": 4549925,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941784048.859, "dur": 27.408, + "args": { + "External id": 4549926,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941784050.137, "dur": 25.928, + "args": { + "External id": 4549927,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 9150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941784052.502, "dur": 3.404, + "args": { + "External id": 4549928,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941784059.370, "dur": 16.304, + "args": { + "External id": 4549929,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 9152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336753, "tid": 1336753, + "ts": 1696941784100.525, "dur": 36075.880, + "args": { + "External id": 4549930,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336753, "tid": 1336753, + "ts": 1696941784102.178, "dur": 36073.487, + "args": { + "External id": 4549931,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941820186.081, "dur": 6.263, + "args": { + "External id": 4549932,"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": 9155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941820189.798, "dur": 0.954, + "args": { + "External id": 4549933,"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": 9156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941820197.337, "dur": 98.540, + "args": { + "External id": 4549934,"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": 9157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941820198.985, "dur": 8.469, + "args": { + "External id": 4549935,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941820203.593, "dur": 3.123, + "args": { + "External id": 4549936,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941820205.491, "dur": 0.975, + "args": { + "External id": 4549937,"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": 9160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941820208.905, "dur": 86.236, + "args": { + "External id": 4549938,"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": 9161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941820210.403, "dur": 84.016, + "args": { + "External id": 4549939,"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": 9162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941820298.906, "dur": 3.773, + "args": { + "External id": 4549940,"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": 9163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941820300.790, "dur": 0.840, + "args": { + "External id": 4549941,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941820310.305, "dur": 2.345, + "args": { + "External id": 4549942,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941820323.279, "dur": 7.025, + "args": { + "External id": 4549943,"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": 9166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941820325.631, "dur": 4.334, + "args": { + "External id": 4549944,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941820453.767, "dur": 232.938, + "args": { + "External id": 4549945,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941820459.083, "dur": 2.476, + "args": { + "External id": 4549946,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941820462.843, "dur": 223.251, + "args": { + "External id": 4549947,"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": 9170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941820464.583, "dur": 0.402, + "args": { + "External id": 4549948,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941820469.170, "dur": 26.757, + "args": { + "External id": 4549949,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941820497.487, "dur": 5.827, + "args": { + "External id": 4549950,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941820502.237, "dur": 0.784, + "args": { + "External id": 4549951,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941820504.342, "dur": 40.460, + "args": { + "External id": 4549952,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941820505.391, "dur": 1.724, + "args": { + "External id": 4549953,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941820508.200, "dur": 35.983, + "args": { + "External id": 4549954,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941820511.951, "dur": 3.624, + "args": { + "External id": 4549955,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941820546.856, "dur": 27.055, + "args": { + "External id": 4549956,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941820575.487, "dur": 17.592, + "args": { + "External id": 4549957,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941820595.942, "dur": 16.836, + "args": { + "External id": 4549958,"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": 9181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941820616.836, "dur": 13.899, + "args": { + "External id": 4549959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941820632.929, "dur": 22.951, + "args": { + "External id": 4549960,"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": 9183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941820634.804, "dur": 2.077, + "args": { + "External id": 4549961,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941820639.132, "dur": 1.374, + "args": { + "External id": 4549962,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941820657.172, "dur": 13.554, + "args": { + "External id": 4549963,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941820672.346, "dur": 12.715, + "args": { + "External id": 4549964,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941820696.998, "dur": 2.365, + "args": { + "External id": 4549965,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941820707.252, "dur": 4.298, + "args": { + "External id": 4549966,"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": 9189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941820709.912, "dur": 0.675, + "args": { + "External id": 4549967,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941820782.809, "dur": 70.931, + "args": { + "External id": 4549968,"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": 9191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941820858.645, "dur": 5.888, + "args": { + "External id": 4549969,"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": 9192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941820861.096, "dur": 1.180, + "args": { + "External id": 4549970,"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": 9193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941820866.077, "dur": 30.164, + "args": { + "External id": 4549971,"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": 9194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941820902.150, "dur": 8.751, + "args": { + "External id": 4549972,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941820906.367, "dur": 3.737, + "args": { + "External id": 4549973,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941820908.534, "dur": 1.344, + "args": { + "External id": 4549974,"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": 9197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941820913.929, "dur": 44.252, + "args": { + "External id": 4549975,"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": 9198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941820915.147, "dur": 42.456, + "args": { + "External id": 4549976,"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": 9199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941820962.585, "dur": 16.285, + "args": { + "External id": 4549977,"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": 9200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941821023.748, "dur": 7.539, + "args": { + "External id": 4549978,"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": 9201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941821028.947, "dur": 1.000, + "args": { + "External id": 4549979,"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": 9202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941821036.704, "dur": 63.650, + "args": { + "External id": 4549980,"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": 9203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941821037.643, "dur": 4.256, + "args": { + "External id": 4549981,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941821038.652, "dur": 2.595, + "args": { + "External id": 4549982,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941821040.283, "dur": 0.795, + "args": { + "External id": 4549983,"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": 9206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941821042.736, "dur": 57.130, + "args": { + "External id": 4549984,"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": 9207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941821049.030, "dur": 50.214, + "args": { + "External id": 4549985,"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": 9208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941821106.925, "dur": 3.969, + "args": { + "External id": 4549986,"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": 9209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941821108.983, "dur": 0.779, + "args": { + "External id": 4549987,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941821117.959, "dur": 1.514, + "args": { + "External id": 4549988,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941821127.662, "dur": 8.460, + "args": { + "External id": 4549989,"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": 9212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941821129.818, "dur": 6.023, + "args": { + "External id": 4549990,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941821233.117, "dur": 202.768, + "args": { + "External id": 4549991,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941821235.515, "dur": 2.234, + "args": { + "External id": 4549992,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941821238.937, "dur": 196.408, + "args": { + "External id": 4549993,"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": 9216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941821240.583, "dur": 0.370, + "args": { + "External id": 4549994,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941821242.148, "dur": 26.679, + "args": { + "External id": 4549995,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941821273.421, "dur": 3.732, + "args": { + "External id": 4549996,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941821276.128, "dur": 0.748, + "args": { + "External id": 4549997,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941821278.126, "dur": 27.886, + "args": { + "External id": 4549998,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941821281.539, "dur": 3.432, + "args": { + "External id": 4549999,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941821286.550, "dur": 19.157, + "args": { + "External id": 4550000,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941821289.548, "dur": 3.385, + "args": { + "External id": 4550001,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941821307.525, "dur": 22.879, + "args": { + "External id": 4550002,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941821331.712, "dur": 15.485, + "args": { + "External id": 4550003,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941821349.846, "dur": 14.832, + "args": { + "External id": 4550004,"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": 9227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941821365.868, "dur": 14.233, + "args": { + "External id": 4550005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941821381.879, "dur": 24.076, + "args": { + "External id": 4550006,"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": 9229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941821383.829, "dur": 1.600, + "args": { + "External id": 4550007,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941821389.613, "dur": 1.229, + "args": { + "External id": 4550008,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941821407.256, "dur": 14.244, + "args": { + "External id": 4550009,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941821422.667, "dur": 11.533, + "args": { + "External id": 4550010,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941821442.458, "dur": 1.827, + "args": { + "External id": 4550011,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941821453.193, "dur": 3.374, + "args": { + "External id": 4550012,"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": 9235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941821455.216, "dur": 0.584, + "args": { + "External id": 4550013,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941821522.486, "dur": 73.392, + "args": { + "External id": 4550014,"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": 9237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941821601.861, "dur": 7.838, + "args": { + "External id": 4550015,"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": 9238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941821607.491, "dur": 0.846, + "args": { + "External id": 4550016,"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": 9239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941821611.012, "dur": 25.571, + "args": { + "External id": 4550017,"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": 9240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941821641.465, "dur": 5.003, + "args": { + "External id": 4550018,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941821642.932, "dur": 2.947, + "args": { + "External id": 4550019,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941821644.682, "dur": 0.998, + "args": { + "External id": 4550020,"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": 9243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941821649.508, "dur": 46.096, + "args": { + "External id": 4550021,"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": 9244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941821652.912, "dur": 41.911, + "args": { + "External id": 4550022,"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": 9245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941821699.563, "dur": 16.673, + "args": { + "External id": 4550023,"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": 9246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941821721.578, "dur": 4.093, + "args": { + "External id": 4550024,"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": 9247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941821723.962, "dur": 0.929, + "args": { + "External id": 4550025,"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": 9248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941821729.564, "dur": 52.823, + "args": { + "External id": 4550026,"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": 9249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941821730.498, "dur": 8.584, + "args": { + "External id": 4550027,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941821731.171, "dur": 7.319, + "args": { + "External id": 4550028,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941821737.718, "dur": 0.659, + "args": { + "External id": 4550029,"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": 9252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941821739.641, "dur": 42.356, + "args": { + "External id": 4550030,"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": 9253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941821740.323, "dur": 40.954, + "args": { + "External id": 4550031,"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": 9254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941821786.293, "dur": 3.961, + "args": { + "External id": 4550032,"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": 9255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941821788.208, "dur": 0.953, + "args": { + "External id": 4550033,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941821796.037, "dur": 1.557, + "args": { + "External id": 4550034,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941821805.391, "dur": 8.410, + "args": { + "External id": 4550035,"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": 9258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941821809.815, "dur": 3.741, + "args": { + "External id": 4550036,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941821898.055, "dur": 239.670, + "args": { + "External id": 4550037,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941821900.295, "dur": 2.105, + "args": { + "External id": 4550038,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941821903.799, "dur": 233.379, + "args": { + "External id": 4550039,"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": 9262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941821907.489, "dur": 0.285, + "args": { + "External id": 4550040,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941821908.616, "dur": 22.302, + "args": { + "External id": 4550041,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941821932.662, "dur": 3.207, + "args": { + "External id": 4550042,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941821934.757, "dur": 0.884, + "args": { + "External id": 4550043,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941821936.921, "dur": 26.689, + "args": { + "External id": 4550044,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941821943.066, "dur": 1.418, + "args": { + "External id": 4550045,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941821945.455, "dur": 17.926, + "args": { + "External id": 4550046,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941821948.017, "dur": 2.488, + "args": { + "External id": 4550047,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941821964.923, "dur": 57.846, + "args": { + "External id": 4550048,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941822025.470, "dur": 15.385, + "args": { + "External id": 4550049,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941822043.973, "dur": 17.383, + "args": { + "External id": 4550050,"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": 9273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941822062.528, "dur": 13.452, + "args": { + "External id": 4550051,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941822077.788, "dur": 24.729, + "args": { + "External id": 4550052,"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": 9275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941822080.226, "dur": 1.835, + "args": { + "External id": 4550053,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941822086.434, "dur": 0.999, + "args": { + "External id": 4550054,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941822103.750, "dur": 13.193, + "args": { + "External id": 4550055,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941822117.918, "dur": 18.169, + "args": { + "External id": 4550056,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941822146.101, "dur": 2.164, + "args": { + "External id": 4550057,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941822157.482, "dur": 3.892, + "args": { + "External id": 4550058,"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": 9281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941822160.018, "dur": 0.437, + "args": { + "External id": 4550059,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941822230.072, "dur": 81.745, + "args": { + "External id": 4550060,"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": 9283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941822318.662, "dur": 6.497, + "args": { + "External id": 4550061,"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": 9284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941822321.146, "dur": 2.941, + "args": { + "External id": 4550062,"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": 9285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941822326.409, "dur": 26.401, + "args": { + "External id": 4550063,"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": 9286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941822357.283, "dur": 5.204, + "args": { + "External id": 4550064,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941822358.699, "dur": 2.890, + "args": { + "External id": 4550065,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941822360.408, "dur": 1.003, + "args": { + "External id": 4550066,"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": 9289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941822367.194, "dur": 41.828, + "args": { + "External id": 4550067,"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": 9290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941822368.229, "dur": 40.282, + "args": { + "External id": 4550068,"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": 9291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941822412.294, "dur": 17.728, + "args": { + "External id": 4550069,"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": 9292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941822435.522, "dur": 3.644, + "args": { + "External id": 4550070,"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": 9293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941822437.418, "dur": 0.879, + "args": { + "External id": 4550071,"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": 9294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941822442.897, "dur": 51.457, + "args": { + "External id": 4550072,"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": 9295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941822444.120, "dur": 6.543, + "args": { + "External id": 4550073,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941822447.680, "dur": 2.452, + "args": { + "External id": 4550074,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941822448.947, "dur": 0.913, + "args": { + "External id": 4550075,"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": 9298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941822451.679, "dur": 42.332, + "args": { + "External id": 4550076,"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": 9299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941822452.577, "dur": 40.727, + "args": { + "External id": 4550077,"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": 9300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941822497.860, "dur": 3.865, + "args": { + "External id": 4550078,"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": 9301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941822500.222, "dur": 0.558, + "args": { + "External id": 4550079,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941822509.309, "dur": 1.410, + "args": { + "External id": 4550080,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941822517.760, "dur": 5.975, + "args": { + "External id": 4550081,"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": 9304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941822519.332, "dur": 4.145, + "args": { + "External id": 4550082,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941822622.392, "dur": 193.795, + "args": { + "External id": 4550083,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941822624.938, "dur": 4.865, + "args": { + "External id": 4550084,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941822631.209, "dur": 184.437, + "args": { + "External id": 4550085,"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": 9308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941822634.964, "dur": 0.323, + "args": { + "External id": 4550086,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941822636.261, "dur": 23.057, + "args": { + "External id": 4550087,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941822660.749, "dur": 5.296, + "args": { + "External id": 4550088,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941822664.926, "dur": 0.846, + "args": { + "External id": 4550089,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941822667.003, "dur": 21.957, + "args": { + "External id": 4550090,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941822668.170, "dur": 1.539, + "args": { + "External id": 4550091,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941822671.046, "dur": 17.623, + "args": { + "External id": 4550092,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941822673.375, "dur": 2.568, + "args": { + "External id": 4550093,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941822690.268, "dur": 21.238, + "args": { + "External id": 4550094,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941822712.726, "dur": 14.709, + "args": { + "External id": 4550095,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941822732.019, "dur": 14.955, + "args": { + "External id": 4550096,"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": 9319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941822748.238, "dur": 13.204, + "args": { + "External id": 4550097,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941822762.949, "dur": 23.397, + "args": { + "External id": 4550098,"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": 9321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941822767.080, "dur": 2.002, + "args": { + "External id": 4550099,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941822770.831, "dur": 1.276, + "args": { + "External id": 4550100,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941822787.559, "dur": 12.910, + "args": { + "External id": 4550101,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941822803.679, "dur": 10.696, + "args": { + "External id": 4550102,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941822822.471, "dur": 2.036, + "args": { + "External id": 4550103,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941822833.115, "dur": 3.021, + "args": { + "External id": 4550104,"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": 9327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941822835.083, "dur": 0.332, + "args": { + "External id": 4550105,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941822896.551, "dur": 50.523, + "args": { + "External id": 4550106,"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": 9329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941822951.358, "dur": 4.606, + "args": { + "External id": 4550107,"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": 9330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941822953.793, "dur": 1.176, + "args": { + "External id": 4550108,"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": 9331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941822957.135, "dur": 21.684, + "args": { + "External id": 4550109,"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": 9332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941823017.543, "dur": 8.951, + "args": { + "External id": 4550110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941823021.532, "dur": 4.131, + "args": { + "External id": 4550111,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941823023.401, "dur": 1.967, + "args": { + "External id": 4550112,"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": 9335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941823029.698, "dur": 47.222, + "args": { + "External id": 4550113,"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": 9336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941823030.974, "dur": 45.124, + "args": { + "External id": 4550114,"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": 9337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941823080.865, "dur": 16.243, + "args": { + "External id": 4550115,"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": 9338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941823103.202, "dur": 6.344, + "args": { + "External id": 4550116,"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": 9339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941823107.991, "dur": 0.712, + "args": { + "External id": 4550117,"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": 9340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941823113.141, "dur": 45.563, + "args": { + "External id": 4550118,"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": 9341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941823113.971, "dur": 4.049, + "args": { + "External id": 4550119,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941823114.940, "dur": 2.560, + "args": { + "External id": 4550120,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941823116.007, "dur": 1.378, + "args": { + "External id": 4550121,"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": 9344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941823118.574, "dur": 39.729, + "args": { + "External id": 4550122,"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": 9345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941823119.138, "dur": 38.451, + "args": { + "External id": 4550123,"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": 9346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941823162.764, "dur": 3.992, + "args": { + "External id": 4550124,"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": 9347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941823164.950, "dur": 0.768, + "args": { + "External id": 4550125,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941823175.074, "dur": 1.503, + "args": { + "External id": 4550126,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941823184.022, "dur": 6.046, + "args": { + "External id": 4550127,"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": 9350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941823185.696, "dur": 4.144, + "args": { + "External id": 4550128,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941823268.952, "dur": 231.520, + "args": { + "External id": 4550129,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941823273.085, "dur": 2.210, + "args": { + "External id": 4550130,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941823279.168, "dur": 220.733, + "args": { + "External id": 4550131,"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": 9354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941823280.674, "dur": 0.285, + "args": { + "External id": 4550132,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941823281.842, "dur": 21.818, + "args": { + "External id": 4550133,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941823305.043, "dur": 5.312, + "args": { + "External id": 4550134,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941823309.194, "dur": 0.898, + "args": { + "External id": 4550135,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941823311.425, "dur": 22.014, + "args": { + "External id": 4550136,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941823312.602, "dur": 1.385, + "args": { + "External id": 4550137,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941823315.299, "dur": 17.866, + "args": { + "External id": 4550138,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941823317.558, "dur": 2.795, + "args": { + "External id": 4550139,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941823334.794, "dur": 23.496, + "args": { + "External id": 4550140,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941823359.817, "dur": 13.568, + "args": { + "External id": 4550141,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941823377.623, "dur": 15.045, + "args": { + "External id": 4550142,"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": 9365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941823393.758, "dur": 13.176, + "args": { + "External id": 4550143,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941823408.581, "dur": 60.765, + "args": { + "External id": 4550144,"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": 9367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941823449.878, "dur": 1.892, + "args": { + "External id": 4550145,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941823453.872, "dur": 0.712, + "args": { + "External id": 4550146,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941823473.304, "dur": 13.125, + "args": { + "External id": 4550147,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941823487.499, "dur": 11.348, + "args": { + "External id": 4550148,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941823506.774, "dur": 1.483, + "args": { + "External id": 4550149,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941823516.374, "dur": 3.117, + "args": { + "External id": 4550150,"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": 9373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941823518.419, "dur": 0.321, + "args": { + "External id": 4550151,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941823602.108, "dur": 59.169, + "args": { + "External id": 4550152,"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": 9375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941823666.514, "dur": 5.636, + "args": { + "External id": 4550153,"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": 9376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941823669.532, "dur": 1.254, + "args": { + "External id": 4550154,"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": 9377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941823675.645, "dur": 26.522, + "args": { + "External id": 4550155,"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": 9378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941823707.102, "dur": 7.170, + "args": { + "External id": 4550156,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941823708.558, "dur": 5.046, + "args": { + "External id": 4550157,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941823710.215, "dur": 3.094, + "args": { + "External id": 4550158,"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": 9381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941823716.817, "dur": 40.923, + "args": { + "External id": 4550159,"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": 9382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941823717.834, "dur": 39.184, + "args": { + "External id": 4550160,"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": 9383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941823761.349, "dur": 15.806, + "args": { + "External id": 4550161,"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": 9384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941823785.284, "dur": 3.833, + "args": { + "External id": 4550162,"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": 9385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941823787.616, "dur": 0.711, + "args": { + "External id": 4550163,"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": 9386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941823793.003, "dur": 47.952, + "args": { + "External id": 4550164,"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": 9387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941823793.747, "dur": 3.043, + "args": { + "External id": 4550165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941823794.363, "dur": 1.893, + "args": { + "External id": 4550166,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941823795.381, "dur": 0.745, + "args": { + "External id": 4550167,"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": 9390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941823799.333, "dur": 41.193, + "args": { + "External id": 4550168,"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": 9391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941823800.017, "dur": 39.827, + "args": { + "External id": 4550169,"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": 9392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941823844.495, "dur": 4.014, + "args": { + "External id": 4550170,"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": 9393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941823846.494, "dur": 0.906, + "args": { + "External id": 4550171,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941823854.260, "dur": 1.677, + "args": { + "External id": 4550172,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941823863.115, "dur": 9.145, + "args": { + "External id": 4550173,"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": 9396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941823867.400, "dur": 4.583, + "args": { + "External id": 4550174,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941823953.525, "dur": 239.000, + "args": { + "External id": 4550175,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941823955.641, "dur": 2.360, + "args": { + "External id": 4550176,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941823962.023, "dur": 229.799, + "args": { + "External id": 4550177,"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": 9400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941823963.289, "dur": 0.276, + "args": { + "External id": 4550178,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941823964.459, "dur": 58.463, + "args": { + "External id": 4550179,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941824025.614, "dur": 5.101, + "args": { + "External id": 4550180,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941824027.775, "dur": 2.586, + "args": { + "External id": 4550181,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941824034.340, "dur": 26.096, + "args": { + "External id": 4550182,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941824035.610, "dur": 2.816, + "args": { + "External id": 4550183,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941824039.824, "dur": 20.336, + "args": { + "External id": 4550184,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824043.125, "dur": 2.811, + "args": { + "External id": 4550185,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941824062.140, "dur": 22.247, + "args": { + "External id": 4550186,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824085.837, "dur": 15.989, + "args": { + "External id": 4550187,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941824104.645, "dur": 15.427, + "args": { + "External id": 4550188,"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": 9411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824121.531, "dur": 13.266, + "args": { + "External id": 4550189,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941824136.421, "dur": 27.490, + "args": { + "External id": 4550190,"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": 9413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824141.295, "dur": 2.025, + "args": { + "External id": 4550191,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941824145.418, "dur": 2.820, + "args": { + "External id": 4550192,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824165.390, "dur": 13.071, + "args": { + "External id": 4550193,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824179.390, "dur": 11.183, + "args": { + "External id": 4550194,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941824200.690, "dur": 2.288, + "args": { + "External id": 4550195,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941824211.395, "dur": 3.980, + "args": { + "External id": 4550196,"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": 9419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941824213.689, "dur": 0.657, + "args": { + "External id": 4550197,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941824282.661, "dur": 54.634, + "args": { + "External id": 4550198,"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": 9421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941824343.781, "dur": 5.069, + "args": { + "External id": 4550199,"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": 9422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941824346.614, "dur": 1.341, + "args": { + "External id": 4550200,"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": 9423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824350.054, "dur": 23.366, + "args": { + "External id": 4550201,"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": 9424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941824377.633, "dur": 6.193, + "args": { + "External id": 4550202,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941824378.969, "dur": 4.017, + "args": { + "External id": 4550203,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941824380.919, "dur": 1.831, + "args": { + "External id": 4550204,"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": 9427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941824388.765, "dur": 40.201, + "args": { + "External id": 4550205,"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": 9428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941824389.877, "dur": 38.550, + "args": { + "External id": 4550206,"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": 9429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824432.507, "dur": 15.164, + "args": { + "External id": 4550207,"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": 9430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941824452.688, "dur": 3.719, + "args": { + "External id": 4550208,"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": 9431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941824454.968, "dur": 0.683, + "args": { + "External id": 4550209,"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": 9432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941824459.850, "dur": 49.280, + "args": { + "External id": 4550210,"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": 9433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941824460.781, "dur": 5.994, + "args": { + "External id": 4550211,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941824463.884, "dur": 2.376, + "args": { + "External id": 4550212,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941824465.090, "dur": 1.046, + "args": { + "External id": 4550213,"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": 9436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941824467.431, "dur": 41.303, + "args": { + "External id": 4550214,"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": 9437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941824468.153, "dur": 40.020, + "args": { + "External id": 4550215,"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": 9438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941824512.762, "dur": 4.205, + "args": { + "External id": 4550216,"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": 9439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941824515.085, "dur": 0.849, + "args": { + "External id": 4550217,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941824521.985, "dur": 1.384, + "args": { + "External id": 4550218,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941824548.611, "dur": 6.815, + "args": { + "External id": 4550219,"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": 9442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941824550.362, "dur": 4.602, + "args": { + "External id": 4550220,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941824639.206, "dur": 199.220, + "args": { + "External id": 4550221,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941824643.623, "dur": 2.403, + "args": { + "External id": 4550222,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941824647.395, "dur": 190.494, + "args": { + "External id": 4550223,"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": 9446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941824648.754, "dur": 0.265, + "args": { + "External id": 4550224,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941824649.819, "dur": 22.033, + "args": { + "External id": 4550225,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941824673.443, "dur": 5.481, + "args": { + "External id": 4550226,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941824677.677, "dur": 0.742, + "args": { + "External id": 4550227,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941824690.288, "dur": 22.048, + "args": { + "External id": 4550228,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941824691.556, "dur": 1.521, + "args": { + "External id": 4550229,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941824694.252, "dur": 17.738, + "args": { + "External id": 4550230,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824696.874, "dur": 2.912, + "args": { + "External id": 4550231,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941824713.713, "dur": 21.525, + "args": { + "External id": 4550232,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824736.622, "dur": 16.792, + "args": { + "External id": 4550233,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941824755.750, "dur": 15.302, + "args": { + "External id": 4550234,"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": 9457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824772.291, "dur": 13.371, + "args": { + "External id": 4550235,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941824787.153, "dur": 22.849, + "args": { + "External id": 4550236,"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": 9459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824791.447, "dur": 1.671, + "args": { + "External id": 4550237,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941824795.054, "dur": 0.631, + "args": { + "External id": 4550238,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824811.386, "dur": 12.795, + "args": { + "External id": 4550239,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824825.157, "dur": 11.686, + "args": { + "External id": 4550240,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941824844.678, "dur": 1.688, + "args": { + "External id": 4550241,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941824854.485, "dur": 3.241, + "args": { + "External id": 4550242,"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": 9465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941824856.703, "dur": 0.314, + "args": { + "External id": 4550243,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941824918.494, "dur": 51.394, + "args": { + "External id": 4550244,"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": 9467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941824974.164, "dur": 4.686, + "args": { + "External id": 4550245,"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": 9468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941824976.658, "dur": 1.092, + "args": { + "External id": 4550246,"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": 9469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941824983.363, "dur": 61.180, + "args": { + "External id": 4550247,"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": 9470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941825050.825, "dur": 10.739, + "args": { + "External id": 4550248,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941825052.473, "dur": 7.978, + "args": { + "External id": 4550249,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825056.958, "dur": 3.280, + "args": { + "External id": 4550250,"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": 9473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941825064.360, "dur": 44.396, + "args": { + "External id": 4550251,"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": 9474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941825065.314, "dur": 42.821, + "args": { + "External id": 4550252,"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": 9475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941825112.208, "dur": 15.919, + "args": { + "External id": 4550253,"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": 9476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941825133.442, "dur": 3.745, + "args": { + "External id": 4550254,"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": 9477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825135.663, "dur": 0.590, + "args": { + "External id": 4550255,"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": 9478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941825143.140, "dur": 46.272, + "args": { + "External id": 4550256,"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": 9479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941825144.091, "dur": 3.291, + "args": { + "External id": 4550257,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941825144.866, "dur": 1.896, + "args": { + "External id": 4550258,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825145.929, "dur": 0.704, + "args": { + "External id": 4550259,"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": 9482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941825148.110, "dur": 40.895, + "args": { + "External id": 4550260,"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": 9483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941825148.533, "dur": 39.867, + "args": { + "External id": 4550261,"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": 9484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941825194.598, "dur": 3.761, + "args": { + "External id": 4550262,"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": 9485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825196.486, "dur": 0.798, + "args": { + "External id": 4550263,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941825204.023, "dur": 1.238, + "args": { + "External id": 4550264,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941825212.142, "dur": 6.916, + "args": { + "External id": 4550265,"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": 9488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941825213.792, "dur": 5.025, + "args": { + "External id": 4550266,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941825301.045, "dur": 186.876, + "args": { + "External id": 4550267,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941825302.945, "dur": 2.140, + "args": { + "External id": 4550268,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941825308.885, "dur": 178.441, + "args": { + "External id": 4550269,"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": 9492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941825309.981, "dur": 0.264, + "args": { + "External id": 4550270,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941825311.254, "dur": 20.736, + "args": { + "External id": 4550271,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941825333.348, "dur": 5.075, + "args": { + "External id": 4550272,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825335.182, "dur": 2.971, + "args": { + "External id": 4550273,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941825339.369, "dur": 24.742, + "args": { + "External id": 4550274,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941825340.449, "dur": 1.482, + "args": { + "External id": 4550275,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941825342.965, "dur": 20.885, + "args": { + "External id": 4550276,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941825347.734, "dur": 3.112, + "args": { + "External id": 4550277,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941825365.317, "dur": 20.394, + "args": { + "External id": 4550278,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941825386.890, "dur": 14.195, + "args": { + "External id": 4550279,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941825403.773, "dur": 14.893, + "args": { + "External id": 4550280,"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": 9503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941825419.775, "dur": 12.839, + "args": { + "External id": 4550281,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941825434.386, "dur": 23.306, + "args": { + "External id": 4550282,"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": 9505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941825436.506, "dur": 1.530, + "args": { + "External id": 4550283,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825440.153, "dur": 1.025, + "args": { + "External id": 4550284,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941825461.484, "dur": 12.440, + "args": { + "External id": 4550285,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941825475.020, "dur": 11.377, + "args": { + "External id": 4550286,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941825493.229, "dur": 1.415, + "args": { + "External id": 4550287,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941825501.568, "dur": 3.540, + "args": { + "External id": 4550288,"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": 9511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825504.010, "dur": 0.277, + "args": { + "External id": 4550289,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941825581.170, "dur": 51.476, + "args": { + "External id": 4550290,"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": 9513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941825637.154, "dur": 7.345, + "args": { + "External id": 4550291,"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": 9514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825640.142, "dur": 3.087, + "args": { + "External id": 4550292,"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": 9515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941825648.100, "dur": 24.363, + "args": { + "External id": 4550293,"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": 9516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941825676.689, "dur": 5.025, + "args": { + "External id": 4550294,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941825677.997, "dur": 3.143, + "args": { + "External id": 4550295,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825679.853, "dur": 1.119, + "args": { + "External id": 4550296,"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": 9519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941825684.092, "dur": 42.686, + "args": { + "External id": 4550297,"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": 9520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941825684.885, "dur": 41.366, + "args": { + "External id": 4550298,"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": 9521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941825730.638, "dur": 15.849, + "args": { + "External id": 4550299,"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": 9522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941825753.328, "dur": 24.859, + "args": { + "External id": 4550300,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941825755.515, "dur": 22.309, + "args": { + "External id": 4550301,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825760.840, "dur": 1.113, + "args": { + "External id": 4550302,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941825783.153, "dur": 26.066, + "args": { + "External id": 4550303,"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": 9526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941825784.678, "dur": 24.336, + "args": { + "External id": 4550304,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], [], []], "Ev Idx": 9527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825788.671, "dur": 4.128, + "args": { + "External id": 4550305,"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": 9528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941825794.139, "dur": 14.407, + "args": { + "External id": 4550306,"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": 9529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941825822.558, "dur": 4.765, + "args": { + "External id": 4550307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941825824.504, "dur": 2.574, + "args": { + "External id": 4550308,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941825828.277, "dur": 3.474, + "args": { + "External id": 4550309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941825831.098, "dur": 0.558, + "args": { + "External id": 4550310,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941825869.936, "dur": 21.833, + "args": { + "External id": 4550311,"Sequence number": 45295796, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941825893.262, "dur": 14.930, + "args": { + "External id": 4550312,"Sequence number": 45295797, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9535 + } + }, + { + "ph": "s", "id": 16, "pid": 1336753, "tid": 1336753, "ts": 1696941825893.262, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941825913.652, "dur": 5.683, + "args": { + "External id": 4550313,"Sequence number": 45295798, "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": 9536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825917.035, "dur": 0.964, + "args": { + "External id": 4550314,"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": 9537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1696941825921.667, "dur": 8.176, + "args": { + "External id": 4550315,"Sequence number": 45295798, "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": 9538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825927.687, "dur": 0.863, + "args": { + "External id": 4550316,"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": 9539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941825931.231, "dur": 3.229, + "args": { + "External id": 4550317,"Sequence number": 45295798, "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": 9540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825932.974, "dur": 0.908, + "args": { + "External id": 4550318,"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": 9541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941825938.127, "dur": 5.598, + "args": { + "External id": 4550319,"Sequence number": 45295798, "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": 9542 + } + }, + { + "ph": "s", "id": 15, "pid": 1336753, "tid": 1336753, "ts": 1696941825938.127, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825941.424, "dur": 1.030, + "args": { + "External id": 4550320,"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": 9543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941825944.619, "dur": 7.079, + "args": { + "External id": 4550321,"Sequence number": 45295799, "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": 9544 + } + }, + { + "ph": "s", "id": 14, "pid": 1336753, "tid": 1336753, "ts": 1696941825944.619, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825949.935, "dur": 0.953, + "args": { + "External id": 4550322,"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": 9545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1696941825952.844, "dur": 5.660, + "args": { + "External id": 4550323,"Sequence number": 45295800, "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": 9546 + } + }, + { + "ph": "s", "id": 13, "pid": 1336753, "tid": 1336753, "ts": 1696941825952.844, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825956.782, "dur": 0.911, + "args": { + "External id": 4550324,"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": 9547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941825959.512, "dur": 4.229, + "args": { + "External id": 4550325,"Sequence number": 45295801, "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": 9548 + } + }, + { + "ph": "s", "id": 12, "pid": 1336753, "tid": 1336753, "ts": 1696941825959.512, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941825962.124, "dur": 0.900, + "args": { + "External id": 4550326,"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": 9549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1696941825967.327, "dur": 69.393, + "args": { + "External id": 4550327,"Sequence number": 45295802, "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": 9550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1696941825968.861, "dur": 67.586, + "args": { + "External id": 4550328,"Sequence number": 45295802, "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": 9551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941825971.517, "dur": 8.269, + "args": { + "External id": 4550329,"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": 9552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941825975.893, "dur": 3.397, + "args": { + "External id": 4550330,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941825980.536, "dur": 54.976, + "args": { + "External id": 4550331,"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": 9554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941826065.406, "dur": 5.412, + "args": { + "External id": 4550332,"Sequence number": 45295802, "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": 9555 + } + }, + { + "ph": "s", "id": 11, "pid": 1336753, "tid": 1336753, "ts": 1696941826065.406, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941826073.107, "dur": 3.534, + "args": { + "External id": 4550333,"Sequence number": 45295803, "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": 9556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941826110.097, "dur": 44819.798, + "args": { + "External id": 4550334,"Sequence number": 45295803, "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": 9557 + } + }, + { + "ph": "s", "id": 10, "pid": 1336753, "tid": 1336753, "ts": 1696941826110.097, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1696941826124.955, "dur": 31.358, + "args": { + "External id": 4550335,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1696941826128.356, "dur": 27.781, + "args": { + "External id": 4550336,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941826129.636, "dur": 6.552, + "args": { + "External id": 4550337,"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": 9560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941826131.102, "dur": 4.421, + "args": { + "External id": 4550338,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941826136.995, "dur": 18.759, + "args": { + "External id": 4550339,"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": 9562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941826171.708, "dur": 27.317, + "args": { + "External id": 4550340,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941826172.886, "dur": 6.501, + "args": { + "External id": 4550341,"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": 9564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941826175.085, "dur": 4.006, + "args": { + "External id": 4550342,"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": 9565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941826180.564, "dur": 18.241, + "args": { + "External id": 4550343,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941826182.502, "dur": 15.900, + "args": { + "External id": 4550344,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941826202.464, "dur": 23.540, + "args": { + "External id": 4550345,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941826202.959, "dur": 4.597, + "args": { + "External id": 4550346,"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": 9569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941826204.306, "dur": 3.009, + "args": { + "External id": 4550347,"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": 9570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941826210.431, "dur": 15.280, + "args": { + "External id": 4550348,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941826211.108, "dur": 14.287, + "args": { + "External id": 4550349,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[32000, 2048], []], "Ev Idx": 9572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1696941826231.202, "dur": 20.622, + "args": { + "External id": 4550350,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 9573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941826233.212, "dur": 5.054, + "args": { + "External id": 4550351,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941826238.918, "dur": 12.656, + "args": { + "External id": 4550352,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 9575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941826239.976, "dur": 11.310, + "args": { + "External id": 4550353,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336753, "tid": 1336753, + "ts": 1696941826256.602, "dur": 22.612, + "args": { + "External id": 4550354,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941826281.620, "dur": 54.240, + "args": { + "External id": 4550355,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941826286.325, "dur": 49.112, + "args": { + "External id": 4550356,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941826291.232, "dur": 1.118, + "args": { + "External id": 4550357,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941826293.530, "dur": 26.388, + "args": { + "External id": 4550358,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941826295.146, "dur": 24.533, + "args": { + "External id": 4550359,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 9582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941826300.075, "dur": 3.461, + "args": { + "External id": 4550360,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941826304.416, "dur": 14.858, + "args": { + "External id": 4550361,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 9584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336753, "tid": 1336753, + "ts": 1696941826339.240, "dur": 38774.614, + "args": { + "External id": 4550362,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336753, "tid": 1336753, + "ts": 1696941826340.746, "dur": 38772.237, + "args": { + "External id": 4550363,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941865122.970, "dur": 6.764, + "args": { + "External id": 4550364,"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": 9587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941865127.064, "dur": 0.941, + "args": { + "External id": 4550365,"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": 9588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941865137.044, "dur": 102.999, + "args": { + "External id": 4550366,"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": 9589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941865139.020, "dur": 6.093, + "args": { + "External id": 4550367,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941865141.164, "dur": 3.139, + "args": { + "External id": 4550368,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941865142.821, "dur": 1.206, + "args": { + "External id": 4550369,"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": 9592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941865146.465, "dur": 93.029, + "args": { + "External id": 4550370,"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": 9593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941865148.087, "dur": 90.546, + "args": { + "External id": 4550371,"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": 9594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941865243.615, "dur": 4.348, + "args": { + "External id": 4550372,"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": 9595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941865245.830, "dur": 0.810, + "args": { + "External id": 4550373,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941865256.968, "dur": 2.537, + "args": { + "External id": 4550374,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941865268.571, "dur": 6.174, + "args": { + "External id": 4550375,"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": 9598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941865270.362, "dur": 4.139, + "args": { + "External id": 4550376,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941865403.804, "dur": 229.522, + "args": { + "External id": 4550377,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941865406.699, "dur": 2.883, + "args": { + "External id": 4550378,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941865413.682, "dur": 219.081, + "args": { + "External id": 4550379,"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": 9602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941865415.573, "dur": 0.410, + "args": { + "External id": 4550380,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941865420.070, "dur": 26.014, + "args": { + "External id": 4550381,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941865447.850, "dur": 4.307, + "args": { + "External id": 4550382,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941865450.599, "dur": 1.063, + "args": { + "External id": 4550383,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941865453.415, "dur": 27.242, + "args": { + "External id": 4550384,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941865454.793, "dur": 3.580, + "args": { + "External id": 4550385,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941865459.946, "dur": 20.453, + "args": { + "External id": 4550386,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941865463.670, "dur": 3.135, + "args": { + "External id": 4550387,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941865484.564, "dur": 22.506, + "args": { + "External id": 4550388,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941865508.951, "dur": 16.329, + "args": { + "External id": 4550389,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941865541.616, "dur": 18.737, + "args": { + "External id": 4550390,"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": 9613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941865561.882, "dur": 14.311, + "args": { + "External id": 4550391,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941865578.150, "dur": 22.737, + "args": { + "External id": 4550392,"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": 9615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941865580.367, "dur": 2.277, + "args": { + "External id": 4550393,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941865584.713, "dur": 0.895, + "args": { + "External id": 4550394,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941865604.850, "dur": 13.673, + "args": { + "External id": 4550395,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941865619.973, "dur": 11.834, + "args": { + "External id": 4550396,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941865641.365, "dur": 2.329, + "args": { + "External id": 4550397,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941865650.629, "dur": 4.234, + "args": { + "External id": 4550398,"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": 9621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941865652.889, "dur": 1.124, + "args": { + "External id": 4550399,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941865732.443, "dur": 70.152, + "args": { + "External id": 4550400,"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": 9623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941865807.913, "dur": 6.621, + "args": { + "External id": 4550401,"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": 9624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941865810.399, "dur": 1.591, + "args": { + "External id": 4550402,"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": 9625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941865818.297, "dur": 27.579, + "args": { + "External id": 4550403,"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": 9626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941865851.139, "dur": 7.849, + "args": { + "External id": 4550404,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941865853.066, "dur": 5.197, + "args": { + "External id": 4550405,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941865855.137, "dur": 2.854, + "args": { + "External id": 4550406,"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": 9629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941865862.510, "dur": 45.033, + "args": { + "External id": 4550407,"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": 9630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941865863.745, "dur": 43.117, + "args": { + "External id": 4550408,"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": 9631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941865911.922, "dur": 15.422, + "args": { + "External id": 4550409,"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": 9632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941865935.584, "dur": 3.855, + "args": { + "External id": 4550410,"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": 9633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941865937.614, "dur": 0.981, + "args": { + "External id": 4550411,"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": 9634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941865943.524, "dur": 86.109, + "args": { + "External id": 4550412,"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": 9635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941865944.289, "dur": 3.664, + "args": { + "External id": 4550413,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941865945.056, "dur": 2.407, + "args": { + "External id": 4550414,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941865946.248, "dur": 1.062, + "args": { + "External id": 4550415,"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": 9638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941865950.755, "dur": 78.358, + "args": { + "External id": 4550416,"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": 9639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941865951.345, "dur": 76.705, + "args": { + "External id": 4550417,"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": 9640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941866035.982, "dur": 5.490, + "args": { + "External id": 4550418,"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": 9641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941866038.578, "dur": 1.465, + "args": { + "External id": 4550419,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941866048.271, "dur": 1.569, + "args": { + "External id": 4550420,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941866058.100, "dur": 10.178, + "args": { + "External id": 4550421,"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": 9644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941866062.416, "dur": 5.624, + "args": { + "External id": 4550422,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941866166.770, "dur": 198.857, + "args": { + "External id": 4550423,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941866168.764, "dur": 2.695, + "args": { + "External id": 4550424,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941866175.316, "dur": 189.883, + "args": { + "External id": 4550425,"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": 9648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941866176.714, "dur": 0.319, + "args": { + "External id": 4550426,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941866177.974, "dur": 23.934, + "args": { + "External id": 4550427,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941866203.706, "dur": 5.228, + "args": { + "External id": 4550428,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941866205.805, "dur": 2.647, + "args": { + "External id": 4550429,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941866212.366, "dur": 22.817, + "args": { + "External id": 4550430,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941866213.444, "dur": 1.722, + "args": { + "External id": 4550431,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941866216.639, "dur": 18.290, + "args": { + "External id": 4550432,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941866219.363, "dur": 2.886, + "args": { + "External id": 4550433,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941866236.826, "dur": 23.046, + "args": { + "External id": 4550434,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941866261.614, "dur": 13.896, + "args": { + "External id": 4550435,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941866278.403, "dur": 16.580, + "args": { + "External id": 4550436,"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": 9659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941866296.408, "dur": 13.570, + "args": { + "External id": 4550437,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941866311.730, "dur": 25.594, + "args": { + "External id": 4550438,"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": 9661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941866316.041, "dur": 1.864, + "args": { + "External id": 4550439,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941866320.009, "dur": 2.624, + "args": { + "External id": 4550440,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941866338.737, "dur": 12.951, + "args": { + "External id": 4550441,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941866352.860, "dur": 11.331, + "args": { + "External id": 4550442,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941866372.232, "dur": 1.601, + "args": { + "External id": 4550443,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941866382.378, "dur": 3.662, + "args": { + "External id": 4550444,"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": 9667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941866384.573, "dur": 0.717, + "args": { + "External id": 4550445,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941866453.173, "dur": 56.364, + "args": { + "External id": 4550446,"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": 9669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941866516.837, "dur": 4.646, + "args": { + "External id": 4550447,"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": 9670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941866519.356, "dur": 1.078, + "args": { + "External id": 4550448,"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": 9671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941866522.783, "dur": 45.780, + "args": { + "External id": 4550449,"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": 9672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941866575.177, "dur": 6.808, + "args": { + "External id": 4550450,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941866577.016, "dur": 4.071, + "args": { + "External id": 4550451,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941866579.193, "dur": 1.676, + "args": { + "External id": 4550452,"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": 9675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941866587.290, "dur": 45.978, + "args": { + "External id": 4550453,"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": 9676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941866588.608, "dur": 43.957, + "args": { + "External id": 4550454,"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": 9677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941866637.058, "dur": 17.196, + "args": { + "External id": 4550455,"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": 9678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941866660.012, "dur": 4.013, + "args": { + "External id": 4550456,"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": 9679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941866662.377, "dur": 0.769, + "args": { + "External id": 4550457,"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": 9680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941866667.701, "dur": 50.548, + "args": { + "External id": 4550458,"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": 9681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941866668.553, "dur": 6.367, + "args": { + "External id": 4550459,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941866671.552, "dur": 2.774, + "args": { + "External id": 4550460,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941866673.048, "dur": 1.125, + "args": { + "External id": 4550461,"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": 9684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941866675.706, "dur": 42.137, + "args": { + "External id": 4550462,"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": 9685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941866676.513, "dur": 40.793, + "args": { + "External id": 4550463,"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": 9686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941866743.415, "dur": 4.146, + "args": { + "External id": 4550464,"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": 9687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941866745.735, "dur": 0.600, + "args": { + "External id": 4550465,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941866753.319, "dur": 1.486, + "args": { + "External id": 4550466,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941866764.900, "dur": 8.214, + "args": { + "External id": 4550467,"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": 9690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941866766.766, "dur": 6.070, + "args": { + "External id": 4550468,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941866859.801, "dur": 229.574, + "args": { + "External id": 4550469,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941866861.696, "dur": 2.331, + "args": { + "External id": 4550470,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941866865.589, "dur": 223.144, + "args": { + "External id": 4550471,"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": 9694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941866867.138, "dur": 0.303, + "args": { + "External id": 4550472,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941866868.389, "dur": 25.754, + "args": { + "External id": 4550473,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941866895.880, "dur": 3.852, + "args": { + "External id": 4550474,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941866897.868, "dur": 1.545, + "args": { + "External id": 4550475,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941866902.617, "dur": 24.661, + "args": { + "External id": 4550476,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941866904.339, "dur": 1.615, + "args": { + "External id": 4550477,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941866907.222, "dur": 19.765, + "args": { + "External id": 4550478,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941866911.822, "dur": 2.393, + "args": { + "External id": 4550479,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941866928.685, "dur": 20.864, + "args": { + "External id": 4550480,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941866950.904, "dur": 14.754, + "args": { + "External id": 4550481,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941866968.187, "dur": 47.067, + "args": { + "External id": 4550482,"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": 9705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941867017.980, "dur": 15.398, + "args": { + "External id": 4550483,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941867035.117, "dur": 25.181, + "args": { + "External id": 4550484,"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": 9707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941867039.714, "dur": 2.447, + "args": { + "External id": 4550485,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941867043.977, "dur": 1.306, + "args": { + "External id": 4550486,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941867061.800, "dur": 13.371, + "args": { + "External id": 4550487,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941867076.163, "dur": 11.371, + "args": { + "External id": 4550488,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941867097.480, "dur": 2.223, + "args": { + "External id": 4550489,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941867108.789, "dur": 3.347, + "args": { + "External id": 4550490,"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": 9713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941867110.689, "dur": 0.586, + "args": { + "External id": 4550491,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941867186.418, "dur": 84.207, + "args": { + "External id": 4550492,"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": 9715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941867274.998, "dur": 4.940, + "args": { + "External id": 4550493,"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": 9716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941867277.628, "dur": 1.389, + "args": { + "External id": 4550494,"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": 9717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941867281.427, "dur": 35.395, + "args": { + "External id": 4550495,"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": 9718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941867321.558, "dur": 7.640, + "args": { + "External id": 4550496,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941867323.096, "dur": 5.286, + "args": { + "External id": 4550497,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941867327.175, "dur": 1.052, + "args": { + "External id": 4550498,"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": 9721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941867335.067, "dur": 55.689, + "args": { + "External id": 4550499,"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": 9722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941867336.129, "dur": 53.906, + "args": { + "External id": 4550500,"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": 9723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941867394.308, "dur": 19.066, + "args": { + "External id": 4550501,"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": 9724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941867418.677, "dur": 4.491, + "args": { + "External id": 4550502,"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": 9725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941867421.039, "dur": 1.252, + "args": { + "External id": 4550503,"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": 9726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941867427.044, "dur": 52.887, + "args": { + "External id": 4550504,"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": 9727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941867430.375, "dur": 5.437, + "args": { + "External id": 4550505,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941867431.088, "dur": 4.120, + "args": { + "External id": 4550506,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941867432.365, "dur": 2.686, + "args": { + "External id": 4550507,"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": 9730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941867436.698, "dur": 42.708, + "args": { + "External id": 4550508,"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": 9731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941867437.278, "dur": 41.236, + "args": { + "External id": 4550509,"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": 9732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941867483.869, "dur": 4.336, + "args": { + "External id": 4550510,"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": 9733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941867486.050, "dur": 0.772, + "args": { + "External id": 4550511,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941867495.782, "dur": 1.697, + "args": { + "External id": 4550512,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941867505.075, "dur": 6.108, + "args": { + "External id": 4550513,"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": 9736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941867506.936, "dur": 4.051, + "args": { + "External id": 4550514,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941867613.480, "dur": 197.401, + "args": { + "External id": 4550515,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941867615.669, "dur": 2.922, + "args": { + "External id": 4550516,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941867622.471, "dur": 187.908, + "args": { + "External id": 4550517,"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": 9740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941867623.800, "dur": 0.298, + "args": { + "External id": 4550518,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941867627.421, "dur": 22.921, + "args": { + "External id": 4550519,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941867652.213, "dur": 3.596, + "args": { + "External id": 4550520,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941867654.240, "dur": 1.218, + "args": { + "External id": 4550521,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941867656.823, "dur": 24.288, + "args": { + "External id": 4550522,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941867658.077, "dur": 3.483, + "args": { + "External id": 4550523,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941867662.918, "dur": 17.817, + "args": { + "External id": 4550524,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941867665.137, "dur": 2.885, + "args": { + "External id": 4550525,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941867684.830, "dur": 22.643, + "args": { + "External id": 4550526,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941867708.587, "dur": 13.677, + "args": { + "External id": 4550527,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941867724.855, "dur": 16.322, + "args": { + "External id": 4550528,"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": 9751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941867742.632, "dur": 13.283, + "args": { + "External id": 4550529,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941867757.608, "dur": 21.697, + "args": { + "External id": 4550530,"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": 9753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941867759.306, "dur": 2.076, + "args": { + "External id": 4550531,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941867763.763, "dur": 0.956, + "args": { + "External id": 4550532,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941867783.019, "dur": 12.940, + "args": { + "External id": 4550533,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941867796.884, "dur": 12.486, + "args": { + "External id": 4550534,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941867816.849, "dur": 1.963, + "args": { + "External id": 4550535,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941867827.210, "dur": 3.793, + "args": { + "External id": 4550536,"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": 9759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941867829.571, "dur": 0.524, + "args": { + "External id": 4550537,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941867891.715, "dur": 53.429, + "args": { + "External id": 4550538,"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": 9761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941867949.485, "dur": 4.664, + "args": { + "External id": 4550539,"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": 9762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941867951.992, "dur": 1.171, + "args": { + "External id": 4550540,"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": 9763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941867955.311, "dur": 24.145, + "args": { + "External id": 4550541,"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": 9764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941868023.201, "dur": 6.835, + "args": { + "External id": 4550542,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941868024.940, "dur": 4.077, + "args": { + "External id": 4550543,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941868027.131, "dur": 1.556, + "args": { + "External id": 4550544,"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": 9767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941868033.086, "dur": 47.302, + "args": { + "External id": 4550545,"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": 9768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941868034.432, "dur": 45.313, + "args": { + "External id": 4550546,"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": 9769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941868084.536, "dur": 17.488, + "args": { + "External id": 4550547,"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": 9770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941868107.532, "dur": 6.064, + "args": { + "External id": 4550548,"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": 9771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941868111.797, "dur": 0.668, + "args": { + "External id": 4550549,"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": 9772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941868117.550, "dur": 52.273, + "args": { + "External id": 4550550,"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": 9773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941868118.346, "dur": 6.030, + "args": { + "External id": 4550551,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941868118.916, "dur": 4.880, + "args": { + "External id": 4550552,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941868122.743, "dur": 0.934, + "args": { + "External id": 4550553,"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": 9776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941868125.192, "dur": 44.214, + "args": { + "External id": 4550554,"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": 9777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941868127.947, "dur": 40.709, + "args": { + "External id": 4550555,"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": 9778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941868180.732, "dur": 3.732, + "args": { + "External id": 4550556,"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": 9779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941868182.506, "dur": 0.775, + "args": { + "External id": 4550557,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941868191.018, "dur": 1.569, + "args": { + "External id": 4550558,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941868200.174, "dur": 8.509, + "args": { + "External id": 4550559,"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": 9782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941868204.412, "dur": 4.027, + "args": { + "External id": 4550560,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941868298.050, "dur": 192.774, + "args": { + "External id": 4550561,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941868302.418, "dur": 2.287, + "args": { + "External id": 4550562,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941868305.861, "dur": 184.364, + "args": { + "External id": 4550563,"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": 9786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941868306.932, "dur": 0.348, + "args": { + "External id": 4550564,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941868308.629, "dur": 22.375, + "args": { + "External id": 4550565,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941868332.403, "dur": 5.455, + "args": { + "External id": 4550566,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941868336.791, "dur": 0.733, + "args": { + "External id": 4550567,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941868338.722, "dur": 25.144, + "args": { + "External id": 4550568,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941868339.951, "dur": 1.551, + "args": { + "External id": 4550569,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941868345.356, "dur": 18.162, + "args": { + "External id": 4550570,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941868348.206, "dur": 2.667, + "args": { + "External id": 4550571,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941868365.203, "dur": 21.203, + "args": { + "External id": 4550572,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941868387.746, "dur": 17.195, + "args": { + "External id": 4550573,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941868407.253, "dur": 14.671, + "args": { + "External id": 4550574,"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": 9797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941868423.051, "dur": 13.913, + "args": { + "External id": 4550575,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941868439.081, "dur": 23.684, + "args": { + "External id": 4550576,"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": 9799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941868440.897, "dur": 1.579, + "args": { + "External id": 4550577,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941868447.305, "dur": 0.966, + "args": { + "External id": 4550578,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941868464.022, "dur": 13.117, + "args": { + "External id": 4550579,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941868478.371, "dur": 10.987, + "args": { + "External id": 4550580,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941868497.010, "dur": 1.595, + "args": { + "External id": 4550581,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941868507.095, "dur": 3.459, + "args": { + "External id": 4550582,"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": 9805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941868509.456, "dur": 0.392, + "args": { + "External id": 4550583,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941868595.189, "dur": 54.459, + "args": { + "External id": 4550584,"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": 9807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941868654.493, "dur": 6.766, + "args": { + "External id": 4550585,"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": 9808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941868659.217, "dur": 0.797, + "args": { + "External id": 4550586,"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": 9809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941868662.496, "dur": 26.281, + "args": { + "External id": 4550587,"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": 9810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941868693.512, "dur": 5.628, + "args": { + "External id": 4550588,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941868694.948, "dur": 3.357, + "args": { + "External id": 4550589,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941868696.784, "dur": 1.335, + "args": { + "External id": 4550590,"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": 9813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941868701.908, "dur": 44.056, + "args": { + "External id": 4550591,"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": 9814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941868705.406, "dur": 39.859, + "args": { + "External id": 4550592,"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": 9815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941868749.593, "dur": 15.277, + "args": { + "External id": 4550593,"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": 9816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941868770.111, "dur": 3.851, + "args": { + "External id": 4550594,"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": 9817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941868772.303, "dur": 0.873, + "args": { + "External id": 4550595,"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": 9818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941868777.491, "dur": 58.445, + "args": { + "External id": 4550596,"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": 9819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941868786.579, "dur": 6.751, + "args": { + "External id": 4550597,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941868789.884, "dur": 2.872, + "args": { + "External id": 4550598,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941868791.881, "dur": 0.746, + "args": { + "External id": 4550599,"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": 9822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941868793.919, "dur": 41.433, + "args": { + "External id": 4550600,"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": 9823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941868794.490, "dur": 40.102, + "args": { + "External id": 4550601,"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": 9824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941868839.372, "dur": 3.880, + "args": { + "External id": 4550602,"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": 9825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941868841.053, "dur": 0.986, + "args": { + "External id": 4550603,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941868851.022, "dur": 1.363, + "args": { + "External id": 4550604,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941868859.428, "dur": 8.882, + "args": { + "External id": 4550605,"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": 9828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941868861.362, "dur": 6.674, + "args": { + "External id": 4550606,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941868951.520, "dur": 240.414, + "args": { + "External id": 4550607,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941868953.755, "dur": 2.407, + "args": { + "External id": 4550608,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941868957.476, "dur": 233.846, + "args": { + "External id": 4550609,"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": 9832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941868961.028, "dur": 0.280, + "args": { + "External id": 4550610,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941868962.512, "dur": 63.439, + "args": { + "External id": 4550611,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941869028.619, "dur": 4.185, + "args": { + "External id": 4550612,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941869031.042, "dur": 1.398, + "args": { + "External id": 4550613,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941869033.726, "dur": 27.917, + "args": { + "External id": 4550614,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941869034.600, "dur": 2.675, + "args": { + "External id": 4550615,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941869038.404, "dur": 22.909, + "args": { + "External id": 4550616,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941869044.108, "dur": 2.889, + "args": { + "External id": 4550617,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941869063.012, "dur": 22.392, + "args": { + "External id": 4550618,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941869086.599, "dur": 14.268, + "args": { + "External id": 4550619,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941869106.034, "dur": 16.040, + "args": { + "External id": 4550620,"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": 9843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941869123.411, "dur": 12.716, + "args": { + "External id": 4550621,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941869137.781, "dur": 22.540, + "args": { + "External id": 4550622,"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": 9845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941869139.711, "dur": 2.111, + "args": { + "External id": 4550623,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941869143.807, "dur": 1.038, + "args": { + "External id": 4550624,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941869161.480, "dur": 13.041, + "args": { + "External id": 4550625,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941869177.776, "dur": 12.478, + "args": { + "External id": 4550626,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941869199.891, "dur": 2.274, + "args": { + "External id": 4550627,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941869211.309, "dur": 3.438, + "args": { + "External id": 4550628,"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": 9851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941869213.507, "dur": 0.422, + "args": { + "External id": 4550629,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941869282.498, "dur": 57.192, + "args": { + "External id": 4550630,"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": 9853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941869343.966, "dur": 4.853, + "args": { + "External id": 4550631,"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": 9854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941869346.692, "dur": 1.039, + "args": { + "External id": 4550632,"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": 9855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941869350.034, "dur": 25.212, + "args": { + "External id": 4550633,"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": 9856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941869379.768, "dur": 8.362, + "args": { + "External id": 4550634,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941869383.694, "dur": 3.812, + "args": { + "External id": 4550635,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941869385.695, "dur": 1.628, + "args": { + "External id": 4550636,"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": 9859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941869390.938, "dur": 40.204, + "args": { + "External id": 4550637,"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": 9860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941869391.990, "dur": 38.365, + "args": { + "External id": 4550638,"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": 9861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941869434.694, "dur": 15.938, + "args": { + "External id": 4550639,"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": 9862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941869455.602, "dur": 6.860, + "args": { + "External id": 4550640,"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": 9863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941869460.417, "dur": 1.198, + "args": { + "External id": 4550641,"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": 9864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941869466.171, "dur": 47.290, + "args": { + "External id": 4550642,"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": 9865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941869467.172, "dur": 3.139, + "args": { + "External id": 4550643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941869467.728, "dur": 2.048, + "args": { + "External id": 4550644,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941869468.794, "dur": 0.835, + "args": { + "External id": 4550645,"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": 9868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941869471.030, "dur": 42.014, + "args": { + "External id": 4550646,"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": 9869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941869471.547, "dur": 40.926, + "args": { + "External id": 4550647,"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": 9870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941869517.183, "dur": 5.640, + "args": { + "External id": 4550648,"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": 9871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941869519.018, "dur": 2.636, + "args": { + "External id": 4550649,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941869546.890, "dur": 2.119, + "args": { + "External id": 4550650,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941869557.269, "dur": 7.219, + "args": { + "External id": 4550651,"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": 9874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941869558.934, "dur": 5.306, + "args": { + "External id": 4550652,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941869651.748, "dur": 224.726, + "args": { + "External id": 4550653,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941869653.449, "dur": 2.387, + "args": { + "External id": 4550654,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941869659.797, "dur": 216.196, + "args": { + "External id": 4550655,"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": 9878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941869661.090, "dur": 0.501, + "args": { + "External id": 4550656,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941869693.649, "dur": 26.673, + "args": { + "External id": 4550657,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941869722.002, "dur": 3.268, + "args": { + "External id": 4550658,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941869723.982, "dur": 0.991, + "args": { + "External id": 4550659,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941869726.130, "dur": 24.730, + "args": { + "External id": 4550660,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941869727.103, "dur": 1.934, + "args": { + "External id": 4550661,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941869730.115, "dur": 20.428, + "args": { + "External id": 4550662,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941869735.015, "dur": 2.917, + "args": { + "External id": 4550663,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941869752.134, "dur": 20.859, + "args": { + "External id": 4550664,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941869774.412, "dur": 14.855, + "args": { + "External id": 4550665,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941869794.145, "dur": 14.370, + "args": { + "External id": 4550666,"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": 9889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941869809.779, "dur": 13.544, + "args": { + "External id": 4550667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941869824.949, "dur": 21.751, + "args": { + "External id": 4550668,"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": 9891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941869826.575, "dur": 1.646, + "args": { + "External id": 4550669,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941869830.215, "dur": 1.640, + "args": { + "External id": 4550670,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941869848.017, "dur": 12.647, + "args": { + "External id": 4550671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941869863.932, "dur": 11.217, + "args": { + "External id": 4550672,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941869882.952, "dur": 1.642, + "args": { + "External id": 4550673,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941869893.449, "dur": 3.501, + "args": { + "External id": 4550674,"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": 9897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941869895.694, "dur": 0.537, + "args": { + "External id": 4550675,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941869960.442, "dur": 93.261, + "args": { + "External id": 4550676,"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": 9899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941870060.015, "dur": 5.705, + "args": { + "External id": 4550677,"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": 9900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941870063.175, "dur": 1.247, + "args": { + "External id": 4550678,"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": 9901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941870067.418, "dur": 27.185, + "args": { + "External id": 4550679,"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": 9902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941870102.748, "dur": 5.105, + "args": { + "External id": 4550680,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941870104.484, "dur": 2.484, + "args": { + "External id": 4550681,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941870106.032, "dur": 0.708, + "args": { + "External id": 4550682,"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": 9905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941870111.080, "dur": 45.037, + "args": { + "External id": 4550683,"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": 9906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941870112.319, "dur": 43.127, + "args": { + "External id": 4550684,"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": 9907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941870159.777, "dur": 15.061, + "args": { + "External id": 4550685,"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": 9908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941870180.294, "dur": 5.912, + "args": { + "External id": 4550686,"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": 9909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941870184.737, "dur": 0.672, + "args": { + "External id": 4550687,"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": 9910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941870190.041, "dur": 50.531, + "args": { + "External id": 4550688,"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": 9911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941870190.899, "dur": 6.171, + "args": { + "External id": 4550689,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941870191.471, "dur": 4.964, + "args": { + "External id": 4550690,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941870195.527, "dur": 0.809, + "args": { + "External id": 4550691,"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": 9914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941870197.601, "dur": 42.641, + "args": { + "External id": 4550692,"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": 9915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941870200.278, "dur": 39.284, + "args": { + "External id": 4550693,"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": 9916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941870243.846, "dur": 4.259, + "args": { + "External id": 4550694,"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": 9917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941870245.838, "dur": 1.076, + "args": { + "External id": 4550695,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941870254.094, "dur": 1.657, + "args": { + "External id": 4550696,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941870263.157, "dur": 8.775, + "args": { + "External id": 4550697,"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": 9920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941870267.618, "dur": 4.051, + "args": { + "External id": 4550698,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941870354.160, "dur": 212.115, + "args": { + "External id": 4550699,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941870356.269, "dur": 2.215, + "args": { + "External id": 4550700,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941870359.913, "dur": 205.883, + "args": { + "External id": 4550701,"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": 9924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941870363.761, "dur": 0.209, + "args": { + "External id": 4550702,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941870364.958, "dur": 22.119, + "args": { + "External id": 4550703,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941870388.642, "dur": 3.363, + "args": { + "External id": 4550704,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941870390.965, "dur": 0.774, + "args": { + "External id": 4550705,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941870393.186, "dur": 32.249, + "args": { + "External id": 4550706,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941870404.260, "dur": 1.720, + "args": { + "External id": 4550707,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941870407.517, "dur": 17.548, + "args": { + "External id": 4550708,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941870409.960, "dur": 2.373, + "args": { + "External id": 4550709,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941870426.592, "dur": 21.969, + "args": { + "External id": 4550710,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941870449.779, "dur": 13.742, + "args": { + "External id": 4550711,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941870465.819, "dur": 14.297, + "args": { + "External id": 4550712,"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": 9935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941870481.330, "dur": 12.774, + "args": { + "External id": 4550713,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941870495.810, "dur": 22.096, + "args": { + "External id": 4550714,"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": 9937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941870497.090, "dur": 1.914, + "args": { + "External id": 4550715,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941870503.319, "dur": 0.789, + "args": { + "External id": 4550716,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941870519.281, "dur": 29.810, + "args": { + "External id": 4550717,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941870550.856, "dur": 13.222, + "args": { + "External id": 4550718,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941870573.971, "dur": 2.199, + "args": { + "External id": 4550719,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941870584.289, "dur": 3.727, + "args": { + "External id": 4550720,"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": 9943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941870586.622, "dur": 0.477, + "args": { + "External id": 4550721,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941870653.651, "dur": 54.008, + "args": { + "External id": 4550722,"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": 9945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941870711.783, "dur": 6.467, + "args": { + "External id": 4550723,"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": 9946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941870716.194, "dur": 1.029, + "args": { + "External id": 4550724,"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": 9947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941870719.373, "dur": 25.384, + "args": { + "External id": 4550725,"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": 9948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941870748.866, "dur": 6.711, + "args": { + "External id": 4550726,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941870750.080, "dur": 4.875, + "args": { + "External id": 4550727,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941870752.011, "dur": 2.708, + "args": { + "External id": 4550728,"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": 9951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941870758.057, "dur": 41.662, + "args": { + "External id": 4550729,"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": 9952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941870761.199, "dur": 37.732, + "args": { + "External id": 4550730,"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": 9953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941870803.083, "dur": 15.731, + "args": { + "External id": 4550731,"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": 9954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941870823.262, "dur": 26.545, + "args": { + "External id": 4550732,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941870825.380, "dur": 24.072, + "args": { + "External id": 4550733,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941870830.506, "dur": 1.090, + "args": { + "External id": 4550734,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941870854.527, "dur": 29.111, + "args": { + "External id": 4550735,"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": 9958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941870856.267, "dur": 27.163, + "args": { + "External id": 4550736,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], [], []], "Ev Idx": 9959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941870860.868, "dur": 4.184, + "args": { + "External id": 4550737,"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": 9960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941870868.700, "dur": 14.292, + "args": { + "External id": 4550738,"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": 9961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941870896.541, "dur": 4.497, + "args": { + "External id": 4550739,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941870898.240, "dur": 2.526, + "args": { + "External id": 4550740,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941870902.118, "dur": 0.883, + "args": { + "External id": 4550741,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941870902.467, "dur": 0.462, + "args": { + "External id": 4550742,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941870946.771, "dur": 22.196, + "args": { + "External id": 4550743,"Sequence number": 45295804, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941870970.695, "dur": 51.190, + "args": { + "External id": 4550744,"Sequence number": 45295805, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9967 + } + }, + { + "ph": "s", "id": 9, "pid": 1336753, "tid": 1336753, "ts": 1696941870970.695, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941871029.832, "dur": 6.732, + "args": { + "External id": 4550745,"Sequence number": 45295806, "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": 9968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941871033.875, "dur": 1.244, + "args": { + "External id": 4550746,"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": 9969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1696941871044.750, "dur": 6.141, + "args": { + "External id": 4550747,"Sequence number": 45295806, "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": 9970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941871048.724, "dur": 1.002, + "args": { + "External id": 4550748,"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": 9971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941871052.228, "dur": 2.840, + "args": { + "External id": 4550749,"Sequence number": 45295806, "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": 9972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941871053.678, "dur": 0.819, + "args": { + "External id": 4550750,"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": 9973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941871061.876, "dur": 7.093, + "args": { + "External id": 4550751,"Sequence number": 45295806, "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": 9974 + } + }, + { + "ph": "s", "id": 8, "pid": 1336753, "tid": 1336753, "ts": 1696941871061.876, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941871066.239, "dur": 1.355, + "args": { + "External id": 4550752,"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": 9975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941871070.035, "dur": 5.585, + "args": { + "External id": 4550753,"Sequence number": 45295807, "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": 9976 + } + }, + { + "ph": "s", "id": 7, "pid": 1336753, "tid": 1336753, "ts": 1696941871070.035, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941871073.904, "dur": 0.914, + "args": { + "External id": 4550754,"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": 9977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1336753, + "ts": 1696941871076.583, "dur": 7.340, + "args": { + "External id": 4550755,"Sequence number": 45295808, "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": 9978 + } + }, + { + "ph": "s", "id": 6, "pid": 1336753, "tid": 1336753, "ts": 1696941871076.583, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941871082.118, "dur": 0.957, + "args": { + "External id": 4550756,"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": 9979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941871084.819, "dur": 6.139, + "args": { + "External id": 4550757,"Sequence number": 45295809, "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": 9980 + } + }, + { + "ph": "s", "id": 5, "pid": 1336753, "tid": 1336753, "ts": 1696941871084.819, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941871087.312, "dur": 2.476, + "args": { + "External id": 4550758,"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": 9981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1696941871095.015, "dur": 34.460, + "args": { + "External id": 4550759,"Sequence number": 45295810, "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": 9982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1696941871096.385, "dur": 32.885, + "args": { + "External id": 4550760,"Sequence number": 45295810, "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": 9983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941871098.957, "dur": 7.144, + "args": { + "External id": 4550761,"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": 9984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941871101.242, "dur": 4.348, + "args": { + "External id": 4550762,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941871106.945, "dur": 21.894, + "args": { + "External id": 4550763,"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": 9986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941871156.368, "dur": 5.604, + "args": { + "External id": 4550764,"Sequence number": 45295810, "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": 9987 + } + }, + { + "ph": "s", "id": 4, "pid": 1336753, "tid": 1336753, "ts": 1696941871156.368, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941871164.289, "dur": 1.208, + "args": { + "External id": 4550765,"Sequence number": 45295811, "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": 9988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 1336753, "tid": 1336753, + "ts": 1696941871197.647, "dur": 44622.074, + "args": { + "External id": 4550766,"Sequence number": 45295811, "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": 9989 + } + }, + { + "ph": "s", "id": 3, "pid": 1336753, "tid": 1336753, "ts": 1696941871197.647, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1696941871212.615, "dur": 26.799, + "args": { + "External id": 4550767,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1696941871213.237, "dur": 25.964, + "args": { + "External id": 4550768,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941871214.314, "dur": 7.467, + "args": { + "External id": 4550769,"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": 9992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941871215.631, "dur": 5.703, + "args": { + "External id": 4550770,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941871222.423, "dur": 16.466, + "args": { + "External id": 4550771,"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": 9994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941871254.150, "dur": 27.127, + "args": { + "External id": 4550772,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941871255.402, "dur": 8.087, + "args": { + "External id": 4550773,"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": 9996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941871259.015, "dur": 4.120, + "args": { + "External id": 4550774,"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": 9997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941871264.963, "dur": 16.117, + "args": { + "External id": 4550775,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941871266.612, "dur": 14.043, + "args": { + "External id": 4550776,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941871284.704, "dur": 19.423, + "args": { + "External id": 4550777,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 10000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941871285.299, "dur": 4.532, + "args": { + "External id": 4550778,"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": 10001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941871286.661, "dur": 2.917, + "args": { + "External id": 4550779,"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": 10002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941871290.444, "dur": 13.504, + "args": { + "External id": 4550780,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941871290.867, "dur": 12.810, + "args": { + "External id": 4550781,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[32000, 2048], []], "Ev Idx": 10004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1696941871309.252, "dur": 19.578, + "args": { + "External id": 4550782,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 10005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941871313.256, "dur": 3.266, + "args": { + "External id": 4550783,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696941871317.199, "dur": 11.370, + "args": { + "External id": 4550784,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 10007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941871317.743, "dur": 10.514, + "args": { + "External id": 4550785,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 10008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336753, "tid": 1336753, + "ts": 1696941871333.393, "dur": 23.846, + "args": { + "External id": 4550786,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 10009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941871359.609, "dur": 48.234, + "args": { + "External id": 4550787,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 10010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941871361.456, "dur": 46.024, + "args": { + "External id": 4550788,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941871367.908, "dur": 0.844, + "args": { + "External id": 4550789,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941871370.040, "dur": 20.657, + "args": { + "External id": 4550790,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941871371.516, "dur": 18.977, + "args": { + "External id": 4550791,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 10014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941871373.708, "dur": 2.830, + "args": { + "External id": 4550792,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941871377.428, "dur": 12.655, + "args": { + "External id": 4550793,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 10016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336753, "tid": 1336753, + "ts": 1696941871414.167, "dur": 38720.514, + "args": { + "External id": 4550794,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 10017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336753, "tid": 1336753, + "ts": 1696941871415.834, "dur": 38717.489, + "args": { + "External id": 4550795,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 10018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941910145.797, "dur": 6.638, + "args": { + "External id": 4550796,"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": 10019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941910149.658, "dur": 1.209, + "args": { + "External id": 4550797,"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": 10020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941910157.276, "dur": 104.295, + "args": { + "External id": 4550798,"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": 10021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941910158.535, "dur": 9.217, + "args": { + "External id": 4550799,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941910160.797, "dur": 5.910, + "args": { + "External id": 4550800,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941910165.290, "dur": 1.164, + "args": { + "External id": 4550801,"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": 10024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941910169.376, "dur": 91.426, + "args": { + "External id": 4550802,"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": 10025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941910170.995, "dur": 88.943, + "args": { + "External id": 4550803,"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": 10026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941910265.332, "dur": 4.172, + "args": { + "External id": 4550804,"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": 10027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941910267.599, "dur": 0.536, + "args": { + "External id": 4550805,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941910276.622, "dur": 2.504, + "args": { + "External id": 4550806,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941910290.024, "dur": 6.609, + "args": { + "External id": 4550807,"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": 10030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941910292.532, "dur": 3.795, + "args": { + "External id": 4550808,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941910420.486, "dur": 228.399, + "args": { + "External id": 4550809,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941910425.274, "dur": 2.341, + "args": { + "External id": 4550810,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941910429.122, "dur": 219.218, + "args": { + "External id": 4550811,"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": 10034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941910430.658, "dur": 0.381, + "args": { + "External id": 4550812,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941910432.535, "dur": 26.792, + "args": { + "External id": 4550813,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941910463.220, "dur": 5.931, + "args": { + "External id": 4550814,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941910468.105, "dur": 0.762, + "args": { + "External id": 4550815,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941910470.476, "dur": 24.597, + "args": { + "External id": 4550816,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941910471.358, "dur": 1.517, + "args": { + "External id": 4550817,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941910474.135, "dur": 20.670, + "args": { + "External id": 4550818,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941910477.976, "dur": 3.399, + "args": { + "External id": 4550819,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941910496.772, "dur": 26.430, + "args": { + "External id": 4550820,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941910524.765, "dur": 29.759, + "args": { + "External id": 4550821,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941910558.635, "dur": 17.005, + "args": { + "External id": 4550822,"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": 10045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941910577.233, "dur": 14.614, + "args": { + "External id": 4550823,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941910596.291, "dur": 23.286, + "args": { + "External id": 4550824,"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": 10047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941910598.110, "dur": 2.095, + "args": { + "External id": 4550825,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941910602.951, "dur": 1.256, + "args": { + "External id": 4550826,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941910620.848, "dur": 12.934, + "args": { + "External id": 4550827,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941910635.063, "dur": 11.984, + "args": { + "External id": 4550828,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941910656.474, "dur": 2.099, + "args": { + "External id": 4550829,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941910667.548, "dur": 4.497, + "args": { + "External id": 4550830,"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": 10053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941910669.920, "dur": 1.134, + "args": { + "External id": 4550831,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941910748.254, "dur": 67.043, + "args": { + "External id": 4550832,"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": 10055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941910820.290, "dur": 5.883, + "args": { + "External id": 4550833,"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": 10056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941910822.641, "dur": 1.093, + "args": { + "External id": 4550834,"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": 10057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941910827.842, "dur": 28.776, + "args": { + "External id": 4550835,"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": 10058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941910862.354, "dur": 8.788, + "args": { + "External id": 4550836,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941910864.091, "dur": 6.156, + "args": { + "External id": 4550837,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941910868.463, "dur": 1.555, + "args": { + "External id": 4550838,"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": 10061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941910873.990, "dur": 43.469, + "args": { + "External id": 4550839,"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": 10062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941910875.047, "dur": 41.753, + "args": { + "External id": 4550840,"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": 10063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941910921.841, "dur": 16.534, + "args": { + "External id": 4550841,"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": 10064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941910944.210, "dur": 4.250, + "args": { + "External id": 4550842,"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": 10065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941910946.568, "dur": 0.776, + "args": { + "External id": 4550843,"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": 10066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941910954.894, "dur": 86.231, + "args": { + "External id": 4550844,"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": 10067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941910955.680, "dur": 3.589, + "args": { + "External id": 4550845,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941910956.405, "dur": 2.374, + "args": { + "External id": 4550846,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941910957.927, "dur": 0.730, + "args": { + "External id": 4550847,"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": 10070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941910959.919, "dur": 80.654, + "args": { + "External id": 4550848,"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": 10071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941910960.434, "dur": 79.101, + "args": { + "External id": 4550849,"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": 10072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941911049.308, "dur": 6.937, + "args": { + "External id": 4550850,"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": 10073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941911051.876, "dur": 2.872, + "args": { + "External id": 4550851,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941911063.228, "dur": 1.492, + "args": { + "External id": 4550852,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941911073.365, "dur": 7.168, + "args": { + "External id": 4550853,"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": 10076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941911075.720, "dur": 4.560, + "args": { + "External id": 4550854,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941911178.147, "dur": 195.525, + "args": { + "External id": 4550855,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941911180.415, "dur": 2.219, + "args": { + "External id": 4550856,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941911184.034, "dur": 189.197, + "args": { + "External id": 4550857,"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": 10080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941911185.448, "dur": 0.313, + "args": { + "External id": 4550858,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941911186.801, "dur": 25.857, + "args": { + "External id": 4550859,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941911214.311, "dur": 3.201, + "args": { + "External id": 4550860,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941911216.510, "dur": 0.757, + "args": { + "External id": 4550861,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941911218.415, "dur": 27.902, + "args": { + "External id": 4550862,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941911219.565, "dur": 1.728, + "args": { + "External id": 4550863,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941911222.472, "dur": 23.532, + "args": { + "External id": 4550864,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941911229.563, "dur": 3.392, + "args": { + "External id": 4550865,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941911247.766, "dur": 21.994, + "args": { + "External id": 4550866,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941911271.103, "dur": 15.298, + "args": { + "External id": 4550867,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941911289.167, "dur": 15.046, + "args": { + "External id": 4550868,"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": 10091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941911305.681, "dur": 12.969, + "args": { + "External id": 4550869,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941911320.634, "dur": 22.023, + "args": { + "External id": 4550870,"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": 10093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941911322.406, "dur": 1.968, + "args": { + "External id": 4550871,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941911326.898, "dur": 1.029, + "args": { + "External id": 4550872,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941911346.397, "dur": 12.932, + "args": { + "External id": 4550873,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941911360.487, "dur": 11.587, + "args": { + "External id": 4550874,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941911380.423, "dur": 1.524, + "args": { + "External id": 4550875,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941911390.401, "dur": 3.384, + "args": { + "External id": 4550876,"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": 10099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941911392.578, "dur": 0.347, + "args": { + "External id": 4550877,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941911458.995, "dur": 52.143, + "args": { + "External id": 4550878,"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": 10101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941911515.751, "dur": 4.287, + "args": { + "External id": 4550879,"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": 10102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941911517.904, "dur": 1.085, + "args": { + "External id": 4550880,"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": 10103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941911523.499, "dur": 43.537, + "args": { + "External id": 4550881,"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": 10104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941911573.662, "dur": 5.284, + "args": { + "External id": 4550882,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941911574.933, "dur": 3.218, + "args": { + "External id": 4550883,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941911576.900, "dur": 1.059, + "args": { + "External id": 4550884,"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": 10107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941911581.756, "dur": 46.099, + "args": { + "External id": 4550885,"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": 10108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941911583.204, "dur": 44.000, + "args": { + "External id": 4550886,"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": 10109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941911632.199, "dur": 16.798, + "args": { + "External id": 4550887,"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": 10110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941911657.067, "dur": 3.640, + "args": { + "External id": 4550888,"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": 10111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941911659.123, "dur": 0.649, + "args": { + "External id": 4550889,"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": 10112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941911664.705, "dur": 51.762, + "args": { + "External id": 4550890,"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": 10113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941911665.603, "dur": 5.957, + "args": { + "External id": 4550891,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941911666.415, "dur": 4.523, + "args": { + "External id": 4550892,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941911670.067, "dur": 0.744, + "args": { + "External id": 4550893,"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": 10116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941911674.428, "dur": 41.612, + "args": { + "External id": 4550894,"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": 10117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941911675.265, "dur": 40.283, + "args": { + "External id": 4550895,"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": 10118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941911720.153, "dur": 4.052, + "args": { + "External id": 4550896,"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": 10119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941911722.135, "dur": 0.941, + "args": { + "External id": 4550897,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941911730.038, "dur": 1.602, + "args": { + "External id": 4550898,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941911738.826, "dur": 6.104, + "args": { + "External id": 4550899,"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": 10122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941911740.966, "dur": 3.721, + "args": { + "External id": 4550900,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941911828.243, "dur": 232.626, + "args": { + "External id": 4550901,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941911830.621, "dur": 2.470, + "args": { + "External id": 4550902,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941911834.327, "dur": 225.999, + "args": { + "External id": 4550903,"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": 10126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941911837.878, "dur": 0.317, + "args": { + "External id": 4550904,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941911839.924, "dur": 21.303, + "args": { + "External id": 4550905,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941911862.566, "dur": 4.132, + "args": { + "External id": 4550906,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941911865.198, "dur": 1.277, + "args": { + "External id": 4550907,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941911867.552, "dur": 29.599, + "args": { + "External id": 4550908,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941911870.899, "dur": 1.893, + "args": { + "External id": 4550909,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941911873.984, "dur": 22.900, + "args": { + "External id": 4550910,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941911878.974, "dur": 2.674, + "args": { + "External id": 4550911,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941911898.527, "dur": 22.663, + "args": { + "External id": 4550912,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941911922.375, "dur": 13.615, + "args": { + "External id": 4550913,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941911938.277, "dur": 15.599, + "args": { + "External id": 4550914,"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": 10137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941911955.254, "dur": 13.224, + "args": { + "External id": 4550915,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941911970.511, "dur": 56.692, + "args": { + "External id": 4550916,"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": 10139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941911971.898, "dur": 1.703, + "args": { + "External id": 4550917,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941911976.057, "dur": 1.018, + "args": { + "External id": 4550918,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941912032.194, "dur": 13.696, + "args": { + "External id": 4550919,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941912046.842, "dur": 12.235, + "args": { + "External id": 4550920,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941912068.055, "dur": 2.063, + "args": { + "External id": 4550921,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941912078.330, "dur": 3.787, + "args": { + "External id": 4550922,"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": 10145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941912080.850, "dur": 0.444, + "args": { + "External id": 4550923,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941912149.620, "dur": 87.028, + "args": { + "External id": 4550924,"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": 10147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941912241.286, "dur": 9.108, + "args": { + "External id": 4550925,"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": 10148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941912245.688, "dur": 3.330, + "args": { + "External id": 4550926,"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": 10149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941912251.766, "dur": 27.935, + "args": { + "External id": 4550927,"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": 10150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941912284.021, "dur": 5.067, + "args": { + "External id": 4550928,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941912285.405, "dur": 3.045, + "args": { + "External id": 4550929,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941912287.419, "dur": 0.836, + "args": { + "External id": 4550930,"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": 10153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941912291.415, "dur": 71.385, + "args": { + "External id": 4550931,"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": 10154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941912292.551, "dur": 69.719, + "args": { + "External id": 4550932,"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": 10155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941912368.344, "dur": 22.578, + "args": { + "External id": 4550933,"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": 10156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941912396.027, "dur": 3.543, + "args": { + "External id": 4550934,"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": 10157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941912398.118, "dur": 0.612, + "args": { + "External id": 4550935,"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": 10158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941912403.308, "dur": 51.394, + "args": { + "External id": 4550936,"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": 10159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941912404.219, "dur": 6.050, + "args": { + "External id": 4550937,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941912404.854, "dur": 4.959, + "args": { + "External id": 4550938,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941912408.919, "dur": 0.752, + "args": { + "External id": 4550939,"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": 10162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941912411.028, "dur": 43.154, + "args": { + "External id": 4550940,"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": 10163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941912411.536, "dur": 41.890, + "args": { + "External id": 4550941,"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": 10164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941912458.069, "dur": 17.636, + "args": { + "External id": 4550942,"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": 10165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941912473.980, "dur": 0.716, + "args": { + "External id": 4550943,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941912480.629, "dur": 1.287, + "args": { + "External id": 4550944,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941912491.560, "dur": 8.015, + "args": { + "External id": 4550945,"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": 10168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941912493.285, "dur": 6.000, + "args": { + "External id": 4550946,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941912596.625, "dur": 191.688, + "args": { + "External id": 4550947,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941912598.798, "dur": 2.958, + "args": { + "External id": 4550948,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941912603.199, "dur": 184.725, + "args": { + "External id": 4550949,"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": 10172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941912604.420, "dur": 0.301, + "args": { + "External id": 4550950,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941912605.969, "dur": 26.973, + "args": { + "External id": 4550951,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941912636.666, "dur": 3.805, + "args": { + "External id": 4550952,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941912639.094, "dur": 1.042, + "args": { + "External id": 4550953,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941912641.352, "dur": 24.313, + "args": { + "External id": 4550954,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941912642.281, "dur": 1.491, + "args": { + "External id": 4550955,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941912644.983, "dur": 20.371, + "args": { + "External id": 4550956,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941912650.131, "dur": 2.953, + "args": { + "External id": 4550957,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941912666.944, "dur": 21.723, + "args": { + "External id": 4550958,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941912689.776, "dur": 14.919, + "args": { + "External id": 4550959,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941912707.441, "dur": 13.887, + "args": { + "External id": 4550960,"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": 10183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941912722.748, "dur": 13.281, + "args": { + "External id": 4550961,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941912740.300, "dur": 20.567, + "args": { + "External id": 4550962,"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": 10185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941912741.830, "dur": 1.827, + "args": { + "External id": 4550963,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941912745.669, "dur": 0.928, + "args": { + "External id": 4550964,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941912762.096, "dur": 12.845, + "args": { + "External id": 4550965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941912776.066, "dur": 10.858, + "args": { + "External id": 4550966,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941912794.257, "dur": 2.026, + "args": { + "External id": 4550967,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941912803.928, "dur": 3.480, + "args": { + "External id": 4550968,"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": 10191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941912806.322, "dur": 0.367, + "args": { + "External id": 4550969,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941912869.990, "dur": 51.903, + "args": { + "External id": 4550970,"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": 10193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941912926.344, "dur": 4.733, + "args": { + "External id": 4550971,"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": 10194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941912928.699, "dur": 1.348, + "args": { + "External id": 4550972,"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": 10195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941912932.208, "dur": 24.828, + "args": { + "External id": 4550973,"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": 10196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941912961.007, "dur": 8.363, + "args": { + "External id": 4550974,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941912962.821, "dur": 5.955, + "args": { + "External id": 4550975,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941912967.739, "dur": 0.851, + "args": { + "External id": 4550976,"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": 10199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941912971.763, "dur": 79.710, + "args": { + "External id": 4550977,"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": 10200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941912972.814, "dur": 77.543, + "args": { + "External id": 4550978,"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": 10201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941913057.394, "dur": 16.496, + "args": { + "External id": 4550979,"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": 10202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941913080.249, "dur": 4.207, + "args": { + "External id": 4550980,"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": 10203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941913082.754, "dur": 0.770, + "args": { + "External id": 4550981,"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": 10204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941913088.494, "dur": 53.005, + "args": { + "External id": 4550982,"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": 10205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941913091.918, "dur": 5.725, + "args": { + "External id": 4550983,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941913092.786, "dur": 4.243, + "args": { + "External id": 4550984,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941913094.223, "dur": 2.605, + "args": { + "External id": 4550985,"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": 10208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941913098.588, "dur": 42.435, + "args": { + "External id": 4550986,"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": 10209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941913099.235, "dur": 41.103, + "args": { + "External id": 4550987,"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": 10210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941913144.946, "dur": 3.613, + "args": { + "External id": 4550988,"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": 10211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941913146.791, "dur": 0.677, + "args": { + "External id": 4550989,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941913154.780, "dur": 1.334, + "args": { + "External id": 4550990,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941913165.686, "dur": 5.723, + "args": { + "External id": 4550991,"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": 10214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941913167.500, "dur": 3.687, + "args": { + "External id": 4550992,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941913250.803, "dur": 196.465, + "args": { + "External id": 4550993,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941913253.213, "dur": 2.613, + "args": { + "External id": 4550994,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941913256.856, "dur": 189.867, + "args": { + "External id": 4550995,"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": 10218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941913257.992, "dur": 0.242, + "args": { + "External id": 4550996,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941913264.276, "dur": 22.184, + "args": { + "External id": 4550997,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941913293.188, "dur": 3.250, + "args": { + "External id": 4550998,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941913295.350, "dur": 0.771, + "args": { + "External id": 4550999,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941913297.377, "dur": 25.091, + "args": { + "External id": 4551000,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941913298.128, "dur": 4.030, + "args": { + "External id": 4551001,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941913303.452, "dur": 18.440, + "args": { + "External id": 4551002,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941913306.103, "dur": 2.852, + "args": { + "External id": 4551003,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941913323.608, "dur": 21.948, + "args": { + "External id": 4551004,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941913346.551, "dur": 13.641, + "args": { + "External id": 4551005,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941913362.643, "dur": 14.830, + "args": { + "External id": 4551006,"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": 10229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941913381.169, "dur": 12.507, + "args": { + "External id": 4551007,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941913395.492, "dur": 20.714, + "args": { + "External id": 4551008,"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": 10231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941913396.833, "dur": 1.625, + "args": { + "External id": 4551009,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941913400.510, "dur": 1.083, + "args": { + "External id": 4551010,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941913417.440, "dur": 12.821, + "args": { + "External id": 4551011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941913431.126, "dur": 11.974, + "args": { + "External id": 4551012,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941913452.730, "dur": 1.553, + "args": { + "External id": 4551013,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941913461.567, "dur": 3.546, + "args": { + "External id": 4551014,"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": 10237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941913463.883, "dur": 0.444, + "args": { + "External id": 4551015,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941913547.935, "dur": 59.114, + "args": { + "External id": 4551016,"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": 10239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941913612.030, "dur": 5.417, + "args": { + "External id": 4551017,"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": 10240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941913615.155, "dur": 0.894, + "args": { + "External id": 4551018,"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": 10241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941913618.660, "dur": 26.134, + "args": { + "External id": 4551019,"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": 10242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941913649.547, "dur": 10.004, + "args": { + "External id": 4551020,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941913653.570, "dur": 5.143, + "args": { + "External id": 4551021,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941913655.538, "dur": 2.971, + "args": { + "External id": 4551022,"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": 10245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941913662.116, "dur": 39.188, + "args": { + "External id": 4551023,"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": 10246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941913663.079, "dur": 37.625, + "args": { + "External id": 4551024,"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": 10247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941913704.857, "dur": 16.091, + "args": { + "External id": 4551025,"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": 10248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941913726.150, "dur": 5.621, + "args": { + "External id": 4551026,"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": 10249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941913730.190, "dur": 0.788, + "args": { + "External id": 4551027,"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": 10250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941913735.388, "dur": 46.303, + "args": { + "External id": 4551028,"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": 10251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941913736.145, "dur": 3.761, + "args": { + "External id": 4551029,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941913736.930, "dur": 2.250, + "args": { + "External id": 4551030,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941913738.249, "dur": 0.802, + "args": { + "External id": 4551031,"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": 10254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941913740.535, "dur": 40.625, + "args": { + "External id": 4551032,"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": 10255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941913741.161, "dur": 39.498, + "args": { + "External id": 4551033,"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": 10256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941913787.765, "dur": 3.698, + "args": { + "External id": 4551034,"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": 10257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941913789.496, "dur": 0.918, + "args": { + "External id": 4551035,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941913797.086, "dur": 1.510, + "args": { + "External id": 4551036,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941913806.091, "dur": 6.755, + "args": { + "External id": 4551037,"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": 10260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941913808.206, "dur": 4.379, + "args": { + "External id": 4551038,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941913898.140, "dur": 229.198, + "args": { + "External id": 4551039,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941913900.031, "dur": 2.282, + "args": { + "External id": 4551040,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941913905.773, "dur": 221.083, + "args": { + "External id": 4551041,"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": 10264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941913906.847, "dur": 0.241, + "args": { + "External id": 4551042,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941913908.343, "dur": 24.781, + "args": { + "External id": 4551043,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941913934.671, "dur": 6.031, + "args": { + "External id": 4551044,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941913937.406, "dur": 2.964, + "args": { + "External id": 4551045,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941913941.558, "dur": 24.197, + "args": { + "External id": 4551046,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941913942.292, "dur": 1.594, + "args": { + "External id": 4551047,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941913947.092, "dur": 18.355, + "args": { + "External id": 4551048,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941913949.622, "dur": 2.568, + "args": { + "External id": 4551049,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941913967.050, "dur": 56.257, + "args": { + "External id": 4551050,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914025.760, "dur": 15.692, + "args": { + "External id": 4551051,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941914044.299, "dur": 14.692, + "args": { + "External id": 4551052,"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": 10275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914060.317, "dur": 13.306, + "args": { + "External id": 4551053,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941914075.564, "dur": 23.698, + "args": { + "External id": 4551054,"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": 10277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914077.790, "dur": 1.991, + "args": { + "External id": 4551055,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941914083.958, "dur": 1.156, + "args": { + "External id": 4551056,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914100.451, "dur": 13.187, + "args": { + "External id": 4551057,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914114.594, "dur": 10.842, + "args": { + "External id": 4551058,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941914135.136, "dur": 2.245, + "args": { + "External id": 4551059,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941914146.088, "dur": 3.283, + "args": { + "External id": 4551060,"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": 10283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941914148.036, "dur": 0.542, + "args": { + "External id": 4551061,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941914215.550, "dur": 54.646, + "args": { + "External id": 4551062,"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": 10285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941914275.014, "dur": 9.817, + "args": { + "External id": 4551063,"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": 10286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941914280.501, "dur": 3.152, + "args": { + "External id": 4551064,"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": 10287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914286.050, "dur": 24.792, + "args": { + "External id": 4551065,"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": 10288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941914315.204, "dur": 5.010, + "args": { + "External id": 4551066,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941914316.492, "dur": 2.913, + "args": { + "External id": 4551067,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941914318.193, "dur": 0.863, + "args": { + "External id": 4551068,"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": 10291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941914322.700, "dur": 39.926, + "args": { + "External id": 4551069,"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": 10292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941914324.187, "dur": 37.898, + "args": { + "External id": 4551070,"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": 10293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914368.421, "dur": 15.003, + "args": { + "External id": 4551071,"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": 10294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941914388.401, "dur": 3.834, + "args": { + "External id": 4551072,"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": 10295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941914390.536, "dur": 0.832, + "args": { + "External id": 4551073,"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": 10296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941914395.712, "dur": 47.507, + "args": { + "External id": 4551074,"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": 10297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941914396.638, "dur": 5.614, + "args": { + "External id": 4551075,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941914397.252, "dur": 4.269, + "args": { + "External id": 4551076,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941914400.470, "dur": 0.947, + "args": { + "External id": 4551077,"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": 10300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941914402.760, "dur": 40.064, + "args": { + "External id": 4551078,"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": 10301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941914403.304, "dur": 39.008, + "args": { + "External id": 4551079,"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": 10302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941914446.740, "dur": 3.988, + "args": { + "External id": 4551080,"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": 10303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941914448.691, "dur": 0.778, + "args": { + "External id": 4551081,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941914455.511, "dur": 1.545, + "args": { + "External id": 4551082,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941914464.025, "dur": 9.184, + "args": { + "External id": 4551083,"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": 10306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941914467.988, "dur": 4.951, + "args": { + "External id": 4551084,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941914568.559, "dur": 189.802, + "args": { + "External id": 4551085,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941914570.501, "dur": 5.430, + "args": { + "External id": 4551086,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941914577.655, "dur": 180.152, + "args": { + "External id": 4551087,"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": 10310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941914578.984, "dur": 0.365, + "args": { + "External id": 4551088,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941914580.188, "dur": 22.549, + "args": { + "External id": 4551089,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941914604.427, "dur": 5.448, + "args": { + "External id": 4551090,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941914608.547, "dur": 1.003, + "args": { + "External id": 4551091,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941914610.693, "dur": 24.642, + "args": { + "External id": 4551092,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941914611.830, "dur": 1.526, + "args": { + "External id": 4551093,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941914616.392, "dur": 18.709, + "args": { + "External id": 4551094,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914618.811, "dur": 2.798, + "args": { + "External id": 4551095,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941914636.520, "dur": 21.545, + "args": { + "External id": 4551096,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914659.166, "dur": 13.525, + "args": { + "External id": 4551097,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941914674.879, "dur": 14.614, + "args": { + "External id": 4551098,"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": 10321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914690.592, "dur": 12.846, + "args": { + "External id": 4551099,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941914705.074, "dur": 24.602, + "args": { + "External id": 4551100,"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": 10323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914706.503, "dur": 1.795, + "args": { + "External id": 4551101,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941914712.587, "dur": 3.403, + "args": { + "External id": 4551102,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914731.147, "dur": 12.938, + "args": { + "External id": 4551103,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914744.996, "dur": 11.971, + "args": { + "External id": 4551104,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941914764.535, "dur": 1.867, + "args": { + "External id": 4551105,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941914775.187, "dur": 3.348, + "args": { + "External id": 4551106,"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": 10329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941914777.311, "dur": 0.347, + "args": { + "External id": 4551107,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941914838.671, "dur": 51.704, + "args": { + "External id": 4551108,"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": 10331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941914894.810, "dur": 6.138, + "args": { + "External id": 4551109,"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": 10332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941914898.930, "dur": 0.933, + "args": { + "External id": 4551110,"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": 10333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914902.154, "dur": 23.209, + "args": { + "External id": 4551111,"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": 10334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941914929.081, "dur": 5.513, + "args": { + "External id": 4551112,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941914930.574, "dur": 3.396, + "args": { + "External id": 4551113,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941914932.313, "dur": 1.458, + "args": { + "External id": 4551114,"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": 10337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941914937.248, "dur": 40.549, + "args": { + "External id": 4551115,"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": 10338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941914940.732, "dur": 36.315, + "args": { + "External id": 4551116,"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": 10339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941914981.189, "dur": 51.609, + "args": { + "External id": 4551117,"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": 10340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941915040.685, "dur": 4.409, + "args": { + "External id": 4551118,"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": 10341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941915043.289, "dur": 0.738, + "args": { + "External id": 4551119,"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": 10342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1696941915049.189, "dur": 55.910, + "args": { + "External id": 4551120,"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": 10343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941915050.164, "dur": 6.221, + "args": { + "External id": 4551121,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941915051.092, "dur": 4.801, + "args": { + "External id": 4551122,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941915055.000, "dur": 0.782, + "args": { + "External id": 4551123,"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": 10346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941915057.234, "dur": 47.442, + "args": { + "External id": 4551124,"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": 10347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941915057.936, "dur": 46.095, + "args": { + "External id": 4551125,"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": 10348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941915108.979, "dur": 3.473, + "args": { + "External id": 4551126,"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": 10349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941915110.599, "dur": 0.897, + "args": { + "External id": 4551127,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941915118.516, "dur": 1.418, + "args": { + "External id": 4551128,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941915129.136, "dur": 6.446, + "args": { + "External id": 4551129,"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": 10352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941915131.096, "dur": 4.292, + "args": { + "External id": 4551130,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941915215.226, "dur": 188.987, + "args": { + "External id": 4551131,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941915219.685, "dur": 2.008, + "args": { + "External id": 4551132,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336753, "tid": 1336753, + "ts": 1696941915222.876, "dur": 180.902, + "args": { + "External id": 4551133,"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": 10356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336753, "tid": 1336753, + "ts": 1696941915224.074, "dur": 0.280, + "args": { + "External id": 4551134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336753, "tid": 1336753, + "ts": 1696941915228.194, "dur": 22.835, + "args": { + "External id": 4551135,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336753, "tid": 1336753, + "ts": 1696941915252.230, "dur": 5.818, + "args": { + "External id": 4551136,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941915256.916, "dur": 0.772, + "args": { + "External id": 4551137,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941915258.996, "dur": 21.082, + "args": { + "External id": 4551138,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696941915259.893, "dur": 1.553, + "args": { + "External id": 4551139,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696941915262.497, "dur": 17.311, + "args": { + "External id": 4551140,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941915265.054, "dur": 2.504, + "args": { + "External id": 4551141,"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::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696941915281.222, "dur": 21.114, + "args": { + "External id": 4551142,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941915303.480, "dur": 14.634, + "args": { + "External id": 4551143,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336753, "tid": 1336753, + "ts": 1696941915320.738, "dur": 14.618, + "args": { + "External id": 4551144,"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": 10367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336753, "tid": 1336753, + "ts": 1696941915339.263, "dur": 13.516, + "args": { + "External id": 4551145,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941915354.342, "dur": 22.540, + "args": { + "External id": 4551146,"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": 10369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696941915358.031, "dur": 1.737, + "args": { + "External id": 4551147,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941915361.985, "dur": 0.780, + "args": { + "External id": 4551148,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336753, "tid": 1336753, + "ts": 1696941915378.176, "dur": 12.569, + "args": { + "External id": 4551149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941915391.731, "dur": 11.074, + "args": { + "External id": 4551150,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696941915412.397, "dur": 1.381, + "args": { + "External id": 4551151,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941915421.075, "dur": 3.045, + "args": { + "External id": 4551152,"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": 10375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941915422.891, "dur": 0.283, + "args": { + "External id": 4551153,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941915483.046, "dur": 66.080, + "args": { + "External id": 4551154,"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": 10377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1696941915555.118, "dur": 6.080, + "args": { + "External id": 4551155,"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": 10378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941915558.531, "dur": 1.341, + "args": { + "External id": 4551156,"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": 10379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941915562.488, "dur": 25.454, + "args": { + "External id": 4551157,"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": 10380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1336753, + "ts": 1696941915592.845, "dur": 7.921, + "args": { + "External id": 4551158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1696941915594.158, "dur": 6.007, + "args": { + "External id": 4551159,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941915598.597, "dur": 1.353, + "args": { + "External id": 4551160,"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": 10383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336753, "tid": 1336753, + "ts": 1696941915603.523, "dur": 43.242, + "args": { + "External id": 4551161,"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": 10384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1696941915604.607, "dur": 41.540, + "args": { + "External id": 4551162,"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": 10385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941915650.551, "dur": 16.564, + "args": { + "External id": 4551163,"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": 10386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941915671.528, "dur": 24.523, + "args": { + "External id": 4551164,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 10387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1336753, + "ts": 1696941915673.948, "dur": 21.751, + "args": { + "External id": 4551165,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941915678.847, "dur": 0.939, + "args": { + "External id": 4551166,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696941915700.747, "dur": 76.686, + "args": { + "External id": 4551167,"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": 10390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336753, "tid": 1336753, + "ts": 1696941915702.428, "dur": 74.628, + "args": { + "External id": 4551168,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], [], []], "Ev Idx": 10391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941915752.377, "dur": 4.650, + "args": { + "External id": 4551169,"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": 10392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696941915758.133, "dur": 18.434, + "args": { + "External id": 4551170,"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": 10393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941915791.105, "dur": 4.426, + "args": { + "External id": 4551171,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 10394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941915792.788, "dur": 2.500, + "args": { + "External id": 4551172,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 10395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941915796.454, "dur": 1.033, + "args": { + "External id": 4551173,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336753, "tid": 1336753, + "ts": 1696941915796.771, "dur": 0.435, + "args": { + "External id": 4551174,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941915838.382, "dur": 25.209, + "args": { + "External id": 4551175,"Sequence number": 45295812, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 10398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336753, "tid": 1336753, + "ts": 1696941915865.328, "dur": 15.174, + "args": { + "External id": 4551176,"Sequence number": 45295813, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 10399 + } + }, + { + "ph": "s", "id": 2, "pid": 1336753, "tid": 1336753, "ts": 1696941915865.328, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 1336753, "tid": 1336753, + "ts": 1696941916031.089, "dur": 44.904, + "args": { + "External id": 4551177,"Record function id": 0, "Ev Idx": 10400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336753, "tid": 1336753, + "ts": 1696941916209.624, "dur": 40.870, + "args": { + "External id": 4551178,"Sequence number": 45295814, "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": "s", "id": 1, "pid": 1336753, "tid": 1336753, "ts": 1696941916209.624, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941916287.449, "dur": 27.525, + "args": { + "External id": 4551179,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 10402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696941916288.855, "dur": 9.111, + "args": { + "External id": 4551180,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 10403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696941916292.998, "dur": 4.303, + "args": { + "External id": 4551181,"Record function id": 0, "Concrete Inputs": ["[1]", "[1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696941916299.518, "dur": 15.139, + "args": { + "External id": 4551182,"Record function id": 0, "Concrete Inputs": ["", "1."], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 10405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336753, "tid": 1336753, + "ts": 1696943223138.884, "dur": 58.424, + "args": { + "External id": 4551183,"Sequence number": 45295815, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336753, "tid": 1336753, + "ts": 1696943223205.252, "dur": 23.724, + "args": { + "External id": 4551184,"Sequence number": 45295816, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 10407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1696943223236.912, "dur": 22.578, + "args": { + "External id": 4551185,"Sequence number": 45295817, "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": 10408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1696943223842.839, "dur": 29.793, + "args": { + "External id": 4551186,"Sequence number": 45295818, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 10409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1696943224560.756, "dur": 37.454, + "args": { + "External id": 4551187,"Sequence number": 45295819, "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": 10410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_norm", "pid": 1336753, "tid": 1336753, + "ts": 1696943226332.607, "dur": 3331.182, + "args": { + "External id": 4551188,"Record function id": 0, "Concrete Inputs": ["", "2.", ""], "Input type": ["TensorList", "Scalar", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 10411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_norm", "pid": 1336753, "tid": 1336753, + "ts": 1696943226964.945, "dur": 1132.905, + "args": { + "External id": 4551189,"Record function id": 0, "Concrete Inputs": ["", "2.", ""], "Input type": ["TensorList", "Scalar", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 10412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336753, "tid": 1336753, + "ts": 1696943227010.609, "dur": 65.328, + "args": { + "External id": 4551190,"Record function id": 0, "Concrete Inputs": ["[36375]", "6", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 10413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696943227015.104, "dur": 12.824, + "args": { + "External id": 4551191,"Record function id": 0, "Concrete Inputs": ["[36375]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336753, "tid": 1336753, + "ts": 1696943227030.485, "dur": 45.166, + "args": { + "External id": 4551192,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[36375]], "Ev Idx": 10415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336753, "tid": 1336753, + "ts": 1696943227033.075, "dur": 42.037, + "args": { + "External id": 4551193,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[36375], []], "Ev Idx": 10416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696943229699.494, "dur": 3.335, + "args": { + "External id": 4551194,"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": 1336753, "tid": 1336753, + "ts": 1696943229705.103, "dur": 0.500, + "args": { + "External id": 4551195,"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": 1336753, "tid": 1336753, + "ts": 1696943229706.856, "dur": 0.434, + "args": { + "External id": 4551196,"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": 1336753, "tid": 1336753, + "ts": 1696943229708.307, "dur": 0.243, + "args": { + "External id": 4551197,"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": 1336753, "tid": 1336753, + "ts": 1696943229709.869, "dur": 0.215, + "args": { + "External id": 4551198,"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": 1336753, "tid": 1336753, + "ts": 1696943229711.502, "dur": 0.212, + "args": { + "External id": 4551199,"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": 1336753, "tid": 1336753, + "ts": 1696943229712.754, "dur": 0.212, + "args": { + "External id": 4551200,"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": 1336753, "tid": 1336753, + "ts": 1696943229716.559, "dur": 0.209, + "args": { + "External id": 4551201,"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": 1336753, "tid": 1336753, + "ts": 1696943229717.581, "dur": 0.213, + "args": { + "External id": 4551202,"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": 1336753, "tid": 1336753, + "ts": 1696943229718.748, "dur": 0.207, + "args": { + "External id": 4551203,"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": 1336753, "tid": 1336753, + "ts": 1696943229719.765, "dur": 0.207, + "args": { + "External id": 4551204,"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": 1336753, "tid": 1336753, + "ts": 1696943229720.762, "dur": 0.229, + "args": { + "External id": 4551205,"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": 1336753, "tid": 1336753, + "ts": 1696943229721.800, "dur": 0.206, + "args": { + "External id": 4551206,"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": 1336753, "tid": 1336753, + "ts": 1696943229722.775, "dur": 0.207, + "args": { + "External id": 4551207,"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": 1336753, "tid": 1336753, + "ts": 1696943229723.777, "dur": 0.211, + "args": { + "External id": 4551208,"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": 1336753, "tid": 1336753, + "ts": 1696943229727.065, "dur": 0.216, + "args": { + "External id": 4551209,"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": 1336753, "tid": 1336753, + "ts": 1696943229728.060, "dur": 0.598, + "args": { + "External id": 4551210,"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": 1336753, "tid": 1336753, + "ts": 1696943229729.641, "dur": 0.202, + "args": { + "External id": 4551211,"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": 1336753, "tid": 1336753, + "ts": 1696943229730.584, "dur": 0.225, + "args": { + "External id": 4551212,"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": 1336753, "tid": 1336753, + "ts": 1696943229731.620, "dur": 0.204, + "args": { + "External id": 4551213,"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": 1336753, "tid": 1336753, + "ts": 1696943229732.680, "dur": 0.244, + "args": { + "External id": 4551214,"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": 1336753, "tid": 1336753, + "ts": 1696943229733.637, "dur": 0.204, + "args": { + "External id": 4551215,"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": 1336753, "tid": 1336753, + "ts": 1696943229734.636, "dur": 0.211, + "args": { + "External id": 4551216,"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": 1336753, "tid": 1336753, + "ts": 1696943229737.961, "dur": 0.211, + "args": { + "External id": 4551217,"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": 1336753, "tid": 1336753, + "ts": 1696943229738.984, "dur": 0.221, + "args": { + "External id": 4551218,"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": 1336753, "tid": 1336753, + "ts": 1696943229740.154, "dur": 0.206, + "args": { + "External id": 4551219,"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": 1336753, "tid": 1336753, + "ts": 1696943229741.398, "dur": 0.243, + "args": { + "External id": 4551220,"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": 1336753, "tid": 1336753, + "ts": 1696943229742.691, "dur": 0.269, + "args": { + "External id": 4551221,"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": 1336753, "tid": 1336753, + "ts": 1696943229743.789, "dur": 0.211, + "args": { + "External id": 4551222,"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": 1336753, "tid": 1336753, + "ts": 1696943229744.854, "dur": 0.215, + "args": { + "External id": 4551223,"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": 1336753, "tid": 1336753, + "ts": 1696943229745.985, "dur": 0.218, + "args": { + "External id": 4551224,"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": 1336753, "tid": 1336753, + "ts": 1696943229749.139, "dur": 0.396, + "args": { + "External id": 4551225,"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": 1336753, "tid": 1336753, + "ts": 1696943229750.426, "dur": 0.401, + "args": { + "External id": 4551226,"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": 1336753, "tid": 1336753, + "ts": 1696943229752.287, "dur": 0.208, + "args": { + "External id": 4551227,"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": 1336753, "tid": 1336753, + "ts": 1696943229753.200, "dur": 0.407, + "args": { + "External id": 4551228,"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": 1336753, "tid": 1336753, + "ts": 1696943229754.416, "dur": 0.204, + "args": { + "External id": 4551229,"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": 1336753, "tid": 1336753, + "ts": 1696943229755.347, "dur": 0.399, + "args": { + "External id": 4551230,"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": 1336753, "tid": 1336753, + "ts": 1696943229756.495, "dur": 0.227, + "args": { + "External id": 4551231,"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": 1336753, "tid": 1336753, + "ts": 1696943229757.526, "dur": 0.210, + "args": { + "External id": 4551232,"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": 1336753, "tid": 1336753, + "ts": 1696943229760.741, "dur": 0.411, + "args": { + "External id": 4551233,"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": 1336753, "tid": 1336753, + "ts": 1696943229762.063, "dur": 0.428, + "args": { + "External id": 4551234,"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": 1336753, "tid": 1336753, + "ts": 1696943229763.371, "dur": 0.204, + "args": { + "External id": 4551235,"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": 1336753, "tid": 1336753, + "ts": 1696943229764.274, "dur": 0.207, + "args": { + "External id": 4551236,"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": 1336753, "tid": 1336753, + "ts": 1696943229765.243, "dur": 0.200, + "args": { + "External id": 4551237,"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": 1336753, "tid": 1336753, + "ts": 1696943229766.144, "dur": 0.223, + "args": { + "External id": 4551238,"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": 1336753, "tid": 1336753, + "ts": 1696943229768.408, "dur": 0.213, + "args": { + "External id": 4551239,"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": 1336753, "tid": 1336753, + "ts": 1696943229769.441, "dur": 0.214, + "args": { + "External id": 4551240,"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": 1336753, "tid": 1336753, + "ts": 1696943229772.572, "dur": 0.227, + "args": { + "External id": 4551241,"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": 1336753, "tid": 1336753, + "ts": 1696943229773.636, "dur": 0.208, + "args": { + "External id": 4551242,"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": 1336753, "tid": 1336753, + "ts": 1696943229774.553, "dur": 0.203, + "args": { + "External id": 4551243,"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": 1336753, "tid": 1336753, + "ts": 1696943229775.460, "dur": 0.407, + "args": { + "External id": 4551244,"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": 1336753, "tid": 1336753, + "ts": 1696943229776.595, "dur": 0.237, + "args": { + "External id": 4551245,"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": 1336753, "tid": 1336753, + "ts": 1696943229777.540, "dur": 0.412, + "args": { + "External id": 4551246,"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": 1336753, "tid": 1336753, + "ts": 1696943229778.834, "dur": 0.405, + "args": { + "External id": 4551247,"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": 1336753, "tid": 1336753, + "ts": 1696943229779.964, "dur": 0.381, + "args": { + "External id": 4551248,"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": 1336753, "tid": 1336753, + "ts": 1696943229783.242, "dur": 0.216, + "args": { + "External id": 4551249,"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": 1336753, "tid": 1336753, + "ts": 1696943229784.198, "dur": 0.229, + "args": { + "External id": 4551250,"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": 1336753, "tid": 1336753, + "ts": 1696943229785.135, "dur": 0.386, + "args": { + "External id": 4551251,"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": 1336753, "tid": 1336753, + "ts": 1696943229786.280, "dur": 0.425, + "args": { + "External id": 4551252,"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": 1336753, "tid": 1336753, + "ts": 1696943229787.418, "dur": 0.205, + "args": { + "External id": 4551253,"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": 1336753, "tid": 1336753, + "ts": 1696943229788.425, "dur": 0.210, + "args": { + "External id": 4551254,"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": 1336753, "tid": 1336753, + "ts": 1696943229789.359, "dur": 0.232, + "args": { + "External id": 4551255,"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": 1336753, "tid": 1336753, + "ts": 1696943229790.422, "dur": 0.202, + "args": { + "External id": 4551256,"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": 1336753, "tid": 1336753, + "ts": 1696943229793.690, "dur": 0.295, + "args": { + "External id": 4551257,"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": 1336753, "tid": 1336753, + "ts": 1696943229794.781, "dur": 0.343, + "args": { + "External id": 4551258,"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": 1336753, "tid": 1336753, + "ts": 1696943229796.119, "dur": 0.215, + "args": { + "External id": 4551259,"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": 1336753, "tid": 1336753, + "ts": 1696943229797.215, "dur": 0.204, + "args": { + "External id": 4551260,"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": 1336753, "tid": 1336753, + "ts": 1696943229798.240, "dur": 0.201, + "args": { + "External id": 4551261,"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": 1336753, "tid": 1336753, + "ts": 1696943229799.293, "dur": 0.205, + "args": { + "External id": 4551262,"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": 1336753, "tid": 1336753, + "ts": 1696943229800.204, "dur": 0.201, + "args": { + "External id": 4551263,"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": 1336753, "tid": 1336753, + "ts": 1696943229801.240, "dur": 0.218, + "args": { + "External id": 4551264,"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": 1336753, "tid": 1336753, + "ts": 1696943229804.357, "dur": 0.201, + "args": { + "External id": 4551265,"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": 1336753, "tid": 1336753, + "ts": 1696943229805.273, "dur": 0.206, + "args": { + "External id": 4551266,"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": 1336753, "tid": 1336753, + "ts": 1696943229806.225, "dur": 0.202, + "args": { + "External id": 4551267,"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": 1336753, "tid": 1336753, + "ts": 1696943229807.226, "dur": 0.216, + "args": { + "External id": 4551268,"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": 1336753, "tid": 1336753, + "ts": 1696943229808.149, "dur": 0.229, + "args": { + "External id": 4551269,"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": 1336753, "tid": 1336753, + "ts": 1696943229809.114, "dur": 0.207, + "args": { + "External id": 4551270,"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": 1336753, "tid": 1336753, + "ts": 1696943229811.259, "dur": 0.214, + "args": { + "External id": 4551271,"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": 1336753, "tid": 1336753, + "ts": 1696943229812.297, "dur": 0.207, + "args": { + "External id": 4551272,"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": 1336753, "tid": 1336753, + "ts": 1696943229815.370, "dur": 0.399, + "args": { + "External id": 4551273,"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": 1336753, "tid": 1336753, + "ts": 1696943229816.481, "dur": 0.222, + "args": { + "External id": 4551274,"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": 1336753, "tid": 1336753, + "ts": 1696943229817.411, "dur": 0.220, + "args": { + "External id": 4551275,"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": 1336753, "tid": 1336753, + "ts": 1696943229818.359, "dur": 0.218, + "args": { + "External id": 4551276,"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": 1336753, "tid": 1336753, + "ts": 1696943229819.293, "dur": 0.200, + "args": { + "External id": 4551277,"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": 1336753, "tid": 1336753, + "ts": 1696943229820.440, "dur": 0.211, + "args": { + "External id": 4551278,"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": 1336753, "tid": 1336753, + "ts": 1696943229821.366, "dur": 0.394, + "args": { + "External id": 4551279,"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": 1336753, "tid": 1336753, + "ts": 1696943229822.463, "dur": 0.425, + "args": { + "External id": 4551280,"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": 1336753, "tid": 1336753, + "ts": 1696943229825.839, "dur": 0.210, + "args": { + "External id": 4551281,"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": 1336753, "tid": 1336753, + "ts": 1696943229826.775, "dur": 0.203, + "args": { + "External id": 4551282,"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": 1336753, "tid": 1336753, + "ts": 1696943229827.755, "dur": 0.201, + "args": { + "External id": 4551283,"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": 1336753, "tid": 1336753, + "ts": 1696943229828.676, "dur": 0.206, + "args": { + "External id": 4551284,"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": 1336753, "tid": 1336753, + "ts": 1696943229829.624, "dur": 0.202, + "args": { + "External id": 4551285,"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": 1336753, "tid": 1336753, + "ts": 1696943229830.560, "dur": 0.210, + "args": { + "External id": 4551286,"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": 1336753, "tid": 1336753, + "ts": 1696943229832.235, "dur": 0.201, + "args": { + "External id": 4551287,"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": 1336753, "tid": 1336753, + "ts": 1696943229833.176, "dur": 0.205, + "args": { + "External id": 4551288,"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": 1336753, "tid": 1336753, + "ts": 1696943229836.474, "dur": 0.207, + "args": { + "External id": 4551289,"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": 1336753, "tid": 1336753, + "ts": 1696943229837.399, "dur": 0.211, + "args": { + "External id": 4551290,"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": 1336753, "tid": 1336753, + "ts": 1696943229838.315, "dur": 0.227, + "args": { + "External id": 4551291,"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": 1336753, "tid": 1336753, + "ts": 1696943229839.338, "dur": 0.204, + "args": { + "External id": 4551292,"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": 1336753, "tid": 1336753, + "ts": 1696943229840.248, "dur": 0.199, + "args": { + "External id": 4551293,"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": 1336753, "tid": 1336753, + "ts": 1696943229841.215, "dur": 0.208, + "args": { + "External id": 4551294,"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": 1336753, "tid": 1336753, + "ts": 1696943229842.133, "dur": 0.202, + "args": { + "External id": 4551295,"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": 1336753, "tid": 1336753, + "ts": 1696943229843.037, "dur": 0.210, + "args": { + "External id": 4551296,"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": 1336753, "tid": 1336753, + "ts": 1696943229846.565, "dur": 0.216, + "args": { + "External id": 4551297,"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": 1336753, "tid": 1336753, + "ts": 1696943229847.509, "dur": 0.208, + "args": { + "External id": 4551298,"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": 1336753, "tid": 1336753, + "ts": 1696943229848.456, "dur": 0.197, + "args": { + "External id": 4551299,"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": 1336753, "tid": 1336753, + "ts": 1696943229849.357, "dur": 0.204, + "args": { + "External id": 4551300,"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": 1336753, "tid": 1336753, + "ts": 1696943229850.284, "dur": 0.196, + "args": { + "External id": 4551301,"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": 1336753, "tid": 1336753, + "ts": 1696943229851.710, "dur": 0.203, + "args": { + "External id": 4551302,"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": 1336753, "tid": 1336753, + "ts": 1696943229853.455, "dur": 0.219, + "args": { + "External id": 4551303,"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": 1336753, "tid": 1336753, + "ts": 1696943229854.585, "dur": 0.204, + "args": { + "External id": 4551304,"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": 1336753, "tid": 1336753, + "ts": 1696943229857.899, "dur": 0.200, + "args": { + "External id": 4551305,"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": 1336753, "tid": 1336753, + "ts": 1696943229859.057, "dur": 0.200, + "args": { + "External id": 4551306,"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": 1336753, "tid": 1336753, + "ts": 1696943229860.172, "dur": 0.369, + "args": { + "External id": 4551307,"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": 1336753, "tid": 1336753, + "ts": 1696943229861.458, "dur": 0.245, + "args": { + "External id": 4551308,"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": 1336753, "tid": 1336753, + "ts": 1696943229862.418, "dur": 0.196, + "args": { + "External id": 4551309,"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": 1336753, "tid": 1336753, + "ts": 1696943229863.324, "dur": 0.218, + "args": { + "External id": 4551310,"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": 1336753, "tid": 1336753, + "ts": 1696943229864.292, "dur": 0.201, + "args": { + "External id": 4551311,"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": 1336753, "tid": 1336753, + "ts": 1696943229865.261, "dur": 0.313, + "args": { + "External id": 4551312,"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": 1336753, "tid": 1336753, + "ts": 1696943229868.091, "dur": 0.214, + "args": { + "External id": 4551313,"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": 1336753, "tid": 1336753, + "ts": 1696943229869.044, "dur": 0.254, + "args": { + "External id": 4551314,"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": 1336753, "tid": 1336753, + "ts": 1696943229870.013, "dur": 0.411, + "args": { + "External id": 4551315,"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": 1336753, "tid": 1336753, + "ts": 1696943229871.140, "dur": 0.392, + "args": { + "External id": 4551316,"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": 1336753, "tid": 1336753, + "ts": 1696943229872.275, "dur": 0.198, + "args": { + "External id": 4551317,"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": 1336753, "tid": 1336753, + "ts": 1696943229873.174, "dur": 0.416, + "args": { + "External id": 4551318,"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": 1336753, "tid": 1336753, + "ts": 1696943229874.303, "dur": 0.377, + "args": { + "External id": 4551319,"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": 1336753, "tid": 1336753, + "ts": 1696943229875.409, "dur": 0.391, + "args": { + "External id": 4551320,"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": 1336753, "tid": 1336753, + "ts": 1696943229878.722, "dur": 0.420, + "args": { + "External id": 4551321,"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": 1336753, "tid": 1336753, + "ts": 1696943229879.881, "dur": 0.532, + "args": { + "External id": 4551322,"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": 1336753, "tid": 1336753, + "ts": 1696943229881.717, "dur": 0.396, + "args": { + "External id": 4551323,"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": 1336753, "tid": 1336753, + "ts": 1696943229882.856, "dur": 0.479, + "args": { + "External id": 4551324,"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": 1336753, "tid": 1336753, + "ts": 1696943229884.089, "dur": 0.195, + "args": { + "External id": 4551325,"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": 1336753, "tid": 1336753, + "ts": 1696943229885.000, "dur": 0.232, + "args": { + "External id": 4551326,"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": 1336753, "tid": 1336753, + "ts": 1696943229885.945, "dur": 0.198, + "args": { + "External id": 4551327,"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": 1336753, "tid": 1336753, + "ts": 1696943229886.853, "dur": 0.207, + "args": { + "External id": 4551328,"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": 1336753, "tid": 1336753, + "ts": 1696943229890.299, "dur": 0.204, + "args": { + "External id": 4551329,"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": 1336753, "tid": 1336753, + "ts": 1696943229891.207, "dur": 0.297, + "args": { + "External id": 4551330,"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": 1336753, "tid": 1336753, + "ts": 1696943229892.235, "dur": 0.214, + "args": { + "External id": 4551331,"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": 1336753, "tid": 1336753, + "ts": 1696943229893.150, "dur": 0.216, + "args": { + "External id": 4551332,"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": 1336753, "tid": 1336753, + "ts": 1696943229894.100, "dur": 0.201, + "args": { + "External id": 4551333,"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": 1336753, "tid": 1336753, + "ts": 1696943229895.004, "dur": 0.202, + "args": { + "External id": 4551334,"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": 1336753, "tid": 1336753, + "ts": 1696943229895.927, "dur": 0.199, + "args": { + "External id": 4551335,"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": 1336753, "tid": 1336753, + "ts": 1696943229896.921, "dur": 0.217, + "args": { + "External id": 4551336,"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": 1336753, "tid": 1336753, + "ts": 1696943229900.692, "dur": 0.223, + "args": { + "External id": 4551337,"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": 1336753, "tid": 1336753, + "ts": 1696943229901.640, "dur": 0.219, + "args": { + "External id": 4551338,"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": 1336753, "tid": 1336753, + "ts": 1696943229902.572, "dur": 0.217, + "args": { + "External id": 4551339,"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": 1336753, "tid": 1336753, + "ts": 1696943229903.495, "dur": 0.205, + "args": { + "External id": 4551340,"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": 1336753, "tid": 1336753, + "ts": 1696943229904.453, "dur": 0.199, + "args": { + "External id": 4551341,"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": 1336753, "tid": 1336753, + "ts": 1696943229905.358, "dur": 0.201, + "args": { + "External id": 4551342,"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": 1336753, "tid": 1336753, + "ts": 1696943229906.747, "dur": 0.198, + "args": { + "External id": 4551343,"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": 1336753, "tid": 1336753, + "ts": 1696943229907.865, "dur": 0.668, + "args": { + "External id": 4551344,"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": 1336753, "tid": 1336753, + "ts": 1696943229911.351, "dur": 0.209, + "args": { + "External id": 4551345,"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": 1336753, "tid": 1336753, + "ts": 1696943229912.473, "dur": 0.217, + "args": { + "External id": 4551346,"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": 1336753, "tid": 1336753, + "ts": 1696943229913.553, "dur": 0.405, + "args": { + "External id": 4551347,"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": 1336753, "tid": 1336753, + "ts": 1696943229914.855, "dur": 0.437, + "args": { + "External id": 4551348,"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": 1336753, "tid": 1336753, + "ts": 1696943229916.171, "dur": 0.200, + "args": { + "External id": 4551349,"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": 1336753, "tid": 1336753, + "ts": 1696943229917.455, "dur": 0.203, + "args": { + "External id": 4551350,"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": 1336753, "tid": 1336753, + "ts": 1696943229918.570, "dur": 0.400, + "args": { + "External id": 4551351,"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": 1336753, "tid": 1336753, + "ts": 1696943229919.671, "dur": 0.395, + "args": { + "External id": 4551352,"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": 1336753, "tid": 1336753, + "ts": 1696943229923.793, "dur": 0.216, + "args": { + "External id": 4551353,"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": 1336753, "tid": 1336753, + "ts": 1696943229924.784, "dur": 0.205, + "args": { + "External id": 4551354,"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": 1336753, "tid": 1336753, + "ts": 1696943229925.719, "dur": 0.207, + "args": { + "External id": 4551355,"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": 1336753, "tid": 1336753, + "ts": 1696943229926.678, "dur": 0.202, + "args": { + "External id": 4551356,"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": 1336753, "tid": 1336753, + "ts": 1696943229927.621, "dur": 0.199, + "args": { + "External id": 4551357,"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": 1336753, "tid": 1336753, + "ts": 1696943229928.551, "dur": 0.209, + "args": { + "External id": 4551358,"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": 1336753, "tid": 1336753, + "ts": 1696943229929.491, "dur": 0.199, + "args": { + "External id": 4551359,"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": 1336753, "tid": 1336753, + "ts": 1696943229930.437, "dur": 0.205, + "args": { + "External id": 4551360,"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": 1336753, "tid": 1336753, + "ts": 1696943229933.502, "dur": 0.200, + "args": { + "External id": 4551361,"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": 1336753, "tid": 1336753, + "ts": 1696943229934.437, "dur": 0.205, + "args": { + "External id": 4551362,"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": 1336753, "tid": 1336753, + "ts": 1696943229935.453, "dur": 0.209, + "args": { + "External id": 4551363,"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": 1336753, "tid": 1336753, + "ts": 1696943229936.409, "dur": 0.220, + "args": { + "External id": 4551364,"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": 1336753, "tid": 1336753, + "ts": 1696943229937.532, "dur": 0.254, + "args": { + "External id": 4551365,"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": 1336753, "tid": 1336753, + "ts": 1696943229938.489, "dur": 0.204, + "args": { + "External id": 4551366,"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": 1336753, "tid": 1336753, + "ts": 1696943229940.026, "dur": 0.209, + "args": { + "External id": 4551367,"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": 1336753, "tid": 1336753, + "ts": 1696943229940.990, "dur": 0.205, + "args": { + "External id": 4551368,"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": 1336753, "tid": 1336753, + "ts": 1696943229943.963, "dur": 0.220, + "args": { + "External id": 4551369,"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": 1336753, "tid": 1336753, + "ts": 1696943229944.912, "dur": 0.344, + "args": { + "External id": 4551370,"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": 1336753, "tid": 1336753, + "ts": 1696943229945.983, "dur": 0.207, + "args": { + "External id": 4551371,"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": 1336753, "tid": 1336753, + "ts": 1696943229946.934, "dur": 0.253, + "args": { + "External id": 4551372,"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": 1336753, "tid": 1336753, + "ts": 1696943229947.935, "dur": 0.202, + "args": { + "External id": 4551373,"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": 1336753, "tid": 1336753, + "ts": 1696943229948.836, "dur": 0.343, + "args": { + "External id": 4551374,"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": 1336753, "tid": 1336753, + "ts": 1696943229949.907, "dur": 0.203, + "args": { + "External id": 4551375,"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": 1336753, "tid": 1336753, + "ts": 1696943229950.813, "dur": 0.207, + "args": { + "External id": 4551376,"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": 1336753, "tid": 1336753, + "ts": 1696943229954.107, "dur": 0.202, + "args": { + "External id": 4551377,"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": 1336753, "tid": 1336753, + "ts": 1696943229955.019, "dur": 0.204, + "args": { + "External id": 4551378,"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": 1336753, "tid": 1336753, + "ts": 1696943229955.976, "dur": 0.223, + "args": { + "External id": 4551379,"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": 1336753, "tid": 1336753, + "ts": 1696943229956.916, "dur": 0.201, + "args": { + "External id": 4551380,"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": 1336753, "tid": 1336753, + "ts": 1696943229957.832, "dur": 0.198, + "args": { + "External id": 4551381,"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": 1336753, "tid": 1336753, + "ts": 1696943229958.777, "dur": 0.204, + "args": { + "External id": 4551382,"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": 1336753, "tid": 1336753, + "ts": 1696943229959.686, "dur": 0.230, + "args": { + "External id": 4551383,"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": 1336753, "tid": 1336753, + "ts": 1696943229960.614, "dur": 0.204, + "args": { + "External id": 4551384,"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": 1336753, "tid": 1336753, + "ts": 1696943229963.482, "dur": 0.200, + "args": { + "External id": 4551385,"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": 1336753, "tid": 1336753, + "ts": 1696943229964.382, "dur": 0.212, + "args": { + "External id": 4551386,"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": 1336753, "tid": 1336753, + "ts": 1696943229965.466, "dur": 0.204, + "args": { + "External id": 4551387,"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": 1336753, "tid": 1336753, + "ts": 1696943229966.673, "dur": 0.202, + "args": { + "External id": 4551388,"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": 1336753, "tid": 1336753, + "ts": 1696943229967.743, "dur": 0.195, + "args": { + "External id": 4551389,"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": 1336753, "tid": 1336753, + "ts": 1696943229968.762, "dur": 0.208, + "args": { + "External id": 4551390,"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": 1336753, "tid": 1336753, + "ts": 1696943229969.782, "dur": 0.508, + "args": { + "External id": 4551391,"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": 1336753, "tid": 1336753, + "ts": 1696943229971.109, "dur": 0.217, + "args": { + "External id": 4551392,"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": 1336753, "tid": 1336753, + "ts": 1696943229974.185, "dur": 0.225, + "args": { + "External id": 4551393,"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": 1336753, "tid": 1336753, + "ts": 1696943229975.100, "dur": 0.415, + "args": { + "External id": 4551394,"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": 1336753, "tid": 1336753, + "ts": 1696943229976.529, "dur": 0.400, + "args": { + "External id": 4551395,"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": 1336753, "tid": 1336753, + "ts": 1696943229977.664, "dur": 0.398, + "args": { + "External id": 4551396,"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": 1336753, "tid": 1336753, + "ts": 1696943229978.775, "dur": 0.200, + "args": { + "External id": 4551397,"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": 1336753, "tid": 1336753, + "ts": 1696943229979.685, "dur": 0.204, + "args": { + "External id": 4551398,"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": 1336753, "tid": 1336753, + "ts": 1696943229980.633, "dur": 0.196, + "args": { + "External id": 4551399,"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": 1336753, "tid": 1336753, + "ts": 1696943229981.608, "dur": 0.202, + "args": { + "External id": 4551400,"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": 1336753, "tid": 1336753, + "ts": 1696943230009.887, "dur": 0.704, + "args": { + "External id": 4551401,"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": 1336753, "tid": 1336753, + "ts": 1696943230012.421, "dur": 0.205, + "args": { + "External id": 4551402,"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": 1336753, "tid": 1336753, + "ts": 1696943230013.426, "dur": 0.564, + "args": { + "External id": 4551403,"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": 1336753, "tid": 1336753, + "ts": 1696943230014.786, "dur": 0.491, + "args": { + "External id": 4551404,"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": 1336753, "tid": 1336753, + "ts": 1696943230016.081, "dur": 0.214, + "args": { + "External id": 4551405,"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": 1336753, "tid": 1336753, + "ts": 1696943230017.072, "dur": 0.209, + "args": { + "External id": 4551406,"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": 1336753, "tid": 1336753, + "ts": 1696943230017.994, "dur": 0.218, + "args": { + "External id": 4551407,"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": 1336753, "tid": 1336753, + "ts": 1696943230018.966, "dur": 0.245, + "args": { + "External id": 4551408,"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": 1336753, "tid": 1336753, + "ts": 1696943230021.877, "dur": 0.217, + "args": { + "External id": 4551409,"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": 1336753, "tid": 1336753, + "ts": 1696943230022.828, "dur": 0.409, + "args": { + "External id": 4551410,"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": 1336753, "tid": 1336753, + "ts": 1696943230023.970, "dur": 0.454, + "args": { + "External id": 4551411,"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": 1336753, "tid": 1336753, + "ts": 1696943230025.144, "dur": 0.662, + "args": { + "External id": 4551412,"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": 1336753, "tid": 1336753, + "ts": 1696943230026.612, "dur": 0.212, + "args": { + "External id": 4551413,"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": 1336753, "tid": 1336753, + "ts": 1696943230027.545, "dur": 0.408, + "args": { + "External id": 4551414,"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": 1336753, "tid": 1336753, + "ts": 1696943230028.672, "dur": 0.401, + "args": { + "External id": 4551415,"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": 1336753, "tid": 1336753, + "ts": 1696943230029.935, "dur": 0.438, + "args": { + "External id": 4551416,"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": 1336753, "tid": 1336753, + "ts": 1696943230033.126, "dur": 0.577, + "args": { + "External id": 4551417,"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": 1336753, "tid": 1336753, + "ts": 1696943230034.428, "dur": 0.409, + "args": { + "External id": 4551418,"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": 1336753, "tid": 1336753, + "ts": 1696943230035.585, "dur": 0.432, + "args": { + "External id": 4551419,"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": 1336753, "tid": 1336753, + "ts": 1696943230036.735, "dur": 0.403, + "args": { + "External id": 4551420,"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": 1336753, "tid": 1336753, + "ts": 1696943230037.845, "dur": 0.215, + "args": { + "External id": 4551421,"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": 1336753, "tid": 1336753, + "ts": 1696943230038.791, "dur": 0.417, + "args": { + "External id": 4551422,"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": 1336753, "tid": 1336753, + "ts": 1696943230039.945, "dur": 0.420, + "args": { + "External id": 4551423,"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": 1336753, "tid": 1336753, + "ts": 1696943230041.465, "dur": 0.183, + "args": { + "External id": 4551424,"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": 1336753, "tid": 1336753, + "ts": 1696943230044.388, "dur": 0.462, + "args": { + "External id": 4551425,"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": 1336753, "tid": 1336753, + "ts": 1696943230045.566, "dur": 0.412, + "args": { + "External id": 4551426,"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": 1336753, "tid": 1336753, + "ts": 1696943230047.185, "dur": 0.212, + "args": { + "External id": 4551427,"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": 1336753, "tid": 1336753, + "ts": 1696943230048.279, "dur": 0.220, + "args": { + "External id": 4551428,"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": 1336753, "tid": 1336753, + "ts": 1696943230049.237, "dur": 0.213, + "args": { + "External id": 4551429,"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": 1336753, "tid": 1336753, + "ts": 1696943230050.233, "dur": 0.211, + "args": { + "External id": 4551430,"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": 1336753, "tid": 1336753, + "ts": 1696943230051.348, "dur": 0.210, + "args": { + "External id": 4551431,"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": 1336753, "tid": 1336753, + "ts": 1696943230052.418, "dur": 0.213, + "args": { + "External id": 4551432,"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": 1336753, "tid": 1336753, + "ts": 1696943230055.358, "dur": 0.213, + "args": { + "External id": 4551433,"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": 1336753, "tid": 1336753, + "ts": 1696943230056.475, "dur": 0.209, + "args": { + "External id": 4551434,"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": 1336753, "tid": 1336753, + "ts": 1696943230057.559, "dur": 0.216, + "args": { + "External id": 4551435,"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": 1336753, "tid": 1336753, + "ts": 1696943230058.563, "dur": 0.246, + "args": { + "External id": 4551436,"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": 1336753, "tid": 1336753, + "ts": 1696943230059.525, "dur": 0.247, + "args": { + "External id": 4551437,"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": 1336753, "tid": 1336753, + "ts": 1696943230060.506, "dur": 0.231, + "args": { + "External id": 4551438,"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": 1336753, "tid": 1336753, + "ts": 1696943230061.557, "dur": 0.242, + "args": { + "External id": 4551439,"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": 1336753, "tid": 1336753, + "ts": 1696943230062.532, "dur": 0.206, + "args": { + "External id": 4551440,"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": 1336753, "tid": 1336753, + "ts": 1696943230065.479, "dur": 0.215, + "args": { + "External id": 4551441,"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": 1336753, "tid": 1336753, + "ts": 1696943230066.590, "dur": 0.223, + "args": { + "External id": 4551442,"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": 1336753, "tid": 1336753, + "ts": 1696943230067.515, "dur": 0.215, + "args": { + "External id": 4551443,"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": 1336753, "tid": 1336753, + "ts": 1696943230068.612, "dur": 0.216, + "args": { + "External id": 4551444,"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": 1336753, "tid": 1336753, + "ts": 1696943230069.530, "dur": 0.217, + "args": { + "External id": 4551445,"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": 1336753, "tid": 1336753, + "ts": 1696943230070.489, "dur": 0.205, + "args": { + "External id": 4551446,"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": 1336753, "tid": 1336753, + "ts": 1696943230071.403, "dur": 0.216, + "args": { + "External id": 4551447,"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": 1336753, "tid": 1336753, + "ts": 1696943230072.341, "dur": 0.209, + "args": { + "External id": 4551448,"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": 1336753, "tid": 1336753, + "ts": 1696943230075.517, "dur": 0.215, + "args": { + "External id": 4551449,"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": 1336753, "tid": 1336753, + "ts": 1696943230078.808, "dur": 0.253, + "args": { + "External id": 4551450,"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": 1336753, "tid": 1336753, + "ts": 1696943230079.799, "dur": 0.210, + "args": { + "External id": 4551451,"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": 1336753, "tid": 1336753, + "ts": 1696943230080.752, "dur": 0.208, + "args": { + "External id": 4551452,"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": 1336753, "tid": 1336753, + "ts": 1696943230081.696, "dur": 0.211, + "args": { + "External id": 4551453,"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": 1336753, "tid": 1336753, + "ts": 1696943230082.621, "dur": 0.208, + "args": { + "External id": 4551454,"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": 1336753, "tid": 1336753, + "ts": 1696943230083.537, "dur": 0.212, + "args": { + "External id": 4551455,"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": 1336753, "tid": 1336753, + "ts": 1696943230084.469, "dur": 0.206, + "args": { + "External id": 4551456,"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": 1336753, "tid": 1336753, + "ts": 1696943230087.223, "dur": 0.439, + "args": { + "External id": 4551457,"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": 1336753, "tid": 1336753, + "ts": 1696943230088.369, "dur": 0.427, + "args": { + "External id": 4551458,"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": 1336753, "tid": 1336753, + "ts": 1696943230089.544, "dur": 0.413, + "args": { + "External id": 4551459,"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": 1336753, "tid": 1336753, + "ts": 1696943230090.668, "dur": 0.410, + "args": { + "External id": 4551460,"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": 1336753, "tid": 1336753, + "ts": 1696943230091.782, "dur": 0.210, + "args": { + "External id": 4551461,"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": 1336753, "tid": 1336753, + "ts": 1696943230092.699, "dur": 0.416, + "args": { + "External id": 4551462,"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": 1336753, "tid": 1336753, + "ts": 1696943230094.210, "dur": 0.445, + "args": { + "External id": 4551463,"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": 1336753, "tid": 1336753, + "ts": 1696943230095.367, "dur": 0.466, + "args": { + "External id": 4551464,"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": 1336753, "tid": 1336753, + "ts": 1696943230098.942, "dur": 0.610, + "args": { + "External id": 4551465,"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": 1336753, "tid": 1336753, + "ts": 1696943230100.429, "dur": 0.399, + "args": { + "External id": 4551466,"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": 1336753, "tid": 1336753, + "ts": 1696943230103.001, "dur": 0.415, + "args": { + "External id": 4551467,"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": 1336753, "tid": 1336753, + "ts": 1696943230104.362, "dur": 0.259, + "args": { + "External id": 4551468,"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": 1336753, "tid": 1336753, + "ts": 1696943230105.592, "dur": 0.216, + "args": { + "External id": 4551469,"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": 1336753, "tid": 1336753, + "ts": 1696943230106.519, "dur": 0.219, + "args": { + "External id": 4551470,"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": 1336753, "tid": 1336753, + "ts": 1696943230107.474, "dur": 0.211, + "args": { + "External id": 4551471,"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": 1336753, "tid": 1336753, + "ts": 1696943230108.403, "dur": 0.207, + "args": { + "External id": 4551472,"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": 1336753, "tid": 1336753, + "ts": 1696943230111.629, "dur": 0.549, + "args": { + "External id": 4551473,"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": 1336753, "tid": 1336753, + "ts": 1696943230113.012, "dur": 0.386, + "args": { + "External id": 4551474,"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": 1336753, "tid": 1336753, + "ts": 1696943230114.094, "dur": 0.431, + "args": { + "External id": 4551475,"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": 1336753, "tid": 1336753, + "ts": 1696943230115.321, "dur": 0.607, + "args": { + "External id": 4551476,"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": 1336753, "tid": 1336753, + "ts": 1696943230116.785, "dur": 0.209, + "args": { + "External id": 4551477,"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": 1336753, "tid": 1336753, + "ts": 1696943230117.706, "dur": 0.395, + "args": { + "External id": 4551478,"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::to", "pid": 1336753, "tid": 1336753, + "ts": 1696943230118.801, "dur": 0.434, + "args": { + "External id": 4551479,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696943230120.186, "dur": 0.393, + "args": { + "External id": 4551480,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696943230123.372, "dur": 0.462, + "args": { + "External id": 4551481,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696943230124.541, "dur": 0.428, + "args": { + "External id": 4551482,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696943230125.681, "dur": 0.413, + "args": { + "External id": 4551483,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696943230126.813, "dur": 0.444, + "args": { + "External id": 4551484,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 1336753, "tid": 1336753, + "ts": 1696943230183.011, "dur": 1684.222, + "args": { + "External id": 4551485,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 1336753, "tid": 1336753, + "ts": 1696943230642.292, "dur": 1147.819, + "args": { + "External id": 4551486,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1696943230651.697, "dur": 7.222, + "args": { + "External id": 4551487,"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": 1336753, "tid": 1336753, + "ts": 1696943230655.508, "dur": 2.911, + "args": { + "External id": 4551488,"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": 1336753, "tid": 1336753, + "ts": 1696943230659.746, "dur": 4.118, + "args": { + "External id": 4551489,"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": 1336753, "tid": 1336753, + "ts": 1696943230660.682, "dur": 3.042, + "args": { + "External id": 4551490,"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": 1336753, "tid": 1336753, + "ts": 1696943230664.262, "dur": 3.283, + "args": { + "External id": 4551491,"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": 1336753, "tid": 1336753, + "ts": 1696943230666.897, "dur": 0.572, + "args": { + "External id": 4551492,"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": 1336753, "tid": 1336753, + "ts": 1696943230667.822, "dur": 1.286, + "args": { + "External id": 4551493,"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": 1336753, "tid": 1336753, + "ts": 1696943230668.281, "dur": 0.754, + "args": { + "External id": 4551494,"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": 1336753, "tid": 1336753, + "ts": 1696943230671.460, "dur": 5.992, + "args": { + "External id": 4551495,"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": 1336753, "tid": 1336753, + "ts": 1696943230676.884, "dur": 0.501, + "args": { + "External id": 4551496,"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": 1336753, "tid": 1336753, + "ts": 1696943230677.748, "dur": 1.475, + "args": { + "External id": 4551497,"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": 1336753, "tid": 1336753, + "ts": 1696943230678.236, "dur": 0.921, + "args": { + "External id": 4551498,"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": 1336753, "tid": 1336753, + "ts": 1696943230679.746, "dur": 1.378, + "args": { + "External id": 4551499,"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": 1336753, "tid": 1336753, + "ts": 1696943230680.372, "dur": 0.683, + "args": { + "External id": 4551500,"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": 1336753, "tid": 1336753, + "ts": 1696943230681.583, "dur": 5.539, + "args": { + "External id": 4551501,"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": 1336753, "tid": 1336753, + "ts": 1696943230686.114, "dur": 0.941, + "args": { + "External id": 4551502,"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": 1336753, "tid": 1336753, + "ts": 1696943230687.534, "dur": 1.557, + "args": { + "External id": 4551503,"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": 1336753, "tid": 1336753, + "ts": 1696943230688.075, "dur": 0.950, + "args": { + "External id": 4551504,"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": 1336753, "tid": 1336753, + "ts": 1696943230689.425, "dur": 3.126, + "args": { + "External id": 4551505,"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": 1336753, "tid": 1336753, + "ts": 1696943230690.007, "dur": 2.208, + "args": { + "External id": 4551506,"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": 1336753, "tid": 1336753, + "ts": 1696943230692.788, "dur": 2.793, + "args": { + "External id": 4551507,"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": 1336753, "tid": 1336753, + "ts": 1696943230694.972, "dur": 0.542, + "args": { + "External id": 4551508,"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": 1336753, "tid": 1336753, + "ts": 1696943230696.108, "dur": 1.089, + "args": { + "External id": 4551509,"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": 1336753, "tid": 1336753, + "ts": 1696943230696.507, "dur": 0.627, + "args": { + "External id": 4551510,"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": 1336753, "tid": 1336753, + "ts": 1696943230699.488, "dur": 5.076, + "args": { + "External id": 4551511,"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": 1336753, "tid": 1336753, + "ts": 1696943230703.894, "dur": 0.609, + "args": { + "External id": 4551512,"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": 1336753, "tid": 1336753, + "ts": 1696943230704.829, "dur": 1.509, + "args": { + "External id": 4551513,"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": 1336753, "tid": 1336753, + "ts": 1696943230705.443, "dur": 0.832, + "args": { + "External id": 4551514,"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": 1336753, "tid": 1336753, + "ts": 1696943230706.581, "dur": 1.465, + "args": { + "External id": 4551515,"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": 1336753, "tid": 1336753, + "ts": 1696943230707.128, "dur": 0.855, + "args": { + "External id": 4551516,"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": 1336753, "tid": 1336753, + "ts": 1696943230708.385, "dur": 3.630, + "args": { + "External id": 4551517,"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": 1336753, "tid": 1336753, + "ts": 1696943230711.037, "dur": 0.911, + "args": { + "External id": 4551518,"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": 1336753, "tid": 1336753, + "ts": 1696943230712.338, "dur": 1.659, + "args": { + "External id": 4551519,"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": 1336753, "tid": 1336753, + "ts": 1696943230713.059, "dur": 0.873, + "args": { + "External id": 4551520,"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": 1336753, "tid": 1336753, + "ts": 1696943230714.350, "dur": 3.400, + "args": { + "External id": 4551521,"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": 1336753, "tid": 1336753, + "ts": 1696943230715.088, "dur": 2.458, + "args": { + "External id": 4551522,"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": 1336753, "tid": 1336753, + "ts": 1696943230717.975, "dur": 3.326, + "args": { + "External id": 4551523,"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": 1336753, "tid": 1336753, + "ts": 1696943230720.235, "dur": 1.000, + "args": { + "External id": 4551524,"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": 1336753, "tid": 1336753, + "ts": 1696943230721.693, "dur": 1.319, + "args": { + "External id": 4551525,"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": 1336753, "tid": 1336753, + "ts": 1696943230722.050, "dur": 0.900, + "args": { + "External id": 4551526,"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": 1336753, "tid": 1336753, + "ts": 1696943230725.839, "dur": 5.037, + "args": { + "External id": 4551527,"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": 1336753, "tid": 1336753, + "ts": 1696943230730.043, "dur": 0.764, + "args": { + "External id": 4551528,"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": 1336753, "tid": 1336753, + "ts": 1696943230731.141, "dur": 1.368, + "args": { + "External id": 4551529,"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": 1336753, "tid": 1336753, + "ts": 1696943230731.678, "dur": 0.770, + "args": { + "External id": 4551530,"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": 1336753, "tid": 1336753, + "ts": 1696943230732.848, "dur": 1.610, + "args": { + "External id": 4551531,"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": 1336753, "tid": 1336753, + "ts": 1696943230733.551, "dur": 0.844, + "args": { + "External id": 4551532,"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": 1336753, "tid": 1336753, + "ts": 1696943230734.991, "dur": 3.548, + "args": { + "External id": 4551533,"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": 1336753, "tid": 1336753, + "ts": 1696943230737.642, "dur": 0.824, + "args": { + "External id": 4551534,"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": 1336753, "tid": 1336753, + "ts": 1696943230738.967, "dur": 1.658, + "args": { + "External id": 4551535,"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": 1336753, "tid": 1336753, + "ts": 1696943230739.626, "dur": 0.931, + "args": { + "External id": 4551536,"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": 1336753, "tid": 1336753, + "ts": 1696943230740.850, "dur": 2.984, + "args": { + "External id": 4551537,"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": 1336753, "tid": 1336753, + "ts": 1696943230741.415, "dur": 2.344, + "args": { + "External id": 4551538,"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": 1336753, "tid": 1336753, + "ts": 1696943230744.222, "dur": 2.815, + "args": { + "External id": 4551539,"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": 1336753, "tid": 1336753, + "ts": 1696943230746.392, "dur": 0.579, + "args": { + "External id": 4551540,"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": 1336753, "tid": 1336753, + "ts": 1696943230747.377, "dur": 1.318, + "args": { + "External id": 4551541,"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": 1336753, "tid": 1336753, + "ts": 1696943230747.888, "dur": 0.745, + "args": { + "External id": 4551542,"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": 1336753, "tid": 1336753, + "ts": 1696943230751.134, "dur": 5.060, + "args": { + "External id": 4551543,"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": 1336753, "tid": 1336753, + "ts": 1696943230755.328, "dur": 0.797, + "args": { + "External id": 4551544,"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": 1336753, "tid": 1336753, + "ts": 1696943230756.435, "dur": 1.766, + "args": { + "External id": 4551545,"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": 1336753, "tid": 1336753, + "ts": 1696943230756.997, "dur": 1.143, + "args": { + "External id": 4551546,"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": 1336753, "tid": 1336753, + "ts": 1696943230758.552, "dur": 1.591, + "args": { + "External id": 4551547,"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": 1336753, "tid": 1336753, + "ts": 1696943230759.036, "dur": 1.046, + "args": { + "External id": 4551548,"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": 1336753, "tid": 1336753, + "ts": 1696943230760.492, "dur": 4.331, + "args": { + "External id": 4551549,"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": 1336753, "tid": 1336753, + "ts": 1696943230763.858, "dur": 0.896, + "args": { + "External id": 4551550,"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": 1336753, "tid": 1336753, + "ts": 1696943230765.168, "dur": 1.699, + "args": { + "External id": 4551551,"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": 1336753, "tid": 1336753, + "ts": 1696943230765.838, "dur": 0.963, + "args": { + "External id": 4551552,"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": 1336753, "tid": 1336753, + "ts": 1696943230767.189, "dur": 3.249, + "args": { + "External id": 4551553,"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": 1336753, "tid": 1336753, + "ts": 1696943230767.703, "dur": 2.484, + "args": { + "External id": 4551554,"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": 1336753, "tid": 1336753, + "ts": 1696943230770.752, "dur": 4.588, + "args": { + "External id": 4551555,"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": 1336753, "tid": 1336753, + "ts": 1696943230774.421, "dur": 0.853, + "args": { + "External id": 4551556,"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": 1336753, "tid": 1336753, + "ts": 1696943230775.609, "dur": 3.485, + "args": { + "External id": 4551557,"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": 1336753, "tid": 1336753, + "ts": 1696943230776.413, "dur": 2.614, + "args": { + "External id": 4551558,"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": 1336753, "tid": 1336753, + "ts": 1696943230781.308, "dur": 2.440, + "args": { + "External id": 4551559,"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": 1336753, "tid": 1336753, + "ts": 1696943230783.083, "dur": 0.598, + "args": { + "External id": 4551560,"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": 1336753, "tid": 1336753, + "ts": 1696943230783.986, "dur": 1.317, + "args": { + "External id": 4551561,"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": 1336753, "tid": 1336753, + "ts": 1696943230784.560, "dur": 0.680, + "args": { + "External id": 4551562,"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": 1336753, "tid": 1336753, + "ts": 1696943230785.959, "dur": 3.649, + "args": { + "External id": 4551563,"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": 1336753, "tid": 1336753, + "ts": 1696943230788.567, "dur": 0.972, + "args": { + "External id": 4551564,"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": 1336753, "tid": 1336753, + "ts": 1696943230790.106, "dur": 2.919, + "args": { + "External id": 4551565,"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": 1336753, "tid": 1336753, + "ts": 1696943230792.036, "dur": 0.924, + "args": { + "External id": 4551566,"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": 1336753, "tid": 1336753, + "ts": 1696943230793.265, "dur": 1.141, + "args": { + "External id": 4551567,"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": 1336753, "tid": 1336753, + "ts": 1696943230793.647, "dur": 0.695, + "args": { + "External id": 4551568,"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": 1336753, "tid": 1336753, + "ts": 1696943230794.658, "dur": 3.076, + "args": { + "External id": 4551569,"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": 1336753, "tid": 1336753, + "ts": 1696943230796.979, "dur": 0.685, + "args": { + "External id": 4551570,"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": 1336753, "tid": 1336753, + "ts": 1696943230798.334, "dur": 2.660, + "args": { + "External id": 4551571,"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": 1336753, "tid": 1336753, + "ts": 1696943230800.264, "dur": 0.665, + "args": { + "External id": 4551572,"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": 1336753, "tid": 1336753, + "ts": 1696943230801.225, "dur": 2.992, + "args": { + "External id": 4551573,"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": 1336753, "tid": 1336753, + "ts": 1696943230801.608, "dur": 2.332, + "args": { + "External id": 4551574,"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": 1336753, "tid": 1336753, + "ts": 1696943230806.796, "dur": 2.729, + "args": { + "External id": 4551575,"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": 1336753, "tid": 1336753, + "ts": 1696943230808.685, "dur": 0.772, + "args": { + "External id": 4551576,"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": 1336753, "tid": 1336753, + "ts": 1696943230809.754, "dur": 1.354, + "args": { + "External id": 4551577,"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": 1336753, "tid": 1336753, + "ts": 1696943230810.211, "dur": 0.832, + "args": { + "External id": 4551578,"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": 1336753, "tid": 1336753, + "ts": 1696943230811.343, "dur": 3.648, + "args": { + "External id": 4551579,"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": 1336753, "tid": 1336753, + "ts": 1696943230813.840, "dur": 1.087, + "args": { + "External id": 4551580,"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": 1336753, "tid": 1336753, + "ts": 1696943230815.432, "dur": 1.565, + "args": { + "External id": 4551581,"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": 1336753, "tid": 1336753, + "ts": 1696943230816.106, "dur": 0.823, + "args": { + "External id": 4551582,"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": 1336753, "tid": 1336753, + "ts": 1696943230817.227, "dur": 2.046, + "args": { + "External id": 4551583,"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": 1336753, "tid": 1336753, + "ts": 1696943230818.331, "dur": 0.880, + "args": { + "External id": 4551584,"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": 1336753, "tid": 1336753, + "ts": 1696943230819.532, "dur": 3.695, + "args": { + "External id": 4551585,"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": 1336753, "tid": 1336753, + "ts": 1696943230822.532, "dur": 0.625, + "args": { + "External id": 4551586,"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": 1336753, "tid": 1336753, + "ts": 1696943230823.456, "dur": 1.975, + "args": { + "External id": 4551587,"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": 1336753, "tid": 1336753, + "ts": 1696943230824.611, "dur": 0.750, + "args": { + "External id": 4551588,"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": 1336753, "tid": 1336753, + "ts": 1696943230825.706, "dur": 3.492, + "args": { + "External id": 4551589,"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": 1336753, "tid": 1336753, + "ts": 1696943230826.784, "dur": 2.347, + "args": { + "External id": 4551590,"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": 1336753, "tid": 1336753, + "ts": 1696943230831.672, "dur": 1.961, + "args": { + "External id": 4551591,"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": 1336753, "tid": 1336753, + "ts": 1696943230832.998, "dur": 0.565, + "args": { + "External id": 4551592,"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": 1336753, "tid": 1336753, + "ts": 1696943230833.884, "dur": 2.080, + "args": { + "External id": 4551593,"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": 1336753, "tid": 1336753, + "ts": 1696943230835.028, "dur": 0.872, + "args": { + "External id": 4551594,"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": 1336753, "tid": 1336753, + "ts": 1696943230836.364, "dur": 4.252, + "args": { + "External id": 4551595,"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": 1336753, "tid": 1336753, + "ts": 1696943230839.836, "dur": 0.712, + "args": { + "External id": 4551596,"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": 1336753, "tid": 1336753, + "ts": 1696943230840.930, "dur": 1.527, + "args": { + "External id": 4551597,"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": 1336753, "tid": 1336753, + "ts": 1696943230841.803, "dur": 0.590, + "args": { + "External id": 4551598,"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": 1336753, "tid": 1336753, + "ts": 1696943230842.687, "dur": 2.288, + "args": { + "External id": 4551599,"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": 1336753, "tid": 1336753, + "ts": 1696943230843.926, "dur": 0.981, + "args": { + "External id": 4551600,"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": 1336753, "tid": 1336753, + "ts": 1696943230845.534, "dur": 3.662, + "args": { + "External id": 4551601,"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": 1336753, "tid": 1336753, + "ts": 1696943230848.356, "dur": 0.779, + "args": { + "External id": 4551602,"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": 1336753, "tid": 1336753, + "ts": 1696943230849.426, "dur": 2.386, + "args": { + "External id": 4551603,"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": 1336753, "tid": 1336753, + "ts": 1696943230850.972, "dur": 0.774, + "args": { + "External id": 4551604,"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": 1336753, "tid": 1336753, + "ts": 1696943230852.063, "dur": 3.426, + "args": { + "External id": 4551605,"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": 1336753, "tid": 1336753, + "ts": 1696943230852.922, "dur": 2.308, + "args": { + "External id": 4551606,"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": 1336753, "tid": 1336753, + "ts": 1696943230858.067, "dur": 2.111, + "args": { + "External id": 4551607,"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": 1336753, "tid": 1336753, + "ts": 1696943230859.447, "dur": 0.669, + "args": { + "External id": 4551608,"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": 1336753, "tid": 1336753, + "ts": 1696943230860.917, "dur": 1.350, + "args": { + "External id": 4551609,"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": 1336753, "tid": 1336753, + "ts": 1696943230861.589, "dur": 0.600, + "args": { + "External id": 4551610,"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": 1336753, "tid": 1336753, + "ts": 1696943230862.702, "dur": 4.392, + "args": { + "External id": 4551611,"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": 1336753, "tid": 1336753, + "ts": 1696943230866.186, "dur": 0.841, + "args": { + "External id": 4551612,"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": 1336753, "tid": 1336753, + "ts": 1696943230867.557, "dur": 1.718, + "args": { + "External id": 4551613,"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": 1336753, "tid": 1336753, + "ts": 1696943230868.729, "dur": 0.483, + "args": { + "External id": 4551614,"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": 1336753, "tid": 1336753, + "ts": 1696943230869.686, "dur": 2.281, + "args": { + "External id": 4551615,"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": 1336753, "tid": 1336753, + "ts": 1696943230870.843, "dur": 1.060, + "args": { + "External id": 4551616,"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": 1336753, "tid": 1336753, + "ts": 1696943230872.425, "dur": 3.203, + "args": { + "External id": 4551617,"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": 1336753, "tid": 1336753, + "ts": 1696943230874.891, "dur": 0.675, + "args": { + "External id": 4551618,"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": 1336753, "tid": 1336753, + "ts": 1696943230875.934, "dur": 2.766, + "args": { + "External id": 4551619,"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": 1336753, "tid": 1336753, + "ts": 1696943230877.578, "dur": 1.053, + "args": { + "External id": 4551620,"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": 1336753, "tid": 1336753, + "ts": 1696943230878.998, "dur": 3.031, + "args": { + "External id": 4551621,"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": 1336753, "tid": 1336753, + "ts": 1696943230879.695, "dur": 2.266, + "args": { + "External id": 4551622,"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": 1336753, "tid": 1336753, + "ts": 1696943230884.202, "dur": 2.432, + "args": { + "External id": 4551623,"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": 1336753, "tid": 1336753, + "ts": 1696943230885.764, "dur": 0.804, + "args": { + "External id": 4551624,"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": 1336753, "tid": 1336753, + "ts": 1696943230886.892, "dur": 1.654, + "args": { + "External id": 4551625,"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": 1336753, "tid": 1336753, + "ts": 1696943230887.685, "dur": 0.796, + "args": { + "External id": 4551626,"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": 1336753, "tid": 1336753, + "ts": 1696943230888.778, "dur": 3.637, + "args": { + "External id": 4551627,"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": 1336753, "tid": 1336753, + "ts": 1696943230891.525, "dur": 0.828, + "args": { + "External id": 4551628,"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": 1336753, "tid": 1336753, + "ts": 1696943230892.698, "dur": 1.589, + "args": { + "External id": 4551629,"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": 1336753, "tid": 1336753, + "ts": 1696943230893.587, "dur": 0.636, + "args": { + "External id": 4551630,"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": 1336753, "tid": 1336753, + "ts": 1696943230894.707, "dur": 1.953, + "args": { + "External id": 4551631,"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": 1336753, "tid": 1336753, + "ts": 1696943230895.934, "dur": 0.663, + "args": { + "External id": 4551632,"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": 1336753, "tid": 1336753, + "ts": 1696943230896.914, "dur": 3.506, + "args": { + "External id": 4551633,"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": 1336753, "tid": 1336753, + "ts": 1696943230899.617, "dur": 0.737, + "args": { + "External id": 4551634,"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": 1336753, "tid": 1336753, + "ts": 1696943230900.835, "dur": 1.873, + "args": { + "External id": 4551635,"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": 1336753, "tid": 1336753, + "ts": 1696943230902.073, "dur": 0.567, + "args": { + "External id": 4551636,"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": 1336753, "tid": 1336753, + "ts": 1696943230903.146, "dur": 3.406, + "args": { + "External id": 4551637,"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": 1336753, "tid": 1336753, + "ts": 1696943230904.055, "dur": 2.425, + "args": { + "External id": 4551638,"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": 1336753, "tid": 1336753, + "ts": 1696943230909.138, "dur": 1.926, + "args": { + "External id": 4551639,"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": 1336753, "tid": 1336753, + "ts": 1696943230910.050, "dur": 0.948, + "args": { + "External id": 4551640,"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": 1336753, "tid": 1336753, + "ts": 1696943230911.327, "dur": 1.408, + "args": { + "External id": 4551641,"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": 1336753, "tid": 1336753, + "ts": 1696943230911.996, "dur": 0.676, + "args": { + "External id": 4551642,"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": 1336753, "tid": 1336753, + "ts": 1696943230912.995, "dur": 4.336, + "args": { + "External id": 4551643,"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": 1336753, "tid": 1336753, + "ts": 1696943230916.253, "dur": 1.007, + "args": { + "External id": 4551644,"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": 1336753, "tid": 1336753, + "ts": 1696943230917.883, "dur": 1.617, + "args": { + "External id": 4551645,"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": 1336753, "tid": 1336753, + "ts": 1696943230918.842, "dur": 0.595, + "args": { + "External id": 4551646,"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": 1336753, "tid": 1336753, + "ts": 1696943230919.939, "dur": 2.190, + "args": { + "External id": 4551647,"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": 1336753, "tid": 1336753, + "ts": 1696943230921.364, "dur": 0.700, + "args": { + "External id": 4551648,"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": 1336753, "tid": 1336753, + "ts": 1696943230922.388, "dur": 3.411, + "args": { + "External id": 4551649,"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": 1336753, "tid": 1336753, + "ts": 1696943230924.980, "dur": 0.750, + "args": { + "External id": 4551650,"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": 1336753, "tid": 1336753, + "ts": 1696943230926.387, "dur": 2.257, + "args": { + "External id": 4551651,"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": 1336753, "tid": 1336753, + "ts": 1696943230927.771, "dur": 0.808, + "args": { + "External id": 4551652,"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": 1336753, "tid": 1336753, + "ts": 1696943230928.900, "dur": 3.421, + "args": { + "External id": 4551653,"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": 1336753, "tid": 1336753, + "ts": 1696943230929.796, "dur": 2.270, + "args": { + "External id": 4551654,"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": 1336753, "tid": 1336753, + "ts": 1696943230934.736, "dur": 1.958, + "args": { + "External id": 4551655,"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": 1336753, "tid": 1336753, + "ts": 1696943230936.020, "dur": 0.611, + "args": { + "External id": 4551656,"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": 1336753, "tid": 1336753, + "ts": 1696943230936.947, "dur": 1.875, + "args": { + "External id": 4551657,"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": 1336753, "tid": 1336753, + "ts": 1696943230937.625, "dur": 1.129, + "args": { + "External id": 4551658,"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": 1336753, "tid": 1336753, + "ts": 1696943230939.068, "dur": 4.204, + "args": { + "External id": 4551659,"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": 1336753, "tid": 1336753, + "ts": 1696943230942.403, "dur": 0.805, + "args": { + "External id": 4551660,"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": 1336753, "tid": 1336753, + "ts": 1696943230943.751, "dur": 1.487, + "args": { + "External id": 4551661,"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": 1336753, "tid": 1336753, + "ts": 1696943230944.431, "dur": 0.740, + "args": { + "External id": 4551662,"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": 1336753, "tid": 1336753, + "ts": 1696943230945.502, "dur": 1.896, + "args": { + "External id": 4551663,"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": 1336753, "tid": 1336753, + "ts": 1696943230946.655, "dur": 0.682, + "args": { + "External id": 4551664,"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": 1336753, "tid": 1336753, + "ts": 1696943230947.908, "dur": 2.991, + "args": { + "External id": 4551665,"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": 1336753, "tid": 1336753, + "ts": 1696943230950.329, "dur": 0.506, + "args": { + "External id": 4551666,"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": 1336753, "tid": 1336753, + "ts": 1696943230951.306, "dur": 2.413, + "args": { + "External id": 4551667,"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": 1336753, "tid": 1336753, + "ts": 1696943230952.827, "dur": 0.819, + "args": { + "External id": 4551668,"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": 1336753, "tid": 1336753, + "ts": 1696943230953.976, "dur": 3.748, + "args": { + "External id": 4551669,"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": 1336753, "tid": 1336753, + "ts": 1696943230954.984, "dur": 2.470, + "args": { + "External id": 4551670,"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": 1336753, "tid": 1336753, + "ts": 1696943230960.600, "dur": 1.791, + "args": { + "External id": 4551671,"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": 1336753, "tid": 1336753, + "ts": 1696943230961.580, "dur": 0.747, + "args": { + "External id": 4551672,"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": 1336753, "tid": 1336753, + "ts": 1696943230962.848, "dur": 1.639, + "args": { + "External id": 4551673,"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": 1336753, "tid": 1336753, + "ts": 1696943230963.513, "dur": 0.911, + "args": { + "External id": 4551674,"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": 1336753, "tid": 1336753, + "ts": 1696943230964.735, "dur": 4.236, + "args": { + "External id": 4551675,"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": 1336753, "tid": 1336753, + "ts": 1696943230968.346, "dur": 0.559, + "args": { + "External id": 4551676,"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": 1336753, "tid": 1336753, + "ts": 1696943230969.249, "dur": 1.772, + "args": { + "External id": 4551677,"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": 1336753, "tid": 1336753, + "ts": 1696943230970.195, "dur": 0.762, + "args": { + "External id": 4551678,"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": 1336753, "tid": 1336753, + "ts": 1696943230971.437, "dur": 1.693, + "args": { + "External id": 4551679,"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": 1336753, "tid": 1336753, + "ts": 1696943230972.388, "dur": 0.680, + "args": { + "External id": 4551680,"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": 1336753, "tid": 1336753, + "ts": 1696943231026.639, "dur": 5.224, + "args": { + "External id": 4557825,"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": 1336753, "tid": 1336753, + "ts": 1696943231030.874, "dur": 0.713, + "args": { + "External id": 4557826,"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": 1336753, "tid": 1336753, + "ts": 1696943231032.258, "dur": 2.039, + "args": { + "External id": 4557827,"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": 1336753, "tid": 1336753, + "ts": 1696943231033.448, "dur": 0.781, + "args": { + "External id": 4557828,"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": 1336753, "tid": 1336753, + "ts": 1696943231034.580, "dur": 3.272, + "args": { + "External id": 4557829,"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": 1336753, "tid": 1336753, + "ts": 1696943231035.446, "dur": 2.326, + "args": { + "External id": 4557830,"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": 1336753, "tid": 1336753, + "ts": 1696943231040.221, "dur": 2.267, + "args": { + "External id": 4557831,"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": 1336753, "tid": 1336753, + "ts": 1696943231041.676, "dur": 0.745, + "args": { + "External id": 4557832,"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": 1336753, "tid": 1336753, + "ts": 1696943231042.976, "dur": 1.510, + "args": { + "External id": 4557833,"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": 1336753, "tid": 1336753, + "ts": 1696943231043.917, "dur": 0.496, + "args": { + "External id": 4557834,"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": 1336753, "tid": 1336753, + "ts": 1696943231044.919, "dur": 3.815, + "args": { + "External id": 4557835,"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": 1336753, "tid": 1336753, + "ts": 1696943231048.058, "dur": 0.603, + "args": { + "External id": 4557836,"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": 1336753, "tid": 1336753, + "ts": 1696943231049.029, "dur": 1.283, + "args": { + "External id": 4557837,"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": 1336753, "tid": 1336753, + "ts": 1696943231049.752, "dur": 0.494, + "args": { + "External id": 4557838,"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": 1336753, "tid": 1336753, + "ts": 1696943231050.543, "dur": 1.983, + "args": { + "External id": 4557839,"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": 1336753, "tid": 1336753, + "ts": 1696943231051.716, "dur": 0.741, + "args": { + "External id": 4557840,"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": 1336753, "tid": 1336753, + "ts": 1696943231052.935, "dur": 3.320, + "args": { + "External id": 4557841,"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": 1336753, "tid": 1336753, + "ts": 1696943231055.416, "dur": 0.771, + "args": { + "External id": 4557842,"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": 1336753, "tid": 1336753, + "ts": 1696943231056.534, "dur": 2.091, + "args": { + "External id": 4557843,"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": 1336753, "tid": 1336753, + "ts": 1696943231057.785, "dur": 0.774, + "args": { + "External id": 4557844,"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": 1336753, "tid": 1336753, + "ts": 1696943231058.945, "dur": 3.095, + "args": { + "External id": 4557845,"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": 1336753, "tid": 1336753, + "ts": 1696943231059.676, "dur": 2.287, + "args": { + "External id": 4557846,"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": 1336753, "tid": 1336753, + "ts": 1696943231064.318, "dur": 2.447, + "args": { + "External id": 4557847,"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": 1336753, "tid": 1336753, + "ts": 1696943231065.925, "dur": 0.777, + "args": { + "External id": 4557848,"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": 1336753, "tid": 1336753, + "ts": 1696943231067.078, "dur": 1.439, + "args": { + "External id": 4557849,"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": 1336753, "tid": 1336753, + "ts": 1696943231067.756, "dur": 0.689, + "args": { + "External id": 4557850,"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": 1336753, "tid": 1336753, + "ts": 1696943231068.759, "dur": 3.598, + "args": { + "External id": 4557851,"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": 1336753, "tid": 1336753, + "ts": 1696943231071.787, "dur": 0.500, + "args": { + "External id": 4557852,"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": 1336753, "tid": 1336753, + "ts": 1696943231072.658, "dur": 1.653, + "args": { + "External id": 4557853,"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": 1336753, "tid": 1336753, + "ts": 1696943231073.496, "dur": 0.751, + "args": { + "External id": 4557854,"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": 1336753, "tid": 1336753, + "ts": 1696943231074.602, "dur": 1.874, + "args": { + "External id": 4557855,"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": 1336753, "tid": 1336753, + "ts": 1696943231075.721, "dur": 0.683, + "args": { + "External id": 4557856,"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": 1336753, "tid": 1336753, + "ts": 1696943231076.752, "dur": 2.966, + "args": { + "External id": 4557857,"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": 1336753, "tid": 1336753, + "ts": 1696943231079.067, "dur": 0.587, + "args": { + "External id": 4557858,"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": 1336753, "tid": 1336753, + "ts": 1696943231080.184, "dur": 2.154, + "args": { + "External id": 4557859,"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": 1336753, "tid": 1336753, + "ts": 1696943231081.511, "dur": 0.761, + "args": { + "External id": 4557860,"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": 1336753, "tid": 1336753, + "ts": 1696943231082.594, "dur": 3.152, + "args": { + "External id": 4557861,"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": 1336753, "tid": 1336753, + "ts": 1696943231083.437, "dur": 2.233, + "args": { + "External id": 4557862,"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": 1336753, "tid": 1336753, + "ts": 1696943231088.372, "dur": 1.838, + "args": { + "External id": 4557863,"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": 1336753, "tid": 1336753, + "ts": 1696943231089.562, "dur": 0.584, + "args": { + "External id": 4557864,"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": 1336753, "tid": 1336753, + "ts": 1696943231090.487, "dur": 1.617, + "args": { + "External id": 4557865,"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": 1336753, "tid": 1336753, + "ts": 1696943231091.338, "dur": 0.696, + "args": { + "External id": 4557866,"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": 1336753, "tid": 1336753, + "ts": 1696943231092.335, "dur": 4.310, + "args": { + "External id": 4557867,"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": 1336753, "tid": 1336753, + "ts": 1696943231095.852, "dur": 0.731, + "args": { + "External id": 4557868,"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": 1336753, "tid": 1336753, + "ts": 1696943231096.925, "dur": 1.312, + "args": { + "External id": 4557869,"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": 1336753, "tid": 1336753, + "ts": 1696943231097.590, "dur": 0.576, + "args": { + "External id": 4557870,"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": 1336753, "tid": 1336753, + "ts": 1696943231098.549, "dur": 2.268, + "args": { + "External id": 4557871,"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": 1336753, "tid": 1336753, + "ts": 1696943231099.934, "dur": 0.810, + "args": { + "External id": 4557872,"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": 1336753, "tid": 1336753, + "ts": 1696943231101.330, "dur": 3.100, + "args": { + "External id": 4557873,"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": 1336753, "tid": 1336753, + "ts": 1696943231103.621, "dur": 0.743, + "args": { + "External id": 4557874,"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": 1336753, "tid": 1336753, + "ts": 1696943231104.658, "dur": 2.034, + "args": { + "External id": 4557875,"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": 1336753, "tid": 1336753, + "ts": 1696943231105.783, "dur": 0.844, + "args": { + "External id": 4557876,"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": 1336753, "tid": 1336753, + "ts": 1696943231106.978, "dur": 2.855, + "args": { + "External id": 4557877,"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": 1336753, "tid": 1336753, + "ts": 1696943231107.716, "dur": 2.039, + "args": { + "External id": 4557878,"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": 1336753, "tid": 1336753, + "ts": 1696943231112.119, "dur": 2.026, + "args": { + "External id": 4557879,"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": 1336753, "tid": 1336753, + "ts": 1696943231113.433, "dur": 0.649, + "args": { + "External id": 4557880,"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": 1336753, "tid": 1336753, + "ts": 1696943231114.667, "dur": 1.734, + "args": { + "External id": 4557881,"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": 1336753, "tid": 1336753, + "ts": 1696943231115.658, "dur": 0.671, + "args": { + "External id": 4557882,"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": 1336753, "tid": 1336753, + "ts": 1696943231116.682, "dur": 4.310, + "args": { + "External id": 4557883,"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": 1336753, "tid": 1336753, + "ts": 1696943231120.196, "dur": 0.731, + "args": { + "External id": 4557884,"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": 1336753, "tid": 1336753, + "ts": 1696943231121.303, "dur": 1.504, + "args": { + "External id": 4557885,"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": 1336753, "tid": 1336753, + "ts": 1696943231122.182, "dur": 0.559, + "args": { + "External id": 4557886,"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": 1336753, "tid": 1336753, + "ts": 1696943231123.049, "dur": 1.773, + "args": { + "External id": 4557887,"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": 1336753, "tid": 1336753, + "ts": 1696943231124.002, "dur": 0.749, + "args": { + "External id": 4557888,"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": 1336753, "tid": 1336753, + "ts": 1696943231125.092, "dur": 3.498, + "args": { + "External id": 4557889,"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": 1336753, "tid": 1336753, + "ts": 1696943231127.765, "dur": 0.760, + "args": { + "External id": 4557890,"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": 1336753, "tid": 1336753, + "ts": 1696943231129.009, "dur": 1.741, + "args": { + "External id": 4557891,"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": 1336753, "tid": 1336753, + "ts": 1696943231130.040, "dur": 0.637, + "args": { + "External id": 4557892,"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": 1336753, "tid": 1336753, + "ts": 1696943231131.004, "dur": 3.325, + "args": { + "External id": 4557893,"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": 1336753, "tid": 1336753, + "ts": 1696943231131.888, "dur": 2.191, + "args": { + "External id": 4557894,"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": 1336753, "tid": 1336753, + "ts": 1696943231136.912, "dur": 2.078, + "args": { + "External id": 4557895,"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": 1336753, "tid": 1336753, + "ts": 1696943231138.047, "dur": 0.875, + "args": { + "External id": 4557896,"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": 1336753, "tid": 1336753, + "ts": 1696943231139.452, "dur": 1.816, + "args": { + "External id": 4557897,"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": 1336753, "tid": 1336753, + "ts": 1696943231140.378, "dur": 0.818, + "args": { + "External id": 4557898,"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": 1336753, "tid": 1336753, + "ts": 1696943231141.613, "dur": 4.034, + "args": { + "External id": 4557899,"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": 1336753, "tid": 1336753, + "ts": 1696943231145.108, "dur": 0.474, + "args": { + "External id": 4557900,"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": 1336753, "tid": 1336753, + "ts": 1696943231145.981, "dur": 1.608, + "args": { + "External id": 4557901,"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": 1336753, "tid": 1336753, + "ts": 1696943231146.736, "dur": 0.785, + "args": { + "External id": 4557902,"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": 1336753, "tid": 1336753, + "ts": 1696943231147.816, "dur": 2.180, + "args": { + "External id": 4557903,"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": 1336753, "tid": 1336753, + "ts": 1696943231148.928, "dur": 0.998, + "args": { + "External id": 4557904,"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": 1336753, "tid": 1336753, + "ts": 1696943231150.426, "dur": 3.090, + "args": { + "External id": 4557905,"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": 1336753, "tid": 1336753, + "ts": 1696943231152.699, "dur": 0.753, + "args": { + "External id": 4557906,"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": 1336753, "tid": 1336753, + "ts": 1696943231153.754, "dur": 1.912, + "args": { + "External id": 4557907,"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": 1336753, "tid": 1336753, + "ts": 1696943231154.796, "dur": 0.804, + "args": { + "External id": 4557908,"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": 1336753, "tid": 1336753, + "ts": 1696943231155.934, "dur": 3.544, + "args": { + "External id": 4557909,"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": 1336753, "tid": 1336753, + "ts": 1696943231156.896, "dur": 2.504, + "args": { + "External id": 4557910,"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": 1336753, "tid": 1336753, + "ts": 1696943231161.793, "dur": 1.965, + "args": { + "External id": 4557911,"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": 1336753, "tid": 1336753, + "ts": 1696943231163.073, "dur": 0.614, + "args": { + "External id": 4557912,"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": 1336753, "tid": 1336753, + "ts": 1696943231164.250, "dur": 1.794, + "args": { + "External id": 4557913,"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": 1336753, "tid": 1336753, + "ts": 1696943231165.165, "dur": 0.805, + "args": { + "External id": 4557914,"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": 1336753, "tid": 1336753, + "ts": 1696943231166.491, "dur": 4.162, + "args": { + "External id": 4557915,"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": 1336753, "tid": 1336753, + "ts": 1696943231169.959, "dur": 0.631, + "args": { + "External id": 4557916,"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": 1336753, "tid": 1336753, + "ts": 1696943231170.933, "dur": 1.793, + "args": { + "External id": 4557917,"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": 1336753, "tid": 1336753, + "ts": 1696943231171.877, "dur": 0.783, + "args": { + "External id": 4557918,"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": 1336753, "tid": 1336753, + "ts": 1696943231172.956, "dur": 2.835, + "args": { + "External id": 4557919,"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": 1336753, "tid": 1336753, + "ts": 1696943231174.661, "dur": 1.055, + "args": { + "External id": 4557920,"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": 1336753, "tid": 1336753, + "ts": 1696943231176.042, "dur": 3.283, + "args": { + "External id": 4557921,"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": 1336753, "tid": 1336753, + "ts": 1696943231178.491, "dur": 0.771, + "args": { + "External id": 4557922,"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": 1336753, "tid": 1336753, + "ts": 1696943231179.552, "dur": 2.343, + "args": { + "External id": 4557923,"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": 1336753, "tid": 1336753, + "ts": 1696943231180.986, "dur": 0.837, + "args": { + "External id": 4557924,"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": 1336753, "tid": 1336753, + "ts": 1696943231182.350, "dur": 2.899, + "args": { + "External id": 4557925,"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": 1336753, "tid": 1336753, + "ts": 1696943231182.996, "dur": 2.178, + "args": { + "External id": 4557926,"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": 1336753, "tid": 1336753, + "ts": 1696943231187.456, "dur": 2.187, + "args": { + "External id": 4557927,"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": 1336753, "tid": 1336753, + "ts": 1696943231188.982, "dur": 0.596, + "args": { + "External id": 4557928,"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": 1336753, "tid": 1336753, + "ts": 1696943231190.122, "dur": 1.714, + "args": { + "External id": 4557929,"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": 1336753, "tid": 1336753, + "ts": 1696943231190.872, "dur": 0.891, + "args": { + "External id": 4557930,"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": 1336753, "tid": 1336753, + "ts": 1696943231192.333, "dur": 3.581, + "args": { + "External id": 4557931,"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": 1336753, "tid": 1336753, + "ts": 1696943231195.124, "dur": 0.722, + "args": { + "External id": 4557932,"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": 1336753, "tid": 1336753, + "ts": 1696943231196.198, "dur": 1.562, + "args": { + "External id": 4557933,"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": 1336753, "tid": 1336753, + "ts": 1696943231196.925, "dur": 0.771, + "args": { + "External id": 4557934,"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": 1336753, "tid": 1336753, + "ts": 1696943231197.991, "dur": 2.332, + "args": { + "External id": 4557935,"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": 1336753, "tid": 1336753, + "ts": 1696943231199.202, "dur": 1.049, + "args": { + "External id": 4557936,"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": 1336753, "tid": 1336753, + "ts": 1696943231200.751, "dur": 2.833, + "args": { + "External id": 4557937,"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": 1336753, "tid": 1336753, + "ts": 1696943231202.878, "dur": 0.643, + "args": { + "External id": 4557938,"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": 1336753, "tid": 1336753, + "ts": 1696943231203.854, "dur": 1.836, + "args": { + "External id": 4557939,"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": 1336753, "tid": 1336753, + "ts": 1696943231204.976, "dur": 0.649, + "args": { + "External id": 4557940,"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": 1336753, "tid": 1336753, + "ts": 1696943231206.204, "dur": 2.889, + "args": { + "External id": 4557941,"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": 1336753, "tid": 1336753, + "ts": 1696943231207.091, "dur": 1.927, + "args": { + "External id": 4557942,"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": 1336753, "tid": 1336753, + "ts": 1696943231211.886, "dur": 1.783, + "args": { + "External id": 4557943,"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": 1336753, "tid": 1336753, + "ts": 1696943231212.982, "dur": 0.620, + "args": { + "External id": 4557944,"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": 1336753, "tid": 1336753, + "ts": 1696943231213.931, "dur": 1.815, + "args": { + "External id": 4557945,"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": 1336753, "tid": 1336753, + "ts": 1696943231214.979, "dur": 0.692, + "args": { + "External id": 4557946,"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": 1336753, "tid": 1336753, + "ts": 1696943231215.981, "dur": 3.988, + "args": { + "External id": 4557947,"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": 1336753, "tid": 1336753, + "ts": 1696943231219.120, "dur": 0.782, + "args": { + "External id": 4557948,"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": 1336753, "tid": 1336753, + "ts": 1696943231220.259, "dur": 1.193, + "args": { + "External id": 4557949,"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": 1336753, "tid": 1336753, + "ts": 1696943231220.913, "dur": 0.473, + "args": { + "External id": 4557950,"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": 1336753, "tid": 1336753, + "ts": 1696943231221.698, "dur": 1.899, + "args": { + "External id": 4557951,"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": 1336753, "tid": 1336753, + "ts": 1696943231222.577, "dur": 0.947, + "args": { + "External id": 4557952,"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": 1336753, "tid": 1336753, + "ts": 1696943231223.852, "dur": 3.151, + "args": { + "External id": 4557953,"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": 1336753, "tid": 1336753, + "ts": 1696943231226.164, "dur": 0.769, + "args": { + "External id": 4557954,"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": 1336753, "tid": 1336753, + "ts": 1696943231227.499, "dur": 3.725, + "args": { + "External id": 4557955,"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": 1336753, "tid": 1336753, + "ts": 1696943231230.465, "dur": 0.695, + "args": { + "External id": 4557956,"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": 1336753, "tid": 1336753, + "ts": 1696943231231.680, "dur": 3.222, + "args": { + "External id": 4557957,"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": 1336753, "tid": 1336753, + "ts": 1696943231232.544, "dur": 2.287, + "args": { + "External id": 4557958,"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": 1336753, "tid": 1336753, + "ts": 1696943231237.202, "dur": 1.764, + "args": { + "External id": 4557959,"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": 1336753, "tid": 1336753, + "ts": 1696943231238.246, "dur": 0.650, + "args": { + "External id": 4557960,"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": 1336753, "tid": 1336753, + "ts": 1696943231239.431, "dur": 1.905, + "args": { + "External id": 4557961,"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": 1336753, "tid": 1336753, + "ts": 1696943231240.343, "dur": 0.923, + "args": { + "External id": 4557962,"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": 1336753, "tid": 1336753, + "ts": 1696943231241.568, "dur": 4.134, + "args": { + "External id": 4557963,"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": 1336753, "tid": 1336753, + "ts": 1696943231244.892, "dur": 0.742, + "args": { + "External id": 4557964,"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": 1336753, "tid": 1336753, + "ts": 1696943231245.980, "dur": 1.335, + "args": { + "External id": 4557965,"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": 1336753, "tid": 1336753, + "ts": 1696943231246.666, "dur": 0.579, + "args": { + "External id": 4557966,"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": 1336753, "tid": 1336753, + "ts": 1696943231247.589, "dur": 2.711, + "args": { + "External id": 4557967,"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": 1336753, "tid": 1336753, + "ts": 1696943231249.337, "dur": 0.894, + "args": { + "External id": 4557968,"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": 1336753, "tid": 1336753, + "ts": 1696943231250.555, "dur": 3.264, + "args": { + "External id": 4557969,"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": 1336753, "tid": 1336753, + "ts": 1696943231253.050, "dur": 0.696, + "args": { + "External id": 4557970,"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": 1336753, "tid": 1336753, + "ts": 1696943231254.082, "dur": 1.915, + "args": { + "External id": 4557971,"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": 1336753, "tid": 1336753, + "ts": 1696943231255.093, "dur": 0.838, + "args": { + "External id": 4557972,"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": 1336753, "tid": 1336753, + "ts": 1696943231256.265, "dur": 3.838, + "args": { + "External id": 4557973,"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": 1336753, "tid": 1336753, + "ts": 1696943231257.201, "dur": 2.596, + "args": { + "External id": 4557974,"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": 1336753, "tid": 1336753, + "ts": 1696943231262.370, "dur": 2.178, + "args": { + "External id": 4557975,"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": 1336753, "tid": 1336753, + "ts": 1696943231263.486, "dur": 0.998, + "args": { + "External id": 4557976,"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": 1336753, "tid": 1336753, + "ts": 1696943231265.196, "dur": 1.633, + "args": { + "External id": 4557977,"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": 1336753, "tid": 1336753, + "ts": 1696943231266.136, "dur": 0.626, + "args": { + "External id": 4557978,"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": 1336753, "tid": 1336753, + "ts": 1696943231267.449, "dur": 3.582, + "args": { + "External id": 4557979,"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": 1336753, "tid": 1336753, + "ts": 1696943231270.387, "dur": 0.580, + "args": { + "External id": 4557980,"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": 1336753, "tid": 1336753, + "ts": 1696943231271.310, "dur": 1.682, + "args": { + "External id": 4557981,"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": 1336753, "tid": 1336753, + "ts": 1696943231272.340, "dur": 0.586, + "args": { + "External id": 4557982,"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": 1336753, "tid": 1336753, + "ts": 1696943231273.220, "dur": 2.528, + "args": { + "External id": 4557983,"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": 1336753, "tid": 1336753, + "ts": 1696943231274.741, "dur": 0.933, + "args": { + "External id": 4557984,"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": 1336753, "tid": 1336753, + "ts": 1696943231276.252, "dur": 3.763, + "args": { + "External id": 4557985,"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": 1336753, "tid": 1336753, + "ts": 1696943231279.000, "dur": 0.947, + "args": { + "External id": 4557986,"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": 1336753, "tid": 1336753, + "ts": 1696943231280.255, "dur": 2.147, + "args": { + "External id": 4557987,"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": 1336753, "tid": 1336753, + "ts": 1696943231281.553, "dur": 0.782, + "args": { + "External id": 4557988,"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": 1336753, "tid": 1336753, + "ts": 1696943231282.658, "dur": 3.248, + "args": { + "External id": 4557989,"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": 1336753, "tid": 1336753, + "ts": 1696943231283.560, "dur": 2.192, + "args": { + "External id": 4557990,"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": 1336753, "tid": 1336753, + "ts": 1696943231288.267, "dur": 1.644, + "args": { + "External id": 4557991,"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": 1336753, "tid": 1336753, + "ts": 1696943231289.202, "dur": 0.641, + "args": { + "External id": 4557992,"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": 1336753, "tid": 1336753, + "ts": 1696943231290.167, "dur": 1.681, + "args": { + "External id": 4557993,"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": 1336753, "tid": 1336753, + "ts": 1696943231291.064, "dur": 0.717, + "args": { + "External id": 4557994,"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": 1336753, "tid": 1336753, + "ts": 1696943231292.289, "dur": 4.240, + "args": { + "External id": 4557995,"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": 1336753, "tid": 1336753, + "ts": 1696943231295.877, "dur": 0.587, + "args": { + "External id": 4557996,"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": 1336753, "tid": 1336753, + "ts": 1696943231296.813, "dur": 1.604, + "args": { + "External id": 4557997,"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": 1336753, "tid": 1336753, + "ts": 1696943231297.513, "dur": 0.838, + "args": { + "External id": 4557998,"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": 1336753, "tid": 1336753, + "ts": 1696943231298.654, "dur": 2.085, + "args": { + "External id": 4557999,"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": 1336753, "tid": 1336753, + "ts": 1696943231299.774, "dur": 0.899, + "args": { + "External id": 4558000,"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": 1336753, "tid": 1336753, + "ts": 1696943231300.996, "dur": 2.950, + "args": { + "External id": 4558001,"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": 1336753, "tid": 1336753, + "ts": 1696943231303.284, "dur": 0.595, + "args": { + "External id": 4558002,"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": 1336753, "tid": 1336753, + "ts": 1696943231304.172, "dur": 1.916, + "args": { + "External id": 4558003,"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": 1336753, "tid": 1336753, + "ts": 1696943231305.435, "dur": 0.589, + "args": { + "External id": 4558004,"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": 1336753, "tid": 1336753, + "ts": 1696943231306.364, "dur": 3.400, + "args": { + "External id": 4558005,"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": 1336753, "tid": 1336753, + "ts": 1696943231307.225, "dur": 2.469, + "args": { + "External id": 4558006,"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": 1336753, "tid": 1336753, + "ts": 1696943231312.264, "dur": 1.815, + "args": { + "External id": 4558007,"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": 1336753, "tid": 1336753, + "ts": 1696943231313.439, "dur": 0.572, + "args": { + "External id": 4558008,"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": 1336753, "tid": 1336753, + "ts": 1696943231314.362, "dur": 1.813, + "args": { + "External id": 4558009,"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": 1336753, "tid": 1336753, + "ts": 1696943231315.257, "dur": 0.848, + "args": { + "External id": 4558010,"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": 1336753, "tid": 1336753, + "ts": 1696943231316.401, "dur": 3.900, + "args": { + "External id": 4558011,"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": 1336753, "tid": 1336753, + "ts": 1696943231319.537, "dur": 0.694, + "args": { + "External id": 4558012,"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": 1336753, "tid": 1336753, + "ts": 1696943231320.577, "dur": 1.444, + "args": { + "External id": 4558013,"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": 1336753, "tid": 1336753, + "ts": 1696943231321.224, "dur": 0.731, + "args": { + "External id": 4558014,"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": 1336753, "tid": 1336753, + "ts": 1696943231322.452, "dur": 2.056, + "args": { + "External id": 4558015,"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": 1336753, "tid": 1336753, + "ts": 1696943231323.537, "dur": 0.905, + "args": { + "External id": 4558016,"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": 1336753, "tid": 1336753, + "ts": 1696943231324.769, "dur": 3.090, + "args": { + "External id": 4558017,"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": 1336753, "tid": 1336753, + "ts": 1696943231327.114, "dur": 0.674, + "args": { + "External id": 4558018,"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": 1336753, "tid": 1336753, + "ts": 1696943231328.086, "dur": 1.446, + "args": { + "External id": 4558019,"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": 1336753, "tid": 1336753, + "ts": 1696943231328.951, "dur": 0.514, + "args": { + "External id": 4558020,"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": 1336753, "tid": 1336753, + "ts": 1696943231330.032, "dur": 3.245, + "args": { + "External id": 4558021,"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": 1336753, "tid": 1336753, + "ts": 1696943231331.004, "dur": 1.987, + "args": { + "External id": 4558022,"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": 1336753, "tid": 1336753, + "ts": 1696943231335.704, "dur": 2.079, + "args": { + "External id": 4558023,"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": 1336753, "tid": 1336753, + "ts": 1696943231337.105, "dur": 0.608, + "args": { + "External id": 4558024,"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": 1336753, "tid": 1336753, + "ts": 1696943231338.071, "dur": 1.760, + "args": { + "External id": 4558025,"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": 1336753, "tid": 1336753, + "ts": 1696943231338.902, "dur": 0.859, + "args": { + "External id": 4558026,"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": 1336753, "tid": 1336753, + "ts": 1696943231340.081, "dur": 3.862, + "args": { + "External id": 4558027,"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": 1336753, "tid": 1336753, + "ts": 1696943231343.211, "dur": 0.662, + "args": { + "External id": 4558028,"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": 1336753, "tid": 1336753, + "ts": 1696943231344.248, "dur": 1.733, + "args": { + "External id": 4558029,"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": 1336753, "tid": 1336753, + "ts": 1696943231345.130, "dur": 0.574, + "args": { + "External id": 4558030,"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": 1336753, "tid": 1336753, + "ts": 1696943231346.251, "dur": 2.026, + "args": { + "External id": 4558031,"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": 1336753, "tid": 1336753, + "ts": 1696943231347.291, "dur": 0.918, + "args": { + "External id": 4558032,"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": 1336753, "tid": 1336753, + "ts": 1696943231348.541, "dur": 3.160, + "args": { + "External id": 4558033,"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": 1336753, "tid": 1336753, + "ts": 1696943231351.057, "dur": 0.571, + "args": { + "External id": 4558034,"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": 1336753, "tid": 1336753, + "ts": 1696943231352.006, "dur": 1.822, + "args": { + "External id": 4558035,"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": 1336753, "tid": 1336753, + "ts": 1696943231352.870, "dur": 0.892, + "args": { + "External id": 4558036,"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": 1336753, "tid": 1336753, + "ts": 1696943231354.120, "dur": 3.165, + "args": { + "External id": 4558037,"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": 1336753, "tid": 1336753, + "ts": 1696943231354.790, "dur": 2.422, + "args": { + "External id": 4558038,"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": 1336753, "tid": 1336753, + "ts": 1696943231359.701, "dur": 2.292, + "args": { + "External id": 4558039,"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": 1336753, "tid": 1336753, + "ts": 1696943231360.882, "dur": 0.859, + "args": { + "External id": 4558040,"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": 1336753, "tid": 1336753, + "ts": 1696943231362.248, "dur": 1.420, + "args": { + "External id": 4558041,"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": 1336753, "tid": 1336753, + "ts": 1696943231362.916, "dur": 0.683, + "args": { + "External id": 4558042,"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": 1336753, "tid": 1336753, + "ts": 1696943231363.896, "dur": 3.980, + "args": { + "External id": 4558043,"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": 1336753, "tid": 1336753, + "ts": 1696943231367.244, "dur": 0.565, + "args": { + "External id": 4558044,"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": 1336753, "tid": 1336753, + "ts": 1696943231368.193, "dur": 1.312, + "args": { + "External id": 4558045,"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": 1336753, "tid": 1336753, + "ts": 1696943231368.868, "dur": 0.574, + "args": { + "External id": 4558046,"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": 1336753, "tid": 1336753, + "ts": 1696943231369.763, "dur": 1.972, + "args": { + "External id": 4558047,"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": 1336753, "tid": 1336753, + "ts": 1696943231371.083, "dur": 0.582, + "args": { + "External id": 4558048,"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": 1336753, "tid": 1336753, + "ts": 1696943231372.029, "dur": 3.028, + "args": { + "External id": 4558049,"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": 1336753, "tid": 1336753, + "ts": 1696943231374.352, "dur": 0.638, + "args": { + "External id": 4558050,"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": 1336753, "tid": 1336753, + "ts": 1696943231375.299, "dur": 1.940, + "args": { + "External id": 4558051,"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": 1336753, "tid": 1336753, + "ts": 1696943231376.380, "dur": 0.789, + "args": { + "External id": 4558052,"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": 1336753, "tid": 1336753, + "ts": 1696943231377.522, "dur": 3.178, + "args": { + "External id": 4558053,"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": 1336753, "tid": 1336753, + "ts": 1696943231378.399, "dur": 2.223, + "args": { + "External id": 4558054,"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": 1336753, "tid": 1336753, + "ts": 1696943231382.980, "dur": 1.755, + "args": { + "External id": 4558055,"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": 1336753, "tid": 1336753, + "ts": 1696943231383.832, "dur": 0.834, + "args": { + "External id": 4558056,"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": 1336753, "tid": 1336753, + "ts": 1696943231384.990, "dur": 1.731, + "args": { + "External id": 4558057,"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": 1336753, "tid": 1336753, + "ts": 1696943231385.875, "dur": 0.780, + "args": { + "External id": 4558058,"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": 1336753, "tid": 1336753, + "ts": 1696943231386.951, "dur": 4.264, + "args": { + "External id": 4558059,"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": 1336753, "tid": 1336753, + "ts": 1696943231390.317, "dur": 0.833, + "args": { + "External id": 4558060,"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": 1336753, "tid": 1336753, + "ts": 1696943231391.499, "dur": 1.340, + "args": { + "External id": 4558061,"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": 1336753, "tid": 1336753, + "ts": 1696943231392.155, "dur": 0.613, + "args": { + "External id": 4558062,"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": 1336753, "tid": 1336753, + "ts": 1696943231393.068, "dur": 2.167, + "args": { + "External id": 4558063,"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": 1336753, "tid": 1336753, + "ts": 1696943231394.429, "dur": 0.737, + "args": { + "External id": 4558064,"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": 1336753, "tid": 1336753, + "ts": 1696943231395.492, "dur": 3.064, + "args": { + "External id": 4558065,"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": 1336753, "tid": 1336753, + "ts": 1696943231397.919, "dur": 0.571, + "args": { + "External id": 4558066,"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": 1336753, "tid": 1336753, + "ts": 1696943231398.785, "dur": 1.734, + "args": { + "External id": 4558067,"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": 1336753, "tid": 1336753, + "ts": 1696943231399.845, "dur": 0.610, + "args": { + "External id": 4558068,"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": 1336753, "tid": 1336753, + "ts": 1696943231400.777, "dur": 2.765, + "args": { + "External id": 4558069,"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": 1336753, "tid": 1336753, + "ts": 1696943231401.443, "dur": 2.027, + "args": { + "External id": 4558070,"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": 1336753, "tid": 1336753, + "ts": 1696943231405.596, "dur": 1.965, + "args": { + "External id": 4558071,"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": 1336753, "tid": 1336753, + "ts": 1696943231406.681, "dur": 0.815, + "args": { + "External id": 4558072,"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": 1336753, "tid": 1336753, + "ts": 1696943231407.844, "dur": 1.803, + "args": { + "External id": 4558073,"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": 1336753, "tid": 1336753, + "ts": 1696943231408.760, "dur": 0.820, + "args": { + "External id": 4558074,"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": 1336753, "tid": 1336753, + "ts": 1696943231409.875, "dur": 3.801, + "args": { + "External id": 4558075,"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": 1336753, "tid": 1336753, + "ts": 1696943231413.112, "dur": 0.499, + "args": { + "External id": 4558076,"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": 1336753, "tid": 1336753, + "ts": 1696943231414.263, "dur": 1.644, + "args": { + "External id": 4558077,"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": 1336753, "tid": 1336753, + "ts": 1696943231415.098, "dur": 0.745, + "args": { + "External id": 4558078,"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": 1336753, "tid": 1336753, + "ts": 1696943231416.138, "dur": 1.827, + "args": { + "External id": 4558079,"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": 1336753, "tid": 1336753, + "ts": 1696943231417.161, "dur": 0.739, + "args": { + "External id": 4558080,"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": 1336753, "tid": 1336753, + "ts": 1696943231418.253, "dur": 3.075, + "args": { + "External id": 4558081,"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": 1336753, "tid": 1336753, + "ts": 1696943231420.690, "dur": 0.568, + "args": { + "External id": 4558082,"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": 1336753, "tid": 1336753, + "ts": 1696943231421.568, "dur": 1.612, + "args": { + "External id": 4558083,"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": 1336753, "tid": 1336753, + "ts": 1696943231422.452, "dur": 0.666, + "args": { + "External id": 4558084,"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": 1336753, "tid": 1336753, + "ts": 1696943231423.439, "dur": 2.998, + "args": { + "External id": 4558085,"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": 1336753, "tid": 1336753, + "ts": 1696943231424.324, "dur": 2.042, + "args": { + "External id": 4558086,"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": 1336753, "tid": 1336753, + "ts": 1696943231428.978, "dur": 1.875, + "args": { + "External id": 4558087,"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": 1336753, "tid": 1336753, + "ts": 1696943231430.059, "dur": 0.568, + "args": { + "External id": 4558088,"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": 1336753, "tid": 1336753, + "ts": 1696943231431.327, "dur": 1.632, + "args": { + "External id": 4558089,"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": 1336753, "tid": 1336753, + "ts": 1696943231432.210, "dur": 0.681, + "args": { + "External id": 4558090,"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": 1336753, "tid": 1336753, + "ts": 1696943231433.280, "dur": 3.721, + "args": { + "External id": 4558091,"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": 1336753, "tid": 1336753, + "ts": 1696943231436.348, "dur": 0.584, + "args": { + "External id": 4558092,"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": 1336753, "tid": 1336753, + "ts": 1696943231437.277, "dur": 1.430, + "args": { + "External id": 4558093,"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": 1336753, "tid": 1336753, + "ts": 1696943231438.182, "dur": 0.458, + "args": { + "External id": 4558094,"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": 1336753, "tid": 1336753, + "ts": 1696943231438.972, "dur": 2.110, + "args": { + "External id": 4558095,"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": 1336753, "tid": 1336753, + "ts": 1696943231440.130, "dur": 0.886, + "args": { + "External id": 4558096,"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": 1336753, "tid": 1336753, + "ts": 1696943231441.337, "dur": 3.445, + "args": { + "External id": 4558097,"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": 1336753, "tid": 1336753, + "ts": 1696943231444.165, "dur": 0.548, + "args": { + "External id": 4558098,"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": 1336753, "tid": 1336753, + "ts": 1696943231445.030, "dur": 1.749, + "args": { + "External id": 4558099,"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": 1336753, "tid": 1336753, + "ts": 1696943231445.936, "dur": 0.781, + "args": { + "External id": 4558100,"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": 1336753, "tid": 1336753, + "ts": 1696943231447.044, "dur": 3.177, + "args": { + "External id": 4558101,"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": 1336753, "tid": 1336753, + "ts": 1696943231447.912, "dur": 2.240, + "args": { + "External id": 4558102,"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": 1336753, "tid": 1336753, + "ts": 1696943231452.375, "dur": 1.889, + "args": { + "External id": 4558103,"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": 1336753, "tid": 1336753, + "ts": 1696943231453.487, "dur": 0.707, + "args": { + "External id": 4558104,"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": 1336753, "tid": 1336753, + "ts": 1696943231454.714, "dur": 1.677, + "args": { + "External id": 4558105,"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": 1336753, "tid": 1336753, + "ts": 1696943231455.561, "dur": 0.762, + "args": { + "External id": 4558106,"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": 1336753, "tid": 1336753, + "ts": 1696943231456.636, "dur": 3.915, + "args": { + "External id": 4558107,"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": 1336753, "tid": 1336753, + "ts": 1696943231459.681, "dur": 0.803, + "args": { + "External id": 4558108,"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": 1336753, "tid": 1336753, + "ts": 1696943231460.861, "dur": 1.351, + "args": { + "External id": 4558109,"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": 1336753, "tid": 1336753, + "ts": 1696943231461.510, "dur": 0.634, + "args": { + "External id": 4558110,"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": 1336753, "tid": 1336753, + "ts": 1696943231462.442, "dur": 1.792, + "args": { + "External id": 4558111,"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": 1336753, "tid": 1336753, + "ts": 1696943231463.294, "dur": 0.873, + "args": { + "External id": 4558112,"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": 1336753, "tid": 1336753, + "ts": 1696943231464.491, "dur": 3.110, + "args": { + "External id": 4558113,"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": 1336753, "tid": 1336753, + "ts": 1696943231466.958, "dur": 0.569, + "args": { + "External id": 4558114,"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": 1336753, "tid": 1336753, + "ts": 1696943231467.840, "dur": 1.804, + "args": { + "External id": 4558115,"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": 1336753, "tid": 1336753, + "ts": 1696943231468.984, "dur": 0.593, + "args": { + "External id": 4558116,"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": 1336753, "tid": 1336753, + "ts": 1696943231469.927, "dur": 2.736, + "args": { + "External id": 4558117,"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": 1336753, "tid": 1336753, + "ts": 1696943231470.570, "dur": 2.023, + "args": { + "External id": 4558118,"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": 1336753, "tid": 1336753, + "ts": 1696943231474.872, "dur": 2.266, + "args": { + "External id": 4558119,"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": 1336753, "tid": 1336753, + "ts": 1696943231476.261, "dur": 0.811, + "args": { + "External id": 4558120,"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": 1336753, "tid": 1336753, + "ts": 1696943231477.411, "dur": 1.955, + "args": { + "External id": 4558121,"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": 1336753, "tid": 1336753, + "ts": 1696943231478.280, "dur": 0.823, + "args": { + "External id": 4558122,"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": 1336753, "tid": 1336753, + "ts": 1696943231479.613, "dur": 3.907, + "args": { + "External id": 4558123,"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": 1336753, "tid": 1336753, + "ts": 1696943231482.858, "dur": 0.596, + "args": { + "External id": 4558124,"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": 1336753, "tid": 1336753, + "ts": 1696943231483.823, "dur": 1.511, + "args": { + "External id": 4558125,"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": 1336753, "tid": 1336753, + "ts": 1696943231484.496, "dur": 0.772, + "args": { + "External id": 4558126,"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": 1336753, "tid": 1336753, + "ts": 1696943231485.563, "dur": 2.154, + "args": { + "External id": 4558127,"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": 1336753, "tid": 1336753, + "ts": 1696943231486.568, "dur": 0.887, + "args": { + "External id": 4558128,"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": 1336753, "tid": 1336753, + "ts": 1696943231488.145, "dur": 3.224, + "args": { + "External id": 4558129,"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": 1336753, "tid": 1336753, + "ts": 1696943231490.703, "dur": 0.601, + "args": { + "External id": 4558130,"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": 1336753, "tid": 1336753, + "ts": 1696943231491.597, "dur": 1.987, + "args": { + "External id": 4558131,"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": 1336753, "tid": 1336753, + "ts": 1696943231492.718, "dur": 0.802, + "args": { + "External id": 4558132,"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": 1336753, "tid": 1336753, + "ts": 1696943231493.855, "dur": 2.679, + "args": { + "External id": 4558133,"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": 1336753, "tid": 1336753, + "ts": 1696943231494.515, "dur": 1.946, + "args": { + "External id": 4558134,"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": 1336753, "tid": 1336753, + "ts": 1696943231498.844, "dur": 2.296, + "args": { + "External id": 4558135,"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": 1336753, "tid": 1336753, + "ts": 1696943231500.115, "dur": 0.961, + "args": { + "External id": 4558136,"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": 1336753, "tid": 1336753, + "ts": 1696943231501.714, "dur": 1.624, + "args": { + "External id": 4558137,"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": 1336753, "tid": 1336753, + "ts": 1696943231502.394, "dur": 0.874, + "args": { + "External id": 4558138,"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": 1336753, "tid": 1336753, + "ts": 1696943231503.567, "dur": 3.951, + "args": { + "External id": 4558139,"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": 1336753, "tid": 1336753, + "ts": 1696943231506.482, "dur": 0.972, + "args": { + "External id": 4558140,"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": 1336753, "tid": 1336753, + "ts": 1696943231507.794, "dur": 1.784, + "args": { + "External id": 4558141,"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": 1336753, "tid": 1336753, + "ts": 1696943231508.762, "dur": 0.750, + "args": { + "External id": 4558142,"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": 1336753, "tid": 1336753, + "ts": 1696943231509.822, "dur": 2.002, + "args": { + "External id": 4558143,"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": 1336753, "tid": 1336753, + "ts": 1696943231510.923, "dur": 0.833, + "args": { + "External id": 4558144,"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": 1336753, "tid": 1336753, + "ts": 1696943231512.098, "dur": 3.854, + "args": { + "External id": 4558145,"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": 1336753, "tid": 1336753, + "ts": 1696943231514.964, "dur": 0.711, + "args": { + "External id": 4558146,"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": 1336753, "tid": 1336753, + "ts": 1696943231516.222, "dur": 2.218, + "args": { + "External id": 4558147,"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": 1336753, "tid": 1336753, + "ts": 1696943231517.365, "dur": 1.008, + "args": { + "External id": 4558148,"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": 1336753, "tid": 1336753, + "ts": 1696943231518.695, "dur": 3.106, + "args": { + "External id": 4558149,"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": 1336753, "tid": 1336753, + "ts": 1696943231519.382, "dur": 1.960, + "args": { + "External id": 4558150,"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": 1336753, "tid": 1336753, + "ts": 1696943231524.177, "dur": 13.362, + "args": { + "External id": 4558151,"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": 1336753, "tid": 1336753, + "ts": 1696943231525.384, "dur": 11.634, + "args": { + "External id": 4558152,"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": 1336753, "tid": 1336753, + "ts": 1696943231538.814, "dur": 1.988, + "args": { + "External id": 4558153,"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": 1336753, "tid": 1336753, + "ts": 1696943231539.991, "dur": 0.629, + "args": { + "External id": 4558154,"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": 1336753, "tid": 1336753, + "ts": 1696943231541.069, "dur": 4.076, + "args": { + "External id": 4558155,"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": 1336753, "tid": 1336753, + "ts": 1696943231544.341, "dur": 0.740, + "args": { + "External id": 4558156,"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": 1336753, "tid": 1336753, + "ts": 1696943231545.458, "dur": 1.495, + "args": { + "External id": 4558157,"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": 1336753, "tid": 1336753, + "ts": 1696943231546.144, "dur": 0.741, + "args": { + "External id": 4558158,"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": 1336753, "tid": 1336753, + "ts": 1696943231547.244, "dur": 2.223, + "args": { + "External id": 4558159,"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": 1336753, "tid": 1336753, + "ts": 1696943231548.544, "dur": 0.860, + "args": { + "External id": 4558160,"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": 1336753, "tid": 1336753, + "ts": 1696943231549.740, "dur": 3.107, + "args": { + "External id": 4558161,"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": 1336753, "tid": 1336753, + "ts": 1696943231552.185, "dur": 0.599, + "args": { + "External id": 4558162,"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": 1336753, "tid": 1336753, + "ts": 1696943231553.093, "dur": 1.574, + "args": { + "External id": 4558163,"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": 1336753, "tid": 1336753, + "ts": 1696943231553.941, "dur": 0.659, + "args": { + "External id": 4558164,"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": 1336753, "tid": 1336753, + "ts": 1696943231554.933, "dur": 3.193, + "args": { + "External id": 4558165,"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": 1336753, "tid": 1336753, + "ts": 1696943231555.929, "dur": 2.130, + "args": { + "External id": 4558166,"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": 1336753, "tid": 1336753, + "ts": 1696943231560.598, "dur": 2.093, + "args": { + "External id": 4558167,"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": 1336753, "tid": 1336753, + "ts": 1696943231561.904, "dur": 0.725, + "args": { + "External id": 4558168,"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": 1336753, "tid": 1336753, + "ts": 1696943231563.160, "dur": 1.774, + "args": { + "External id": 4558169,"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": 1336753, "tid": 1336753, + "ts": 1696943231563.844, "dur": 0.823, + "args": { + "External id": 4558170,"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": 1336753, "tid": 1336753, + "ts": 1696943231565.182, "dur": 3.914, + "args": { + "External id": 4558171,"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": 1336753, "tid": 1336753, + "ts": 1696943231568.285, "dur": 0.748, + "args": { + "External id": 4558172,"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": 1336753, "tid": 1336753, + "ts": 1696943231569.379, "dur": 1.721, + "args": { + "External id": 4558173,"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": 1336753, "tid": 1336753, + "ts": 1696943231570.080, "dur": 0.945, + "args": { + "External id": 4558174,"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": 1336753, "tid": 1336753, + "ts": 1696943231571.359, "dur": 2.315, + "args": { + "External id": 4558175,"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": 1336753, "tid": 1336753, + "ts": 1696943231572.687, "dur": 0.706, + "args": { + "External id": 4558176,"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": 1336753, "tid": 1336753, + "ts": 1696943231573.933, "dur": 3.278, + "args": { + "External id": 4558177,"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": 1336753, "tid": 1336753, + "ts": 1696943231576.298, "dur": 0.848, + "args": { + "External id": 4558178,"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": 1336753, "tid": 1336753, + "ts": 1696943231577.451, "dur": 2.049, + "args": { + "External id": 4558179,"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": 1336753, "tid": 1336753, + "ts": 1696943231578.531, "dur": 0.794, + "args": { + "External id": 4558180,"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": 1336753, "tid": 1336753, + "ts": 1696943231579.763, "dur": 2.920, + "args": { + "External id": 4558181,"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": 1336753, "tid": 1336753, + "ts": 1696943231580.419, "dur": 2.196, + "args": { + "External id": 4558182,"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": 1336753, "tid": 1336753, + "ts": 1696943231584.927, "dur": 1.804, + "args": { + "External id": 4558183,"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": 1336753, "tid": 1336753, + "ts": 1696943231585.923, "dur": 0.744, + "args": { + "External id": 4558184,"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": 1336753, "tid": 1336753, + "ts": 1696943231586.991, "dur": 1.420, + "args": { + "External id": 4558185,"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": 1336753, "tid": 1336753, + "ts": 1696943231587.678, "dur": 0.668, + "args": { + "External id": 4558186,"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": 1336753, "tid": 1336753, + "ts": 1696943231588.656, "dur": 4.077, + "args": { + "External id": 4558187,"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": 1336753, "tid": 1336753, + "ts": 1696943231592.044, "dur": 0.620, + "args": { + "External id": 4558188,"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": 1336753, "tid": 1336753, + "ts": 1696943231593.014, "dur": 1.483, + "args": { + "External id": 4558189,"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": 1336753, "tid": 1336753, + "ts": 1696943231593.675, "dur": 0.758, + "args": { + "External id": 4558190,"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": 1336753, "tid": 1336753, + "ts": 1696943231594.730, "dur": 2.345, + "args": { + "External id": 4558191,"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": 1336753, "tid": 1336753, + "ts": 1696943231596.063, "dur": 0.950, + "args": { + "External id": 4558192,"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": 1336753, "tid": 1336753, + "ts": 1696943231597.335, "dur": 3.248, + "args": { + "External id": 4558193,"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": 1336753, "tid": 1336753, + "ts": 1696943231599.503, "dur": 1.012, + "args": { + "External id": 4558194,"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": 1336753, "tid": 1336753, + "ts": 1696943231600.817, "dur": 2.347, + "args": { + "External id": 4558195,"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": 1336753, "tid": 1336753, + "ts": 1696943231602.190, "dur": 0.907, + "args": { + "External id": 4558196,"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": 1336753, "tid": 1336753, + "ts": 1696943231603.649, "dur": 3.110, + "args": { + "External id": 4558197,"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": 1336753, "tid": 1336753, + "ts": 1696943231604.335, "dur": 2.354, + "args": { + "External id": 4558198,"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": 1336753, "tid": 1336753, + "ts": 1696943231609.037, "dur": 1.875, + "args": { + "External id": 4558199,"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": 1336753, "tid": 1336753, + "ts": 1696943231610.225, "dur": 0.624, + "args": { + "External id": 4558200,"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": 1336753, "tid": 1336753, + "ts": 1696943231611.195, "dur": 1.831, + "args": { + "External id": 4558201,"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": 1336753, "tid": 1336753, + "ts": 1696943231612.096, "dur": 0.866, + "args": { + "External id": 4558202,"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": 1336753, "tid": 1336753, + "ts": 1696943231613.262, "dur": 3.900, + "args": { + "External id": 4558203,"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": 1336753, "tid": 1336753, + "ts": 1696943231616.498, "dur": 0.599, + "args": { + "External id": 4558204,"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": 1336753, "tid": 1336753, + "ts": 1696943231617.476, "dur": 1.711, + "args": { + "External id": 4558205,"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": 1336753, "tid": 1336753, + "ts": 1696943231618.350, "dur": 0.576, + "args": { + "External id": 4558206,"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::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1696943231619.435, "dur": 1.998, + "args": { + "External id": 4558207,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696943231620.642, "dur": 0.729, + "args": { + "External id": 4558208,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1696943231621.696, "dur": 2.986, + "args": { + "External id": 4558209,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696943231623.862, "dur": 0.753, + "args": { + "External id": 4558210,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336753, "tid": 1336753, + "ts": 1696943231624.916, "dur": 3.421, + "args": { + "External id": 4558211,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696943231627.666, "dur": 0.607, + "args": { + "External id": 4558212,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 1336753, "tid": 1336753, + "ts": 1696943231646.851, "dur": 131.450, + "args": { + "External id": 4558213,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linalg_vector_norm", "pid": 1336753, "tid": 1336753, + "ts": 1696943231881.708, "dur": 167.499, + "args": { + "External id": 4558214,"Record function id": 0, "Concrete Inputs": ["", "2.", "", "False", ""], "Input type": ["float", "Scalar", "", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[291], [], [], [], []], "Ev Idx": 11293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linalg_vector_norm", "pid": 1336753, "tid": 1336753, + "ts": 1696943231947.800, "dur": 76.881, + "args": { + "External id": 4558215,"Record function id": 0, "Concrete Inputs": ["", "2.", "", "False", ""], "Input type": ["float", "Scalar", "", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[291], [], [], [], []], "Ev Idx": 11294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1696943231960.560, "dur": 0.813, + "args": { + "External id": 4558216,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Redistribute", "pid": 1336753, "tid": 1336753, + "ts": 1696943232505.457, "dur": 1007.369, + "args": { + "External id": 4558217,"Sequence number": 45295820, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "False"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 1336753, "tid": 1336753, + "ts": 1696943232585.844, "dur": 114.383, + "args": { + "External id": 4558218,"Record function id": 0, "Concrete Inputs": ["", "2."], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1696943232590.959, "dur": 1.515, + "args": { + "External id": 4558219,"Record function id": 0, "Concrete Inputs": ["", "2."], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696943232650.226, "dur": 0.904, + "args": { + "External id": 4558220,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::all_reduce", "pid": 1336753, "tid": 1336753, + "ts": 1696943232727.516, "dur": 471.963, + "args": { + "External id": 4558221,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["float", "", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1336753, + "ts": 1696943232730.958, "dur": 48.329, + "args": { + "External id": 4558222,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1696943232734.690, "dur": 10.708, + "args": { + "External id": 4558223,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "0"], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696943232740.764, "dur": 3.952, + "args": { + "External id": 4558224,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336753, "tid": 1336753, + "ts": 1696943232747.020, "dur": 31.709, + "args": { + "External id": 4558225,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::allreduce_", "pid": 1336753, "tid": 1336753, + "ts": 1696943232788.918, "dur": 406.962, + "args": { + "External id": 4558226,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "-1"], "Input type": ["TensorList", "", "", "", "Scalar"], "Input Strides": [[[]], [], [], [], []], "Input Dims": [[[]], [], [], [], []], "Ev Idx": 11305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696943232822.298, "dur": 366.526, + "args": { + "External id": 4558227,"Record function id": 0, "Collective name": "allreduce", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 0, "Input Strides": [[[]], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "0", "", "[]", "[]", "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": 11306, "In msg nelems": 1 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:all_reduce", "pid": 1336753, "tid": 1336753, + "ts": 1696943232840.662, "dur": 338.586, + "args": { + "External id": 4558228,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 1336753, "tid": 1336753, + "ts": 1696943233267.210, "dur": 207.158, + "args": { + "External id": 4558229,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::wait_tensor", "pid": 1336753, "tid": 1336753, + "ts": 1696943233360.243, "dur": 36.021, + "args": { + "External id": 4558230,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336753, "tid": 1336753, + "ts": 1696943233381.731, "dur": 3.907, + "args": { + "External id": 4558231,"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": ["", "", "0", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11310, "In msg nelems": 0, "Rank": 0, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 1336753, "tid": 1336753, + "ts": 1696943233426.151, "dur": 42.089, + "args": { + "External id": 4558232,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1696943233428.414, "dur": 1.202, + "args": { + "External id": 4558233,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696943233430.839, "dur": 0.552, + "args": { + "External id": 4558234,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_ToTorchTensor", "pid": 1336753, "tid": 1336753, + "ts": 1696943233549.653, "dur": 25.542, + "args": { + "External id": 4558235,"Sequence number": 45295821, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1696943233562.299, "dur": 8.891, + "args": { + "External id": 4558236,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1696943233564.818, "dur": 6.035, + "args": { + "External id": 4558237,"Record function id": 0, "Concrete Inputs": ["", "[]"], "Input type": ["float", "ScalarList"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336753, "tid": 1336753, + "ts": 1696943233966.523, "dur": 73.016, + "args": { + "External id": 4558238,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "double", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reciprocal", "pid": 1336753, "tid": 1336753, + "ts": 1696943234050.454, "dur": 30.447, + "args": { + "External id": 4558239,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mul", "pid": 1336753, "tid": 1336753, + "ts": 1696943234091.635, "dur": 28.351, + "args": { + "External id": 4558240,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "double"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clamp", "pid": 1336753, "tid": 1336753, + "ts": 1696943234132.889, "dur": 24.010, + "args": { + "External id": 4558241,"Record function id": 0, "Concrete Inputs": ["", "", "1."], "Input type": ["float", "", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696943234135.326, "dur": 0.605, + "args": { + "External id": 4558242,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336753, "tid": 1336753, + "ts": 1696943234177.213, "dur": 0.473, + "args": { + "External id": 4558243,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 11322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_mul_", "pid": 1336753, "tid": 1336753, + "ts": 1696943234301.537, "dur": 849.655, + "args": { + "External id": 4558244,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["TensorList", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_mul_", "pid": 1336753, "tid": 1336753, + "ts": 1696943234828.127, "dur": 289.047, + "args": { + "External id": 4558245,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["TensorList", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::isnan", "pid": 1336753, "tid": 1336753, + "ts": 1696943235198.870, "dur": 31.886, + "args": { + "External id": 4558246,"Sequence number": 45295822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336753, "tid": 1336753, + "ts": 1696943235202.715, "dur": 27.452, + "args": { + "External id": 4558247,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 1336753, "tid": 1336753, + "ts": 1696943235234.806, "dur": 174.947, + "args": { + "External id": 4558248,"Sequence number": 45295822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336753, "tid": 1336753, + "ts": 1696943235236.701, "dur": 172.848, + "args": { + "External id": 4558249,"Sequence number": 45295822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336753, "tid": 1336753, + "ts": 1696943235238.613, "dur": 170.647, + "args": { + "External id": 4558250,"Sequence number": 45295822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::isinf", "pid": 1336753, "tid": 1336753, + "ts": 1696943235414.309, "dur": 60.964, + "args": { + "External id": 4558251,"Sequence number": 45295822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696943235417.446, "dur": 33.229, + "args": { + "External id": 4558252,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1696943235423.575, "dur": 2.776, + "args": { + "External id": 4558253,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336753, "tid": 1336753, + "ts": 1696943235427.927, "dur": 22.336, + "args": { + "External id": 4558254,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], [1]], "Input Dims": [[], [0]], "Ev Idx": 11333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336753, "tid": 1336753, + "ts": 1696943235432.878, "dur": 2.294, + "args": { + "External id": 4558255,"Record function id": 0, "Concrete Inputs": ["", "[]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 11334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336753, "tid": 1336753, + "ts": 1696943235452.312, "dur": 21.977, + "args": { + "External id": 4558256,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 1336753, "tid": 1336753, + "ts": 1696943235477.157, "dur": 36.295, + "args": { + "External id": 4558257,"Sequence number": 45295822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336753, "tid": 1336753, + "ts": 1696943235479.895, "dur": 33.417, + "args": { + "External id": 4558258,"Sequence number": 45295822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336753, "tid": 1336753, + "ts": 1696943235480.586, "dur": 32.449, + "args": { + "External id": 4558259,"Sequence number": 45295822, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11338 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#OptimizersContainer.step", "pid": 1336753, "tid": 1336753, + "ts": 1696943235561.165, "dur": 6240.071, + "args": { + "External id": 4558260,"Record function id": 0, "Ev Idx": 11339 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#AdamW.step", "pid": 1336753, "tid": 1336753, + "ts": 1696943235597.202, "dur": 6180.795, + "args": { + "External id": 4558261,"Record function id": 0, "Ev Idx": 11340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_add_", "pid": 1336753, "tid": 1336753, + "ts": 1696943237047.626, "dur": 306.683, + "args": { + "External id": 4558262,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1696943237068.332, "dur": 1.227, + "args": { + "External id": 4558263,"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": 1336753, "tid": 1336753, + "ts": 1696943237070.473, "dur": 0.161, + "args": { + "External id": 4558264,"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": 1336753, "tid": 1336753, + "ts": 1696943237071.135, "dur": 0.091, + "args": { + "External id": 4558265,"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": 1336753, "tid": 1336753, + "ts": 1696943237071.888, "dur": 0.285, + "args": { + "External id": 4558266,"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": 1336753, "tid": 1336753, + "ts": 1696943237072.579, "dur": 0.397, + "args": { + "External id": 4558267,"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": 1336753, "tid": 1336753, + "ts": 1696943237073.363, "dur": 0.089, + "args": { + "External id": 4558268,"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": 1336753, "tid": 1336753, + "ts": 1696943237074.200, "dur": 0.092, + "args": { + "External id": 4558269,"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": 1336753, "tid": 1336753, + "ts": 1696943237074.794, "dur": 0.297, + "args": { + "External id": 4558270,"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": 1336753, "tid": 1336753, + "ts": 1696943237075.823, "dur": 0.069, + "args": { + "External id": 4558271,"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": 1336753, "tid": 1336753, + "ts": 1696943237076.192, "dur": 0.248, + "args": { + "External id": 4558272,"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": 1336753, "tid": 1336753, + "ts": 1696943237076.984, "dur": 0.241, + "args": { + "External id": 4558273,"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": 1336753, "tid": 1336753, + "ts": 1696943237077.737, "dur": 0.078, + "args": { + "External id": 4558274,"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": 1336753, "tid": 1336753, + "ts": 1696943237078.422, "dur": 0.250, + "args": { + "External id": 4558275,"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": 1336753, "tid": 1336753, + "ts": 1696943237079.007, "dur": 0.279, + "args": { + "External id": 4558276,"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": 1336753, "tid": 1336753, + "ts": 1696943237079.942, "dur": 0.095, + "args": { + "External id": 4558277,"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": 1336753, "tid": 1336753, + "ts": 1696943237080.588, "dur": 0.069, + "args": { + "External id": 4558278,"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": 1336753, "tid": 1336753, + "ts": 1696943237081.160, "dur": 0.065, + "args": { + "External id": 4558279,"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": 1336753, "tid": 1336753, + "ts": 1696943237081.898, "dur": 0.064, + "args": { + "External id": 4558280,"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": 1336753, "tid": 1336753, + "ts": 1696943237082.341, "dur": 0.065, + "args": { + "External id": 4558281,"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": 1336753, "tid": 1336753, + "ts": 1696943237083.071, "dur": 0.059, + "args": { + "External id": 4558282,"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": 1336753, "tid": 1336753, + "ts": 1696943237083.561, "dur": 0.071, + "args": { + "External id": 4558283,"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": 1336753, "tid": 1336753, + "ts": 1696943237084.132, "dur": 0.070, + "args": { + "External id": 4558284,"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": 1336753, "tid": 1336753, + "ts": 1696943237085.010, "dur": 0.068, + "args": { + "External id": 4558285,"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": 1336753, "tid": 1336753, + "ts": 1696943237085.458, "dur": 0.073, + "args": { + "External id": 4558286,"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": 1336753, "tid": 1336753, + "ts": 1696943237086.030, "dur": 0.068, + "args": { + "External id": 4558287,"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": 1336753, "tid": 1336753, + "ts": 1696943237086.700, "dur": 0.066, + "args": { + "External id": 4558288,"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": 1336753, "tid": 1336753, + "ts": 1696943237087.251, "dur": 0.067, + "args": { + "External id": 4558289,"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": 1336753, "tid": 1336753, + "ts": 1696943237087.680, "dur": 0.064, + "args": { + "External id": 4558290,"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": 1336753, "tid": 1336753, + "ts": 1696943237088.191, "dur": 0.068, + "args": { + "External id": 4558291,"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": 1336753, "tid": 1336753, + "ts": 1696943237088.586, "dur": 0.303, + "args": { + "External id": 4558292,"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": 1336753, "tid": 1336753, + "ts": 1696943237089.649, "dur": 0.105, + "args": { + "External id": 4558293,"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": 1336753, "tid": 1336753, + "ts": 1696943237090.189, "dur": 0.293, + "args": { + "External id": 4558294,"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": 1336753, "tid": 1336753, + "ts": 1696943237090.838, "dur": 0.066, + "args": { + "External id": 4558295,"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": 1336753, "tid": 1336753, + "ts": 1696943237091.351, "dur": 0.074, + "args": { + "External id": 4558296,"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": 1336753, "tid": 1336753, + "ts": 1696943237091.726, "dur": 0.271, + "args": { + "External id": 4558297,"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": 1336753, "tid": 1336753, + "ts": 1696943237092.481, "dur": 0.074, + "args": { + "External id": 4558298,"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": 1336753, "tid": 1336753, + "ts": 1696943237092.906, "dur": 0.270, + "args": { + "External id": 4558299,"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": 1336753, "tid": 1336753, + "ts": 1696943237093.525, "dur": 0.102, + "args": { + "External id": 4558300,"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": 1336753, "tid": 1336753, + "ts": 1696943237094.017, "dur": 0.094, + "args": { + "External id": 4558301,"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": 1336753, "tid": 1336753, + "ts": 1696943237094.511, "dur": 0.270, + "args": { + "External id": 4558302,"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": 1336753, "tid": 1336753, + "ts": 1696943237095.463, "dur": 0.063, + "args": { + "External id": 4558303,"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": 1336753, "tid": 1336753, + "ts": 1696943237096.040, "dur": 0.065, + "args": { + "External id": 4558304,"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": 1336753, "tid": 1336753, + "ts": 1696943237096.565, "dur": 0.068, + "args": { + "External id": 4558305,"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": 1336753, "tid": 1336753, + "ts": 1696943237097.212, "dur": 0.070, + "args": { + "External id": 4558306,"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": 1336753, "tid": 1336753, + "ts": 1696943237097.780, "dur": 0.071, + "args": { + "External id": 4558307,"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": 1336753, "tid": 1336753, + "ts": 1696943237098.199, "dur": 0.070, + "args": { + "External id": 4558308,"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": 1336753, "tid": 1336753, + "ts": 1696943237099.034, "dur": 0.068, + "args": { + "External id": 4558309,"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": 1336753, "tid": 1336753, + "ts": 1696943237099.552, "dur": 0.067, + "args": { + "External id": 4558310,"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": 1336753, "tid": 1336753, + "ts": 1696943237100.052, "dur": 0.065, + "args": { + "External id": 4558311,"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": 1336753, "tid": 1336753, + "ts": 1696943237100.538, "dur": 0.069, + "args": { + "External id": 4558312,"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": 1336753, "tid": 1336753, + "ts": 1696943237101.170, "dur": 0.069, + "args": { + "External id": 4558313,"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": 1336753, "tid": 1336753, + "ts": 1696943237101.766, "dur": 0.069, + "args": { + "External id": 4558314,"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": 1336753, "tid": 1336753, + "ts": 1696943237102.222, "dur": 0.071, + "args": { + "External id": 4558315,"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": 1336753, "tid": 1336753, + "ts": 1696943237102.701, "dur": 0.070, + "args": { + "External id": 4558316,"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": 1336753, "tid": 1336753, + "ts": 1696943237103.054, "dur": 0.096, + "args": { + "External id": 4558317,"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": 1336753, "tid": 1336753, + "ts": 1696943237103.499, "dur": 0.105, + "args": { + "External id": 4558318,"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": 1336753, "tid": 1336753, + "ts": 1696943237103.904, "dur": 0.067, + "args": { + "External id": 4558319,"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": 1336753, "tid": 1336753, + "ts": 1696943237104.423, "dur": 0.076, + "args": { + "External id": 4558320,"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": 1336753, "tid": 1336753, + "ts": 1696943237104.926, "dur": 0.242, + "args": { + "External id": 4558321,"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": 1336753, "tid": 1336753, + "ts": 1696943237105.576, "dur": 0.083, + "args": { + "External id": 4558322,"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": 1336753, "tid": 1336753, + "ts": 1696943237106.106, "dur": 0.101, + "args": { + "External id": 4558323,"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": 1336753, "tid": 1336753, + "ts": 1696943237106.627, "dur": 0.097, + "args": { + "External id": 4558324,"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": 1336753, "tid": 1336753, + "ts": 1696943237107.520, "dur": 0.107, + "args": { + "External id": 4558325,"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": 1336753, "tid": 1336753, + "ts": 1696943237107.997, "dur": 0.103, + "args": { + "External id": 4558326,"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": 1336753, "tid": 1336753, + "ts": 1696943237108.591, "dur": 0.062, + "args": { + "External id": 4558327,"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": 1336753, "tid": 1336753, + "ts": 1696943237109.013, "dur": 0.368, + "args": { + "External id": 4558328,"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": 1336753, "tid": 1336753, + "ts": 1696943237109.717, "dur": 0.063, + "args": { + "External id": 4558329,"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": 1336753, "tid": 1336753, + "ts": 1696943237110.333, "dur": 0.066, + "args": { + "External id": 4558330,"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": 1336753, "tid": 1336753, + "ts": 1696943237110.737, "dur": 0.065, + "args": { + "External id": 4558331,"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": 1336753, "tid": 1336753, + "ts": 1696943237111.292, "dur": 0.063, + "args": { + "External id": 4558332,"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": 1336753, "tid": 1336753, + "ts": 1696943237111.738, "dur": 0.072, + "args": { + "External id": 4558333,"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": 1336753, "tid": 1336753, + "ts": 1696943237112.342, "dur": 0.069, + "args": { + "External id": 4558334,"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": 1336753, "tid": 1336753, + "ts": 1696943237112.921, "dur": 0.065, + "args": { + "External id": 4558335,"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": 1336753, "tid": 1336753, + "ts": 1696943237113.321, "dur": 0.069, + "args": { + "External id": 4558336,"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": 1336753, "tid": 1336753, + "ts": 1696943237143.755, "dur": 0.349, + "args": { + "External id": 4558337,"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": 1336753, "tid": 1336753, + "ts": 1696943237144.744, "dur": 0.053, + "args": { + "External id": 4558338,"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": 1336753, "tid": 1336753, + "ts": 1696943237145.164, "dur": 0.067, + "args": { + "External id": 4558339,"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": 1336753, "tid": 1336753, + "ts": 1696943237145.557, "dur": 0.065, + "args": { + "External id": 4558340,"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": 1336753, "tid": 1336753, + "ts": 1696943237145.960, "dur": 0.052, + "args": { + "External id": 4558341,"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": 1336753, "tid": 1336753, + "ts": 1696943237146.466, "dur": 0.065, + "args": { + "External id": 4558342,"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": 1336753, "tid": 1336753, + "ts": 1696943237146.888, "dur": 0.064, + "args": { + "External id": 4558343,"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": 1336753, "tid": 1336753, + "ts": 1696943237147.511, "dur": 0.059, + "args": { + "External id": 4558344,"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": 1336753, "tid": 1336753, + "ts": 1696943237147.903, "dur": 0.065, + "args": { + "External id": 4558345,"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": 1336753, "tid": 1336753, + "ts": 1696943237148.528, "dur": 0.065, + "args": { + "External id": 4558346,"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": 1336753, "tid": 1336753, + "ts": 1696943237148.929, "dur": 0.057, + "args": { + "External id": 4558347,"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": 1336753, "tid": 1336753, + "ts": 1696943237149.326, "dur": 0.065, + "args": { + "External id": 4558348,"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": 1336753, "tid": 1336753, + "ts": 1696943237149.795, "dur": 0.060, + "args": { + "External id": 4558349,"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": 1336753, "tid": 1336753, + "ts": 1696943237150.426, "dur": 0.059, + "args": { + "External id": 4558350,"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": 1336753, "tid": 1336753, + "ts": 1696943237151.088, "dur": 0.065, + "args": { + "External id": 4558351,"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": 1336753, "tid": 1336753, + "ts": 1696943237151.664, "dur": 0.067, + "args": { + "External id": 4558352,"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": 1336753, "tid": 1336753, + "ts": 1696943237152.108, "dur": 0.069, + "args": { + "External id": 4558353,"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": 1336753, "tid": 1336753, + "ts": 1696943237152.488, "dur": 0.064, + "args": { + "External id": 4558354,"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": 1336753, "tid": 1336753, + "ts": 1696943237152.920, "dur": 0.061, + "args": { + "External id": 4558355,"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": 1336753, "tid": 1336753, + "ts": 1696943237153.335, "dur": 0.065, + "args": { + "External id": 4558356,"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": 1336753, "tid": 1336753, + "ts": 1696943237153.877, "dur": 0.055, + "args": { + "External id": 4558357,"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": 1336753, "tid": 1336753, + "ts": 1696943237154.181, "dur": 0.060, + "args": { + "External id": 4558358,"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": 1336753, "tid": 1336753, + "ts": 1696943237154.644, "dur": 0.048, + "args": { + "External id": 4558359,"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": 1336753, "tid": 1336753, + "ts": 1696943237155.041, "dur": 0.062, + "args": { + "External id": 4558360,"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": 1336753, "tid": 1336753, + "ts": 1696943237155.482, "dur": 0.058, + "args": { + "External id": 4558361,"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": 1336753, "tid": 1336753, + "ts": 1696943237156.008, "dur": 0.059, + "args": { + "External id": 4558362,"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": 1336753, "tid": 1336753, + "ts": 1696943237156.533, "dur": 0.056, + "args": { + "External id": 4558363,"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": 1336753, "tid": 1336753, + "ts": 1696943237157.149, "dur": 0.057, + "args": { + "External id": 4558364,"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": 1336753, "tid": 1336753, + "ts": 1696943237157.723, "dur": 0.056, + "args": { + "External id": 4558365,"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": 1336753, "tid": 1336753, + "ts": 1696943237158.238, "dur": 0.059, + "args": { + "External id": 4558366,"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": 1336753, "tid": 1336753, + "ts": 1696943237158.643, "dur": 0.058, + "args": { + "External id": 4558367,"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": 1336753, "tid": 1336753, + "ts": 1696943237159.248, "dur": 0.066, + "args": { + "External id": 4558368,"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": 1336753, "tid": 1336753, + "ts": 1696943237159.758, "dur": 0.070, + "args": { + "External id": 4558369,"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": 1336753, "tid": 1336753, + "ts": 1696943237160.166, "dur": 0.055, + "args": { + "External id": 4558370,"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": 1336753, "tid": 1336753, + "ts": 1696943237160.674, "dur": 0.066, + "args": { + "External id": 4558371,"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": 1336753, "tid": 1336753, + "ts": 1696943237161.534, "dur": 0.065, + "args": { + "External id": 4558372,"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": 1336753, "tid": 1336753, + "ts": 1696943237162.243, "dur": 0.051, + "args": { + "External id": 4558373,"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": 1336753, "tid": 1336753, + "ts": 1696943237162.643, "dur": 0.056, + "args": { + "External id": 4558374,"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": 1336753, "tid": 1336753, + "ts": 1696943237163.068, "dur": 0.060, + "args": { + "External id": 4558375,"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": 1336753, "tid": 1336753, + "ts": 1696943237163.476, "dur": 0.062, + "args": { + "External id": 4558376,"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": 1336753, "tid": 1336753, + "ts": 1696943237163.937, "dur": 0.061, + "args": { + "External id": 4558377,"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": 1336753, "tid": 1336753, + "ts": 1696943237164.348, "dur": 0.060, + "args": { + "External id": 4558378,"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": 1336753, "tid": 1336753, + "ts": 1696943237164.702, "dur": 0.059, + "args": { + "External id": 4558379,"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": 1336753, "tid": 1336753, + "ts": 1696943237165.056, "dur": 0.056, + "args": { + "External id": 4558380,"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": 1336753, "tid": 1336753, + "ts": 1696943237165.561, "dur": 0.057, + "args": { + "External id": 4558381,"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": 1336753, "tid": 1336753, + "ts": 1696943237165.868, "dur": 0.058, + "args": { + "External id": 4558382,"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": 1336753, "tid": 1336753, + "ts": 1696943237166.351, "dur": 0.049, + "args": { + "External id": 4558383,"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": 1336753, "tid": 1336753, + "ts": 1696943237166.797, "dur": 0.056, + "args": { + "External id": 4558384,"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": 1336753, "tid": 1336753, + "ts": 1696943237167.239, "dur": 0.055, + "args": { + "External id": 4558385,"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": 1336753, "tid": 1336753, + "ts": 1696943237167.620, "dur": 0.058, + "args": { + "External id": 4558386,"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": 1336753, "tid": 1336753, + "ts": 1696943237168.001, "dur": 0.056, + "args": { + "External id": 4558387,"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": 1336753, "tid": 1336753, + "ts": 1696943237168.815, "dur": 0.060, + "args": { + "External id": 4558388,"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": 1336753, "tid": 1336753, + "ts": 1696943237169.458, "dur": 0.054, + "args": { + "External id": 4558389,"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": 1336753, "tid": 1336753, + "ts": 1696943237176.600, "dur": 0.087, + "args": { + "External id": 4558390,"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": 1336753, "tid": 1336753, + "ts": 1696943237177.603, "dur": 0.068, + "args": { + "External id": 4558391,"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": 1336753, "tid": 1336753, + "ts": 1696943237178.038, "dur": 0.066, + "args": { + "External id": 4558392,"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": 1336753, "tid": 1336753, + "ts": 1696943237178.457, "dur": 0.066, + "args": { + "External id": 4558393,"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": 1336753, "tid": 1336753, + "ts": 1696943237178.941, "dur": 0.057, + "args": { + "External id": 4558394,"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": 1336753, "tid": 1336753, + "ts": 1696943237179.265, "dur": 0.060, + "args": { + "External id": 4558395,"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": 1336753, "tid": 1336753, + "ts": 1696943237179.768, "dur": 0.057, + "args": { + "External id": 4558396,"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": 1336753, "tid": 1336753, + "ts": 1696943237180.230, "dur": 0.095, + "args": { + "External id": 4558397,"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": 1336753, "tid": 1336753, + "ts": 1696943237180.644, "dur": 0.059, + "args": { + "External id": 4558398,"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": 1336753, "tid": 1336753, + "ts": 1696943237181.086, "dur": 0.061, + "args": { + "External id": 4558399,"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": 1336753, "tid": 1336753, + "ts": 1696943237181.503, "dur": 0.060, + "args": { + "External id": 4558400,"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": 1336753, "tid": 1336753, + "ts": 1696943237181.919, "dur": 0.060, + "args": { + "External id": 4558401,"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": 1336753, "tid": 1336753, + "ts": 1696943237182.325, "dur": 0.060, + "args": { + "External id": 4558402,"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": 1336753, "tid": 1336753, + "ts": 1696943237182.704, "dur": 0.053, + "args": { + "External id": 4558403,"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": 1336753, "tid": 1336753, + "ts": 1696943237183.185, "dur": 0.055, + "args": { + "External id": 4558404,"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": 1336753, "tid": 1336753, + "ts": 1696943237183.642, "dur": 0.045, + "args": { + "External id": 4558405,"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": 1336753, "tid": 1336753, + "ts": 1696943237184.053, "dur": 0.053, + "args": { + "External id": 4558406,"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": 1336753, "tid": 1336753, + "ts": 1696943237184.580, "dur": 0.066, + "args": { + "External id": 4558407,"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": 1336753, "tid": 1336753, + "ts": 1696943237185.299, "dur": 0.091, + "args": { + "External id": 4558408,"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": 1336753, "tid": 1336753, + "ts": 1696943237185.744, "dur": 0.060, + "args": { + "External id": 4558409,"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": 1336753, "tid": 1336753, + "ts": 1696943237186.055, "dur": 0.063, + "args": { + "External id": 4558410,"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": 1336753, "tid": 1336753, + "ts": 1696943237186.653, "dur": 0.060, + "args": { + "External id": 4558411,"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": 1336753, "tid": 1336753, + "ts": 1696943237187.468, "dur": 0.060, + "args": { + "External id": 4558412,"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": 1336753, "tid": 1336753, + "ts": 1696943237187.785, "dur": 0.061, + "args": { + "External id": 4558413,"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": 1336753, "tid": 1336753, + "ts": 1696943237188.373, "dur": 0.060, + "args": { + "External id": 4558414,"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": 1336753, "tid": 1336753, + "ts": 1696943237188.792, "dur": 0.056, + "args": { + "External id": 4558415,"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": 1336753, "tid": 1336753, + "ts": 1696943237189.240, "dur": 0.056, + "args": { + "External id": 4558416,"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": 1336753, "tid": 1336753, + "ts": 1696943237189.549, "dur": 0.059, + "args": { + "External id": 4558417,"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": 1336753, "tid": 1336753, + "ts": 1696943237189.957, "dur": 0.069, + "args": { + "External id": 4558418,"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": 1336753, "tid": 1336753, + "ts": 1696943237190.337, "dur": 0.068, + "args": { + "External id": 4558419,"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": 1336753, "tid": 1336753, + "ts": 1696943237191.157, "dur": 0.069, + "args": { + "External id": 4558420,"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": 1336753, "tid": 1336753, + "ts": 1696943237191.555, "dur": 0.065, + "args": { + "External id": 4558421,"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": 1336753, "tid": 1336753, + "ts": 1696943237192.068, "dur": 0.056, + "args": { + "External id": 4558422,"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": 1336753, "tid": 1336753, + "ts": 1696943237192.487, "dur": 0.059, + "args": { + "External id": 4558423,"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": 1336753, "tid": 1336753, + "ts": 1696943237192.864, "dur": 0.083, + "args": { + "External id": 4558424,"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": 1336753, "tid": 1336753, + "ts": 1696943237193.266, "dur": 0.067, + "args": { + "External id": 4558425,"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": 1336753, "tid": 1336753, + "ts": 1696943237193.887, "dur": 0.044, + "args": { + "External id": 4558426,"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": 1336753, "tid": 1336753, + "ts": 1696943237194.306, "dur": 0.058, + "args": { + "External id": 4558427,"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": 1336753, "tid": 1336753, + "ts": 1696943237194.739, "dur": 0.060, + "args": { + "External id": 4558428,"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": 1336753, "tid": 1336753, + "ts": 1696943237195.383, "dur": 0.059, + "args": { + "External id": 4558429,"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": 1336753, "tid": 1336753, + "ts": 1696943237196.011, "dur": 0.055, + "args": { + "External id": 4558430,"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": 1336753, "tid": 1336753, + "ts": 1696943237196.539, "dur": 0.058, + "args": { + "External id": 4558431,"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": 1336753, "tid": 1336753, + "ts": 1696943237196.992, "dur": 0.056, + "args": { + "External id": 4558432,"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": 1336753, "tid": 1336753, + "ts": 1696943237197.397, "dur": 0.067, + "args": { + "External id": 4558433,"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": 1336753, "tid": 1336753, + "ts": 1696943237197.793, "dur": 0.065, + "args": { + "External id": 4558434,"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": 1336753, "tid": 1336753, + "ts": 1696943237198.175, "dur": 0.070, + "args": { + "External id": 4558435,"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": 1336753, "tid": 1336753, + "ts": 1696943237198.631, "dur": 0.071, + "args": { + "External id": 4558436,"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": 1336753, "tid": 1336753, + "ts": 1696943237199.112, "dur": 0.069, + "args": { + "External id": 4558437,"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": 1336753, "tid": 1336753, + "ts": 1696943237199.478, "dur": 0.063, + "args": { + "External id": 4558438,"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": 1336753, "tid": 1336753, + "ts": 1696943237199.911, "dur": 0.069, + "args": { + "External id": 4558439,"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": 1336753, "tid": 1336753, + "ts": 1696943237200.586, "dur": 0.068, + "args": { + "External id": 4558440,"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": 1336753, "tid": 1336753, + "ts": 1696943237200.953, "dur": 0.068, + "args": { + "External id": 4558441,"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": 1336753, "tid": 1336753, + "ts": 1696943237201.539, "dur": 0.058, + "args": { + "External id": 4558442,"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": 1336753, "tid": 1336753, + "ts": 1696943237201.992, "dur": 0.051, + "args": { + "External id": 4558443,"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": 1336753, "tid": 1336753, + "ts": 1696943237202.395, "dur": 0.064, + "args": { + "External id": 4558444,"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": 1336753, "tid": 1336753, + "ts": 1696943237202.903, "dur": 0.068, + "args": { + "External id": 4558445,"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": 1336753, "tid": 1336753, + "ts": 1696943237203.288, "dur": 0.050, + "args": { + "External id": 4558446,"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": 1336753, "tid": 1336753, + "ts": 1696943237203.735, "dur": 0.065, + "args": { + "External id": 4558447,"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": 1336753, "tid": 1336753, + "ts": 1696943237204.188, "dur": 0.064, + "args": { + "External id": 4558448,"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": 1336753, "tid": 1336753, + "ts": 1696943237204.772, "dur": 0.065, + "args": { + "External id": 4558449,"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": 1336753, "tid": 1336753, + "ts": 1696943237205.225, "dur": 0.067, + "args": { + "External id": 4558450,"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": 1336753, "tid": 1336753, + "ts": 1696943237205.615, "dur": 0.064, + "args": { + "External id": 4558451,"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": 1336753, "tid": 1336753, + "ts": 1696943237206.039, "dur": 0.066, + "args": { + "External id": 4558452,"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": 1336753, "tid": 1336753, + "ts": 1696943237206.527, "dur": 0.062, + "args": { + "External id": 4558453,"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": 1336753, "tid": 1336753, + "ts": 1696943237206.912, "dur": 0.062, + "args": { + "External id": 4558454,"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": 1336753, "tid": 1336753, + "ts": 1696943237207.339, "dur": 0.064, + "args": { + "External id": 4558455,"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": 1336753, "tid": 1336753, + "ts": 1696943237207.745, "dur": 0.067, + "args": { + "External id": 4558456,"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": 1336753, "tid": 1336753, + "ts": 1696943237208.332, "dur": 0.051, + "args": { + "External id": 4558457,"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": 1336753, "tid": 1336753, + "ts": 1696943237208.882, "dur": 0.066, + "args": { + "External id": 4558458,"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": 1336753, "tid": 1336753, + "ts": 1696943237209.319, "dur": 0.066, + "args": { + "External id": 4558459,"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": 1336753, "tid": 1336753, + "ts": 1696943237209.915, "dur": 0.053, + "args": { + "External id": 4558460,"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": 1336753, "tid": 1336753, + "ts": 1696943237210.324, "dur": 0.066, + "args": { + "External id": 4558461,"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": 1336753, "tid": 1336753, + "ts": 1696943237210.773, "dur": 0.068, + "args": { + "External id": 4558462,"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": 1336753, "tid": 1336753, + "ts": 1696943237211.270, "dur": 0.067, + "args": { + "External id": 4558463,"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": 1336753, "tid": 1336753, + "ts": 1696943237211.714, "dur": 0.069, + "args": { + "External id": 4558464,"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": 1336753, "tid": 1336753, + "ts": 1696943237212.100, "dur": 0.066, + "args": { + "External id": 4558465,"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": 1336753, "tid": 1336753, + "ts": 1696943237212.456, "dur": 0.067, + "args": { + "External id": 4558466,"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": 1336753, "tid": 1336753, + "ts": 1696943237212.864, "dur": 0.054, + "args": { + "External id": 4558467,"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": 1336753, "tid": 1336753, + "ts": 1696943237213.197, "dur": 0.069, + "args": { + "External id": 4558468,"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": 1336753, "tid": 1336753, + "ts": 1696943237213.614, "dur": 0.067, + "args": { + "External id": 4558469,"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": 1336753, "tid": 1336753, + "ts": 1696943237213.929, "dur": 0.055, + "args": { + "External id": 4558470,"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": 1336753, "tid": 1336753, + "ts": 1696943237214.633, "dur": 0.086, + "args": { + "External id": 4558471,"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": 1336753, "tid": 1336753, + "ts": 1696943237215.041, "dur": 0.056, + "args": { + "External id": 4558472,"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": 1336753, "tid": 1336753, + "ts": 1696943237215.690, "dur": 0.068, + "args": { + "External id": 4558473,"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": 1336753, "tid": 1336753, + "ts": 1696943237216.021, "dur": 0.069, + "args": { + "External id": 4558474,"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": 1336753, "tid": 1336753, + "ts": 1696943237216.633, "dur": 0.062, + "args": { + "External id": 4558475,"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": 1336753, "tid": 1336753, + "ts": 1696943237216.951, "dur": 0.052, + "args": { + "External id": 4558476,"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": 1336753, "tid": 1336753, + "ts": 1696943237217.538, "dur": 0.063, + "args": { + "External id": 4558477,"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": 1336753, "tid": 1336753, + "ts": 1696943237217.857, "dur": 0.047, + "args": { + "External id": 4558478,"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": 1336753, "tid": 1336753, + "ts": 1696943237218.424, "dur": 0.061, + "args": { + "External id": 4558479,"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": 1336753, "tid": 1336753, + "ts": 1696943237218.741, "dur": 0.054, + "args": { + "External id": 4558480,"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": 1336753, "tid": 1336753, + "ts": 1696943237219.575, "dur": 0.067, + "args": { + "External id": 4558481,"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": 1336753, "tid": 1336753, + "ts": 1696943237219.897, "dur": 0.055, + "args": { + "External id": 4558482,"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": 1336753, "tid": 1336753, + "ts": 1696943237220.690, "dur": 0.069, + "args": { + "External id": 4558483,"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": 1336753, "tid": 1336753, + "ts": 1696943237221.018, "dur": 0.053, + "args": { + "External id": 4558484,"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": 1336753, "tid": 1336753, + "ts": 1696943237221.800, "dur": 0.068, + "args": { + "External id": 4558485,"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": 1336753, "tid": 1336753, + "ts": 1696943237222.120, "dur": 0.058, + "args": { + "External id": 4558486,"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": 1336753, "tid": 1336753, + "ts": 1696943237222.915, "dur": 0.066, + "args": { + "External id": 4558487,"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": 1336753, "tid": 1336753, + "ts": 1696943237223.242, "dur": 0.051, + "args": { + "External id": 4558488,"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": 1336753, "tid": 1336753, + "ts": 1696943237224.252, "dur": 0.062, + "args": { + "External id": 4558489,"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": 1336753, "tid": 1336753, + "ts": 1696943237224.594, "dur": 0.050, + "args": { + "External id": 4558490,"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": 1336753, "tid": 1336753, + "ts": 1696943237225.555, "dur": 0.065, + "args": { + "External id": 4558491,"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": 1336753, "tid": 1336753, + "ts": 1696943237225.880, "dur": 0.053, + "args": { + "External id": 4558492,"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": 1336753, "tid": 1336753, + "ts": 1696943237226.628, "dur": 0.068, + "args": { + "External id": 4558493,"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": 1336753, "tid": 1336753, + "ts": 1696943237226.949, "dur": 0.054, + "args": { + "External id": 4558494,"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": 1336753, "tid": 1336753, + "ts": 1696943237227.904, "dur": 0.065, + "args": { + "External id": 4558495,"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": 1336753, "tid": 1336753, + "ts": 1696943237228.251, "dur": 0.055, + "args": { + "External id": 4558496,"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": 1336753, "tid": 1336753, + "ts": 1696943237229.040, "dur": 0.071, + "args": { + "External id": 4558497,"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": 1336753, "tid": 1336753, + "ts": 1696943237229.361, "dur": 0.056, + "args": { + "External id": 4558498,"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": 1336753, "tid": 1336753, + "ts": 1696943237230.052, "dur": 0.066, + "args": { + "External id": 4558499,"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": 1336753, "tid": 1336753, + "ts": 1696943237230.373, "dur": 0.054, + "args": { + "External id": 4558500,"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": 1336753, "tid": 1336753, + "ts": 1696943237230.923, "dur": 0.074, + "args": { + "External id": 4558501,"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": 1336753, "tid": 1336753, + "ts": 1696943237231.251, "dur": 0.053, + "args": { + "External id": 4558502,"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": 1336753, "tid": 1336753, + "ts": 1696943237231.952, "dur": 0.069, + "args": { + "External id": 4558503,"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": 1336753, "tid": 1336753, + "ts": 1696943237232.277, "dur": 0.054, + "args": { + "External id": 4558504,"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": 1336753, "tid": 1336753, + "ts": 1696943237232.810, "dur": 0.067, + "args": { + "External id": 4558505,"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": 1336753, "tid": 1336753, + "ts": 1696943237233.144, "dur": 0.048, + "args": { + "External id": 4558506,"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": 1336753, "tid": 1336753, + "ts": 1696943237233.688, "dur": 0.057, + "args": { + "External id": 4558507,"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": 1336753, "tid": 1336753, + "ts": 1696943237234.002, "dur": 0.054, + "args": { + "External id": 4558508,"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": 1336753, "tid": 1336753, + "ts": 1696943237234.535, "dur": 0.061, + "args": { + "External id": 4558509,"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": 1336753, "tid": 1336753, + "ts": 1696943237234.855, "dur": 0.048, + "args": { + "External id": 4558510,"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": 1336753, "tid": 1336753, + "ts": 1696943237235.765, "dur": 0.057, + "args": { + "External id": 4558511,"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": 1336753, "tid": 1336753, + "ts": 1696943237236.083, "dur": 0.048, + "args": { + "External id": 4558512,"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": 1336753, "tid": 1336753, + "ts": 1696943237237.035, "dur": 0.060, + "args": { + "External id": 4558513,"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": 1336753, "tid": 1336753, + "ts": 1696943237237.351, "dur": 0.048, + "args": { + "External id": 4558514,"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": 1336753, "tid": 1336753, + "ts": 1696943237238.126, "dur": 0.057, + "args": { + "External id": 4558515,"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": 1336753, "tid": 1336753, + "ts": 1696943237238.439, "dur": 0.046, + "args": { + "External id": 4558516,"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": 1336753, "tid": 1336753, + "ts": 1696943237239.324, "dur": 0.055, + "args": { + "External id": 4558517,"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": 1336753, "tid": 1336753, + "ts": 1696943237239.636, "dur": 0.050, + "args": { + "External id": 4558518,"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": 1336753, "tid": 1336753, + "ts": 1696943237240.397, "dur": 0.062, + "args": { + "External id": 4558519,"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": 1336753, "tid": 1336753, + "ts": 1696943237240.717, "dur": 0.047, + "args": { + "External id": 4558520,"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": 1336753, "tid": 1336753, + "ts": 1696943237241.314, "dur": 0.051, + "args": { + "External id": 4558521,"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": 1336753, "tid": 1336753, + "ts": 1696943237241.621, "dur": 0.049, + "args": { + "External id": 4558522,"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": 1336753, "tid": 1336753, + "ts": 1696943237242.190, "dur": 0.067, + "args": { + "External id": 4558523,"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": 1336753, "tid": 1336753, + "ts": 1696943237242.511, "dur": 0.052, + "args": { + "External id": 4558524,"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": 1336753, "tid": 1336753, + "ts": 1696943237243.294, "dur": 0.065, + "args": { + "External id": 4558525,"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": 1336753, "tid": 1336753, + "ts": 1696943237243.639, "dur": 0.049, + "args": { + "External id": 4558526,"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": 1336753, "tid": 1336753, + "ts": 1696943237244.410, "dur": 0.065, + "args": { + "External id": 4558527,"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": 1336753, "tid": 1336753, + "ts": 1696943237244.763, "dur": 0.055, + "args": { + "External id": 4558528,"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": 1336753, "tid": 1336753, + "ts": 1696943237245.592, "dur": 0.073, + "args": { + "External id": 4558529,"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": 1336753, "tid": 1336753, + "ts": 1696943237245.915, "dur": 0.053, + "args": { + "External id": 4558530,"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": 1336753, "tid": 1336753, + "ts": 1696943237246.632, "dur": 0.066, + "args": { + "External id": 4558531,"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": 1336753, "tid": 1336753, + "ts": 1696943237246.954, "dur": 0.049, + "args": { + "External id": 4558532,"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": 1336753, "tid": 1336753, + "ts": 1696943237247.758, "dur": 0.062, + "args": { + "External id": 4558533,"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": 1336753, "tid": 1336753, + "ts": 1696943237248.076, "dur": 0.054, + "args": { + "External id": 4558534,"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": 1336753, "tid": 1336753, + "ts": 1696943237248.710, "dur": 0.066, + "args": { + "External id": 4558535,"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": 1336753, "tid": 1336753, + "ts": 1696943237249.035, "dur": 0.051, + "args": { + "External id": 4558536,"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": 1336753, "tid": 1336753, + "ts": 1696943237249.594, "dur": 0.065, + "args": { + "External id": 4558537,"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": 1336753, "tid": 1336753, + "ts": 1696943237249.917, "dur": 0.055, + "args": { + "External id": 4558538,"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": 1336753, "tid": 1336753, + "ts": 1696943237250.538, "dur": 0.068, + "args": { + "External id": 4558539,"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": 1336753, "tid": 1336753, + "ts": 1696943237250.863, "dur": 0.050, + "args": { + "External id": 4558540,"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": 1336753, "tid": 1336753, + "ts": 1696943237251.755, "dur": 0.064, + "args": { + "External id": 4558541,"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": 1336753, "tid": 1336753, + "ts": 1696943237252.071, "dur": 0.053, + "args": { + "External id": 4558542,"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": 1336753, "tid": 1336753, + "ts": 1696943237252.706, "dur": 0.064, + "args": { + "External id": 4558543,"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": 1336753, "tid": 1336753, + "ts": 1696943237253.032, "dur": 0.051, + "args": { + "External id": 4558544,"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": 1336753, "tid": 1336753, + "ts": 1696943237253.858, "dur": 0.052, + "args": { + "External id": 4558545,"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": 1336753, "tid": 1336753, + "ts": 1696943237254.170, "dur": 0.050, + "args": { + "External id": 4558546,"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": 1336753, "tid": 1336753, + "ts": 1696943237254.945, "dur": 0.070, + "args": { + "External id": 4558547,"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::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1696943237255.302, "dur": 0.053, + "args": { + "External id": 4558548,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1696943237256.067, "dur": 0.066, + "args": { + "External id": 4558549,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1696943237256.390, "dur": 0.044, + "args": { + "External id": 4558550,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1696943237257.180, "dur": 0.049, + "args": { + "External id": 4558551,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1696943237257.482, "dur": 0.046, + "args": { + "External id": 4558552,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336753, "tid": 1336753, + "ts": 1696943237258.273, "dur": 0.059, + "args": { + "External id": 4558553,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_fused_adamw_", "pid": 1336753, "tid": 1336753, + "ts": 1696943237877.618, "dur": 3804.282, + "args": { + "External id": 4558554,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "2.1516164802683451e-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": 11633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_fused_adamw_", "pid": 1336753, "tid": 1336753, + "ts": 1696943241120.815, "dur": 343.724, + "args": { + "External id": 4558555,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "2.1516164802683451e-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": 11634 + } + }, + { + "name": "process_name", "ph": "M", "ts": 1696941146090.019, "pid": 1336753, "tid": 0, + "args": { + "name": "python3.12" + } + }, + { + "name": "process_labels", "ph": "M", "ts": 1696941146090.019, "pid": 1336753, "tid": 0, + "args": { + "labels": "CPU" + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 1696941146090.019, "pid": 1336753, "tid": 0, + "args": { + "sort_index": 1336753 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1696941146090.019, "pid": 1336753, "tid": 1381210, + "args": { + "name": "thread 1381210 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1696941146090.019, "pid": 1336753, "tid": 1381210, + "args": { + "sort_index": 1381210 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1696941146090.019, "pid": 1336753, "tid": 1336753, + "args": { + "name": "thread 1336753 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1696941146090.019, "pid": 1336753, "tid": 1336753, + "args": { + "sort_index": 1336753 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1696941146090.019, "pid": 1336753, "tid": 1381210, + "args": { + "name": "thread 1381210 (pt_autograd_0)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1696941146090.019, "pid": 1336753, "tid": 1381210, + "args": { + "sort_index": 1381210 + } + }, + { + "ph": "X", "cat": "Trace", "ts": 1696941146013.445, "dur": 2097383.514, + "pid": "Spans", "tid": "PyTorch Profiler", + "name": "PyTorch Profiler (0)", + "args": { + "Op count": 0 + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 1696941146013.445, + "pid": "Spans", "tid": 0, + "args": { + "sort_index": 536870912 + } + }, + { + "name": "Iteration Start: PyTorch Profiler", "ph": "i", "s": "g", + "pid": "Traces", "tid": "Trace PyTorch Profiler", "ts": 1696941146013.445 + }, + { + "name": "Record Window End", "ph": "i", "s": "g", + "pid": "", "tid": "", "ts": 1696943319673.400 + } + ], + "traceName": "exp/mtp.1B.batch16.seqlen4096.context4096.warmup2000.update1.steps200000.lr2e-4.cosine/profile_trace/iteration_188416/rank0_trace.json", + "displayTimeUnit": "ms", + "baseTimeNanoseconds": 1751410836000000000 +} \ No newline at end of file