diff --git "a/profile_trace/iteration_193536/rank0_trace.json" "b/profile_trace/iteration_193536/rank0_trace.json" new file mode 100644--- /dev/null +++ "b/profile_trace/iteration_193536/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": "E0EFE7451A8F4458AB2F42769438C79A", + "traceEvents": [ + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037382367.230, "dur": 178.735, + "args": { + "External id": 4675585,"Record function id": 0, "Sequence number": 46526662, "Fwd thread id": 1, "Ev Idx": 0 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037382409.633, "dur": 111.170, + "args": { + "External id": 4675586,"Sequence number": 46526662, "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": 1708037382409.633, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336753, "tid": 1381210, + "ts": 1708037382420.452, "dur": 97.637, + "args": { + "External id": 4675587,"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": 1708037382563.245, "dur": 312.303, + "args": { + "External id": 4675588,"Record function id": 0, "Ev Idx": 3 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037382652.074, "dur": 118.535, + "args": { + "External id": 4675589,"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": 1708037382695.347, "dur": 62.846, + "args": { + "External id": 4675590,"Record function id": 0, "Ev Idx": 5 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037382776.019, "dur": 1.854, + "args": { + "External id": 4675591,"Sequence number": 46526661, "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": 1708037382776.019, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1708037382783.309, "dur": 82.638, + "args": { + "External id": 4675592,"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": 1708037382803.515, "dur": 61.797, + "args": { + "External id": 4675593,"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": 1708037382817.353, "dur": 4.355, + "args": { + "External id": 4675594,"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": 1708037382885.455, "dur": 36904.787, + "args": { + "External id": 4675595,"Record function id": 0, "Sequence number": 46526659, "Fwd thread id": 1, "Ev Idx": 10 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037382887.111, "dur": 36886.276, + "args": { + "External id": 4675596,"Sequence number": 46526659, "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": 1708037382887.111, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037382944.572, "dur": 5.349, + "args": { + "External id": 4675597,"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": 1708037382956.306, "dur": 36671.423, + "args": { + "External id": 4675598,"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": 1708037382959.146, "dur": 36668.037, + "args": { + "External id": 4675599,"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": 1708037382965.176, "dur": 7.939, + "args": { + "External id": 4675600,"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": 1708037382975.429, "dur": 36649.156, + "args": { + "External id": 4675601,"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": 1708037419635.036, "dur": 0.838, + "args": { + "External id": 4675602,"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": 1708037419639.345, "dur": 4.354, + "args": { + "External id": 4675603,"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": 1708037419641.824, "dur": 1.706, + "args": { + "External id": 4675604,"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": 1708037419653.117, "dur": 41.090, + "args": { + "External id": 4675605,"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": 1708037419704.418, "dur": 56.898, + "args": { + "External id": 4675606,"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": 1708037419706.587, "dur": 54.525, + "args": { + "External id": 4675607,"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": 1708037419709.304, "dur": 51.466, + "args": { + "External id": 4675608,"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": 1708037419807.864, "dur": 25.915, + "args": { + "External id": 4675609,"Record function id": 0, "Sequence number": 46526658, "Fwd thread id": 1, "Ev Idx": 24 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037419810.731, "dur": 18.876, + "args": { + "External id": 4675610,"Sequence number": 46526658, "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": 1708037419810.731, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037419816.157, "dur": 13.196, + "args": { + "External id": 4675611,"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": 1708037419821.343, "dur": 7.836, + "args": { + "External id": 4675612,"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": 1708037419838.038, "dur": 120.525, + "args": { + "External id": 4675613,"Record function id": 0, "Sequence number": 46526657, "Fwd thread id": 1, "Ev Idx": 28 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037419839.009, "dur": 108.305, + "args": { + "External id": 4675614,"Sequence number": 46526657, "Fwd thread 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": 1708037419839.009, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037419842.617, "dur": 104.141, + "args": { + "External id": 4675615,"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": 1708037419848.357, "dur": 39.678, + "args": { + "External id": 4675616,"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": 1708037419853.352, "dur": 6.071, + "args": { + "External id": 4675617,"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": 1708037419861.874, "dur": 25.849, + "args": { + "External id": 4675618,"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": 1708037419865.896, "dur": 21.357, + "args": { + "External id": 4675619,"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": 1708037419893.941, "dur": 4.819, + "args": { + "External id": 4675620,"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": 1708037419896.802, "dur": 1.641, + "args": { + "External id": 4675621,"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": 1708037419900.507, "dur": 45.480, + "args": { + "External id": 4675622,"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": 1708037419963.172, "dur": 106.109, + "args": { + "External id": 4675623,"Record function id": 0, "Sequence number": 46526656, "Fwd thread id": 1, "Ev Idx": 38 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037419964.285, "dur": 98.578, + "args": { + "External id": 4675624,"Sequence number": 46526656, "Fwd thread 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": 1708037419964.285, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037419968.216, "dur": 94.327, + "args": { + "External id": 4675625,"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": 1708037419973.183, "dur": 53.021, + "args": { + "External id": 4675626,"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": 1708037419974.349, "dur": 3.655, + "args": { + "External id": 4675627,"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": 1708037419978.807, "dur": 47.089, + "args": { + "External id": 4675628,"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": 1708037420007.701, "dur": 17.490, + "args": { + "External id": 4675629,"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": 1708037420031.676, "dur": 7.325, + "args": { + "External id": 4675630,"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": 1708037420036.222, "dur": 1.931, + "args": { + "External id": 4675631,"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": 1708037420040.042, "dur": 21.852, + "args": { + "External id": 4675632,"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": 1708037420075.076, "dur": 137.108, + "args": { + "External id": 4675633,"Record function id": 0, "Sequence number": 46526655, "Fwd thread id": 1, "Ev Idx": 48 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037420076.108, "dur": 131.701, + "args": { + "External id": 4675634,"Sequence number": 46526655, "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": 1708037420076.108, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037420080.652, "dur": 126.838, + "args": { + "External id": 4675635,"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": 1708037420084.803, "dur": 17.723, + "args": { + "External id": 4675636,"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": 1708037420085.770, "dur": 3.045, + "args": { + "External id": 4675637,"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": 1708037420089.666, "dur": 12.583, + "args": { + "External id": 4675638,"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": 1708037420090.723, "dur": 11.216, + "args": { + "External id": 4675639,"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": 1708037420105.986, "dur": 2.606, + "args": { + "External id": 4675640,"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": 1708037420107.418, "dur": 0.915, + "args": { + "External id": 4675641,"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": 1708037420109.261, "dur": 97.540, + "args": { + "External id": 4675642,"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": 1708037420219.057, "dur": 107.599, + "args": { + "External id": 4675643,"Record function id": 0, "Sequence number": 46526654, "Fwd thread id": 1, "Ev Idx": 58 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037420220.325, "dur": 103.194, + "args": { + "External id": 4675644,"Sequence number": 46526654, "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": 1708037420220.325, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037420222.272, "dur": 100.948, + "args": { + "External id": 4675645,"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": 1708037420225.879, "dur": 19.292, + "args": { + "External id": 4675646,"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": 1708037420226.914, "dur": 4.520, + "args": { + "External id": 4675647,"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": 1708037420232.261, "dur": 12.680, + "args": { + "External id": 4675648,"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": 1708037420233.059, "dur": 11.575, + "args": { + "External id": 4675649,"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": 1708037420246.419, "dur": 4.612, + "args": { + "External id": 4675650,"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": 1708037420250.294, "dur": 0.591, + "args": { + "External id": 4675651,"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": 1708037420254.485, "dur": 68.172, + "args": { + "External id": 4675652,"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": 1708037420330.953, "dur": 44.540, + "args": { + "External id": 4675653,"Record function id": 0, "Sequence number": 46526653, "Fwd thread id": 1, "Ev Idx": 68 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037420332.223, "dur": 1.315, + "args": { + "External id": 4675654,"Sequence number": 46526653, "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": 1708037420332.223, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1708037420336.972, "dur": 32.929, + "args": { + "External id": 4675655,"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": 1708037420339.293, "dur": 30.220, + "args": { + "External id": 4675656,"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": 1708037420349.307, "dur": 0.814, + "args": { + "External id": 4675657,"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": 1708037420380.853, "dur": 2211.516, + "args": { + "External id": 4675658,"Record function id": 0, "Sequence number": 46526651, "Fwd thread id": 1, "Ev Idx": 73 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037420382.509, "dur": 2167.205, + "args": { + "External id": 4675659,"Sequence number": 46526651, "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": 1708037420382.509, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037420428.234, "dur": 2.946, + "args": { + "External id": 4675660,"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": 1708037420433.741, "dur": 2011.701, + "args": { + "External id": 4675661,"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": 1708037420435.717, "dur": 2009.383, + "args": { + "External id": 4675662,"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": 1708037420438.568, "dur": 5.486, + "args": { + "External id": 4675663,"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": 1708037420445.200, "dur": 1998.453, + "args": { + "External id": 4675664,"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": 1708037422448.934, "dur": 0.487, + "args": { + "External id": 4675665,"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": 1708037422453.581, "dur": 2.552, + "args": { + "External id": 4675666,"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": 1708037422454.744, "dur": 1.121, + "args": { + "External id": 4675667,"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": 1708037422460.246, "dur": 22.342, + "args": { + "External id": 4675668,"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": 1708037422488.360, "dur": 52.428, + "args": { + "External id": 4675669,"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": 1708037422489.619, "dur": 50.972, + "args": { + "External id": 4675670,"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": 1708037422490.804, "dur": 49.186, + "args": { + "External id": 4675671,"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": 1708037422562.960, "dur": 25.132, + "args": { + "External id": 4675672,"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": 1708037422600.165, "dur": 17.430, + "args": { + "External id": 4675673,"Record function id": 0, "Sequence number": 46526650, "Fwd thread id": 1, "Ev Idx": 88 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037422602.172, "dur": 12.606, + "args": { + "External id": 4675674,"Sequence number": 46526650, "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": 1708037422602.172, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037422609.581, "dur": 4.961, + "args": { + "External id": 4675675,"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": 1708037422610.643, "dur": 3.744, + "args": { + "External id": 4675676,"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": 1708037422621.123, "dur": 74.377, + "args": { + "External id": 4675677,"Record function id": 0, "Sequence number": 46526649, "Fwd thread id": 1, "Ev Idx": 92 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037422622.010, "dur": 68.026, + "args": { + "External id": 4675678,"Sequence number": 46526649, "Fwd thread 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": 1708037422622.010, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037422624.065, "dur": 65.659, + "args": { + "External id": 4675679,"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": 1708037422628.634, "dur": 22.654, + "args": { + "External id": 4675680,"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": 1708037422630.167, "dur": 3.240, + "args": { + "External id": 4675681,"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": 1708037422634.241, "dur": 16.806, + "args": { + "External id": 4675682,"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": 1708037422635.568, "dur": 15.122, + "args": { + "External id": 4675683,"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": 1708037422653.060, "dur": 5.044, + "args": { + "External id": 4675684,"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": 1708037422654.715, "dur": 3.189, + "args": { + "External id": 4675685,"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": 1708037422658.977, "dur": 30.049, + "args": { + "External id": 4675686,"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": 1708037422702.601, "dur": 57.687, + "args": { + "External id": 4675687,"Record function id": 0, "Sequence number": 46526648, "Fwd thread id": 1, "Ev Idx": 102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037422703.773, "dur": 53.014, + "args": { + "External id": 4675688,"Sequence number": 46526648, "Fwd thread 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": 1708037422703.773, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037422708.308, "dur": 48.209, + "args": { + "External id": 4675689,"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": 1708037422710.485, "dur": 21.481, + "args": { + "External id": 4675690,"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": 1708037422711.272, "dur": 2.487, + "args": { + "External id": 4675691,"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": 1708037422714.395, "dur": 17.320, + "args": { + "External id": 4675692,"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": 1708037422715.251, "dur": 16.124, + "args": { + "External id": 4675693,"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": 1708037422733.075, "dur": 7.122, + "args": { + "External id": 4675694,"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": 1708037422738.857, "dur": 0.851, + "args": { + "External id": 4675695,"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": 1708037422741.057, "dur": 14.953, + "args": { + "External id": 4675696,"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": 1708037422764.006, "dur": 99.886, + "args": { + "External id": 4675697,"Record function id": 0, "Sequence number": 46526647, "Fwd thread id": 1, "Ev Idx": 112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037422767.846, "dur": 91.619, + "args": { + "External id": 4675698,"Sequence number": 46526647, "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": 1708037422767.846, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037422769.761, "dur": 89.416, + "args": { + "External id": 4675699,"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": 1708037422770.822, "dur": 21.833, + "args": { + "External id": 4675700,"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": 1708037422771.678, "dur": 2.343, + "args": { + "External id": 4675701,"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": 1708037422774.749, "dur": 17.643, + "args": { + "External id": 4675702,"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": 1708037422775.572, "dur": 16.452, + "args": { + "External id": 4675703,"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": 1708037422793.610, "dur": 4.673, + "args": { + "External id": 4675704,"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": 1708037422797.428, "dur": 0.669, + "args": { + "External id": 4675705,"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": 1708037422798.848, "dur": 59.684, + "args": { + "External id": 4675706,"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": 1708037422867.762, "dur": 99.088, + "args": { + "External id": 4675707,"Record function id": 0, "Sequence number": 46526646, "Fwd thread id": 1, "Ev Idx": 122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037422872.457, "dur": 75.267, + "args": { + "External id": 4675708,"Sequence number": 46526646, "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": 1708037422872.457, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037422876.335, "dur": 71.074, + "args": { + "External id": 4675709,"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": 1708037422877.329, "dur": 17.102, + "args": { + "External id": 4675710,"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": 1708037422878.230, "dur": 1.714, + "args": { + "External id": 4675711,"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": 1708037422880.567, "dur": 13.636, + "args": { + "External id": 4675712,"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": 1708037422881.645, "dur": 12.220, + "args": { + "External id": 4675713,"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": 1708037422895.225, "dur": 1.894, + "args": { + "External id": 4675714,"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": 1708037422896.306, "dur": 0.676, + "args": { + "External id": 4675715,"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": 1708037422897.974, "dur": 48.861, + "args": { + "External id": 4675716,"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": 1708037422951.674, "dur": 14.038, + "args": { + "External id": 4675717,"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": 1708037422970.943, "dur": 74.065, + "args": { + "External id": 4675718,"Record function id": 0, "Sequence number": 46526645, "Fwd thread id": 1, "Ev Idx": 133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037422975.162, "dur": 0.890, + "args": { + "External id": 4675719,"Sequence number": 46526645, "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": 1708037422975.162, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1708037422979.107, "dur": 61.461, + "args": { + "External id": 4675720,"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": 1708037422980.695, "dur": 59.467, + "args": { + "External id": 4675721,"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": 1708037423017.065, "dur": 2.903, + "args": { + "External id": 4675722,"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": 1708037423051.541, "dur": 3070.975, + "args": { + "External id": 4675723,"Record function id": 0, "Sequence number": 46526643, "Fwd thread id": 1, "Ev Idx": 138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037423055.508, "dur": 3039.859, + "args": { + "External id": 4675724,"Sequence number": 46526643, "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": 1708037423055.508, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037423086.281, "dur": 2.107, + "args": { + "External id": 4675725,"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": 1708037423090.494, "dur": 2916.092, + "args": { + "External id": 4675726,"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": 1708037423091.945, "dur": 2914.300, + "args": { + "External id": 4675727,"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": 1708037423094.192, "dur": 4.936, + "args": { + "External id": 4675728,"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": 1708037423099.954, "dur": 2905.318, + "args": { + "External id": 4675729,"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": 1708037426009.742, "dur": 0.265, + "args": { + "External id": 4675730,"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": 1708037426011.134, "dur": 2.076, + "args": { + "External id": 4675731,"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": 1708037426012.130, "dur": 0.952, + "args": { + "External id": 4675732,"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": 1708037426016.584, "dur": 22.252, + "args": { + "External id": 4675733,"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": 1708037426049.253, "dur": 39.216, + "args": { + "External id": 4675734,"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": 1708037426050.298, "dur": 37.984, + "args": { + "External id": 4675735,"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": 1708037426051.364, "dur": 36.512, + "args": { + "External id": 4675736,"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": 1708037426104.393, "dur": 14.636, + "args": { + "External id": 4675737,"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": 1708037426132.541, "dur": 10.536, + "args": { + "External id": 4675738,"Record function id": 0, "Sequence number": 46526642, "Fwd thread id": 1, "Ev Idx": 153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037426134.100, "dur": 6.480, + "args": { + "External id": 4675739,"Sequence number": 46526642, "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": 1708037426134.100, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037426136.722, "dur": 3.665, + "args": { + "External id": 4675740,"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": 1708037426137.498, "dur": 2.744, + "args": { + "External id": 4675741,"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": 1708037426146.404, "dur": 67.464, + "args": { + "External id": 4675742,"Record function id": 0, "Sequence number": 46526641, "Fwd thread id": 1, "Ev Idx": 157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037426147.493, "dur": 61.436, + "args": { + "External id": 4675743,"Sequence number": 46526641, "Fwd thread 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": 1708037426147.493, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037426151.709, "dur": 56.823, + "args": { + "External id": 4675744,"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": 1708037426155.915, "dur": 20.132, + "args": { + "External id": 4675745,"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": 1708037426157.084, "dur": 2.230, + "args": { + "External id": 4675746,"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": 1708037426160.023, "dur": 15.773, + "args": { + "External id": 4675747,"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": 1708037426161.785, "dur": 13.468, + "args": { + "External id": 4675748,"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": 1708037426177.396, "dur": 5.650, + "args": { + "External id": 4675749,"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": 1708037426181.860, "dur": 0.877, + "args": { + "External id": 4675750,"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": 1708037426183.866, "dur": 23.980, + "args": { + "External id": 4675751,"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": 1708037426217.784, "dur": 55.628, + "args": { + "External id": 4675752,"Record function id": 0, "Sequence number": 46526640, "Fwd thread id": 1, "Ev Idx": 167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037426218.950, "dur": 51.170, + "args": { + "External id": 4675753,"Sequence number": 46526640, "Fwd thread 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": 1708037426218.950, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037426221.284, "dur": 48.618, + "args": { + "External id": 4675754,"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": 1708037426222.868, "dur": 20.541, + "args": { + "External id": 4675755,"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": 1708037426225.868, "dur": 2.156, + "args": { + "External id": 4675756,"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": 1708037426228.551, "dur": 14.637, + "args": { + "External id": 4675757,"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": 1708037426229.700, "dur": 13.183, + "args": { + "External id": 4675758,"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": 1708037426244.720, "dur": 8.683, + "args": { + "External id": 4675759,"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": 1708037426249.912, "dur": 3.079, + "args": { + "External id": 4675760,"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": 1708037426254.367, "dur": 15.072, + "args": { + "External id": 4675761,"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": 1708037426277.001, "dur": 100.793, + "args": { + "External id": 4675762,"Record function id": 0, "Sequence number": 46526639, "Fwd thread id": 1, "Ev Idx": 177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037426278.169, "dur": 95.270, + "args": { + "External id": 4675763,"Sequence number": 46526639, "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": 1708037426278.169, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037426280.128, "dur": 93.012, + "args": { + "External id": 4675764,"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": 1708037426280.983, "dur": 22.004, + "args": { + "External id": 4675765,"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": 1708037426281.605, "dur": 1.707, + "args": { + "External id": 4675766,"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": 1708037426286.883, "dur": 15.831, + "args": { + "External id": 4675767,"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": 1708037426287.685, "dur": 14.643, + "args": { + "External id": 4675768,"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": 1708037426304.190, "dur": 4.385, + "args": { + "External id": 4675769,"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": 1708037426307.776, "dur": 0.618, + "args": { + "External id": 4675770,"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": 1708037426309.657, "dur": 62.803, + "args": { + "External id": 4675771,"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": 1708037426381.725, "dur": 100.281, + "args": { + "External id": 4675772,"Record function id": 0, "Sequence number": 46526638, "Fwd thread id": 1, "Ev Idx": 187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037426382.816, "dur": 82.221, + "args": { + "External id": 4675773,"Sequence number": 46526638, "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": 1708037426382.816, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037426387.479, "dur": 77.266, + "args": { + "External id": 4675774,"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": 1708037426388.559, "dur": 18.390, + "args": { + "External id": 4675775,"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": 1708037426389.313, "dur": 1.736, + "args": { + "External id": 4675776,"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": 1708037426391.729, "dur": 14.992, + "args": { + "External id": 4675777,"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": 1708037426394.818, "dur": 11.604, + "args": { + "External id": 4675778,"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": 1708037426407.878, "dur": 4.420, + "args": { + "External id": 4675779,"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": 1708037426411.347, "dur": 0.799, + "args": { + "External id": 4675780,"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": 1708037426413.141, "dur": 50.968, + "args": { + "External id": 4675781,"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": 1708037426468.280, "dur": 12.690, + "args": { + "External id": 4675782,"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": 1708037426485.986, "dur": 31.822, + "args": { + "External id": 4675783,"Record function id": 0, "Sequence number": 46526637, "Fwd thread id": 1, "Ev Idx": 198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037426487.027, "dur": 1.199, + "args": { + "External id": 4675784,"Sequence number": 46526637, "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": 1708037426487.027, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336753, "tid": 1381210, + "ts": 1708037426489.906, "dur": 21.914, + "args": { + "External id": 4675785,"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": 1708037426491.846, "dur": 19.644, + "args": { + "External id": 4675786,"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": 1708037426495.741, "dur": 0.382, + "args": { + "External id": 4675787,"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": 1708037426522.261, "dur": 3124.236, + "args": { + "External id": 4675788,"Record function id": 0, "Sequence number": 46526636, "Fwd thread id": 1, "Ev Idx": 203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037426548.814, "dur": 3064.899, + "args": { + "External id": 4675789,"Sequence number": 46526636, "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": 1708037426548.814, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037426576.079, "dur": 4.489, + "args": { + "External id": 4675790,"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": 1708037426582.788, "dur": 2936.111, + "args": { + "External id": 4675791,"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": 1708037426583.882, "dur": 2934.775, + "args": { + "External id": 4675792,"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": 1708037426587.994, "dur": 3.399, + "args": { + "External id": 4675793,"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": 1708037426592.269, "dur": 2925.240, + "args": { + "External id": 4675794,"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": 1708037429521.516, "dur": 0.311, + "args": { + "External id": 4675795,"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": 1708037429522.883, "dur": 12.494, + "args": { + "External id": 4675796,"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": 1708037429534.177, "dur": 0.912, + "args": { + "External id": 4675797,"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": 1708037429538.831, "dur": 22.748, + "args": { + "External id": 4675798,"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": 1708037429566.123, "dur": 42.170, + "args": { + "External id": 4675799,"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": 1708037429567.082, "dur": 41.022, + "args": { + "External id": 4675800,"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": 1708037429568.143, "dur": 39.602, + "args": { + "External id": 4675801,"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": 1708037429625.604, "dur": 15.343, + "args": { + "External id": 4675802,"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": 1708037429657.787, "dur": 14.272, + "args": { + "External id": 4675803,"Record function id": 0, "Ev Idx": 218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037429660.741, "dur": 9.581, + "args": { + "External id": 4675804,"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": 1708037429664.182, "dur": 4.862, + "args": { + "External id": 4675805,"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": 1708037429665.266, "dur": 3.656, + "args": { + "External id": 4675806,"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": 1708037429675.612, "dur": 12.494, + "args": { + "External id": 4675807,"Record function id": 0, "Sequence number": 46526635, "Fwd thread id": 1, "Ev Idx": 222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037429677.031, "dur": 8.461, + "args": { + "External id": 4675808,"Sequence number": 46526635, "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": 1708037429677.031, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037429679.399, "dur": 5.904, + "args": { + "External id": 4675809,"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": 1708037429682.535, "dur": 2.637, + "args": { + "External id": 4675810,"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": 1708037429691.376, "dur": 73.082, + "args": { + "External id": 4675811,"Record function id": 0, "Sequence number": 46526634, "Fwd thread id": 1, "Ev Idx": 226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037429692.492, "dur": 66.628, + "args": { + "External id": 4675812,"Sequence number": 46526634, "Fwd thread 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": 1708037429692.492, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037429694.207, "dur": 64.566, + "args": { + "External id": 4675813,"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": 1708037429699.273, "dur": 22.174, + "args": { + "External id": 4675814,"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": 1708037429700.732, "dur": 2.683, + "args": { + "External id": 4675815,"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": 1708037429704.369, "dur": 16.766, + "args": { + "External id": 4675816,"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": 1708037429705.831, "dur": 14.719, + "args": { + "External id": 4675817,"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": 1708037429722.781, "dur": 5.075, + "args": { + "External id": 4675818,"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": 1708037429726.609, "dur": 1.033, + "args": { + "External id": 4675819,"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": 1708037429728.592, "dur": 29.428, + "args": { + "External id": 4675820,"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": 1708037429771.057, "dur": 57.008, + "args": { + "External id": 4675821,"Record function id": 0, "Sequence number": 46526633, "Fwd thread id": 1, "Ev Idx": 236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037429772.124, "dur": 51.833, + "args": { + "External id": 4675822,"Sequence number": 46526633, "Fwd thread 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": 1708037429772.124, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037429774.646, "dur": 49.046, + "args": { + "External id": 4675823,"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": 1708037429776.039, "dur": 26.536, + "args": { + "External id": 4675824,"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": 1708037429785.041, "dur": 2.487, + "args": { + "External id": 4675825,"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": 1708037429788.288, "dur": 14.042, + "args": { + "External id": 4675826,"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": 1708037429789.296, "dur": 12.725, + "args": { + "External id": 4675827,"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": 1708037429803.603, "dur": 4.373, + "args": { + "External id": 4675828,"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": 1708037429806.589, "dur": 0.964, + "args": { + "External id": 4675829,"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": 1708037429808.632, "dur": 14.566, + "args": { + "External id": 4675830,"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": 1708037429831.663, "dur": 95.061, + "args": { + "External id": 4675831,"Record function id": 0, "Sequence number": 46526632, "Fwd thread id": 1, "Ev Idx": 246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037429833.031, "dur": 90.894, + "args": { + "External id": 4675832,"Sequence number": 46526632, "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": 1708037429833.031, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037429834.882, "dur": 88.631, + "args": { + "External id": 4675833,"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": 1708037429838.850, "dur": 18.868, + "args": { + "External id": 4675834,"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": 1708037429839.745, "dur": 2.365, + "args": { + "External id": 4675835,"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": 1708037429844.498, "dur": 12.990, + "args": { + "External id": 4675836,"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": 1708037429845.568, "dur": 11.619, + "args": { + "External id": 4675837,"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": 1708037429858.705, "dur": 5.160, + "args": { + "External id": 4675838,"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": 1708037429860.163, "dur": 3.550, + "args": { + "External id": 4675839,"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": 1708037429864.521, "dur": 58.324, + "args": { + "External id": 4675840,"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": 1708037429930.816, "dur": 145.511, + "args": { + "External id": 4675841,"Record function id": 0, "Sequence number": 46526631, "Fwd thread id": 1, "Ev Idx": 256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037429931.750, "dur": 122.453, + "args": { + "External id": 4675842,"Sequence number": 46526631, "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": 1708037429931.750, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336753, "tid": 1381210, + "ts": 1708037429933.762, "dur": 120.081, + "args": { + "External id": 4675843,"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": 1708037429935.190, "dur": 40.820, + "args": { + "External id": 4675844,"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": 1708037429940.391, "dur": 1.821, + "args": { + "External id": 4675845,"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": 1708037429956.072, "dur": 19.688, + "args": { + "External id": 4675846,"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": 1708037429961.635, "dur": 13.620, + "args": { + "External id": 4675847,"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": 1708037429977.030, "dur": 2.218, + "args": { + "External id": 4675848,"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": 1708037429978.384, "dur": 0.696, + "args": { + "External id": 4675849,"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": 1708037429980.008, "dur": 72.751, + "args": { + "External id": 4675850,"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": 1708037430059.311, "dur": 15.004, + "args": { + "External id": 4675851,"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": 1708037430084.393, "dur": 420.354, + "args": { + "External id": 4675852,"Record function id": 0, "Sequence number": 46526630, "Fwd thread id": 1, "Ev Idx": 267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037430085.912, "dur": 408.072, + "args": { + "External id": 4675853,"Sequence number": 46526630, "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": 1708037430085.912, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336753, "tid": 1381210, + "ts": 1708037430305.433, "dur": 47.577, + "args": { + "External id": 4675854,"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": 1708037430395.041, "dur": 32.848, + "args": { + "External id": 4675855,"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": 1708037430446.567, "dur": 20.662, + "args": { + "External id": 4675856,"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": 1708037430513.808, "dur": 29.561, + "args": { + "External id": 4675857,"Record function id": 0, "Ev Idx": 272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037430516.087, "dur": 25.862, + "args": { + "External id": 4675858,"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": 1708037430518.983, "dur": 21.703, + "args": { + "External id": 4675859,"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": 1708037430522.497, "dur": 17.734, + "args": { + "External id": 4675860,"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": 1708037430551.758, "dur": 41.748, + "args": { + "External id": 4675861,"Record function id": 0, "Sequence number": 46526629, "Fwd thread id": 1, "Ev Idx": 276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037430553.182, "dur": 28.689, + "args": { + "External id": 4675862,"Sequence number": 46526629, "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": 1708037430553.182, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336753, "tid": 1381210, + "ts": 1708037430555.492, "dur": 8.273, + "args": { + "External id": 4675863,"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": 1708037430560.752, "dur": 1.282, + "args": { + "External id": 4675864,"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": 1708037430564.432, "dur": 6.981, + "args": { + "External id": 4675865,"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": 1708037430569.931, "dur": 0.604, + "args": { + "External id": 4675866,"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": 1708037430572.146, "dur": 2.725, + "args": { + "External id": 4675867,"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": 1708037430573.566, "dur": 0.560, + "args": { + "External id": 4675868,"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": 1708037430575.404, "dur": 5.846, + "args": { + "External id": 4675869,"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": 1708037430579.484, "dur": 0.459, + "args": { + "External id": 4675870,"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": 1708037430597.305, "dur": 8.968, + "args": { + "External id": 4675871,"Record function id": 0, "Sequence number": 46526628, "Fwd thread id": 1, "Ev Idx": 286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037430598.287, "dur": 1.284, + "args": { + "External id": 4675872,"Sequence number": 46526628, "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": 1708037430598.287, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037430610.642, "dur": 636.154, + "args": { + "External id": 4675873,"Record function id": 0, "Sequence number": 46526627, "Fwd thread id": 1, "Ev Idx": 288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037430612.112, "dur": 618.417, + "args": { + "External id": 4675874,"Sequence number": 46526627, "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": 1708037430612.112, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037430668.391, "dur": 12.368, + "args": { + "External id": 4675875,"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": 1708037430676.434, "dur": 4.032, + "args": { + "External id": 4675876,"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": 1708037430687.318, "dur": 7.810, + "args": { + "External id": 4675877,"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": 1708037430691.210, "dur": 2.713, + "args": { + "External id": 4675878,"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": 1708037430692.713, "dur": 0.992, + "args": { + "External id": 4675879,"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": 1708037430703.400, "dur": 145.076, + "args": { + "External id": 4675880,"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": 1708037430704.945, "dur": 6.813, + "args": { + "External id": 4675881,"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": 1708037430705.625, "dur": 5.190, + "args": { + "External id": 4675882,"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": 1708037430708.335, "dur": 2.353, + "args": { + "External id": 4675883,"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": 1708037430714.010, "dur": 133.668, + "args": { + "External id": 4675884,"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": 1708037430716.954, "dur": 129.911, + "args": { + "External id": 4675885,"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": 1708037430855.516, "dur": 7.386, + "args": { + "External id": 4675886,"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": 1708037430860.025, "dur": 2.741, + "args": { + "External id": 4675887,"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": 1708037430905.824, "dur": 3.935, + "args": { + "External id": 4675888,"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": 1708037430910.832, "dur": 3.530, + "args": { + "External id": 4675889,"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": 1708037430917.585, "dur": 1.630, + "args": { + "External id": 4675890,"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": 1708037430965.087, "dur": 2.425, + "args": { + "External id": 4675891,"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": 1708037430965.992, "dur": 1.355, + "args": { + "External id": 4675892,"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": 1708037431038.606, "dur": 166.669, + "args": { + "External id": 4675893,"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": 1708037431046.738, "dur": 10.453, + "args": { + "External id": 4675894,"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": 1708037431052.932, "dur": 1.261, + "args": { + "External id": 4675895,"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": 1708037431059.341, "dur": 9.038, + "args": { + "External id": 4675896,"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": 1708037431064.613, "dur": 2.719, + "args": { + "External id": 4675897,"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": 1708037431070.461, "dur": 4.208, + "args": { + "External id": 4675898,"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": 1708037431073.852, "dur": 0.487, + "args": { + "External id": 4675899,"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": 1708037431075.317, "dur": 5.054, + "args": { + "External id": 4675900,"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": 1708037431079.213, "dur": 0.615, + "args": { + "External id": 4675901,"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": 1708037431085.174, "dur": 4.635, + "args": { + "External id": 4675902,"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": 1708037431088.897, "dur": 0.594, + "args": { + "External id": 4675903,"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": 1708037431093.156, "dur": 8.393, + "args": { + "External id": 4675904,"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": 1708037431099.328, "dur": 2.026, + "args": { + "External id": 4675905,"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": 1708037431102.554, "dur": 3.816, + "args": { + "External id": 4675906,"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": 1708037431105.598, "dur": 0.488, + "args": { + "External id": 4675907,"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": 1708037431107.028, "dur": 2.662, + "args": { + "External id": 4675908,"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": 1708037431107.888, "dur": 1.694, + "args": { + "External id": 4675909,"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": 1708037431112.062, "dur": 77.603, + "args": { + "External id": 4675910,"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": 1708037431191.385, "dur": 3.404, + "args": { + "External id": 4675911,"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": 1708037431197.998, "dur": 2.586, + "args": { + "External id": 4675912,"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": 1708037431199.173, "dur": 0.614, + "args": { + "External id": 4675913,"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": 1708037431202.964, "dur": 0.916, + "args": { + "External id": 4675914,"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": 1708037431260.033, "dur": 10.034, + "args": { + "External id": 4675915,"Record function id": 0, "Ev Idx": 330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037431262.414, "dur": 6.940, + "args": { + "External id": 4675916,"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": 1708037431264.693, "dur": 3.605, + "args": { + "External id": 4675917,"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": 1708037431265.867, "dur": 2.279, + "args": { + "External id": 4675918,"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": 1708037431274.007, "dur": 9.514, + "args": { + "External id": 4675919,"Record function id": 0, "Sequence number": 46526626, "Fwd thread id": 1, "Ev Idx": 334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037431275.000, "dur": 5.260, + "args": { + "External id": 4675920,"Sequence number": 46526626, "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": 1708037431275.000, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037431278.279, "dur": 1.785, + "args": { + "External id": 4675921,"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": 1708037431279.050, "dur": 0.895, + "args": { + "External id": 4675922,"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": 1708037431287.482, "dur": 172.905, + "args": { + "External id": 4675923,"Record function id": 0, "Sequence number": 46526625, "Fwd thread id": 1, "Ev Idx": 338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037431288.402, "dur": 161.631, + "args": { + "External id": 4675924,"Sequence number": 46526625, "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": 1708037431288.402, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037431296.728, "dur": 3.996, + "args": { + "External id": 4675925,"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": 1708037431298.214, "dur": 1.918, + "args": { + "External id": 4675926,"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": 1708037431299.419, "dur": 0.552, + "args": { + "External id": 4675927,"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": 1708037431302.206, "dur": 58.456, + "args": { + "External id": 4675928,"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": 1708037431361.903, "dur": 5.933, + "args": { + "External id": 4675929,"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": 1708037431362.635, "dur": 4.593, + "args": { + "External id": 4675930,"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": 1708037431366.165, "dur": 0.904, + "args": { + "External id": 4675931,"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": 1708037431369.968, "dur": 5.005, + "args": { + "External id": 4675932,"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": 1708037431371.001, "dur": 3.391, + "args": { + "External id": 4675933,"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": 1708037431373.681, "dur": 0.642, + "args": { + "External id": 4675934,"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": 1708037431375.553, "dur": 73.704, + "args": { + "External id": 4675935,"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": 1708037431465.077, "dur": 7.013, + "args": { + "External id": 4675936,"Record function id": 0, "Sequence number": 46526624, "Fwd thread id": 1, "Ev Idx": 351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037431466.023, "dur": 3.967, + "args": { + "External id": 4675937,"Sequence number": 46526624, "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": 1708037431466.023, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037431467.923, "dur": 1.906, + "args": { + "External id": 4675938,"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": 1708037431468.643, "dur": 1.052, + "args": { + "External id": 4675939,"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": 1708037431475.556, "dur": 13.096, + "args": { + "External id": 4675940,"Record function id": 0, "Sequence number": 46526623, "Fwd thread id": 1, "Ev Idx": 355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037431478.982, "dur": 7.097, + "args": { + "External id": 4675941,"Sequence number": 46526623, "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": 1708037431478.982, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037431480.594, "dur": 5.270, + "args": { + "External id": 4675942,"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": 1708037431481.364, "dur": 3.931, + "args": { + "External id": 4675943,"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": 1708037431484.756, "dur": 0.455, + "args": { + "External id": 4675944,"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": 1708037431492.539, "dur": 5.392, + "args": { + "External id": 4675945,"Record function id": 0, "Ev Idx": 360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037431493.678, "dur": 3.696, + "args": { + "External id": 4675946,"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": 1708037431495.005, "dur": 1.820, + "args": { + "External id": 4675947,"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": 1708037431495.392, "dur": 1.339, + "args": { + "External id": 4675948,"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": 1708037431501.033, "dur": 9.627, + "args": { + "External id": 4675949,"Record function id": 0, "Sequence number": 46526622, "Fwd thread id": 1, "Ev Idx": 364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037431502.584, "dur": 5.165, + "args": { + "External id": 4675950,"Sequence number": 46526622, "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": 1708037431502.584, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037431503.942, "dur": 3.626, + "args": { + "External id": 4675951,"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": 1708037431506.636, "dur": 0.746, + "args": { + "External id": 4675952,"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": 1708037431513.652, "dur": 147.417, + "args": { + "External id": 4675953,"Record function id": 0, "Sequence number": 46526621, "Fwd thread id": 1, "Ev Idx": 368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037431514.621, "dur": 134.454, + "args": { + "External id": 4675954,"Sequence number": 46526621, "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": 1708037431514.621, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037431517.555, "dur": 2.716, + "args": { + "External id": 4675955,"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": 1708037431518.210, "dur": 1.672, + "args": { + "External id": 4675956,"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": 1708037431519.221, "dur": 0.572, + "args": { + "External id": 4675957,"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": 1708037431537.089, "dur": 43.380, + "args": { + "External id": 4675958,"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": 1708037431582.284, "dur": 6.442, + "args": { + "External id": 4675959,"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": 1708037431582.920, "dur": 5.135, + "args": { + "External id": 4675960,"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": 1708037431587.054, "dur": 0.861, + "args": { + "External id": 4675961,"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": 1708037431590.265, "dur": 8.350, + "args": { + "External id": 4675962,"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": 1708037431591.956, "dur": 6.210, + "args": { + "External id": 4675963,"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": 1708037431595.403, "dur": 2.640, + "args": { + "External id": 4675964,"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": 1708037431599.170, "dur": 49.201, + "args": { + "External id": 4675965,"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": 1708037431669.361, "dur": 37.312, + "args": { + "External id": 4675966,"Record function id": 0, "Sequence number": 46526620, "Fwd thread id": 1, "Ev Idx": 381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037431670.539, "dur": 6.195, + "args": { + "External id": 4675967,"Sequence number": 46526620, "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": 1708037431670.539, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037431672.125, "dur": 4.454, + "args": { + "External id": 4675968,"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": 1708037431674.992, "dur": 1.442, + "args": { + "External id": 4675969,"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": 1708037431680.418, "dur": 23.379, + "args": { + "External id": 4675970,"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": 1708037431710.514, "dur": 11.864, + "args": { + "External id": 4675971,"Record function id": 0, "Sequence number": 46526619, "Fwd thread id": 1, "Ev Idx": 386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037431711.892, "dur": 7.212, + "args": { + "External id": 4675972,"Sequence number": 46526619, "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": 1708037431711.892, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037431713.017, "dur": 5.873, + "args": { + "External id": 4675973,"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": 1708037431716.616, "dur": 1.742, + "args": { + "External id": 4675974,"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": 1708037431717.761, "dur": 0.449, + "args": { + "External id": 4675975,"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": 1708037431726.621, "dur": 5.789, + "args": { + "External id": 4675976,"Record function id": 0, "Ev Idx": 391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037431728.145, "dur": 3.758, + "args": { + "External id": 4675977,"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": 1708037431729.198, "dur": 1.966, + "args": { + "External id": 4675978,"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": 1708037431729.790, "dur": 1.261, + "args": { + "External id": 4675979,"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": 1708037431736.797, "dur": 563.628, + "args": { + "External id": 4675980,"Record function id": 0, "Sequence number": 46526618, "Fwd thread id": 1, "Ev Idx": 395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037431738.044, "dur": 541.928, + "args": { + "External id": 4675981,"Sequence number": 46526618, "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": 1708037431738.044, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1381210, + "ts": 1708037431767.675, "dur": 37.163, + "args": { + "External id": 4675982,"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": 1708037431769.945, "dur": 34.691, + "args": { + "External id": 4675983,"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": 1708037431773.294, "dur": 5.684, + "args": { + "External id": 4675984,"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": 1708037431775.613, "dur": 2.780, + "args": { + "External id": 4675985,"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": 1708037431780.223, "dur": 23.980, + "args": { + "External id": 4675986,"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": 1708037431818.331, "dur": 4.306, + "args": { + "External id": 4675987,"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": 1708037431820.961, "dur": 1.544, + "args": { + "External id": 4675988,"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": 1708037431826.583, "dur": 4.005, + "args": { + "External id": 4675989,"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": 1708037431827.481, "dur": 3.009, + "args": { + "External id": 4675990,"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": 1708037431848.443, "dur": 2.055, + "args": { + "External id": 4675991,"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": 1708037431866.636, "dur": 3.408, + "args": { + "External id": 4675992,"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": 1708037432150.186, "dur": 3.659, + "args": { + "External id": 4675993,"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": 1708037432159.473, "dur": 41.902, + "args": { + "External id": 4675994,"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": 1708037432172.865, "dur": 1.330, + "args": { + "External id": 4675995,"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": 1708037432207.990, "dur": 32.879, + "args": { + "External id": 4675996,"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": 1708037432210.131, "dur": 30.535, + "args": { + "External id": 4675997,"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": 1708037432214.176, "dur": 4.336, + "args": { + "External id": 4675998,"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": 1708037432220.050, "dur": 20.185, + "args": { + "External id": 4675999,"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": 1708037432247.478, "dur": 2.543, + "args": { + "External id": 4676000,"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": 1708037432248.673, "dur": 1.244, + "args": { + "External id": 4676001,"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": 1708037432257.841, "dur": 4.878, + "args": { + "External id": 4676002,"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": 1708037432261.336, "dur": 1.219, + "args": { + "External id": 4676003,"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": 1708037432265.213, "dur": 4.219, + "args": { + "External id": 4676004,"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": 1708037432266.027, "dur": 3.319, + "args": { + "External id": 4676005,"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": 1708037432314.986, "dur": 10.776, + "args": { + "External id": 4676006,"Record function id": 0, "Ev Idx": 421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037432317.665, "dur": 7.379, + "args": { + "External id": 4676007,"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": 1708037432320.168, "dur": 3.756, + "args": { + "External id": 4676008,"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": 1708037432321.444, "dur": 2.347, + "args": { + "External id": 4676009,"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": 1708037432329.330, "dur": 10.064, + "args": { + "External id": 4676010,"Record function id": 0, "Sequence number": 46526617, "Fwd thread id": 1, "Ev Idx": 425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037432330.317, "dur": 6.420, + "args": { + "External id": 4676011,"Sequence number": 46526617, "Fwd thread 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": 1708037432330.317, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037432334.272, "dur": 2.297, + "args": { + "External id": 4676012,"Record 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": 1708037432335.197, "dur": 1.264, + "args": { + "External id": 4676013,"Record 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": 1708037432345.593, "dur": 145.466, + "args": { + "External id": 4676014,"Record function id": 0, "Sequence number": 46526616, "Fwd thread id": 1, "Ev Idx": 429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037432346.568, "dur": 138.020, + "args": { + "External id": 4676015,"Sequence number": 46526616, "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": 1708037432346.568, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037432351.105, "dur": 4.390, + "args": { + "External id": 4676016,"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": 1708037432352.276, "dur": 2.556, + "args": { + "External id": 4676017,"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": 1708037432353.749, "dur": 0.841, + "args": { + "External id": 4676018,"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": 1708037432356.836, "dur": 63.917, + "args": { + "External id": 4676019,"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": 1708037432422.260, "dur": 7.852, + "args": { + "External id": 4676020,"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": 1708037432425.338, "dur": 3.982, + "args": { + "External id": 4676021,"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": 1708037432426.646, "dur": 2.490, + "args": { + "External id": 4676022,"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": 1708037432431.836, "dur": 5.557, + "args": { + "External id": 4676023,"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": 1708037432432.827, "dur": 3.982, + "args": { + "External id": 4676024,"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": 1708037432436.386, "dur": 0.325, + "args": { + "External id": 4676025,"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": 1708037432438.163, "dur": 45.390, + "args": { + "External id": 4676026,"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": 1708037432495.695, "dur": 13.253, + "args": { + "External id": 4676027,"Record function id": 0, "Sequence number": 46526615, "Fwd thread id": 1, "Ev Idx": 442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037432496.768, "dur": 9.005, + "args": { + "External id": 4676028,"Sequence number": 46526615, "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": 1708037432496.768, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037432500.462, "dur": 5.156, + "args": { + "External id": 4676029,"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": 1708037432501.467, "dur": 4.013, + "args": { + "External id": 4676030,"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": 1708037432512.514, "dur": 10.222, + "args": { + "External id": 4676031,"Record function id": 0, "Sequence number": 46526614, "Fwd thread id": 1, "Ev Idx": 446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037432513.581, "dur": 6.586, + "args": { + "External id": 4676032,"Sequence number": 46526614, "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": 1708037432513.581, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037432514.620, "dur": 5.332, + "args": { + "External id": 4676033,"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": 1708037432515.405, "dur": 4.018, + "args": { + "External id": 4676034,"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": 1708037432518.731, "dur": 0.580, + "args": { + "External id": 4676035,"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": 1708037432546.972, "dur": 10.785, + "args": { + "External id": 4676036,"Record function id": 0, "Ev Idx": 451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037432548.965, "dur": 7.986, + "args": { + "External id": 4676037,"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": 1708037432550.915, "dur": 5.516, + "args": { + "External id": 4676038,"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": 1708037432554.436, "dur": 1.763, + "args": { + "External id": 4676039,"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": 1708037432561.211, "dur": 8.808, + "args": { + "External id": 4676040,"Record function id": 0, "Sequence number": 46526613, "Fwd thread id": 1, "Ev Idx": 455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037432562.288, "dur": 5.331, + "args": { + "External id": 4676041,"Sequence number": 46526613, "Fwd thread 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": 1708037432562.288, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037432564.646, "dur": 2.822, + "args": { + "External id": 4676042,"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": 1708037432565.869, "dur": 1.469, + "args": { + "External id": 4676043,"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": 1708037432575.064, "dur": 379.373, + "args": { + "External id": 4676044,"Record function id": 0, "Sequence number": 46526612, "Fwd thread id": 1, "Ev Idx": 459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037432576.474, "dur": 351.747, + "args": { + "External id": 4676045,"Sequence number": 46526612, "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": 1708037432576.474, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1708037432598.196, "dur": 11.782, + "args": { + "External id": 4676046,"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": 1708037432605.308, "dur": 4.205, + "args": { + "External id": 4676047,"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": 1708037432612.502, "dur": 3.181, + "args": { + "External id": 4676048,"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": 1708037432613.794, "dur": 1.695, + "args": { + "External id": 4676049,"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": 1708037432617.322, "dur": 7.669, + "args": { + "External id": 4676050,"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": 1708037432620.982, "dur": 3.819, + "args": { + "External id": 4676051,"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": 1708037432672.023, "dur": 227.413, + "args": { + "External id": 4676052,"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": 1708037432782.337, "dur": 3.760, + "args": { + "External id": 4676053,"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": 1708037432787.971, "dur": 4.531, + "args": { + "External id": 4676054,"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": 1708037432914.061, "dur": 4.177, + "args": { + "External id": 4676055,"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": 1708037432921.305, "dur": 0.997, + "args": { + "External id": 4676056,"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": 1708037432924.485, "dur": 0.811, + "args": { + "External id": 4676057,"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": 1708037432962.166, "dur": 317.122, + "args": { + "External id": 4676058,"Record function id": 0, "Sequence number": 46526611, "Fwd thread id": 1, "Ev Idx": 473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037432963.688, "dur": 305.351, + "args": { + "External id": 4676059,"Sequence number": 46526611, "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": 1708037432963.688, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1708037433035.227, "dur": 58.043, + "args": { + "External id": 4676060,"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": 1708037433042.583, "dur": 4.796, + "args": { + "External id": 4676061,"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": 1708037433048.898, "dur": 43.691, + "args": { + "External id": 4676062,"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": 1708037433106.067, "dur": 4.527, + "args": { + "External id": 4676063,"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": 1708037433107.711, "dur": 2.528, + "args": { + "External id": 4676064,"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": 1708037433288.817, "dur": 158.869, + "args": { + "External id": 4676065,"Record function id": 0, "Sequence number": 46526610, "Fwd thread id": 1, "Ev Idx": 480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037433290.668, "dur": 149.990, + "args": { + "External id": 4676066,"Sequence number": 46526610, "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": 1708037433290.668, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1708037433303.334, "dur": 34.052, + "args": { + "External id": 4676067,"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": 1708037433307.487, "dur": 2.754, + "args": { + "External id": 4676068,"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": 1708037433311.355, "dur": 25.479, + "args": { + "External id": 4676069,"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": 1708037433344.162, "dur": 4.800, + "args": { + "External id": 4676070,"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": 1708037433345.876, "dur": 2.779, + "args": { + "External id": 4676071,"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": 1708037433456.486, "dur": 15.543, + "args": { + "External id": 4676072,"Record function id": 0, "Sequence number": 46526609, "Fwd thread id": 1, "Ev Idx": 487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037433458.117, "dur": 11.005, + "args": { + "External id": 4676073,"Sequence number": 46526609, "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": 1708037433458.117, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037433460.280, "dur": 8.556, + "args": { + "External id": 4676074,"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": 1708037433461.716, "dur": 6.927, + "args": { + "External id": 4676075,"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": 1708037433475.646, "dur": 9.536, + "args": { + "External id": 4676076,"Record function id": 0, "Sequence number": 46526608, "Fwd thread id": 1, "Ev Idx": 491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037433476.666, "dur": 6.075, + "args": { + "External id": 4676077,"Sequence number": 46526608, "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": 1708037433476.666, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037433480.877, "dur": 1.734, + "args": { + "External id": 4676078,"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": 1708037433481.609, "dur": 0.859, + "args": { + "External id": 4676079,"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": 1708037433488.521, "dur": 9.433, + "args": { + "External id": 4676080,"Record function id": 0, "Sequence number": 46526607, "Fwd thread id": 1, "Ev Idx": 495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037433489.441, "dur": 5.325, + "args": { + "External id": 4676081,"Sequence number": 46526607, "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": 1708037433489.441, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037433492.904, "dur": 1.733, + "args": { + "External id": 4676082,"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": 1708037433493.513, "dur": 1.027, + "args": { + "External id": 4676083,"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": 1708037433503.427, "dur": 7.356, + "args": { + "External id": 4676084,"Record function id": 0, "Sequence number": 46526606, "Fwd thread id": 1, "Ev Idx": 499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037433504.541, "dur": 3.063, + "args": { + "External id": 4676085,"Sequence number": 46526606, "Fwd thread 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": 1708037433504.541, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037433506.037, "dur": 1.425, + "args": { + "External id": 4676086,"Record 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": 1708037433506.487, "dur": 0.877, + "args": { + "External id": 4676087,"Record 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": 1708037433514.127, "dur": 270.315, + "args": { + "External id": 4676088,"Record function id": 0, "Sequence number": 46526605, "Fwd thread id": 1, "Ev Idx": 503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037433515.207, "dur": 258.042, + "args": { + "External id": 4676089,"Sequence number": 46526605, "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": 1708037433515.207, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037433520.448, "dur": 27.409, + "args": { + "External id": 4676090,"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": 1708037433541.953, "dur": 4.935, + "args": { + "External id": 4676091,"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": 1708037433544.622, "dur": 1.763, + "args": { + "External id": 4676092,"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": 1708037433549.770, "dur": 72.851, + "args": { + "External id": 4676093,"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": 1708037433624.155, "dur": 8.421, + "args": { + "External id": 4676094,"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": 1708037433625.594, "dur": 6.113, + "args": { + "External id": 4676095,"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": 1708037433629.774, "dur": 1.730, + "args": { + "External id": 4676096,"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": 1708037433715.099, "dur": 5.603, + "args": { + "External id": 4676097,"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": 1708037433718.954, "dur": 1.122, + "args": { + "External id": 4676098,"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": 1708037433719.613, "dur": 0.363, + "args": { + "External id": 4676099,"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": 1708037433721.507, "dur": 50.678, + "args": { + "External id": 4676100,"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": 1708037433792.052, "dur": 7.466, + "args": { + "External id": 4676101,"Record function id": 0, "Sequence number": 46526604, "Fwd thread id": 1, "Ev Idx": 516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037433793.152, "dur": 4.045, + "args": { + "External id": 4676102,"Sequence number": 46526604, "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": 1708037433793.152, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037433794.805, "dur": 2.253, + "args": { + "External id": 4676103,"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": 1708037433795.665, "dur": 1.286, + "args": { + "External id": 4676104,"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": 1708037433802.783, "dur": 12.703, + "args": { + "External id": 4676105,"Record function id": 0, "Sequence number": 46526603, "Fwd thread id": 1, "Ev Idx": 520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037433805.622, "dur": 6.299, + "args": { + "External id": 4676106,"Sequence number": 46526603, "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": 1708037433805.622, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037433806.828, "dur": 4.896, + "args": { + "External id": 4676107,"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": 1708037433807.456, "dur": 3.765, + "args": { + "External id": 4676108,"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": 1708037433810.574, "dur": 0.556, + "args": { + "External id": 4676109,"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": 1708037433821.368, "dur": 9.561, + "args": { + "External id": 4676110,"Record function id": 0, "Ev Idx": 525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037433822.921, "dur": 7.135, + "args": { + "External id": 4676111,"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": 1708037433825.331, "dur": 4.206, + "args": { + "External id": 4676112,"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": 1708037433826.583, "dur": 2.859, + "args": { + "External id": 4676113,"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": 1708037433837.613, "dur": 8.376, + "args": { + "External id": 4676114,"Record function id": 0, "Sequence number": 46526602, "Fwd thread id": 1, "Ev Idx": 529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037433838.454, "dur": 4.812, + "args": { + "External id": 4676115,"Sequence number": 46526602, "Fwd thread 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": 1708037433838.454, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037433839.755, "dur": 3.381, + "args": { + "External id": 4676116,"Record 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": 1708037433842.283, "dur": 0.739, + "args": { + "External id": 4676117,"Record 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": 1708037433849.212, "dur": 98.096, + "args": { + "External id": 4676118,"Record function id": 0, "Sequence number": 46526601, "Fwd thread id": 1, "Ev Idx": 533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037433849.905, "dur": 89.069, + "args": { + "External id": 4676119,"Sequence number": 46526601, "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": 1708037433849.905, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037433854.055, "dur": 4.764, + "args": { + "External id": 4676120,"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": 1708037433854.475, "dur": 3.930, + "args": { + "External id": 4676121,"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": 1708037433857.782, "dur": 0.516, + "args": { + "External id": 4676122,"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": 1708037433861.849, "dur": 30.359, + "args": { + "External id": 4676123,"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": 1708037433893.353, "dur": 2.724, + "args": { + "External id": 4676124,"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": 1708037433893.788, "dur": 1.763, + "args": { + "External id": 4676125,"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": 1708037433894.570, "dur": 0.867, + "args": { + "External id": 4676126,"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": 1708037433897.209, "dur": 7.491, + "args": { + "External id": 4676127,"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": 1708037433898.264, "dur": 6.018, + "args": { + "External id": 4676128,"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": 1708037433901.769, "dur": 2.448, + "args": { + "External id": 4676129,"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": 1708037433905.144, "dur": 33.061, + "args": { + "External id": 4676130,"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": 1708037433951.725, "dur": 70.971, + "args": { + "External id": 4676131,"Record function id": 0, "Sequence number": 46526600, "Fwd thread id": 1, "Ev Idx": 546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037433952.758, "dur": 5.660, + "args": { + "External id": 4676132,"Sequence number": 46526600, "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": 1708037433952.758, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037433956.754, "dur": 1.529, + "args": { + "External id": 4676133,"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": 1708037433957.214, "dur": 0.964, + "args": { + "External id": 4676134,"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": 1708037433961.288, "dur": 57.809, + "args": { + "External id": 4676135,"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": 1708037434029.167, "dur": 10.373, + "args": { + "External id": 4676136,"Record function id": 0, "Sequence number": 46526599, "Fwd thread id": 1, "Ev Idx": 551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037434030.469, "dur": 6.856, + "args": { + "External id": 4676137,"Sequence number": 46526599, "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": 1708037434030.469, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037434031.440, "dur": 5.662, + "args": { + "External id": 4676138,"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": 1708037434032.306, "dur": 4.075, + "args": { + "External id": 4676139,"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": 1708037434035.733, "dur": 0.553, + "args": { + "External id": 4676140,"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": 1708037434043.632, "dur": 8.786, + "args": { + "External id": 4676141,"Record function id": 0, "Ev Idx": 556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037434047.362, "dur": 4.514, + "args": { + "External id": 4676142,"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": 1708037434048.821, "dur": 2.421, + "args": { + "External id": 4676143,"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": 1708037434049.520, "dur": 1.581, + "args": { + "External id": 4676144,"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": 1708037434055.392, "dur": 8.156, + "args": { + "External id": 4676145,"Record function id": 0, "Sequence number": 46526598, "Fwd thread id": 1, "Ev Idx": 560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037434056.636, "dur": 3.357, + "args": { + "External id": 4676146,"Sequence number": 46526598, "Fwd thread 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": 1708037434056.636, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037434058.020, "dur": 1.829, + "args": { + "External id": 4676147,"Record 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": 1708037434058.593, "dur": 1.143, + "args": { + "External id": 4676148,"Record 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": 1708037434066.789, "dur": 100.930, + "args": { + "External id": 4676149,"Record function id": 0, "Sequence number": 46526597, "Fwd thread id": 1, "Ev Idx": 564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037434070.166, "dur": 86.277, + "args": { + "External id": 4676150,"Sequence number": 46526597, "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": 1708037434070.166, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037434073.307, "dur": 2.471, + "args": { + "External id": 4676151,"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": 1708037434073.960, "dur": 1.417, + "args": { + "External id": 4676152,"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": 1708037434074.587, "dur": 0.650, + "args": { + "External id": 4676153,"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": 1708037434076.672, "dur": 33.943, + "args": { + "External id": 4676154,"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": 1708037434111.633, "dur": 6.874, + "args": { + "External id": 4676155,"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": 1708037434112.180, "dur": 5.780, + "args": { + "External id": 4676156,"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": 1708037434117.391, "dur": 0.461, + "args": { + "External id": 4676157,"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": 1708037434119.791, "dur": 2.246, + "args": { + "External id": 4676158,"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": 1708037434120.562, "dur": 1.123, + "args": { + "External id": 4676159,"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": 1708037434121.182, "dur": 0.405, + "args": { + "External id": 4676160,"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": 1708037434122.481, "dur": 33.272, + "args": { + "External id": 4676161,"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": 1708037434172.177, "dur": 29.004, + "args": { + "External id": 4676162,"Record function id": 0, "Sequence number": 46526596, "Fwd thread id": 1, "Ev Idx": 577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037434173.131, "dur": 6.399, + "args": { + "External id": 4676163,"Sequence number": 46526596, "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": 1708037434173.131, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037434177.302, "dur": 2.053, + "args": { + "External id": 4676164,"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": 1708037434178.312, "dur": 0.891, + "args": { + "External id": 4676165,"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": 1708037434181.824, "dur": 16.857, + "args": { + "External id": 4676166,"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": 1708037434204.976, "dur": 11.698, + "args": { + "External id": 4676167,"Record function id": 0, "Sequence number": 46526595, "Fwd thread id": 1, "Ev Idx": 582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037434205.963, "dur": 8.753, + "args": { + "External id": 4676168,"Sequence number": 46526595, "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": 1708037434205.963, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037434206.739, "dur": 7.784, + "args": { + "External id": 4676169,"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": 1708037434210.259, "dur": 3.742, + "args": { + "External id": 4676170,"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": 1708037434213.256, "dur": 0.629, + "args": { + "External id": 4676171,"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": 1708037434220.424, "dur": 6.874, + "args": { + "External id": 4676172,"Record function id": 0, "Ev Idx": 587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037434221.643, "dur": 5.183, + "args": { + "External id": 4676173,"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": 1708037434222.548, "dur": 3.799, + "args": { + "External id": 4676174,"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": 1708037434225.142, "dur": 1.099, + "args": { + "External id": 4676175,"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": 1708037434231.488, "dur": 404.330, + "args": { + "External id": 4676176,"Record function id": 0, "Sequence number": 46526594, "Fwd thread id": 1, "Ev Idx": 591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037434232.633, "dur": 362.867, + "args": { + "External id": 4676177,"Sequence number": 46526594, "Fwd thread 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": 1708037434232.633, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037434268.002, "dur": 1.811, + "args": { + "External id": 4676178,"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": 1708037434268.559, "dur": 1.088, + "args": { + "External id": 4676179,"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": 1708037434285.420, "dur": 5.470, + "args": { + "External id": 4676180,"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": 1708037434300.598, "dur": 2.547, + "args": { + "External id": 4676181,"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": 1708037434463.330, "dur": 1.714, + "args": { + "External id": 4676182,"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": 1708037434469.204, "dur": 38.184, + "args": { + "External id": 4676183,"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": 1708037434482.351, "dur": 0.869, + "args": { + "External id": 4676184,"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": 1708037434513.335, "dur": 51.901, + "args": { + "External id": 4676185,"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": 1708037434514.973, "dur": 49.915, + "args": { + "External id": 4676186,"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": 1708037434518.395, "dur": 23.576, + "args": { + "External id": 4676187,"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": 1708037434544.570, "dur": 19.799, + "args": { + "External id": 4676188,"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": 1708037434570.833, "dur": 3.155, + "args": { + "External id": 4676189,"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": 1708037434572.225, "dur": 1.645, + "args": { + "External id": 4676190,"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": 1708037434583.870, "dur": 4.086, + "args": { + "External id": 4676191,"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": 1708037434586.979, "dur": 0.871, + "args": { + "External id": 4676192,"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": 1708037434609.452, "dur": 19.787, + "args": { + "External id": 4676193,"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": 1708037434648.401, "dur": 8.653, + "args": { + "External id": 4676194,"Record function id": 0, "Ev Idx": 609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037434650.572, "dur": 5.788, + "args": { + "External id": 4676195,"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": 1708037434652.626, "dur": 2.686, + "args": { + "External id": 4676196,"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": 1708037434653.413, "dur": 1.756, + "args": { + "External id": 4676197,"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": 1708037434663.658, "dur": 6.680, + "args": { + "External id": 4676198,"Record function id": 0, "Sequence number": 46526593, "Fwd thread id": 1, "Ev Idx": 613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037434664.773, "dur": 1.536, + "args": { + "External id": 4676199,"Sequence number": 46526593, "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": 1708037434664.773, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037434674.471, "dur": 470.810, + "args": { + "External id": 4676200,"Record function id": 0, "Sequence number": 46526592, "Fwd thread id": 1, "Ev Idx": 615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037434675.625, "dur": 453.775, + "args": { + "External id": 4676201,"Sequence number": 46526592, "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": 1708037434675.625, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037434709.303, "dur": 7.914, + "args": { + "External id": 4676202,"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": 1708037434713.908, "dur": 3.050, + "args": { + "External id": 4676203,"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": 1708037434720.957, "dur": 7.268, + "args": { + "External id": 4676204,"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": 1708037434722.387, "dur": 5.177, + "args": { + "External id": 4676205,"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": 1708037434726.262, "dur": 1.126, + "args": { + "External id": 4676206,"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": 1708037434733.632, "dur": 88.998, + "args": { + "External id": 4676207,"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": 1708037434734.561, "dur": 4.466, + "args": { + "External id": 4676208,"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": 1708037434735.159, "dur": 3.349, + "args": { + "External id": 4676209,"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": 1708037434735.917, "dur": 2.485, + "args": { + "External id": 4676210,"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": 1708037434740.113, "dur": 82.044, + "args": { + "External id": 4676211,"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": 1708037434741.266, "dur": 80.050, + "args": { + "External id": 4676212,"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": 1708037434826.290, "dur": 4.481, + "args": { + "External id": 4676213,"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": 1708037434829.443, "dur": 1.192, + "args": { + "External id": 4676214,"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": 1708037434862.336, "dur": 5.945, + "args": { + "External id": 4676215,"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": 1708037434869.256, "dur": 2.476, + "args": { + "External id": 4676216,"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": 1708037434872.364, "dur": 1.528, + "args": { + "External id": 4676217,"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": 1708037434905.993, "dur": 1.962, + "args": { + "External id": 4676218,"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": 1708037434906.684, "dur": 1.117, + "args": { + "External id": 4676219,"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": 1708037434933.639, "dur": 173.081, + "args": { + "External id": 4676220,"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": 1708037434938.578, "dur": 3.919, + "args": { + "External id": 4676221,"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": 1708037434941.037, "dur": 0.721, + "args": { + "External id": 4676222,"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": 1708037434943.683, "dur": 10.115, + "args": { + "External id": 4676223,"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": 1708037434950.430, "dur": 2.488, + "args": { + "External id": 4676224,"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": 1708037434955.250, "dur": 3.353, + "args": { + "External id": 4676225,"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": 1708037434957.681, "dur": 0.588, + "args": { + "External id": 4676226,"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": 1708037434959.119, "dur": 3.917, + "args": { + "External id": 4676227,"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": 1708037434961.996, "dur": 0.523, + "args": { + "External id": 4676228,"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": 1708037434966.545, "dur": 2.037, + "args": { + "External id": 4676229,"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": 1708037434967.754, "dur": 0.549, + "args": { + "External id": 4676230,"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": 1708037434973.200, "dur": 4.527, + "args": { + "External id": 4676231,"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": 1708037434975.583, "dur": 1.944, + "args": { + "External id": 4676232,"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": 1708037434980.141, "dur": 1.377, + "args": { + "External id": 4676233,"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": 1708037434980.781, "dur": 0.457, + "args": { + "External id": 4676234,"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": 1708037434982.124, "dur": 46.894, + "args": { + "External id": 4676235,"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": 1708037435024.770, "dur": 3.894, + "args": { + "External id": 4676236,"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": 1708037435030.521, "dur": 61.474, + "args": { + "External id": 4676237,"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": 1708037435093.980, "dur": 3.302, + "args": { + "External id": 4676238,"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": 1708037435098.016, "dur": 4.561, + "args": { + "External id": 4676239,"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": 1708037435101.438, "dur": 0.474, + "args": { + "External id": 4676240,"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": 1708037435104.690, "dur": 0.885, + "args": { + "External id": 4676241,"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": 1708037435156.561, "dur": 8.849, + "args": { + "External id": 4676242,"Record function id": 0, "Ev Idx": 657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037435158.726, "dur": 5.953, + "args": { + "External id": 4676243,"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": 1708037435160.892, "dur": 2.933, + "args": { + "External id": 4676244,"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": 1708037435161.706, "dur": 1.988, + "args": { + "External id": 4676245,"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": 1708037435169.049, "dur": 8.347, + "args": { + "External id": 4676246,"Record function id": 0, "Sequence number": 46526591, "Fwd thread id": 1, "Ev Idx": 661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037435170.055, "dur": 3.227, + "args": { + "External id": 4676247,"Sequence number": 46526591, "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": 1708037435170.055, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037435171.821, "dur": 1.272, + "args": { + "External id": 4676248,"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": 1708037435172.270, "dur": 0.688, + "args": { + "External id": 4676249,"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": 1708037435180.972, "dur": 130.951, + "args": { + "External id": 4676250,"Record function id": 0, "Sequence number": 46526590, "Fwd thread id": 1, "Ev Idx": 665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037435182.004, "dur": 122.431, + "args": { + "External id": 4676251,"Sequence number": 46526590, "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": 1708037435182.004, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037435187.548, "dur": 5.866, + "args": { + "External id": 4676252,"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": 1708037435188.619, "dur": 4.177, + "args": { + "External id": 4676253,"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": 1708037435191.973, "dur": 0.666, + "args": { + "External id": 4676254,"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": 1708037435194.525, "dur": 42.927, + "args": { + "External id": 4676255,"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": 1708037435238.711, "dur": 6.036, + "args": { + "External id": 4676256,"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": 1708037435239.369, "dur": 4.291, + "args": { + "External id": 4676257,"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": 1708037435242.464, "dur": 1.004, + "args": { + "External id": 4676258,"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": 1708037435246.863, "dur": 2.898, + "args": { + "External id": 4676259,"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": 1708037435247.872, "dur": 1.330, + "args": { + "External id": 4676260,"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": 1708037435248.614, "dur": 0.466, + "args": { + "External id": 4676261,"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": 1708037435250.491, "dur": 53.118, + "args": { + "External id": 4676262,"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": 1708037435316.603, "dur": 8.095, + "args": { + "External id": 4676263,"Record function id": 0, "Sequence number": 46526589, "Fwd thread id": 1, "Ev Idx": 678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037435317.460, "dur": 6.003, + "args": { + "External id": 4676264,"Sequence number": 46526589, "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": 1708037435317.460, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037435321.490, "dur": 1.801, + "args": { + "External id": 4676265,"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": 1708037435322.238, "dur": 0.937, + "args": { + "External id": 4676266,"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": 1708037435327.826, "dur": 10.111, + "args": { + "External id": 4676267,"Record function id": 0, "Sequence number": 46526588, "Fwd thread id": 1, "Ev Idx": 682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037435331.193, "dur": 3.550, + "args": { + "External id": 4676268,"Sequence number": 46526588, "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": 1708037435331.193, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037435331.917, "dur": 2.595, + "args": { + "External id": 4676269,"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": 1708037435332.387, "dur": 1.657, + "args": { + "External id": 4676270,"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": 1708037435333.269, "dur": 0.686, + "args": { + "External id": 4676271,"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": 1708037435341.662, "dur": 5.009, + "args": { + "External id": 4676272,"Record function id": 0, "Ev Idx": 687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037435342.920, "dur": 3.293, + "args": { + "External id": 4676273,"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": 1708037435343.949, "dur": 1.950, + "args": { + "External id": 4676274,"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": 1708037435344.429, "dur": 1.380, + "args": { + "External id": 4676275,"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": 1708037435349.915, "dur": 10.592, + "args": { + "External id": 4676276,"Record function id": 0, "Sequence number": 46526587, "Fwd thread id": 1, "Ev Idx": 691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037435353.207, "dur": 5.092, + "args": { + "External id": 4676277,"Sequence number": 46526587, "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": 1708037435353.207, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037435354.570, "dur": 3.578, + "args": { + "External id": 4676278,"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": 1708037435357.348, "dur": 0.656, + "args": { + "External id": 4676279,"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": 1708037435363.584, "dur": 130.830, + "args": { + "External id": 4676280,"Record function id": 0, "Sequence number": 46526586, "Fwd thread id": 1, "Ev Idx": 695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037435364.502, "dur": 119.554, + "args": { + "External id": 4676281,"Sequence number": 46526586, "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": 1708037435364.502, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037435367.266, "dur": 15.672, + "args": { + "External id": 4676282,"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": 1708037435367.924, "dur": 14.435, + "args": { + "External id": 4676283,"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": 1708037435381.310, "dur": 0.692, + "args": { + "External id": 4676284,"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": 1708037435386.240, "dur": 35.935, + "args": { + "External id": 4676285,"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": 1708037435423.282, "dur": 4.850, + "args": { + "External id": 4676286,"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": 1708037435424.024, "dur": 3.532, + "args": { + "External id": 4676287,"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": 1708037435424.895, "dur": 2.500, + "args": { + "External id": 4676288,"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": 1708037435429.322, "dur": 8.962, + "args": { + "External id": 4676289,"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": 1708037435430.258, "dur": 7.537, + "args": { + "External id": 4676290,"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": 1708037435434.969, "dur": 2.751, + "args": { + "External id": 4676291,"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": 1708037435438.778, "dur": 44.561, + "args": { + "External id": 4676292,"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": 1708037435498.824, "dur": 48.098, + "args": { + "External id": 4676293,"Record function id": 0, "Sequence number": 46526585, "Fwd thread id": 1, "Ev Idx": 708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037435499.845, "dur": 3.820, + "args": { + "External id": 4676294,"Sequence number": 46526585, "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": 1708037435499.845, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037435501.592, "dur": 1.918, + "args": { + "External id": 4676295,"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": 1708037435502.367, "dur": 1.018, + "args": { + "External id": 4676296,"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": 1708037435506.400, "dur": 36.409, + "args": { + "External id": 4676297,"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": 1708037435553.331, "dur": 13.423, + "args": { + "External id": 4676298,"Record function id": 0, "Sequence number": 46526584, "Fwd thread id": 1, "Ev Idx": 713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037435554.750, "dur": 9.083, + "args": { + "External id": 4676299,"Sequence number": 46526584, "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": 1708037435554.750, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037435555.824, "dur": 7.786, + "args": { + "External id": 4676300,"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": 1708037435556.875, "dur": 6.040, + "args": { + "External id": 4676301,"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": 1708037435562.090, "dur": 0.718, + "args": { + "External id": 4676302,"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": 1708037435570.887, "dur": 5.613, + "args": { + "External id": 4676303,"Record function id": 0, "Ev Idx": 718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037435572.014, "dur": 3.984, + "args": { + "External id": 4676304,"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": 1708037435573.269, "dur": 2.291, + "args": { + "External id": 4676305,"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": 1708037435573.821, "dur": 1.671, + "args": { + "External id": 4676306,"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": 1708037435583.166, "dur": 466.754, + "args": { + "External id": 4676307,"Record function id": 0, "Sequence number": 46526583, "Fwd thread id": 1, "Ev Idx": 722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037435584.319, "dur": 376.870, + "args": { + "External id": 4676308,"Sequence number": 46526583, "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": 1708037435584.319, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1381210, + "ts": 1708037435608.148, "dur": 36.876, + "args": { + "External id": 4676309,"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": 1708037435609.667, "dur": 35.167, + "args": { + "External id": 4676310,"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": 1708037435612.204, "dur": 7.992, + "args": { + "External id": 4676311,"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": 1708037435616.406, "dur": 3.371, + "args": { + "External id": 4676312,"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": 1708037435621.458, "dur": 22.957, + "args": { + "External id": 4676313,"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": 1708037435656.780, "dur": 4.796, + "args": { + "External id": 4676314,"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": 1708037435660.007, "dur": 1.432, + "args": { + "External id": 4676315,"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": 1708037435665.231, "dur": 3.413, + "args": { + "External id": 4676316,"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": 1708037435666.035, "dur": 2.503, + "args": { + "External id": 4676317,"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": 1708037435680.364, "dur": 1.979, + "args": { + "External id": 4676318,"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": 1708037435693.076, "dur": 2.621, + "args": { + "External id": 4676319,"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": 1708037435854.935, "dur": 2.533, + "args": { + "External id": 4676320,"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": 1708037435861.334, "dur": 30.484, + "args": { + "External id": 4676321,"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": 1708037435868.937, "dur": 0.830, + "args": { + "External id": 4676322,"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": 1708037435896.986, "dur": 30.068, + "args": { + "External id": 4676323,"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": 1708037435898.399, "dur": 28.457, + "args": { + "External id": 4676324,"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": 1708037435904.563, "dur": 4.559, + "args": { + "External id": 4676325,"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": 1708037435910.287, "dur": 16.089, + "args": { + "External id": 4676326,"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": 1708037435931.078, "dur": 5.019, + "args": { + "External id": 4676327,"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": 1708037435934.573, "dur": 1.381, + "args": { + "External id": 4676328,"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": 1708037435942.214, "dur": 1.931, + "args": { + "External id": 4676329,"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": 1708037435942.965, "dur": 1.075, + "args": { + "External id": 4676330,"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": 1708037435948.346, "dur": 3.790, + "args": { + "External id": 4676331,"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": 1708037435948.775, "dur": 3.259, + "args": { + "External id": 4676332,"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": 1708037435978.879, "dur": 68.319, + "args": { + "External id": 4676333,"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": 1708037436062.917, "dur": 11.006, + "args": { + "External id": 4676334,"Record function id": 0, "Ev Idx": 749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037436065.326, "dur": 7.730, + "args": { + "External id": 4676335,"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": 1708037436067.294, "dur": 4.812, + "args": { + "External id": 4676336,"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": 1708037436069.914, "dur": 2.092, + "args": { + "External id": 4676337,"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": 1708037436077.662, "dur": 8.544, + "args": { + "External id": 4676338,"Record function id": 0, "Sequence number": 46526582, "Fwd thread id": 1, "Ev Idx": 753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037436078.616, "dur": 4.318, + "args": { + "External id": 4676339,"Sequence number": 46526582, "Fwd thread 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": 1708037436078.616, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037436080.454, "dur": 2.259, + "args": { + "External id": 4676340,"Record 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": 1708037436081.059, "dur": 1.490, + "args": { + "External id": 4676341,"Record 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": 1708037436089.608, "dur": 135.473, + "args": { + "External id": 4676342,"Record function id": 0, "Sequence number": 46526581, "Fwd thread id": 1, "Ev Idx": 757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037436090.324, "dur": 127.312, + "args": { + "External id": 4676343,"Sequence number": 46526581, "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": 1708037436090.324, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037436094.494, "dur": 9.515, + "args": { + "External id": 4676344,"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": 1708037436098.055, "dur": 5.335, + "args": { + "External id": 4676345,"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": 1708037436102.269, "dur": 0.928, + "args": { + "External id": 4676346,"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": 1708037436105.212, "dur": 57.599, + "args": { + "External id": 4676347,"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": 1708037436163.770, "dur": 5.482, + "args": { + "External id": 4676348,"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": 1708037436164.530, "dur": 4.155, + "args": { + "External id": 4676349,"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": 1708037436165.543, "dur": 2.982, + "args": { + "External id": 4676350,"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": 1708037436173.381, "dur": 3.674, + "args": { + "External id": 4676351,"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": 1708037436175.200, "dur": 1.308, + "args": { + "External id": 4676352,"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": 1708037436175.892, "dur": 0.520, + "args": { + "External id": 4676353,"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": 1708037436177.540, "dur": 39.262, + "args": { + "External id": 4676354,"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": 1708037436229.848, "dur": 11.873, + "args": { + "External id": 4676355,"Record function id": 0, "Sequence number": 46526580, "Fwd thread id": 1, "Ev Idx": 770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037436230.831, "dur": 7.456, + "args": { + "External id": 4676356,"Sequence number": 46526580, "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": 1708037436230.831, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037436234.234, "dur": 3.880, + "args": { + "External id": 4676357,"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": 1708037436234.900, "dur": 3.118, + "args": { + "External id": 4676358,"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": 1708037436247.671, "dur": 9.077, + "args": { + "External id": 4676359,"Record function id": 0, "Sequence number": 46526579, "Fwd thread id": 1, "Ev Idx": 774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037436250.935, "dur": 3.858, + "args": { + "External id": 4676360,"Sequence number": 46526579, "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": 1708037436250.935, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037436251.757, "dur": 2.823, + "args": { + "External id": 4676361,"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": 1708037436252.218, "dur": 1.880, + "args": { + "External id": 4676362,"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": 1708037436253.300, "dur": 0.674, + "args": { + "External id": 4676363,"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": 1708037436260.626, "dur": 4.616, + "args": { + "External id": 4676364,"Record function id": 0, "Ev Idx": 779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037436261.709, "dur": 3.049, + "args": { + "External id": 4676365,"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": 1708037436262.683, "dur": 1.882, + "args": { + "External id": 4676366,"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": 1708037436263.341, "dur": 1.132, + "args": { + "External id": 4676367,"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": 1708037436268.340, "dur": 12.492, + "args": { + "External id": 4676368,"Record function id": 0, "Sequence number": 46526578, "Fwd thread id": 1, "Ev Idx": 783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037436269.005, "dur": 8.255, + "args": { + "External id": 4676369,"Sequence number": 46526578, "Fwd thread 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": 1708037436269.005, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037436272.844, "dur": 4.272, + "args": { + "External id": 4676370,"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": 1708037436275.792, "dur": 1.201, + "args": { + "External id": 4676371,"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": 1708037436285.039, "dur": 309.708, + "args": { + "External id": 4676372,"Record function id": 0, "Sequence number": 46526577, "Fwd thread id": 1, "Ev Idx": 787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037436286.069, "dur": 284.227, + "args": { + "External id": 4676373,"Sequence number": 46526577, "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": 1708037436286.069, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1708037436303.980, "dur": 5.834, + "args": { + "External id": 4676374,"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": 1708037436306.071, "dur": 3.319, + "args": { + "External id": 4676375,"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": 1708037436311.800, "dur": 5.443, + "args": { + "External id": 4676376,"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": 1708037436315.164, "dur": 1.864, + "args": { + "External id": 4676377,"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": 1708037436318.845, "dur": 4.249, + "args": { + "External id": 4676378,"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": 1708037436319.664, "dur": 3.262, + "args": { + "External id": 4676379,"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": 1708037436348.075, "dur": 193.605, + "args": { + "External id": 4676380,"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": 1708037436430.490, "dur": 3.110, + "args": { + "External id": 4676381,"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": 1708037436435.070, "dur": 4.520, + "args": { + "External id": 4676382,"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": 1708037436557.585, "dur": 3.701, + "args": { + "External id": 4676383,"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": 1708037436564.477, "dur": 0.617, + "args": { + "External id": 4676384,"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": 1708037436566.951, "dur": 0.716, + "args": { + "External id": 4676385,"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": 1708037436603.864, "dur": 222.688, + "args": { + "External id": 4676386,"Record function id": 0, "Sequence number": 46526576, "Fwd thread id": 1, "Ev Idx": 801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037436605.288, "dur": 215.053, + "args": { + "External id": 4676387,"Sequence number": 46526576, "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": 1708037436605.288, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1708037436628.113, "dur": 45.805, + "args": { + "External id": 4676388,"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": 1708037436631.075, "dur": 3.396, + "args": { + "External id": 4676389,"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": 1708037436635.694, "dur": 37.552, + "args": { + "External id": 4676390,"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": 1708037436683.720, "dur": 6.182, + "args": { + "External id": 4676391,"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": 1708037436687.202, "dur": 2.355, + "args": { + "External id": 4676392,"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": 1708037436833.365, "dur": 149.510, + "args": { + "External id": 4676393,"Record function id": 0, "Sequence number": 46526575, "Fwd thread id": 1, "Ev Idx": 808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037436834.951, "dur": 141.470, + "args": { + "External id": 4676394,"Sequence number": 46526575, "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": 1708037436834.951, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1708037436847.160, "dur": 31.921, + "args": { + "External id": 4676395,"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": 1708037436849.203, "dur": 2.163, + "args": { + "External id": 4676396,"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": 1708037436852.247, "dur": 26.154, + "args": { + "External id": 4676397,"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": 1708037436886.049, "dur": 8.078, + "args": { + "External id": 4676398,"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": 1708037436891.899, "dur": 1.923, + "args": { + "External id": 4676399,"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": 1708037437029.906, "dur": 17.222, + "args": { + "External id": 4676400,"Record function id": 0, "Sequence number": 46526574, "Fwd thread id": 1, "Ev Idx": 815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437031.591, "dur": 10.893, + "args": { + "External id": 4676401,"Sequence number": 46526574, "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": 1708037437031.591, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037437034.182, "dur": 8.003, + "args": { + "External id": 4676402,"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": 1708037437035.463, "dur": 6.472, + "args": { + "External id": 4676403,"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": 1708037437050.694, "dur": 11.809, + "args": { + "External id": 4676404,"Record function id": 0, "Sequence number": 46526573, "Fwd thread id": 1, "Ev Idx": 819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437053.857, "dur": 5.206, + "args": { + "External id": 4676405,"Sequence number": 46526573, "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": 1708037437053.857, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037437055.121, "dur": 3.785, + "args": { + "External id": 4676406,"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": 1708037437057.872, "dur": 0.887, + "args": { + "External id": 4676407,"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": 1708037437067.599, "dur": 6.441, + "args": { + "External id": 4676408,"Record function id": 0, "Sequence number": 46526572, "Fwd thread id": 1, "Ev Idx": 823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437068.494, "dur": 2.627, + "args": { + "External id": 4676409,"Sequence number": 46526572, "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": 1708037437068.494, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037437069.593, "dur": 1.378, + "args": { + "External id": 4676410,"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": 1708037437070.066, "dur": 0.803, + "args": { + "External id": 4676411,"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": 1708037437077.401, "dur": 10.108, + "args": { + "External id": 4676412,"Record function id": 0, "Sequence number": 46526571, "Fwd thread id": 1, "Ev Idx": 827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437078.274, "dur": 6.630, + "args": { + "External id": 4676413,"Sequence number": 46526571, "Fwd thread 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": 1708037437078.274, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037437079.555, "dur": 5.213, + "args": { + "External id": 4676414,"Record 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": 1708037437083.684, "dur": 0.991, + "args": { + "External id": 4676415,"Record 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": 1708037437091.041, "dur": 149.045, + "args": { + "External id": 4676416,"Record function id": 0, "Sequence number": 46526570, "Fwd thread id": 1, "Ev Idx": 831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437091.906, "dur": 138.361, + "args": { + "External id": 4676417,"Sequence number": 46526570, "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": 1708037437091.906, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037437096.151, "dur": 5.857, + "args": { + "External id": 4676418,"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": 1708037437097.868, "dur": 3.549, + "args": { + "External id": 4676419,"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": 1708037437099.615, "dur": 1.515, + "args": { + "External id": 4676420,"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": 1708037437103.555, "dur": 66.826, + "args": { + "External id": 4676421,"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": 1708037437171.676, "dur": 6.300, + "args": { + "External id": 4676422,"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": 1708037437175.051, "dur": 2.239, + "args": { + "External id": 4676423,"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": 1708037437176.026, "dur": 1.086, + "args": { + "External id": 4676424,"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": 1708037437180.122, "dur": 5.094, + "args": { + "External id": 4676425,"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": 1708037437181.509, "dur": 3.283, + "args": { + "External id": 4676426,"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": 1708037437184.296, "dur": 0.407, + "args": { + "External id": 4676427,"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": 1708037437185.795, "dur": 43.673, + "args": { + "External id": 4676428,"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": 1708037437244.579, "dur": 9.471, + "args": { + "External id": 4676429,"Record function id": 0, "Sequence number": 46526569, "Fwd thread id": 1, "Ev Idx": 844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437245.555, "dur": 6.665, + "args": { + "External id": 4676430,"Sequence number": 46526569, "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": 1708037437245.555, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037437250.252, "dur": 1.806, + "args": { + "External id": 4676431,"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": 1708037437250.975, "dur": 0.894, + "args": { + "External id": 4676432,"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": 1708037437257.246, "dur": 6.399, + "args": { + "External id": 4676433,"Record function id": 0, "Sequence number": 46526568, "Fwd thread id": 1, "Ev Idx": 848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437258.099, "dur": 3.512, + "args": { + "External id": 4676434,"Sequence number": 46526568, "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": 1708037437258.099, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037437258.794, "dur": 2.605, + "args": { + "External id": 4676435,"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": 1708037437259.451, "dur": 1.412, + "args": { + "External id": 4676436,"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": 1708037437260.344, "dur": 0.420, + "args": { + "External id": 4676437,"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": 1708037437271.190, "dur": 10.608, + "args": { + "External id": 4676438,"Record function id": 0, "Ev Idx": 853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037437272.473, "dur": 8.645, + "args": { + "External id": 4676439,"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": 1708037437274.638, "dur": 6.027, + "args": { + "External id": 4676440,"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": 1708037437277.765, "dur": 2.807, + "args": { + "External id": 4676441,"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": 1708037437284.903, "dur": 5.402, + "args": { + "External id": 4676442,"Record function id": 0, "Sequence number": 46526567, "Fwd thread id": 1, "Ev Idx": 857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437285.812, "dur": 2.423, + "args": { + "External id": 4676443,"Sequence number": 46526567, "Fwd thread 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": 1708037437285.812, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037437286.831, "dur": 1.260, + "args": { + "External id": 4676444,"Record 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": 1708037437287.289, "dur": 0.694, + "args": { + "External id": 4676445,"Record 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": 1708037437293.410, "dur": 90.976, + "args": { + "External id": 4676446,"Record function id": 0, "Sequence number": 46526566, "Fwd thread id": 1, "Ev Idx": 861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437294.550, "dur": 84.020, + "args": { + "External id": 4676447,"Sequence number": 46526566, "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": 1708037437294.550, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037437297.973, "dur": 4.502, + "args": { + "External id": 4676448,"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": 1708037437300.911, "dur": 1.133, + "args": { + "External id": 4676449,"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": 1708037437301.519, "dur": 0.398, + "args": { + "External id": 4676450,"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": 1708037437303.155, "dur": 27.038, + "args": { + "External id": 4676451,"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": 1708037437331.029, "dur": 5.627, + "args": { + "External id": 4676452,"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": 1708037437331.829, "dur": 4.326, + "args": { + "External id": 4676453,"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": 1708037437335.232, "dur": 0.808, + "args": { + "External id": 4676454,"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": 1708037437340.399, "dur": 5.025, + "args": { + "External id": 4676455,"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": 1708037437341.873, "dur": 3.134, + "args": { + "External id": 4676456,"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": 1708037437342.558, "dur": 2.364, + "args": { + "External id": 4676457,"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": 1708037437346.032, "dur": 31.756, + "args": { + "External id": 4676458,"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": 1708037437388.332, "dur": 36.266, + "args": { + "External id": 4676459,"Record function id": 0, "Sequence number": 46526565, "Fwd thread id": 1, "Ev Idx": 874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437389.300, "dur": 5.630, + "args": { + "External id": 4676460,"Sequence number": 46526565, "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": 1708037437389.300, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037437390.804, "dur": 3.994, + "args": { + "External id": 4676461,"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": 1708037437393.586, "dur": 1.122, + "args": { + "External id": 4676462,"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": 1708037437397.845, "dur": 22.500, + "args": { + "External id": 4676463,"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": 1708037437428.265, "dur": 8.240, + "args": { + "External id": 4676464,"Record function id": 0, "Sequence number": 46526564, "Fwd thread id": 1, "Ev Idx": 879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437429.541, "dur": 4.278, + "args": { + "External id": 4676465,"Sequence number": 46526564, "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": 1708037437429.541, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037437430.465, "dur": 3.163, + "args": { + "External id": 4676466,"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": 1708037437431.334, "dur": 1.823, + "args": { + "External id": 4676467,"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": 1708037437432.354, "dur": 0.683, + "args": { + "External id": 4676468,"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": 1708037437440.230, "dur": 6.567, + "args": { + "External id": 4676469,"Record function id": 0, "Ev Idx": 884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037437441.276, "dur": 5.038, + "args": { + "External id": 4676470,"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": 1708037437442.380, "dur": 3.425, + "args": { + "External id": 4676471,"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": 1708037437444.783, "dur": 0.906, + "args": { + "External id": 4676472,"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": 1708037437450.082, "dur": 8.273, + "args": { + "External id": 4676473,"Record function id": 0, "Sequence number": 46526563, "Fwd thread id": 1, "Ev Idx": 888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437450.812, "dur": 5.122, + "args": { + "External id": 4676474,"Sequence number": 46526563, "Fwd thread 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": 1708037437450.812, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037437452.270, "dur": 3.527, + "args": { + "External id": 4676475,"Record 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": 1708037437454.892, "dur": 0.803, + "args": { + "External id": 4676476,"Record 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": 1708037437463.163, "dur": 142.005, + "args": { + "External id": 4676477,"Record function id": 0, "Sequence number": 46526562, "Fwd thread id": 1, "Ev Idx": 892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437463.868, "dur": 131.010, + "args": { + "External id": 4676478,"Sequence number": 46526562, "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": 1708037437463.868, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037437468.194, "dur": 4.684, + "args": { + "External id": 4676479,"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": 1708037437468.722, "dur": 3.759, + "args": { + "External id": 4676480,"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": 1708037437472.024, "dur": 0.352, + "args": { + "External id": 4676481,"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": 1708037437473.444, "dur": 29.054, + "args": { + "External id": 4676482,"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": 1708037437503.591, "dur": 3.046, + "args": { + "External id": 4676483,"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": 1708037437504.096, "dur": 2.032, + "args": { + "External id": 4676484,"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": 1708037437504.892, "dur": 1.121, + "args": { + "External id": 4676485,"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": 1708037437508.026, "dur": 10.032, + "args": { + "External id": 4676486,"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": 1708037437514.307, "dur": 3.358, + "args": { + "External id": 4676487,"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": 1708037437517.111, "dur": 0.453, + "args": { + "External id": 4676488,"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": 1708037437518.561, "dur": 75.150, + "args": { + "External id": 4676489,"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": 1708037437611.622, "dur": 27.157, + "args": { + "External id": 4676490,"Record function id": 0, "Sequence number": 46526561, "Fwd thread id": 1, "Ev Idx": 905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437612.629, "dur": 4.418, + "args": { + "External id": 4676491,"Sequence number": 46526561, "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": 1708037437612.629, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037437614.562, "dur": 2.358, + "args": { + "External id": 4676492,"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": 1708037437615.244, "dur": 1.547, + "args": { + "External id": 4676493,"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": 1708037437619.284, "dur": 17.048, + "args": { + "External id": 4676494,"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": 1708037437642.355, "dur": 12.369, + "args": { + "External id": 4676495,"Record function id": 0, "Sequence number": 46526560, "Fwd thread id": 1, "Ev Idx": 910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037437645.284, "dur": 7.424, + "args": { + "External id": 4676496,"Sequence number": 46526560, "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": 1708037437645.284, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037437646.399, "dur": 6.115, + "args": { + "External id": 4676497,"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": 1708037437647.324, "dur": 4.620, + "args": { + "External id": 4676498,"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": 1708037437651.108, "dur": 0.727, + "args": { + "External id": 4676499,"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": 1708037437658.611, "dur": 5.017, + "args": { + "External id": 4676500,"Record function id": 0, "Ev Idx": 915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037437659.736, "dur": 3.379, + "args": { + "External id": 4676501,"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": 1708037437661.027, "dur": 1.808, + "args": { + "External id": 4676502,"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": 1708037437661.519, "dur": 1.193, + "args": { + "External id": 4676503,"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": 1708037437667.704, "dur": 416.096, + "args": { + "External id": 4676504,"Record function id": 0, "Sequence number": 46526559, "Fwd thread id": 1, "Ev Idx": 919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037437668.653, "dur": 374.724, + "args": { + "External id": 4676505,"Sequence number": 46526559, "Fwd thread 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": 1708037437668.653, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037437712.492, "dur": 4.424, + "args": { + "External id": 4676506,"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": 1708037437715.520, "dur": 1.194, + "args": { + "External id": 4676507,"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": 1708037437730.721, "dur": 6.064, + "args": { + "External id": 4676508,"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": 1708037437746.027, "dur": 1.800, + "args": { + "External id": 4676509,"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": 1708037437893.475, "dur": 1.891, + "args": { + "External id": 4676510,"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": 1708037437899.235, "dur": 35.953, + "args": { + "External id": 4676511,"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": 1708037437909.511, "dur": 0.869, + "args": { + "External id": 4676512,"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": 1708037437944.434, "dur": 34.331, + "args": { + "External id": 4676513,"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": 1708037437946.083, "dur": 32.405, + "args": { + "External id": 4676514,"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": 1708037437953.743, "dur": 5.597, + "args": { + "External id": 4676515,"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": 1708037437961.042, "dur": 16.851, + "args": { + "External id": 4676516,"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": 1708037437982.970, "dur": 40.891, + "args": { + "External id": 4676517,"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": 1708037438020.792, "dur": 2.579, + "args": { + "External id": 4676518,"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": 1708037438033.465, "dur": 1.664, + "args": { + "External id": 4676519,"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": 1708037438034.219, "dur": 0.800, + "args": { + "External id": 4676520,"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": 1708037438058.821, "dur": 20.458, + "args": { + "External id": 4676521,"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": 1708037438097.369, "dur": 10.843, + "args": { + "External id": 4676522,"Record function id": 0, "Ev Idx": 937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037438101.121, "dur": 6.266, + "args": { + "External id": 4676523,"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": 1708037438103.041, "dur": 3.246, + "args": { + "External id": 4676524,"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": 1708037438104.288, "dur": 1.878, + "args": { + "External id": 4676525,"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": 1708037438112.052, "dur": 6.337, + "args": { + "External id": 4676526,"Record function id": 0, "Sequence number": 46526558, "Fwd thread id": 1, "Ev Idx": 941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037438113.352, "dur": 1.410, + "args": { + "External id": 4676527,"Sequence number": 46526558, "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": 1708037438113.352, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037438122.243, "dur": 466.992, + "args": { + "External id": 4676528,"Record function id": 0, "Sequence number": 46526557, "Fwd thread id": 1, "Ev Idx": 943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037438123.323, "dur": 450.281, + "args": { + "External id": 4676529,"Sequence number": 46526557, "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": 1708037438123.323, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037438155.556, "dur": 7.993, + "args": { + "External id": 4676530,"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": 1708037438160.203, "dur": 3.089, + "args": { + "External id": 4676531,"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": 1708037438166.888, "dur": 9.799, + "args": { + "External id": 4676532,"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": 1708037438168.284, "dur": 7.738, + "args": { + "External id": 4676533,"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": 1708037438172.767, "dur": 3.077, + "args": { + "External id": 4676534,"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": 1708037438180.453, "dur": 106.221, + "args": { + "External id": 4676535,"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": 1708037438181.378, "dur": 4.872, + "args": { + "External id": 4676536,"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": 1708037438184.350, "dur": 1.433, + "args": { + "External id": 4676537,"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": 1708037438185.020, "dur": 0.632, + "args": { + "External id": 4676538,"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": 1708037438187.244, "dur": 98.858, + "args": { + "External id": 4676539,"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": 1708037438188.564, "dur": 96.552, + "args": { + "External id": 4676540,"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": 1708037438290.437, "dur": 2.388, + "args": { + "External id": 4676541,"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": 1708037438291.455, "dur": 1.229, + "args": { + "External id": 4676542,"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": 1708037438324.171, "dur": 5.834, + "args": { + "External id": 4676543,"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": 1708037438333.057, "dur": 2.158, + "args": { + "External id": 4676544,"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": 1708037438335.891, "dur": 2.427, + "args": { + "External id": 4676545,"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": 1708037438370.230, "dur": 1.778, + "args": { + "External id": 4676546,"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": 1708037438370.720, "dur": 1.099, + "args": { + "External id": 4676547,"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": 1708037438396.127, "dur": 157.824, + "args": { + "External id": 4676548,"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": 1708037438401.354, "dur": 8.674, + "args": { + "External id": 4676549,"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": 1708037438405.923, "dur": 3.269, + "args": { + "External id": 4676550,"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": 1708037438411.134, "dur": 7.811, + "args": { + "External id": 4676551,"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": 1708037438417.855, "dur": 0.455, + "args": { + "External id": 4676552,"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": 1708037438420.203, "dur": 1.704, + "args": { + "External id": 4676553,"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": 1708037438421.278, "dur": 0.311, + "args": { + "External id": 4676554,"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": 1708037438424.869, "dur": 2.076, + "args": { + "External id": 4676555,"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": 1708037438425.783, "dur": 0.511, + "args": { + "External id": 4676556,"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": 1708037438432.372, "dur": 1.656, + "args": { + "External id": 4676557,"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": 1708037438433.248, "dur": 0.502, + "args": { + "External id": 4676558,"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": 1708037438434.772, "dur": 6.764, + "args": { + "External id": 4676559,"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": 1708037438439.554, "dur": 1.801, + "args": { + "External id": 4676560,"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": 1708037438442.143, "dur": 3.319, + "args": { + "External id": 4676561,"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": 1708037438444.702, "dur": 0.514, + "args": { + "External id": 4676562,"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": 1708037438447.929, "dur": 3.649, + "args": { + "External id": 4676563,"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": 1708037438448.498, "dur": 3.003, + "args": { + "External id": 4676564,"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": 1708037438452.625, "dur": 67.320, + "args": { + "External id": 4676565,"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": 1708037438540.419, "dur": 2.264, + "args": { + "External id": 4676566,"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": 1708037438544.391, "dur": 5.381, + "args": { + "External id": 4676567,"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": 1708037438548.151, "dur": 0.839, + "args": { + "External id": 4676568,"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": 1708037438552.133, "dur": 0.809, + "args": { + "External id": 4676569,"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": 1708037438601.255, "dur": 9.371, + "args": { + "External id": 4676570,"Record function id": 0, "Ev Idx": 985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037438603.404, "dur": 6.429, + "args": { + "External id": 4676571,"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": 1708037438605.342, "dur": 3.316, + "args": { + "External id": 4676572,"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": 1708037438606.521, "dur": 2.026, + "args": { + "External id": 4676573,"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": 1708037438617.460, "dur": 9.667, + "args": { + "External id": 4676574,"Record function id": 0, "Sequence number": 46526556, "Fwd thread id": 1, "Ev Idx": 989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037438618.293, "dur": 5.869, + "args": { + "External id": 4676575,"Sequence number": 46526556, "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": 1708037438618.293, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037438622.135, "dur": 1.813, + "args": { + "External id": 4676576,"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": 1708037438622.985, "dur": 0.828, + "args": { + "External id": 4676577,"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": 1708037438630.502, "dur": 139.662, + "args": { + "External id": 4676578,"Record function id": 0, "Sequence number": 46526555, "Fwd thread id": 1, "Ev Idx": 993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037438631.272, "dur": 131.187, + "args": { + "External id": 4676579,"Sequence number": 46526555, "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": 1708037438631.272, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037438636.056, "dur": 5.634, + "args": { + "External id": 4676580,"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": 1708037438637.362, "dur": 3.782, + "args": { + "External id": 4676581,"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": 1708037438640.290, "dur": 0.675, + "args": { + "External id": 4676582,"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": 1708037438642.913, "dur": 52.903, + "args": { + "External id": 4676583,"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": 1708037438697.261, "dur": 6.067, + "args": { + "External id": 4676584,"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": 1708037438697.874, "dur": 4.539, + "args": { + "External id": 4676585,"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": 1708037438701.315, "dur": 0.949, + "args": { + "External id": 4676586,"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": 1708037438704.949, "dur": 7.348, + "args": { + "External id": 4676587,"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": 1708037438706.839, "dur": 4.815, + "args": { + "External id": 4676588,"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": 1708037438709.509, "dur": 2.078, + "args": { + "External id": 4676589,"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": 1708037438712.757, "dur": 48.889, + "args": { + "External id": 4676590,"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": 1708037438774.822, "dur": 8.570, + "args": { + "External id": 4676591,"Record function id": 0, "Sequence number": 46526554, "Fwd thread id": 1, "Ev Idx": 1006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037438775.987, "dur": 5.921, + "args": { + "External id": 4676592,"Sequence number": 46526554, "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": 1708037438775.987, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037438777.671, "dur": 4.092, + "args": { + "External id": 4676593,"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": 1708037438780.554, "dur": 1.095, + "args": { + "External id": 4676594,"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": 1708037438786.807, "dur": 10.290, + "args": { + "External id": 4676595,"Record function id": 0, "Sequence number": 46526553, "Fwd thread id": 1, "Ev Idx": 1010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037438787.754, "dur": 6.526, + "args": { + "External id": 4676596,"Sequence number": 46526553, "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": 1708037438787.754, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037438788.669, "dur": 5.388, + "args": { + "External id": 4676597,"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": 1708037438789.324, "dur": 4.266, + "args": { + "External id": 4676598,"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": 1708037438792.900, "dur": 0.578, + "args": { + "External id": 4676599,"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": 1708037438800.819, "dur": 4.684, + "args": { + "External id": 4676600,"Record function id": 0, "Ev Idx": 1015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037438801.995, "dur": 2.999, + "args": { + "External id": 4676601,"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": 1708037438803.006, "dur": 1.518, + "args": { + "External id": 4676602,"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": 1708037438803.376, "dur": 1.084, + "args": { + "External id": 4676603,"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": 1708037438810.814, "dur": 9.528, + "args": { + "External id": 4676604,"Record function id": 0, "Sequence number": 46526552, "Fwd thread id": 1, "Ev Idx": 1019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037438811.978, "dur": 5.047, + "args": { + "External id": 4676605,"Sequence number": 46526552, "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": 1708037438811.978, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037438813.557, "dur": 3.306, + "args": { + "External id": 4676606,"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": 1708037438816.078, "dur": 0.658, + "args": { + "External id": 4676607,"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": 1708037438823.453, "dur": 241.577, + "args": { + "External id": 4676608,"Record function id": 0, "Sequence number": 46526551, "Fwd thread id": 1, "Ev Idx": 1023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037438899.524, "dur": 152.546, + "args": { + "External id": 4676609,"Sequence number": 46526551, "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": 1708037438899.524, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037438906.104, "dur": 2.659, + "args": { + "External id": 4676610,"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": 1708037438906.804, "dur": 1.455, + "args": { + "External id": 4676611,"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": 1708037438907.618, "dur": 0.489, + "args": { + "External id": 4676612,"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": 1708037438909.272, "dur": 35.401, + "args": { + "External id": 4676613,"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": 1708037438945.782, "dur": 9.465, + "args": { + "External id": 4676614,"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": 1708037438946.379, "dur": 8.317, + "args": { + "External id": 4676615,"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": 1708037438949.533, "dur": 5.009, + "args": { + "External id": 4676616,"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": 1708037438956.635, "dur": 5.273, + "args": { + "External id": 4676617,"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": 1708037438957.982, "dur": 3.452, + "args": { + "External id": 4676618,"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": 1708037438960.875, "dur": 0.473, + "args": { + "External id": 4676619,"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": 1708037438962.352, "dur": 88.271, + "args": { + "External id": 4676620,"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": 1708037439072.541, "dur": 37.322, + "args": { + "External id": 4676621,"Record function id": 0, "Sequence number": 46526550, "Fwd thread id": 1, "Ev Idx": 1036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037439073.642, "dur": 7.350, + "args": { + "External id": 4676622,"Sequence number": 46526550, "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": 1708037439073.642, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037439078.393, "dur": 2.457, + "args": { + "External id": 4676623,"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": 1708037439078.992, "dur": 1.710, + "args": { + "External id": 4676624,"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": 1708037439084.033, "dur": 22.566, + "args": { + "External id": 4676625,"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": 1708037439113.663, "dur": 9.806, + "args": { + "External id": 4676626,"Record function id": 0, "Sequence number": 46526549, "Fwd thread id": 1, "Ev Idx": 1041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037439114.627, "dur": 6.251, + "args": { + "External id": 4676627,"Sequence number": 46526549, "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": 1708037439114.627, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037439115.545, "dur": 5.111, + "args": { + "External id": 4676628,"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": 1708037439116.133, "dur": 3.954, + "args": { + "External id": 4676629,"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": 1708037439119.478, "dur": 0.495, + "args": { + "External id": 4676630,"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": 1708037439127.665, "dur": 8.210, + "args": { + "External id": 4676631,"Record function id": 0, "Ev Idx": 1046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037439128.944, "dur": 6.266, + "args": { + "External id": 4676632,"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": 1708037439130.138, "dur": 4.584, + "args": { + "External id": 4676633,"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": 1708037439133.172, "dur": 1.452, + "args": { + "External id": 4676634,"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": 1708037439139.576, "dur": 441.497, + "args": { + "External id": 4676635,"Record function id": 0, "Sequence number": 46526548, "Fwd thread id": 1, "Ev Idx": 1050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037439140.991, "dur": 382.210, + "args": { + "External id": 4676636,"Sequence number": 46526548, "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": 1708037439140.991, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1381210, + "ts": 1708037439167.210, "dur": 33.338, + "args": { + "External id": 4676637,"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": 1708037439168.457, "dur": 31.890, + "args": { + "External id": 4676638,"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": 1708037439170.944, "dur": 5.871, + "args": { + "External id": 4676639,"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": 1708037439173.223, "dur": 3.033, + "args": { + "External id": 4676640,"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": 1708037439178.088, "dur": 21.841, + "args": { + "External id": 4676641,"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": 1708037439215.653, "dur": 4.295, + "args": { + "External id": 4676642,"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": 1708037439216.362, "dur": 3.433, + "args": { + "External id": 4676643,"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": 1708037439223.664, "dur": 3.567, + "args": { + "External id": 4676644,"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": 1708037439226.442, "dur": 0.659, + "args": { + "External id": 4676645,"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": 1708037439238.949, "dur": 2.222, + "args": { + "External id": 4676646,"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": 1708037439251.133, "dur": 2.507, + "args": { + "External id": 4676647,"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": 1708037439413.260, "dur": 2.150, + "args": { + "External id": 4676648,"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": 1708037439421.350, "dur": 30.579, + "args": { + "External id": 4676649,"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": 1708037439429.225, "dur": 0.905, + "args": { + "External id": 4676650,"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": 1708037439456.910, "dur": 31.340, + "args": { + "External id": 4676651,"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": 1708037439460.644, "dur": 27.376, + "args": { + "External id": 4676652,"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": 1708037439466.301, "dur": 4.281, + "args": { + "External id": 4676653,"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": 1708037439471.912, "dur": 15.568, + "args": { + "External id": 4676654,"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": 1708037439492.422, "dur": 2.271, + "args": { + "External id": 4676655,"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": 1708037439493.447, "dur": 1.144, + "args": { + "External id": 4676656,"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": 1708037439501.595, "dur": 6.640, + "args": { + "External id": 4676657,"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": 1708037439504.364, "dur": 3.767, + "args": { + "External id": 4676658,"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": 1708037439510.201, "dur": 4.071, + "args": { + "External id": 4676659,"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": 1708037439513.166, "dur": 1.012, + "args": { + "External id": 4676660,"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": 1708037439559.335, "dur": 19.893, + "args": { + "External id": 4676661,"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": 1708037439593.341, "dur": 9.308, + "args": { + "External id": 4676662,"Record function id": 0, "Ev Idx": 1077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037439595.734, "dur": 6.160, + "args": { + "External id": 4676663,"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": 1708037439597.885, "dur": 3.004, + "args": { + "External id": 4676664,"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": 1708037439598.816, "dur": 1.938, + "args": { + "External id": 4676665,"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": 1708037439606.675, "dur": 10.420, + "args": { + "External id": 4676666,"Record function id": 0, "Sequence number": 46526547, "Fwd thread id": 1, "Ev Idx": 1081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037439607.609, "dur": 6.348, + "args": { + "External id": 4676667,"Sequence number": 46526547, "Fwd thread 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": 1708037439607.609, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037439611.533, "dur": 2.194, + "args": { + "External id": 4676668,"Record 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": 1708037439612.268, "dur": 1.288, + "args": { + "External id": 4676669,"Record 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": 1708037439620.852, "dur": 133.813, + "args": { + "External id": 4676670,"Record function id": 0, "Sequence number": 46526546, "Fwd thread id": 1, "Ev Idx": 1085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037439621.939, "dur": 124.906, + "args": { + "External id": 4676671,"Sequence number": 46526546, "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": 1708037439621.939, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037439626.496, "dur": 7.076, + "args": { + "External id": 4676672,"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": 1708037439627.787, "dur": 5.194, + "args": { + "External id": 4676673,"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": 1708037439631.854, "dur": 0.909, + "args": { + "External id": 4676674,"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": 1708037439634.960, "dur": 55.526, + "args": { + "External id": 4676675,"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": 1708037439691.781, "dur": 7.281, + "args": { + "External id": 4676676,"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": 1708037439692.638, "dur": 5.799, + "args": { + "External id": 4676677,"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": 1708037439695.841, "dur": 2.417, + "args": { + "External id": 4676678,"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": 1708037439700.765, "dur": 5.817, + "args": { + "External id": 4676679,"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": 1708037439702.550, "dur": 3.443, + "args": { + "External id": 4676680,"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": 1708037439705.509, "dur": 0.421, + "args": { + "External id": 4676681,"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": 1708037439707.315, "dur": 38.809, + "args": { + "External id": 4676682,"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": 1708037439759.426, "dur": 12.543, + "args": { + "External id": 4676683,"Record function id": 0, "Sequence number": 46526545, "Fwd thread id": 1, "Ev Idx": 1098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037439760.443, "dur": 8.168, + "args": { + "External id": 4676684,"Sequence number": 46526545, "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": 1708037439760.443, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037439762.242, "dur": 6.210, + "args": { + "External id": 4676685,"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": 1708037439764.934, "dur": 3.352, + "args": { + "External id": 4676686,"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": 1708037439777.282, "dur": 8.987, + "args": { + "External id": 4676687,"Record function id": 0, "Sequence number": 46526544, "Fwd thread id": 1, "Ev Idx": 1102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037439778.331, "dur": 5.851, + "args": { + "External id": 4676688,"Sequence number": 46526544, "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": 1708037439778.331, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037439779.378, "dur": 4.579, + "args": { + "External id": 4676689,"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": 1708037439780.181, "dur": 3.310, + "args": { + "External id": 4676690,"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": 1708037439782.980, "dur": 0.361, + "args": { + "External id": 4676691,"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": 1708037439790.237, "dur": 4.907, + "args": { + "External id": 4676692,"Record function id": 0, "Ev Idx": 1107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037439791.688, "dur": 2.955, + "args": { + "External id": 4676693,"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": 1708037439792.704, "dur": 1.659, + "args": { + "External id": 4676694,"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": 1708037439793.273, "dur": 0.963, + "args": { + "External id": 4676695,"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": 1708037439800.376, "dur": 6.716, + "args": { + "External id": 4676696,"Record function id": 0, "Sequence number": 46526543, "Fwd thread id": 1, "Ev Idx": 1111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037439801.178, "dur": 3.230, + "args": { + "External id": 4676697,"Sequence number": 46526543, "Fwd thread 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": 1708037439801.178, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037439802.359, "dur": 1.896, + "args": { + "External id": 4676698,"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": 1708037439802.969, "dur": 1.150, + "args": { + "External id": 4676699,"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": 1708037439812.991, "dur": 387.297, + "args": { + "External id": 4676700,"Record function id": 0, "Sequence number": 46526542, "Fwd thread id": 1, "Ev Idx": 1115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037439814.388, "dur": 359.045, + "args": { + "External id": 4676701,"Sequence number": 46526542, "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": 1708037439814.388, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1708037439830.735, "dur": 6.003, + "args": { + "External id": 4676702,"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": 1708037439833.017, "dur": 3.342, + "args": { + "External id": 4676703,"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": 1708037439838.781, "dur": 6.696, + "args": { + "External id": 4676704,"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": 1708037439841.701, "dur": 3.565, + "args": { + "External id": 4676705,"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": 1708037439884.559, "dur": 5.522, + "args": { + "External id": 4676706,"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": 1708037439887.842, "dur": 2.030, + "args": { + "External id": 4676707,"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": 1708037439918.622, "dur": 227.876, + "args": { + "External id": 4676708,"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": 1708037440044.224, "dur": 6.689, + "args": { + "External id": 4676709,"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": 1708037440052.705, "dur": 4.231, + "args": { + "External id": 4676710,"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": 1708037440160.220, "dur": 4.097, + "args": { + "External id": 4676711,"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": 1708037440167.110, "dur": 0.769, + "args": { + "External id": 4676712,"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": 1708037440169.762, "dur": 0.729, + "args": { + "External id": 4676713,"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": 1708037440210.247, "dur": 222.976, + "args": { + "External id": 4676714,"Record function id": 0, "Sequence number": 46526541, "Fwd thread id": 1, "Ev Idx": 1129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037440211.933, "dur": 213.677, + "args": { + "External id": 4676715,"Sequence number": 46526541, "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": 1708037440211.933, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1708037440231.719, "dur": 44.296, + "args": { + "External id": 4676716,"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": 1708037440234.523, "dur": 3.425, + "args": { + "External id": 4676717,"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": 1708037440239.381, "dur": 36.129, + "args": { + "External id": 4676718,"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": 1708037440285.480, "dur": 6.825, + "args": { + "External id": 4676719,"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": 1708037440289.430, "dur": 2.527, + "args": { + "External id": 4676720,"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": 1708037440439.844, "dur": 194.546, + "args": { + "External id": 4676721,"Record function id": 0, "Sequence number": 46526540, "Fwd thread id": 1, "Ev Idx": 1136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037440441.885, "dur": 184.288, + "args": { + "External id": 4676722,"Sequence number": 46526540, "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": 1708037440441.885, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1708037440452.949, "dur": 51.090, + "args": { + "External id": 4676723,"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": 1708037440454.801, "dur": 2.348, + "args": { + "External id": 4676724,"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": 1708037440470.931, "dur": 32.624, + "args": { + "External id": 4676725,"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": 1708037440510.967, "dur": 5.890, + "args": { + "External id": 4676726,"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": 1708037440514.612, "dur": 1.973, + "args": { + "External id": 4676727,"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": 1708037440643.274, "dur": 20.535, + "args": { + "External id": 4676728,"Record function id": 0, "Sequence number": 46526539, "Fwd thread id": 1, "Ev Idx": 1143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037440645.128, "dur": 14.843, + "args": { + "External id": 4676729,"Sequence number": 46526539, "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": 1708037440645.128, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037440647.858, "dur": 11.799, + "args": { + "External id": 4676730,"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": 1708037440651.504, "dur": 7.954, + "args": { + "External id": 4676731,"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": 1708037440667.753, "dur": 9.612, + "args": { + "External id": 4676732,"Record function id": 0, "Sequence number": 46526538, "Fwd thread id": 1, "Ev Idx": 1147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037440668.857, "dur": 6.094, + "args": { + "External id": 4676733,"Sequence number": 46526538, "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": 1708037440668.857, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037440670.491, "dur": 4.309, + "args": { + "External id": 4676734,"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": 1708037440673.795, "dur": 0.901, + "args": { + "External id": 4676735,"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": 1708037440680.610, "dur": 6.711, + "args": { + "External id": 4676736,"Record function id": 0, "Sequence number": 46526537, "Fwd thread id": 1, "Ev Idx": 1151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037440681.315, "dur": 3.261, + "args": { + "External id": 4676737,"Sequence number": 46526537, "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": 1708037440681.315, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037440682.649, "dur": 1.780, + "args": { + "External id": 4676738,"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": 1708037440683.283, "dur": 1.055, + "args": { + "External id": 4676739,"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": 1708037440690.670, "dur": 11.264, + "args": { + "External id": 4676740,"Record function id": 0, "Sequence number": 46526536, "Fwd thread id": 1, "Ev Idx": 1155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037440691.694, "dur": 7.602, + "args": { + "External id": 4676741,"Sequence number": 46526536, "Fwd thread 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": 1708037440691.694, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037440692.885, "dur": 6.270, + "args": { + "External id": 4676742,"Record 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": 1708037440697.679, "dur": 1.353, + "args": { + "External id": 4676743,"Record 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": 1708037440705.302, "dur": 154.982, + "args": { + "External id": 4676744,"Record function id": 0, "Sequence number": 46526535, "Fwd thread id": 1, "Ev Idx": 1159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037440706.318, "dur": 145.169, + "args": { + "External id": 4676745,"Sequence number": 46526535, "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": 1708037440706.318, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037440710.818, "dur": 6.400, + "args": { + "External id": 4676746,"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": 1708037440712.818, "dur": 3.734, + "args": { + "External id": 4676747,"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": 1708037440714.810, "dur": 1.428, + "args": { + "External id": 4676748,"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": 1708037440720.751, "dur": 66.338, + "args": { + "External id": 4676749,"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": 1708037440788.258, "dur": 3.779, + "args": { + "External id": 4676750,"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": 1708037440788.893, "dur": 2.296, + "args": { + "External id": 4676751,"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": 1708037440790.189, "dur": 0.862, + "args": { + "External id": 4676752,"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": 1708037440793.713, "dur": 6.044, + "args": { + "External id": 4676753,"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": 1708037440795.763, "dur": 3.472, + "args": { + "External id": 4676754,"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": 1708037440798.795, "dur": 0.348, + "args": { + "External id": 4676755,"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": 1708037440802.499, "dur": 48.248, + "args": { + "External id": 4676756,"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": 1708037440867.406, "dur": 7.886, + "args": { + "External id": 4676757,"Record function id": 0, "Sequence number": 46526534, "Fwd thread id": 1, "Ev Idx": 1172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037440868.487, "dur": 3.802, + "args": { + "External id": 4676758,"Sequence number": 46526534, "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": 1708037440868.487, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037440869.905, "dur": 2.217, + "args": { + "External id": 4676759,"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": 1708037440870.818, "dur": 1.188, + "args": { + "External id": 4676760,"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": 1708037440878.733, "dur": 10.310, + "args": { + "External id": 4676761,"Record function id": 0, "Sequence number": 46526533, "Fwd thread id": 1, "Ev Idx": 1176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037440879.645, "dur": 6.837, + "args": { + "External id": 4676762,"Sequence number": 46526533, "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": 1708037440879.645, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037440881.037, "dur": 5.228, + "args": { + "External id": 4676763,"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": 1708037440881.871, "dur": 3.900, + "args": { + "External id": 4676764,"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": 1708037440885.313, "dur": 0.349, + "args": { + "External id": 4676765,"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": 1708037440897.206, "dur": 9.631, + "args": { + "External id": 4676766,"Record function id": 0, "Ev Idx": 1181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037440898.728, "dur": 7.318, + "args": { + "External id": 4676767,"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": 1708037440901.576, "dur": 3.994, + "args": { + "External id": 4676768,"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": 1708037440902.854, "dur": 2.619, + "args": { + "External id": 4676769,"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": 1708037440910.112, "dur": 7.160, + "args": { + "External id": 4676770,"Record function id": 0, "Sequence number": 46526532, "Fwd thread id": 1, "Ev Idx": 1185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037440911.379, "dur": 2.943, + "args": { + "External id": 4676771,"Sequence number": 46526532, "Fwd thread 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": 1708037440911.379, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037440912.563, "dur": 1.618, + "args": { + "External id": 4676772,"Record 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": 1708037440913.361, "dur": 0.727, + "args": { + "External id": 4676773,"Record 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": 1708037440920.324, "dur": 145.085, + "args": { + "External id": 4676774,"Record function id": 0, "Sequence number": 46526531, "Fwd thread id": 1, "Ev Idx": 1189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037440921.341, "dur": 136.868, + "args": { + "External id": 4676775,"Sequence number": 46526531, "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": 1708037440921.341, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037440926.906, "dur": 2.779, + "args": { + "External id": 4676776,"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": 1708037440927.725, "dur": 1.563, + "args": { + "External id": 4676777,"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": 1708037440928.596, "dur": 0.574, + "args": { + "External id": 4676778,"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": 1708037440930.510, "dur": 28.030, + "args": { + "External id": 4676779,"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": 1708037440959.531, "dur": 7.595, + "args": { + "External id": 4676780,"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": 1708037440960.197, "dur": 6.443, + "args": { + "External id": 4676781,"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": 1708037440965.759, "dur": 0.775, + "args": { + "External id": 4676782,"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": 1708037440968.325, "dur": 5.627, + "args": { + "External id": 4676783,"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": 1708037440970.136, "dur": 3.311, + "args": { + "External id": 4676784,"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": 1708037440970.874, "dur": 2.458, + "args": { + "External id": 4676785,"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": 1708037440974.658, "dur": 82.081, + "args": { + "External id": 4676786,"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": 1708037441072.184, "dur": 38.822, + "args": { + "External id": 4676787,"Record function id": 0, "Sequence number": 46526530, "Fwd thread id": 1, "Ev Idx": 1202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037441073.726, "dur": 8.278, + "args": { + "External id": 4676788,"Sequence number": 46526530, "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": 1708037441073.726, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037441077.306, "dur": 4.541, + "args": { + "External id": 4676789,"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": 1708037441080.122, "dur": 1.600, + "args": { + "External id": 4676790,"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": 1708037441084.964, "dur": 23.869, + "args": { + "External id": 4676791,"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": 1708037441117.004, "dur": 8.722, + "args": { + "External id": 4676792,"Record function id": 0, "Sequence number": 46526529, "Fwd thread id": 1, "Ev Idx": 1207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037441118.326, "dur": 5.155, + "args": { + "External id": 4676793,"Sequence number": 46526529, "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": 1708037441118.326, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037441119.727, "dur": 3.581, + "args": { + "External id": 4676794,"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": 1708037441120.573, "dur": 2.142, + "args": { + "External id": 4676795,"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": 1708037441121.626, "dur": 0.933, + "args": { + "External id": 4676796,"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": 1708037441129.999, "dur": 8.784, + "args": { + "External id": 4676797,"Record function id": 0, "Ev Idx": 1212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037441131.155, "dur": 6.970, + "args": { + "External id": 4676798,"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": 1708037441132.411, "dur": 4.874, + "args": { + "External id": 4676799,"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": 1708037441135.589, "dur": 1.599, + "args": { + "External id": 4676800,"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": 1708037441142.142, "dur": 12.947, + "args": { + "External id": 4676801,"Record function id": 0, "Sequence number": 46526528, "Fwd thread id": 1, "Ev Idx": 1216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037441143.464, "dur": 9.121, + "args": { + "External id": 4676802,"Sequence number": 46526528, "Fwd thread 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": 1708037441143.464, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037441144.916, "dur": 7.521, + "args": { + "External id": 4676803,"Record 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": 1708037441151.275, "dur": 1.074, + "args": { + "External id": 4676804,"Record 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": 1708037441158.202, "dur": 98.108, + "args": { + "External id": 4676805,"Record function id": 0, "Sequence number": 46526527, "Fwd thread id": 1, "Ev Idx": 1220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037441158.988, "dur": 88.251, + "args": { + "External id": 4676806,"Sequence number": 46526527, "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": 1708037441158.988, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037441164.280, "dur": 2.630, + "args": { + "External id": 4676807,"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": 1708037441164.952, "dur": 1.547, + "args": { + "External id": 4676808,"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": 1708037441165.797, "dur": 0.592, + "args": { + "External id": 4676809,"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": 1708037441167.695, "dur": 30.622, + "args": { + "External id": 4676810,"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": 1708037441199.316, "dur": 7.218, + "args": { + "External id": 4676811,"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": 1708037441200.219, "dur": 5.813, + "args": { + "External id": 4676812,"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": 1708037441203.357, "dur": 2.538, + "args": { + "External id": 4676813,"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": 1708037441207.977, "dur": 5.167, + "args": { + "External id": 4676814,"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": 1708037441209.364, "dur": 3.327, + "args": { + "External id": 4676815,"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": 1708037441212.063, "dur": 0.501, + "args": { + "External id": 4676816,"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": 1708037441213.799, "dur": 32.756, + "args": { + "External id": 4676817,"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": 1708037441260.645, "dur": 24.653, + "args": { + "External id": 4676818,"Record function id": 0, "Sequence number": 46526526, "Fwd thread id": 1, "Ev Idx": 1233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037441261.677, "dur": 3.769, + "args": { + "External id": 4676819,"Sequence number": 46526526, "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": 1708037441261.677, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037441263.341, "dur": 1.950, + "args": { + "External id": 4676820,"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": 1708037441264.078, "dur": 1.050, + "args": { + "External id": 4676821,"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": 1708037441267.603, "dur": 15.710, + "args": { + "External id": 4676822,"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": 1708037441291.551, "dur": 7.935, + "args": { + "External id": 4676823,"Record function id": 0, "Sequence number": 46526525, "Fwd thread id": 1, "Ev Idx": 1238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037441292.611, "dur": 4.420, + "args": { + "External id": 4676824,"Sequence number": 46526525, "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": 1708037441292.611, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037441293.551, "dur": 3.266, + "args": { + "External id": 4676825,"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": 1708037441294.331, "dur": 1.932, + "args": { + "External id": 4676826,"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": 1708037441295.443, "dur": 0.727, + "args": { + "External id": 4676827,"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": 1708037441305.153, "dur": 5.189, + "args": { + "External id": 4676828,"Record function id": 0, "Ev Idx": 1243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037441306.602, "dur": 3.256, + "args": { + "External id": 4676829,"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": 1708037441307.418, "dur": 2.011, + "args": { + "External id": 4676830,"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": 1708037441308.033, "dur": 1.292, + "args": { + "External id": 4676831,"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": 1708037441316.361, "dur": 373.856, + "args": { + "External id": 4676832,"Record function id": 0, "Sequence number": 46526524, "Fwd thread id": 1, "Ev Idx": 1247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037441317.621, "dur": 339.816, + "args": { + "External id": 4676833,"Sequence number": 46526524, "Fwd thread 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": 1708037441317.621, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037441350.881, "dur": 2.339, + "args": { + "External id": 4676834,"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": 1708037441352.007, "dur": 1.029, + "args": { + "External id": 4676835,"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": 1708037441366.918, "dur": 5.833, + "args": { + "External id": 4676836,"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": 1708037441381.219, "dur": 1.607, + "args": { + "External id": 4676837,"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": 1708037441547.135, "dur": 2.573, + "args": { + "External id": 4676838,"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": 1708037441554.178, "dur": 36.918, + "args": { + "External id": 4676839,"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": 1708037441564.123, "dur": 0.883, + "args": { + "External id": 4676840,"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": 1708037441596.750, "dur": 36.075, + "args": { + "External id": 4676841,"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": 1708037441600.733, "dur": 31.799, + "args": { + "External id": 4676842,"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": 1708037441606.769, "dur": 6.294, + "args": { + "External id": 4676843,"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": 1708037441614.412, "dur": 17.606, + "args": { + "External id": 4676844,"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": 1708037441637.251, "dur": 2.449, + "args": { + "External id": 4676845,"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": 1708037441638.485, "dur": 1.085, + "args": { + "External id": 4676846,"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": 1708037441646.686, "dur": 4.293, + "args": { + "External id": 4676847,"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": 1708037441649.704, "dur": 1.180, + "args": { + "External id": 4676848,"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": 1708037441668.573, "dur": 17.111, + "args": { + "External id": 4676849,"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": 1708037441701.275, "dur": 7.896, + "args": { + "External id": 4676850,"Record function id": 0, "Ev Idx": 1265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037441703.321, "dur": 5.146, + "args": { + "External id": 4676851,"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": 1708037441704.833, "dur": 2.541, + "args": { + "External id": 4676852,"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": 1708037441705.827, "dur": 1.454, + "args": { + "External id": 4676853,"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": 1708037441712.920, "dur": 7.000, + "args": { + "External id": 4676854,"Record function id": 0, "Sequence number": 46526523, "Fwd thread id": 1, "Ev Idx": 1269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037441714.271, "dur": 1.229, + "args": { + "External id": 4676855,"Sequence number": 46526523, "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": 1708037441714.271, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037441723.693, "dur": 455.064, + "args": { + "External id": 4676856,"Record function id": 0, "Sequence number": 46526522, "Fwd thread id": 1, "Ev Idx": 1271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037441726.958, "dur": 438.552, + "args": { + "External id": 4676857,"Sequence number": 46526522, "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": 1708037441726.958, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037441758.539, "dur": 7.733, + "args": { + "External id": 4676858,"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": 1708037441763.126, "dur": 2.869, + "args": { + "External id": 4676859,"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": 1708037441769.350, "dur": 6.097, + "args": { + "External id": 4676860,"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": 1708037441770.614, "dur": 4.287, + "args": { + "External id": 4676861,"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": 1708037441771.887, "dur": 2.846, + "args": { + "External id": 4676862,"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": 1708037441778.573, "dur": 82.229, + "args": { + "External id": 4676863,"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": 1708037441781.266, "dur": 4.743, + "args": { + "External id": 4676864,"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": 1708037441781.825, "dur": 3.685, + "args": { + "External id": 4676865,"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": 1708037441784.820, "dur": 0.617, + "args": { + "External id": 4676866,"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": 1708037441787.077, "dur": 73.260, + "args": { + "External id": 4676867,"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": 1708037441788.547, "dur": 71.096, + "args": { + "External id": 4676868,"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": 1708037441864.129, "dur": 2.410, + "args": { + "External id": 4676869,"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": 1708037441865.037, "dur": 1.357, + "args": { + "External id": 4676870,"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": 1708037441896.159, "dur": 5.718, + "args": { + "External id": 4676871,"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": 1708037441905.303, "dur": 2.603, + "args": { + "External id": 4676872,"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": 1708037441908.695, "dur": 2.122, + "args": { + "External id": 4676873,"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": 1708037441942.553, "dur": 2.580, + "args": { + "External id": 4676874,"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": 1708037441943.492, "dur": 1.460, + "args": { + "External id": 4676875,"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": 1708037441968.505, "dur": 171.199, + "args": { + "External id": 4676876,"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": 1708037441973.236, "dur": 45.332, + "args": { + "External id": 4676877,"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": 1708037441978.941, "dur": 4.616, + "args": { + "External id": 4676878,"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": 1708037442021.385, "dur": 6.872, + "args": { + "External id": 4676879,"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": 1708037442026.457, "dur": 0.753, + "args": { + "External id": 4676880,"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": 1708037442029.945, "dur": 2.285, + "args": { + "External id": 4676881,"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": 1708037442031.104, "dur": 0.772, + "args": { + "External id": 4676882,"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": 1708037442034.817, "dur": 1.946, + "args": { + "External id": 4676883,"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": 1708037442035.413, "dur": 0.751, + "args": { + "External id": 4676884,"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": 1708037442040.022, "dur": 3.974, + "args": { + "External id": 4676885,"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": 1708037442042.985, "dur": 0.706, + "args": { + "External id": 4676886,"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": 1708037442044.865, "dur": 7.420, + "args": { + "External id": 4676887,"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": 1708037442049.995, "dur": 2.081, + "args": { + "External id": 4676888,"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": 1708037442055.096, "dur": 4.179, + "args": { + "External id": 4676889,"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": 1708037442058.272, "dur": 0.725, + "args": { + "External id": 4676890,"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": 1708037442059.768, "dur": 3.871, + "args": { + "External id": 4676891,"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": 1708037442060.523, "dur": 3.022, + "args": { + "External id": 4676892,"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": 1708037442064.881, "dur": 60.301, + "args": { + "External id": 4676893,"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": 1708037442128.396, "dur": 1.289, + "args": { + "External id": 4676894,"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": 1708037442130.410, "dur": 2.261, + "args": { + "External id": 4676895,"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": 1708037442131.405, "dur": 0.687, + "args": { + "External id": 4676896,"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": 1708037442137.575, "dur": 1.142, + "args": { + "External id": 4676897,"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": 1708037442189.583, "dur": 8.924, + "args": { + "External id": 4676898,"Record function id": 0, "Ev Idx": 1313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037442191.568, "dur": 6.226, + "args": { + "External id": 4676899,"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": 1708037442193.820, "dur": 3.039, + "args": { + "External id": 4676900,"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": 1708037442194.963, "dur": 1.811, + "args": { + "External id": 4676901,"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": 1708037442202.043, "dur": 7.705, + "args": { + "External id": 4676902,"Record function id": 0, "Sequence number": 46526521, "Fwd thread id": 1, "Ev Idx": 1317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037442202.922, "dur": 3.392, + "args": { + "External id": 4676903,"Sequence number": 46526521, "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": 1708037442202.922, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037442204.381, "dur": 1.740, + "args": { + "External id": 4676904,"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": 1708037442205.061, "dur": 0.899, + "args": { + "External id": 4676905,"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": 1708037442213.359, "dur": 125.656, + "args": { + "External id": 4676906,"Record function id": 0, "Sequence number": 46526520, "Fwd thread id": 1, "Ev Idx": 1321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037442214.387, "dur": 117.467, + "args": { + "External id": 4676907,"Sequence number": 46526520, "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": 1708037442214.387, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037442218.847, "dur": 6.533, + "args": { + "External id": 4676908,"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": 1708037442220.388, "dur": 4.345, + "args": { + "External id": 4676909,"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": 1708037442223.693, "dur": 0.879, + "args": { + "External id": 4676910,"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": 1708037442226.210, "dur": 40.737, + "args": { + "External id": 4676911,"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": 1708037442268.044, "dur": 6.606, + "args": { + "External id": 4676912,"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": 1708037442268.738, "dur": 5.084, + "args": { + "External id": 4676913,"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": 1708037442272.358, "dur": 1.305, + "args": { + "External id": 4676914,"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": 1708037442276.284, "dur": 7.712, + "args": { + "External id": 4676915,"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": 1708037442280.124, "dur": 3.466, + "args": { + "External id": 4676916,"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": 1708037442281.078, "dur": 2.445, + "args": { + "External id": 4676917,"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": 1708037442284.480, "dur": 46.705, + "args": { + "External id": 4676918,"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": 1708037442343.920, "dur": 6.077, + "args": { + "External id": 4676919,"Record function id": 0, "Sequence number": 46526519, "Fwd thread id": 1, "Ev Idx": 1334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037442344.817, "dur": 3.745, + "args": { + "External id": 4676920,"Sequence number": 46526519, "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": 1708037442344.817, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037442346.365, "dur": 2.065, + "args": { + "External id": 4676921,"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": 1708037442347.171, "dur": 1.107, + "args": { + "External id": 4676922,"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": 1708037442353.483, "dur": 12.941, + "args": { + "External id": 4676923,"Record function id": 0, "Sequence number": 46526518, "Fwd thread id": 1, "Ev Idx": 1338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037442354.249, "dur": 9.029, + "args": { + "External id": 4676924,"Sequence number": 46526518, "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": 1708037442354.249, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037442358.039, "dur": 5.005, + "args": { + "External id": 4676925,"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": 1708037442358.495, "dur": 4.064, + "args": { + "External id": 4676926,"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": 1708037442361.979, "dur": 0.419, + "args": { + "External id": 4676927,"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": 1708037442370.121, "dur": 5.465, + "args": { + "External id": 4676928,"Record function id": 0, "Ev Idx": 1343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037442371.421, "dur": 3.738, + "args": { + "External id": 4676929,"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": 1708037442372.575, "dur": 2.056, + "args": { + "External id": 4676930,"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": 1708037442373.311, "dur": 1.245, + "args": { + "External id": 4676931,"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": 1708037442378.879, "dur": 9.532, + "args": { + "External id": 4676932,"Record function id": 0, "Sequence number": 46526517, "Fwd thread id": 1, "Ev Idx": 1347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037442380.158, "dur": 5.067, + "args": { + "External id": 4676933,"Sequence number": 46526517, "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": 1708037442380.158, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037442381.543, "dur": 3.544, + "args": { + "External id": 4676934,"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": 1708037442384.221, "dur": 0.721, + "args": { + "External id": 4676935,"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": 1708037442391.590, "dur": 116.711, + "args": { + "External id": 4676936,"Record function id": 0, "Sequence number": 46526516, "Fwd thread id": 1, "Ev Idx": 1351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037442392.433, "dur": 103.964, + "args": { + "External id": 4676937,"Sequence number": 46526516, "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": 1708037442392.433, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037442395.483, "dur": 4.416, + "args": { + "External id": 4676938,"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": 1708037442396.204, "dur": 3.254, + "args": { + "External id": 4676939,"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": 1708037442399.002, "dur": 0.355, + "args": { + "External id": 4676940,"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": 1708037442400.639, "dur": 31.018, + "args": { + "External id": 4676941,"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": 1708037442434.563, "dur": 5.986, + "args": { + "External id": 4676942,"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": 1708037442435.319, "dur": 4.684, + "args": { + "External id": 4676943,"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": 1708037442436.733, "dur": 3.125, + "args": { + "External id": 4676944,"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": 1708037442442.012, "dur": 3.375, + "args": { + "External id": 4676945,"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": 1708037442443.488, "dur": 1.531, + "args": { + "External id": 4676946,"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": 1708037442444.520, "dur": 0.430, + "args": { + "External id": 4676947,"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": 1708037442447.453, "dur": 48.279, + "args": { + "External id": 4676948,"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": 1708037442514.936, "dur": 57.744, + "args": { + "External id": 4676949,"Record function id": 0, "Sequence number": 46526515, "Fwd thread id": 1, "Ev Idx": 1364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037442515.743, "dur": 5.280, + "args": { + "External id": 4676950,"Sequence number": 46526515, "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": 1708037442515.743, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037442519.249, "dur": 1.640, + "args": { + "External id": 4676951,"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": 1708037442519.855, "dur": 0.896, + "args": { + "External id": 4676952,"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": 1708037442541.563, "dur": 27.316, + "args": { + "External id": 4676953,"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": 1708037442578.181, "dur": 12.145, + "args": { + "External id": 4676954,"Record function id": 0, "Sequence number": 46526514, "Fwd thread id": 1, "Ev Idx": 1369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037442579.689, "dur": 7.945, + "args": { + "External id": 4676955,"Sequence number": 46526514, "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": 1708037442579.689, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037442581.164, "dur": 6.248, + "args": { + "External id": 4676956,"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": 1708037442582.277, "dur": 4.440, + "args": { + "External id": 4676957,"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": 1708037442585.621, "dur": 0.971, + "args": { + "External id": 4676958,"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": 1708037442594.329, "dur": 8.411, + "args": { + "External id": 4676959,"Record function id": 0, "Ev Idx": 1374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037442598.180, "dur": 4.120, + "args": { + "External id": 4676960,"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": 1708037442599.642, "dur": 2.127, + "args": { + "External id": 4676961,"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": 1708037442600.387, "dur": 1.284, + "args": { + "External id": 4676962,"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": 1708037442607.309, "dur": 478.742, + "args": { + "External id": 4676963,"Record function id": 0, "Sequence number": 46526513, "Fwd thread id": 1, "Ev Idx": 1378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037442623.669, "dur": 421.860, + "args": { + "External id": 4676964,"Sequence number": 46526513, "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": 1708037442623.669, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1381210, + "ts": 1708037442652.784, "dur": 35.585, + "args": { + "External id": 4676965,"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": 1708037442654.330, "dur": 33.808, + "args": { + "External id": 4676966,"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": 1708037442657.006, "dur": 6.375, + "args": { + "External id": 4676967,"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": 1708037442659.402, "dur": 3.470, + "args": { + "External id": 4676968,"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": 1708037442664.714, "dur": 22.748, + "args": { + "External id": 4676969,"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": 1708037442702.681, "dur": 7.426, + "args": { + "External id": 4676970,"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": 1708037442705.818, "dur": 4.173, + "args": { + "External id": 4676971,"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": 1708037442714.584, "dur": 1.623, + "args": { + "External id": 4676972,"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": 1708037442715.387, "dur": 0.677, + "args": { + "External id": 4676973,"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": 1708037442729.740, "dur": 2.395, + "args": { + "External id": 4676974,"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": 1708037442742.032, "dur": 4.010, + "args": { + "External id": 4676975,"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": 1708037442895.551, "dur": 3.746, + "args": { + "External id": 4676976,"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": 1708037442903.250, "dur": 31.930, + "args": { + "External id": 4676977,"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": 1708037442913.360, "dur": 0.867, + "args": { + "External id": 4676978,"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": 1708037442940.878, "dur": 27.795, + "args": { + "External id": 4676979,"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": 1708037442942.432, "dur": 26.031, + "args": { + "External id": 4676980,"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": 1708037442945.963, "dur": 3.949, + "args": { + "External id": 4676981,"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": 1708037442953.086, "dur": 14.928, + "args": { + "External id": 4676982,"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": 1708037442972.754, "dur": 5.178, + "args": { + "External id": 4676983,"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": 1708037442976.685, "dur": 1.115, + "args": { + "External id": 4676984,"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": 1708037443020.975, "dur": 5.043, + "args": { + "External id": 4676985,"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": 1708037443021.673, "dur": 4.076, + "args": { + "External id": 4676986,"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": 1708037443029.173, "dur": 4.334, + "args": { + "External id": 4676987,"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": 1708037443032.016, "dur": 1.397, + "args": { + "External id": 4676988,"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": 1708037443063.464, "dur": 20.784, + "args": { + "External id": 4676989,"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": 1708037443097.980, "dur": 8.551, + "args": { + "External id": 4676990,"Record function id": 0, "Ev Idx": 1405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037443100.143, "dur": 5.676, + "args": { + "External id": 4676991,"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": 1708037443102.275, "dur": 2.679, + "args": { + "External id": 4676992,"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": 1708037443103.157, "dur": 1.677, + "args": { + "External id": 4676993,"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": 1708037443109.946, "dur": 10.859, + "args": { + "External id": 4676994,"Record function id": 0, "Sequence number": 46526512, "Fwd thread id": 1, "Ev Idx": 1409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037443110.974, "dur": 6.771, + "args": { + "External id": 4676995,"Sequence number": 46526512, "Fwd thread 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": 1708037443110.974, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037443112.832, "dur": 4.677, + "args": { + "External id": 4676996,"Record 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": 1708037443116.227, "dur": 1.183, + "args": { + "External id": 4676997,"Record 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": 1708037443124.654, "dur": 140.838, + "args": { + "External id": 4676998,"Record function id": 0, "Sequence number": 46526511, "Fwd thread id": 1, "Ev Idx": 1413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037443125.706, "dur": 132.805, + "args": { + "External id": 4676999,"Sequence number": 46526511, "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": 1708037443125.706, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037443130.477, "dur": 4.196, + "args": { + "External id": 4677000,"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": 1708037443131.787, "dur": 2.300, + "args": { + "External id": 4677001,"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": 1708037443132.915, "dur": 0.983, + "args": { + "External id": 4677002,"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": 1708037443135.930, "dur": 61.842, + "args": { + "External id": 4677003,"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": 1708037443200.990, "dur": 7.260, + "args": { + "External id": 4677004,"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": 1708037443201.658, "dur": 5.954, + "args": { + "External id": 4677005,"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": 1708037443204.712, "dur": 2.743, + "args": { + "External id": 4677006,"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": 1708037443210.029, "dur": 3.205, + "args": { + "External id": 4677007,"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": 1708037443211.649, "dur": 1.040, + "args": { + "External id": 4677008,"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": 1708037443212.217, "dur": 0.395, + "args": { + "External id": 4677009,"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": 1708037443215.787, "dur": 41.911, + "args": { + "External id": 4677010,"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": 1708037443270.301, "dur": 11.330, + "args": { + "External id": 4677011,"Record function id": 0, "Sequence number": 46526510, "Fwd thread id": 1, "Ev Idx": 1426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037443271.457, "dur": 7.456, + "args": { + "External id": 4677012,"Sequence number": 46526510, "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": 1708037443271.457, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037443272.942, "dur": 5.806, + "args": { + "External id": 4677013,"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": 1708037443276.036, "dur": 2.574, + "args": { + "External id": 4677014,"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": 1708037443284.939, "dur": 8.716, + "args": { + "External id": 4677015,"Record function id": 0, "Sequence number": 46526509, "Fwd thread id": 1, "Ev Idx": 1430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037443285.982, "dur": 5.730, + "args": { + "External id": 4677016,"Sequence number": 46526509, "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": 1708037443285.982, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037443287.040, "dur": 4.430, + "args": { + "External id": 4677017,"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": 1708037443287.696, "dur": 3.288, + "args": { + "External id": 4677018,"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": 1708037443290.365, "dur": 0.519, + "args": { + "External id": 4677019,"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": 1708037443297.374, "dur": 5.282, + "args": { + "External id": 4677020,"Record function id": 0, "Ev Idx": 1435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037443298.727, "dur": 3.400, + "args": { + "External id": 4677021,"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": 1708037443300.033, "dur": 1.683, + "args": { + "External id": 4677022,"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": 1708037443300.611, "dur": 0.986, + "args": { + "External id": 4677023,"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": 1708037443305.942, "dur": 6.750, + "args": { + "External id": 4677024,"Record function id": 0, "Sequence number": 46526508, "Fwd thread id": 1, "Ev Idx": 1439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037443306.833, "dur": 3.660, + "args": { + "External id": 4677025,"Sequence number": 46526508, "Fwd thread 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": 1708037443306.833, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037443308.388, "dur": 1.946, + "args": { + "External id": 4677026,"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": 1708037443309.086, "dur": 1.127, + "args": { + "External id": 4677027,"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": 1708037443319.908, "dur": 316.978, + "args": { + "External id": 4677028,"Record function id": 0, "Sequence number": 46526507, "Fwd thread id": 1, "Ev Idx": 1443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037443323.262, "dur": 285.331, + "args": { + "External id": 4677029,"Sequence number": 46526507, "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": 1708037443323.262, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1381210, + "ts": 1708037443340.162, "dur": 9.226, + "args": { + "External id": 4677030,"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": 1708037443344.742, "dur": 4.146, + "args": { + "External id": 4677031,"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": 1708037443351.563, "dur": 5.068, + "args": { + "External id": 4677032,"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": 1708037443354.294, "dur": 2.101, + "args": { + "External id": 4677033,"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": 1708037443358.010, "dur": 2.533, + "args": { + "External id": 4677034,"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": 1708037443358.800, "dur": 1.566, + "args": { + "External id": 4677035,"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": 1708037443383.970, "dur": 196.875, + "args": { + "External id": 4677036,"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": 1708037443465.868, "dur": 5.048, + "args": { + "External id": 4677037,"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": 1708037443474.814, "dur": 4.137, + "args": { + "External id": 4677038,"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": 1708037443595.455, "dur": 3.711, + "args": { + "External id": 4677039,"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": 1708037443602.157, "dur": 0.754, + "args": { + "External id": 4677040,"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": 1708037443604.980, "dur": 0.772, + "args": { + "External id": 4677041,"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": 1708037443645.429, "dur": 234.201, + "args": { + "External id": 4677042,"Record function id": 0, "Sequence number": 46526506, "Fwd thread id": 1, "Ev Idx": 1457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037443647.146, "dur": 224.514, + "args": { + "External id": 4677043,"Sequence number": 46526506, "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": 1708037443647.146, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1708037443666.307, "dur": 55.279, + "args": { + "External id": 4677044,"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": 1708037443671.378, "dur": 3.431, + "args": { + "External id": 4677045,"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": 1708037443676.352, "dur": 44.693, + "args": { + "External id": 4677046,"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": 1708037443730.478, "dur": 4.285, + "args": { + "External id": 4677047,"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": 1708037443731.979, "dur": 2.483, + "args": { + "External id": 4677048,"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": 1708037443886.531, "dur": 219.463, + "args": { + "External id": 4677049,"Record function id": 0, "Sequence number": 46526505, "Fwd thread id": 1, "Ev Idx": 1464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037443889.924, "dur": 205.368, + "args": { + "External id": 4677050,"Sequence number": 46526505, "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": 1708037443889.924, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336753, "tid": 1381210, + "ts": 1708037443902.073, "dur": 31.437, + "args": { + "External id": 4677051,"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": 1708037443904.018, "dur": 2.491, + "args": { + "External id": 4677052,"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": 1708037443907.398, "dur": 25.561, + "args": { + "External id": 4677053,"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": 1708037443940.127, "dur": 4.532, + "args": { + "External id": 4677054,"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": 1708037443941.518, "dur": 2.794, + "args": { + "External id": 4677055,"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": 1708037444116.100, "dur": 19.050, + "args": { + "External id": 4677056,"Record function id": 0, "Sequence number": 46526504, "Fwd thread id": 1, "Ev Idx": 1471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444118.370, "dur": 13.938, + "args": { + "External id": 4677057,"Sequence number": 46526504, "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": 1708037444118.370, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037444123.414, "dur": 8.605, + "args": { + "External id": 4677058,"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": 1708037444124.629, "dur": 7.135, + "args": { + "External id": 4677059,"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": 1708037444139.037, "dur": 6.873, + "args": { + "External id": 4677060,"Record function id": 0, "Sequence number": 46526503, "Fwd thread id": 1, "Ev Idx": 1475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444140.123, "dur": 3.269, + "args": { + "External id": 4677061,"Sequence number": 46526503, "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": 1708037444140.123, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037444141.392, "dur": 1.853, + "args": { + "External id": 4677062,"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": 1708037444142.117, "dur": 0.987, + "args": { + "External id": 4677063,"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": 1708037444149.130, "dur": 11.413, + "args": { + "External id": 4677064,"Record function id": 0, "Sequence number": 46526502, "Fwd thread id": 1, "Ev Idx": 1479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444150.192, "dur": 7.216, + "args": { + "External id": 4677065,"Sequence number": 46526502, "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": 1708037444150.192, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037444155.670, "dur": 1.609, + "args": { + "External id": 4677066,"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": 1708037444156.192, "dur": 0.989, + "args": { + "External id": 4677067,"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": 1708037444163.867, "dur": 5.980, + "args": { + "External id": 4677068,"Record function id": 0, "Sequence number": 46526501, "Fwd thread id": 1, "Ev Idx": 1483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444164.903, "dur": 2.813, + "args": { + "External id": 4677069,"Sequence number": 46526501, "Fwd thread 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": 1708037444164.903, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037444165.958, "dur": 1.618, + "args": { + "External id": 4677070,"Record 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": 1708037444166.516, "dur": 0.927, + "args": { + "External id": 4677071,"Record 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": 1708037444173.329, "dur": 155.733, + "args": { + "External id": 4677072,"Record function id": 0, "Sequence number": 46526500, "Fwd thread id": 1, "Ev Idx": 1487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444174.339, "dur": 146.931, + "args": { + "External id": 4677073,"Sequence number": 46526500, "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": 1708037444174.339, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037444179.712, "dur": 10.880, + "args": { + "External id": 4677074,"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": 1708037444183.802, "dur": 6.073, + "args": { + "External id": 4677075,"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": 1708037444187.643, "dur": 1.904, + "args": { + "External id": 4677076,"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": 1708037444192.308, "dur": 67.288, + "args": { + "External id": 4677077,"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": 1708037444261.054, "dur": 4.416, + "args": { + "External id": 4677078,"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": 1708037444261.747, "dur": 2.950, + "args": { + "External id": 4677079,"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": 1708037444263.250, "dur": 1.287, + "args": { + "External id": 4677080,"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": 1708037444267.057, "dur": 5.631, + "args": { + "External id": 4677081,"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": 1708037444270.625, "dur": 1.601, + "args": { + "External id": 4677082,"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": 1708037444271.748, "dur": 0.390, + "args": { + "External id": 4677083,"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": 1708037444273.341, "dur": 47.218, + "args": { + "External id": 4677084,"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": 1708037444333.666, "dur": 9.122, + "args": { + "External id": 4677085,"Record function id": 0, "Sequence number": 46526499, "Fwd thread id": 1, "Ev Idx": 1500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444334.746, "dur": 6.251, + "args": { + "External id": 4677086,"Sequence number": 46526499, "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": 1708037444334.746, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037444338.630, "dur": 2.223, + "args": { + "External id": 4677087,"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": 1708037444339.473, "dur": 1.237, + "args": { + "External id": 4677088,"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": 1708037444346.286, "dur": 9.967, + "args": { + "External id": 4677089,"Record function id": 0, "Sequence number": 46526498, "Fwd thread id": 1, "Ev Idx": 1504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444347.134, "dur": 5.942, + "args": { + "External id": 4677090,"Sequence number": 46526498, "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": 1708037444347.134, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037444350.124, "dur": 2.752, + "args": { + "External id": 4677091,"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": 1708037444350.854, "dur": 1.480, + "args": { + "External id": 4677092,"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": 1708037444351.679, "dur": 0.545, + "args": { + "External id": 4677093,"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": 1708037444362.458, "dur": 9.046, + "args": { + "External id": 4677094,"Record function id": 0, "Ev Idx": 1509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037444364.128, "dur": 6.589, + "args": { + "External id": 4677095,"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": 1708037444366.593, "dur": 3.706, + "args": { + "External id": 4677096,"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": 1708037444367.697, "dur": 2.513, + "args": { + "External id": 4677097,"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": 1708037444374.736, "dur": 11.182, + "args": { + "External id": 4677098,"Record function id": 0, "Sequence number": 46526497, "Fwd thread id": 1, "Ev Idx": 1513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444377.997, "dur": 5.199, + "args": { + "External id": 4677099,"Sequence number": 46526497, "Fwd thread 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": 1708037444377.997, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037444379.447, "dur": 3.585, + "args": { + "External id": 4677100,"Record 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": 1708037444382.128, "dur": 0.767, + "args": { + "External id": 4677101,"Record 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": 1708037444389.259, "dur": 95.164, + "args": { + "External id": 4677102,"Record function id": 0, "Sequence number": 46526496, "Fwd thread id": 1, "Ev Idx": 1517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444390.315, "dur": 88.675, + "args": { + "External id": 4677103,"Sequence number": 46526496, "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": 1708037444390.315, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037444394.192, "dur": 2.783, + "args": { + "External id": 4677104,"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": 1708037444395.027, "dur": 1.536, + "args": { + "External id": 4677105,"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": 1708037444395.894, "dur": 0.509, + "args": { + "External id": 4677106,"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": 1708037444397.815, "dur": 27.953, + "args": { + "External id": 4677107,"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": 1708037444428.770, "dur": 3.382, + "args": { + "External id": 4677108,"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": 1708037444429.430, "dur": 2.158, + "args": { + "External id": 4677109,"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": 1708037444430.339, "dur": 1.119, + "args": { + "External id": 4677110,"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": 1708037444433.887, "dur": 7.629, + "args": { + "External id": 4677111,"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": 1708037444435.298, "dur": 5.679, + "args": { + "External id": 4677112,"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": 1708037444438.245, "dur": 2.649, + "args": { + "External id": 4677113,"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": 1708037444444.577, "dur": 33.582, + "args": { + "External id": 4677114,"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": 1708037444490.740, "dur": 54.468, + "args": { + "External id": 4677115,"Record function id": 0, "Sequence number": 46526495, "Fwd thread id": 1, "Ev Idx": 1530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444491.570, "dur": 7.257, + "args": { + "External id": 4677116,"Sequence number": 46526495, "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": 1708037444491.570, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037444493.004, "dur": 5.672, + "args": { + "External id": 4677117,"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": 1708037444497.485, "dur": 1.052, + "args": { + "External id": 4677118,"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": 1708037444501.577, "dur": 40.420, + "args": { + "External id": 4677119,"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": 1708037444551.449, "dur": 94.700, + "args": { + "External id": 4677120,"Record function id": 0, "Sequence number": 46526494, "Fwd thread id": 1, "Ev Idx": 1535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444631.572, "dur": 10.918, + "args": { + "External id": 4677121,"Sequence number": 46526494, "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": 1708037444631.572, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037444635.686, "dur": 6.578, + "args": { + "External id": 4677122,"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": 1708037444636.980, "dur": 4.548, + "args": { + "External id": 4677123,"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": 1708037444640.593, "dur": 0.846, + "args": { + "External id": 4677124,"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": 1708037444650.828, "dur": 6.482, + "args": { + "External id": 4677125,"Record function id": 0, "Ev Idx": 1540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037444652.058, "dur": 4.744, + "args": { + "External id": 4677126,"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": 1708037444653.606, "dur": 2.699, + "args": { + "External id": 4677127,"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": 1708037444654.258, "dur": 1.919, + "args": { + "External id": 4677128,"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": 1708037444660.497, "dur": 9.149, + "args": { + "External id": 4677129,"Record function id": 0, "Sequence number": 46526493, "Fwd thread id": 1, "Ev Idx": 1544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444661.435, "dur": 5.292, + "args": { + "External id": 4677130,"Sequence number": 46526493, "Fwd thread 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": 1708037444661.435, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037444662.699, "dur": 3.877, + "args": { + "External id": 4677131,"Record 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": 1708037444665.442, "dur": 1.037, + "args": { + "External id": 4677132,"Record 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": 1708037444672.972, "dur": 108.102, + "args": { + "External id": 4677133,"Record function id": 0, "Sequence number": 46526492, "Fwd thread id": 1, "Ev Idx": 1548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444673.807, "dur": 97.694, + "args": { + "External id": 4677134,"Sequence number": 46526492, "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": 1708037444673.807, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037444680.542, "dur": 4.386, + "args": { + "External id": 4677135,"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": 1708037444681.122, "dur": 3.372, + "args": { + "External id": 4677136,"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": 1708037444683.906, "dur": 0.484, + "args": { + "External id": 4677137,"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": 1708037444685.872, "dur": 36.034, + "args": { + "External id": 4677138,"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": 1708037444725.150, "dur": 2.491, + "args": { + "External id": 4677139,"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": 1708037444725.771, "dur": 1.354, + "args": { + "External id": 4677140,"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": 1708037444726.517, "dur": 0.484, + "args": { + "External id": 4677141,"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": 1708037444729.397, "dur": 2.678, + "args": { + "External id": 4677142,"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": 1708037444730.555, "dur": 1.124, + "args": { + "External id": 4677143,"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": 1708037444731.083, "dur": 0.491, + "args": { + "External id": 4677144,"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": 1708037444735.159, "dur": 35.638, + "args": { + "External id": 4677145,"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": 1708037444785.381, "dur": 27.787, + "args": { + "External id": 4677146,"Record function id": 0, "Sequence number": 46526491, "Fwd thread id": 1, "Ev Idx": 1561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444786.563, "dur": 5.306, + "args": { + "External id": 4677147,"Sequence number": 46526491, "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": 1708037444786.563, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037444790.116, "dur": 1.598, + "args": { + "External id": 4677148,"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": 1708037444790.586, "dur": 0.988, + "args": { + "External id": 4677149,"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": 1708037444794.150, "dur": 16.867, + "args": { + "External id": 4677150,"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": 1708037444816.799, "dur": 9.017, + "args": { + "External id": 4677151,"Record function id": 0, "Sequence number": 46526490, "Fwd thread id": 1, "Ev Idx": 1566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336753, "tid": 1381210, + "ts": 1708037444817.744, "dur": 5.900, + "args": { + "External id": 4677152,"Sequence number": 46526490, "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": 1708037444817.744, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336753, "tid": 1381210, + "ts": 1708037444818.601, "dur": 4.823, + "args": { + "External id": 4677153,"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": 1708037444819.365, "dur": 3.531, + "args": { + "External id": 4677154,"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": 1708037444822.396, "dur": 0.411, + "args": { + "External id": 4677155,"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": 1708037444829.794, "dur": 5.339, + "args": { + "External id": 4677156,"Record function id": 0, "Ev Idx": 1571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037444831.180, "dur": 3.479, + "args": { + "External id": 4677157,"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": 1708037444832.259, "dur": 1.877, + "args": { + "External id": 4677158,"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": 1708037444832.872, "dur": 1.161, + "args": { + "External id": 4677159,"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": 1708037444839.247, "dur": 417.709, + "args": { + "External id": 4677160,"Record function id": 0, "Sequence number": 46526489, "Fwd thread id": 1, "Ev Idx": 1575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037444842.672, "dur": 374.134, + "args": { + "External id": 4677161,"Sequence number": 46526489, "Fwd thread 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": 1708037444842.672, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1381210, + "ts": 1708037444876.942, "dur": 1.612, + "args": { + "External id": 4677162,"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": 1708037444877.398, "dur": 1.013, + "args": { + "External id": 4677163,"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": 1708037444897.853, "dur": 5.704, + "args": { + "External id": 4677164,"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": 1708037444912.506, "dur": 2.192, + "args": { + "External id": 4677165,"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": 1708037445104.746, "dur": 2.952, + "args": { + "External id": 4677166,"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": 1708037445111.721, "dur": 40.903, + "args": { + "External id": 4677167,"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": 1708037445125.817, "dur": 1.037, + "args": { + "External id": 4677168,"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": 1708037445158.410, "dur": 33.101, + "args": { + "External id": 4677169,"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": 1708037445160.468, "dur": 30.842, + "args": { + "External id": 4677170,"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": 1708037445164.424, "dur": 4.960, + "args": { + "External id": 4677171,"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": 1708037445173.207, "dur": 17.607, + "args": { + "External id": 4677172,"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": 1708037445196.142, "dur": 4.513, + "args": { + "External id": 4677173,"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": 1708037445199.596, "dur": 0.908, + "args": { + "External id": 4677174,"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": 1708037445208.017, "dur": 1.706, + "args": { + "External id": 4677175,"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": 1708037445208.744, "dur": 0.875, + "args": { + "External id": 4677176,"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": 1708037445234.866, "dur": 16.858, + "args": { + "External id": 4677177,"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": 1708037445268.416, "dur": 9.889, + "args": { + "External id": 4677178,"Record function id": 0, "Ev Idx": 1593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037445270.257, "dur": 7.418, + "args": { + "External id": 4677179,"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": 1708037445272.277, "dur": 4.259, + "args": { + "External id": 4677180,"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": 1708037445274.868, "dur": 1.530, + "args": { + "External id": 4677181,"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": 1708037445282.810, "dur": 2957.780, + "args": { + "External id": 4677182,"Record function id": 0, "Ev Idx": 1597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.27)", "pid": 1336753, "tid": 1381210, + "ts": 1708037445315.503, "dur": 1130.051, + "args": { + "External id": 4677183,"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": 1708037445344.280, "dur": 1090.992, + "args": { + "External id": 4677184,"Record function id": 0, "Ev Idx": 1599 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1708037445360.972, "dur": 1054.860, + "args": { + "External id": 4677185,"Record function id": 0, "Ev Idx": 1600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037445459.395, "dur": 6.700, + "args": { + "External id": 4677186,"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": 1708037445487.895, "dur": 54.587, + "args": { + "External id": 4677187,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037445493.655, "dur": 3.448, + "args": { + "External id": 4677188,"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": 1708037445498.342, "dur": 0.678, + "args": { + "External id": 4677189,"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": 1708037445503.891, "dur": 0.262, + "args": { + "External id": 4677190,"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": 1708037445504.837, "dur": 0.414, + "args": { + "External id": 4677191,"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": 1708037445505.795, "dur": 0.659, + "args": { + "External id": 4677192,"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": 1708037445510.906, "dur": 0.291, + "args": { + "External id": 4677193,"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": 1708037445511.732, "dur": 0.378, + "args": { + "External id": 4677194,"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": 1708037445512.682, "dur": 2.494, + "args": { + "External id": 4677195,"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": 1708037445517.986, "dur": 2.451, + "args": { + "External id": 4677196,"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": 1708037445576.184, "dur": 40.408, + "args": { + "External id": 4677197,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037445664.803, "dur": 128.186, + "args": { + "External id": 4677198,"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": 1708037445679.359, "dur": 8.462, + "args": { + "External id": 4677199,"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": 1708037445696.132, "dur": 10.115, + "args": { + "External id": 4677200,"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": 1708037445700.352, "dur": 5.523, + "args": { + "External id": 4677201,"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": 1708037445703.617, "dur": 0.750, + "args": { + "External id": 4677202,"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": 1708037445714.030, "dur": 34.348, + "args": { + "External id": 4677203,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037445717.750, "dur": 0.394, + "args": { + "External id": 4677204,"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": 1708037445719.025, "dur": 2.474, + "args": { + "External id": 4677205,"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": 1708037445722.354, "dur": 0.261, + "args": { + "External id": 4677206,"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": 1708037445725.805, "dur": 0.517, + "args": { + "External id": 4677207,"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": 1708037445728.958, "dur": 0.321, + "args": { + "External id": 4677208,"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": 1708037445729.925, "dur": 2.163, + "args": { + "External id": 4677209,"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": 1708037445734.925, "dur": 0.407, + "args": { + "External id": 4677210,"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": 1708037445737.910, "dur": 0.382, + "args": { + "External id": 4677211,"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": 1708037445740.698, "dur": 0.456, + "args": { + "External id": 4677212,"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": 1708037445759.583, "dur": 24.991, + "args": { + "External id": 4677213,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037445858.903, "dur": 443.189, + "args": { + "External id": 4677214,"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": 1708037445898.482, "dur": 397.698, + "args": { + "External id": 4677215,"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": 1708037445910.929, "dur": 378.676, + "args": { + "External id": 4677216,"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": 1708037446329.382, "dur": 3.061, + "args": { + "External id": 4677217,"Record function id": 0, "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": 1708037446454.251, "dur": 1754.637, + "args": { + "External id": 4677218,"Sequence number": 46526488, "Fwd thread 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": 1708037446454.251, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708037446610.648, "dur": 109.402, + "args": { + "External id": 4677219,"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": 1708037446770.895, "dur": 46.439, + "args": { + "External id": 4677220,"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": 1708037446836.988, "dur": 46.216, + "args": { + "External id": 4677221,"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": 1708037446893.166, "dur": 32.032, + "args": { + "External id": 4677222,"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": 1708037446931.683, "dur": 44.870, + "args": { + "External id": 4677223,"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": 1708037447021.087, "dur": 34.282, + "args": { + "External id": 4677224,"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": 1708037447069.116, "dur": 43.730, + "args": { + "External id": 4677225,"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": 1708037447145.701, "dur": 27.682, + "args": { + "External id": 4677226,"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": 1708037447194.286, "dur": 33.324, + "args": { + "External id": 4677227,"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": 1708037447256.019, "dur": 23.612, + "args": { + "External id": 4677228,"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": 1708037447296.062, "dur": 20.528, + "args": { + "External id": 4677229,"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": 1708037447326.132, "dur": 28.891, + "args": { + "External id": 4677230,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037447358.211, "dur": 32.753, + "args": { + "External id": 4677231,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037447423.818, "dur": 190.979, + "args": { + "External id": 4677232,"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": 1708037447502.641, "dur": 7.713, + "args": { + "External id": 4677233,"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": 1708037447511.995, "dur": 2.273, + "args": { + "External id": 4677234,"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": 1708037447656.622, "dur": 27.516, + "args": { + "External id": 4677235,"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": 1708037447703.366, "dur": 14.846, + "args": { + "External id": 4677236,"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": 1708037447726.675, "dur": 39.129, + "args": { + "External id": 4677237,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037447771.310, "dur": 33.694, + "args": { + "External id": 4677238,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037447811.580, "dur": 21.466, + "args": { + "External id": 4677239,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037447839.650, "dur": 29.321, + "args": { + "External id": 4677240,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037447877.612, "dur": 20.837, + "args": { + "External id": 4677241,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037447904.784, "dur": 31.611, + "args": { + "External id": 4677242,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037447958.481, "dur": 25.418, + "args": { + "External id": 4677243,"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": 1708037448039.452, "dur": 30.619, + "args": { + "External id": 4677244,"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": 1708037448091.823, "dur": 17.723, + "args": { + "External id": 4677245,"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": 1708037448123.713, "dur": 17.610, + "args": { + "External id": 4677246,"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": 1708037448161.567, "dur": 19.092, + "args": { + "External id": 4677247,"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": 1708037448263.765, "dur": 16.283, + "args": { + "External id": 4677248,"Record function id": 0, "Ev Idx": 1663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037448267.104, "dur": 11.885, + "args": { + "External id": 4677249,"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": 1708037448271.345, "dur": 5.786, + "args": { + "External id": 4677250,"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": 1708037448273.242, "dur": 3.800, + "args": { + "External id": 4677251,"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": 1708037448283.681, "dur": 7.360, + "args": { + "External id": 4677252,"Record function id": 0, "Ev Idx": 1667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037448287.246, "dur": 3.292, + "args": { + "External id": 4677253,"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": 1708037448288.196, "dur": 1.655, + "args": { + "External id": 4677254,"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": 1708037448288.999, "dur": 0.750, + "args": { + "External id": 4677255,"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": 1708037448294.176, "dur": 4.872, + "args": { + "External id": 4677256,"Record function id": 0, "Ev Idx": 1671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037448295.643, "dur": 2.988, + "args": { + "External id": 4677257,"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": 1708037448296.314, "dur": 1.674, + "args": { + "External id": 4677258,"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": 1708037448297.015, "dur": 0.846, + "args": { + "External id": 4677259,"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": 1708037448302.171, "dur": 6.190, + "args": { + "External id": 4677260,"Record function id": 0, "Ev Idx": 1675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037448303.031, "dur": 4.886, + "args": { + "External id": 4677261,"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": 1708037448303.683, "dur": 3.629, + "args": { + "External id": 4677262,"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": 1708037448304.347, "dur": 2.882, + "args": { + "External id": 4677263,"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": 1708037448311.288, "dur": 5.035, + "args": { + "External id": 4677264,"Record function id": 0, "Ev Idx": 1679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037448312.972, "dur": 2.925, + "args": { + "External id": 4677265,"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": 1708037448313.810, "dur": 1.502, + "args": { + "External id": 4677266,"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": 1708037448314.409, "dur": 0.791, + "args": { + "External id": 4677267,"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": 1708037448319.239, "dur": 4.239, + "args": { + "External id": 4677268,"Record function id": 0, "Ev Idx": 1683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037448320.436, "dur": 2.636, + "args": { + "External id": 4677269,"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": 1708037448321.109, "dur": 1.304, + "args": { + "External id": 4677270,"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": 1708037448321.558, "dur": 0.742, + "args": { + "External id": 4677271,"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": 1708037448326.619, "dur": 4.261, + "args": { + "External id": 4677272,"Record function id": 0, "Ev Idx": 1687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037448327.907, "dur": 2.554, + "args": { + "External id": 4677273,"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": 1708037448328.646, "dur": 1.398, + "args": { + "External id": 4677274,"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": 1708037448329.193, "dur": 0.746, + "args": { + "External id": 4677275,"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": 1708037448333.812, "dur": 5.963, + "args": { + "External id": 4677276,"Record function id": 0, "Ev Idx": 1691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037448334.964, "dur": 4.395, + "args": { + "External id": 4677277,"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": 1708037448335.419, "dur": 3.295, + "args": { + "External id": 4677278,"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": 1708037448337.987, "dur": 0.634, + "args": { + "External id": 4677279,"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": 1708037448344.746, "dur": 4.192, + "args": { + "External id": 4677280,"Record function id": 0, "Ev Idx": 1695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037448345.945, "dur": 2.565, + "args": { + "External id": 4677281,"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": 1708037448346.412, "dur": 1.663, + "args": { + "External id": 4677282,"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": 1708037448347.081, "dur": 0.892, + "args": { + "External id": 4677283,"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": 1708037448353.681, "dur": 172113.811, + "args": { + "External id": 4677284,"Record function id": 0, "Sequence number": 46526487, "Fwd thread id": 1, "Ev Idx": 1699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037448355.385, "dur": 172103.471, + "args": { + "External id": 4677285,"Sequence number": 46526487, "Fwd thread 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": 1708037448355.385, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.27)", "pid": 1336753, "tid": 1381210, + "ts": 1708037448391.118, "dur": 44.726, + "args": { + "External id": 4677286,"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": 1708037448443.846, "dur": 112.535, + "args": { + "External id": 4677287,"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": 1708037448565.520, "dur": 171885.549, + "args": { + "External id": 4677288,"Record function id": 0, "Ev Idx": 1703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037448629.183, "dur": 8.153, + "args": { + "External id": 4677289,"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": 1708037448649.274, "dur": 5.037, + "args": { + "External id": 4677290,"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": 1708037448674.513, "dur": 170956.972, + "args": { + "External id": 4677291,"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": 1708037448691.271, "dur": 170926.692, + "args": { + "External id": 4677292,"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": 1708037448776.577, "dur": 5.613, + "args": { + "External id": 4677293,"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": 1708037448795.586, "dur": 170770.249, + "args": { + "External id": 4677294,"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": 1708037448797.887, "dur": 170766.876, + "args": { + "External id": 4677295,"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": 1708037448801.228, "dur": 8.093, + "args": { + "External id": 4677296,"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": 1708037448810.940, "dur": 170749.249, + "args": { + "External id": 4677297,"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": 1708037619743.668, "dur": 12.116, + "args": { + "External id": 4677298,"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": 1708037619747.514, "dur": 7.828, + "args": { + "External id": 4677299,"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": 1708037619796.116, "dur": 327.674, + "args": { + "External id": 4677300,"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": 1708037619831.090, "dur": 287.882, + "args": { + "External id": 4677301,"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": 1708037619846.016, "dur": 267.268, + "args": { + "External id": 4677302,"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": 1708037620148.199, "dur": 2.459, + "args": { + "External id": 4677303,"Record function id": 0, "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": 1708037620211.732, "dur": 6.640, + "args": { + "External id": 4677304,"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": 1708037620278.046, "dur": 1.614, + "args": { + "External id": 4677305,"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": 1708037620297.454, "dur": 1.155, + "args": { + "External id": 4677306,"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": 1708037620315.477, "dur": 1.214, + "args": { + "External id": 4677307,"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": 1708037620328.211, "dur": 1.143, + "args": { + "External id": 4677308,"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": 1708037620339.120, "dur": 0.707, + "args": { + "External id": 4677309,"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": 1708037620352.905, "dur": 1.374, + "args": { + "External id": 4677310,"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": 1708037620369.485, "dur": 2.585, + "args": { + "External id": 4677311,"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": 1708037620383.909, "dur": 1.074, + "args": { + "External id": 4677312,"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": 1708037620480.839, "dur": 2908.830, + "args": { + "External id": 4677313,"Record function id": 0, "Ev Idx": 1728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1708037620501.036, "dur": 1155.133, + "args": { + "External id": 4677314,"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": 1708037620517.630, "dur": 369.837, + "args": { + "External id": 4677315,"Record function id": 0, "Ev Idx": 1730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708037620626.324, "dur": 4.394, + "args": { + "External id": 4677316,"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": 1708037620634.482, "dur": 0.985, + "args": { + "External id": 4677317,"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": 1708037620637.011, "dur": 1.160, + "args": { + "External id": 4677318,"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": 1708037620639.664, "dur": 2.880, + "args": { + "External id": 4677319,"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": 1708037620646.349, "dur": 0.954, + "args": { + "External id": 4677320,"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": 1708037620648.557, "dur": 1.036, + "args": { + "External id": 4677321,"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": 1708037620650.994, "dur": 2.973, + "args": { + "External id": 4677322,"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": 1708037620655.940, "dur": 1.067, + "args": { + "External id": 4677323,"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": 1708037620662.677, "dur": 0.793, + "args": { + "External id": 4677324,"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": 1708037620664.829, "dur": 0.794, + "args": { + "External id": 4677325,"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": 1708037620687.967, "dur": 169.432, + "args": { + "External id": 4677326,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037620709.751, "dur": 143.786, + "args": { + "External id": 4677327,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037620735.675, "dur": 12.062, + "args": { + "External id": 4677328,"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": 1708037620751.777, "dur": 70.542, + "args": { + "External id": 4677329,"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": 1708037620756.223, "dur": 65.763, + "args": { + "External id": 4677330,"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": 1708037620759.477, "dur": 9.300, + "args": { + "External id": 4677331,"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": 1708037620770.552, "dur": 50.885, + "args": { + "External id": 4677332,"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": 1708037620980.535, "dur": 667.478, + "args": { + "External id": 4677333,"Record function id": 0, "Ev Idx": 1748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1708037621033.654, "dur": 601.198, + "args": { + "External id": 4677334,"Record function id": 0, "Ev Idx": 1749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037621102.204, "dur": 6.268, + "args": { + "External id": 4677335,"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": 1708037621124.274, "dur": 44.042, + "args": { + "External id": 4677336,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037621130.876, "dur": 3.198, + "args": { + "External id": 4677337,"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": 1708037621135.294, "dur": 0.590, + "args": { + "External id": 4677338,"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": 1708037621136.721, "dur": 0.514, + "args": { + "External id": 4677339,"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": 1708037621142.341, "dur": 0.486, + "args": { + "External id": 4677340,"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": 1708037621143.430, "dur": 0.598, + "args": { + "External id": 4677341,"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": 1708037621144.677, "dur": 0.507, + "args": { + "External id": 4677342,"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": 1708037621149.910, "dur": 2.649, + "args": { + "External id": 4677343,"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": 1708037621153.043, "dur": 0.490, + "args": { + "External id": 4677344,"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": 1708037621156.205, "dur": 5.229, + "args": { + "External id": 4677345,"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": 1708037621192.378, "dur": 36.414, + "args": { + "External id": 4677346,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037621261.180, "dur": 112.824, + "args": { + "External id": 4677347,"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": 1708037621271.102, "dur": 5.547, + "args": { + "External id": 4677348,"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": 1708037621281.714, "dur": 11.757, + "args": { + "External id": 4677349,"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": 1708037621285.749, "dur": 7.316, + "args": { + "External id": 4677350,"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": 1708037621290.875, "dur": 0.603, + "args": { + "External id": 4677351,"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": 1708037621299.969, "dur": 30.699, + "args": { + "External id": 4677352,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037621301.248, "dur": 0.496, + "args": { + "External id": 4677353,"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": 1708037621304.476, "dur": 2.001, + "args": { + "External id": 4677354,"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": 1708037621307.491, "dur": 0.364, + "args": { + "External id": 4677355,"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": 1708037621308.434, "dur": 2.763, + "args": { + "External id": 4677356,"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": 1708037621316.004, "dur": 0.410, + "args": { + "External id": 4677357,"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": 1708037621316.893, "dur": 0.449, + "args": { + "External id": 4677358,"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": 1708037621319.841, "dur": 0.252, + "args": { + "External id": 4677359,"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": 1708037621322.721, "dur": 0.520, + "args": { + "External id": 4677360,"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": 1708037621323.827, "dur": 0.463, + "args": { + "External id": 4677361,"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": 1708037621344.900, "dur": 20.846, + "args": { + "External id": 4677362,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037621416.422, "dur": 142.786, + "args": { + "External id": 4677363,"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": 1708037621446.703, "dur": 108.699, + "args": { + "External id": 4677364,"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": 1708037621457.967, "dur": 92.575, + "args": { + "External id": 4677365,"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": 1708037621580.407, "dur": 1.959, + "args": { + "External id": 4677366,"Record function id": 0, "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": 1708037621664.398, "dur": 1701.965, + "args": { + "External id": 4677367,"Sequence number": 46526486, "Fwd thread 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": 1708037621664.398, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708037621774.650, "dur": 100.792, + "args": { + "External id": 4677368,"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": 1708037621921.062, "dur": 45.804, + "args": { + "External id": 4677369,"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": 1708037622022.377, "dur": 56.768, + "args": { + "External id": 4677370,"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": 1708037622091.313, "dur": 34.531, + "args": { + "External id": 4677371,"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": 1708037622134.674, "dur": 45.338, + "args": { + "External id": 4677372,"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": 1708037622186.655, "dur": 27.825, + "args": { + "External id": 4677373,"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": 1708037622221.513, "dur": 41.617, + "args": { + "External id": 4677374,"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": 1708037622289.546, "dur": 25.491, + "args": { + "External id": 4677375,"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": 1708037622339.818, "dur": 27.967, + "args": { + "External id": 4677376,"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": 1708037622390.968, "dur": 20.757, + "args": { + "External id": 4677377,"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": 1708037622430.268, "dur": 17.020, + "args": { + "External id": 4677378,"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": 1708037622455.416, "dur": 31.207, + "args": { + "External id": 4677379,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037622489.556, "dur": 31.056, + "args": { + "External id": 4677380,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037622569.051, "dur": 175.723, + "args": { + "External id": 4677381,"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": 1708037622652.479, "dur": 5.694, + "args": { + "External id": 4677382,"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": 1708037622659.897, "dur": 2.162, + "args": { + "External id": 4677383,"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": 1708037622790.977, "dur": 25.338, + "args": { + "External id": 4677384,"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": 1708037622830.132, "dur": 14.564, + "args": { + "External id": 4677385,"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": 1708037622852.666, "dur": 39.415, + "args": { + "External id": 4677386,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037622898.048, "dur": 33.571, + "args": { + "External id": 4677387,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037622953.652, "dur": 65.200, + "args": { + "External id": 4677388,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037623028.298, "dur": 38.654, + "args": { + "External id": 4677389,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037623074.470, "dur": 22.136, + "args": { + "External id": 4677390,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037623102.989, "dur": 31.816, + "args": { + "External id": 4677391,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037623157.899, "dur": 28.490, + "args": { + "External id": 4677392,"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": 1708037623207.320, "dur": 27.334, + "args": { + "External id": 4677393,"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": 1708037623253.099, "dur": 17.574, + "args": { + "External id": 4677394,"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": 1708037623290.664, "dur": 16.129, + "args": { + "External id": 4677395,"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": 1708037623321.107, "dur": 16.589, + "args": { + "External id": 4677396,"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": 1708037623411.671, "dur": 14.037, + "args": { + "External id": 4677397,"Record function id": 0, "Ev Idx": 1812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037623414.633, "dur": 10.184, + "args": { + "External id": 4677398,"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": 1708037623418.544, "dur": 5.343, + "args": { + "External id": 4677399,"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": 1708037623419.909, "dur": 3.856, + "args": { + "External id": 4677400,"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": 1708037623429.796, "dur": 4.575, + "args": { + "External id": 4677401,"Record function id": 0, "Ev Idx": 1816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037623430.888, "dur": 3.044, + "args": { + "External id": 4677402,"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": 1708037623431.939, "dur": 1.515, + "args": { + "External id": 4677403,"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": 1708037623432.569, "dur": 0.785, + "args": { + "External id": 4677404,"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": 1708037623437.747, "dur": 6.422, + "args": { + "External id": 4677405,"Record function id": 0, "Ev Idx": 1820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037623438.870, "dur": 4.829, + "args": { + "External id": 4677406,"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": 1708037623439.447, "dur": 3.816, + "args": { + "External id": 4677407,"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": 1708037623439.878, "dur": 3.252, + "args": { + "External id": 4677408,"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": 1708037623447.429, "dur": 4.684, + "args": { + "External id": 4677409,"Record function id": 0, "Ev Idx": 1824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037623448.894, "dur": 2.793, + "args": { + "External id": 4677410,"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": 1708037623449.672, "dur": 1.361, + "args": { + "External id": 4677411,"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": 1708037623450.007, "dur": 0.932, + "args": { + "External id": 4677412,"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": 1708037623455.460, "dur": 4.092, + "args": { + "External id": 4677413,"Record function id": 0, "Ev Idx": 1828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037623456.636, "dur": 2.487, + "args": { + "External id": 4677414,"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": 1708037623457.603, "dur": 1.080, + "args": { + "External id": 4677415,"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": 1708037623457.871, "dur": 0.709, + "args": { + "External id": 4677416,"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": 1708037623462.993, "dur": 6.322, + "args": { + "External id": 4677417,"Record function id": 0, "Ev Idx": 1832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037623465.898, "dur": 2.949, + "args": { + "External id": 4677418,"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": 1708037623467.002, "dur": 1.065, + "args": { + "External id": 4677419,"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": 1708037623467.417, "dur": 0.544, + "args": { + "External id": 4677420,"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": 1708037623472.676, "dur": 3.483, + "args": { + "External id": 4677421,"Record function id": 0, "Ev Idx": 1836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037623473.591, "dur": 2.120, + "args": { + "External id": 4677422,"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": 1708037623474.051, "dur": 1.001, + "args": { + "External id": 4677423,"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": 1708037623474.346, "dur": 0.610, + "args": { + "External id": 4677424,"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": 1708037623479.336, "dur": 5.802, + "args": { + "External id": 4677425,"Record function id": 0, "Ev Idx": 1840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037623480.301, "dur": 4.425, + "args": { + "External id": 4677426,"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": 1708037623480.939, "dur": 3.347, + "args": { + "External id": 4677427,"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": 1708037623483.558, "dur": 0.626, + "args": { + "External id": 4677428,"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": 1708037623488.264, "dur": 3.421, + "args": { + "External id": 4677429,"Record function id": 0, "Ev Idx": 1844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037623489.212, "dur": 2.053, + "args": { + "External id": 4677430,"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": 1708037623489.755, "dur": 1.113, + "args": { + "External id": 4677431,"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": 1708037623490.078, "dur": 0.689, + "args": { + "External id": 4677432,"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": 1708037623495.551, "dur": 38482.562, + "args": { + "External id": 4677433,"Record function id": 0, "Sequence number": 46526485, "Fwd thread id": 1, "Ev Idx": 1848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037623497.097, "dur": 38472.681, + "args": { + "External id": 4677434,"Sequence number": 46526485, "Fwd thread 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": 1708037623497.097, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.26)", "pid": 1336753, "tid": 1381210, + "ts": 1708037623539.371, "dur": 38.920, + "args": { + "External id": 4677435,"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": 1708037623586.699, "dur": 65.090, + "args": { + "External id": 4677436,"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": 1708037623659.952, "dur": 38302.171, + "args": { + "External id": 4677437,"Record function id": 0, "Ev Idx": 1852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037623750.785, "dur": 7.142, + "args": { + "External id": 4677438,"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": 1708037623767.566, "dur": 7.217, + "args": { + "External id": 4677439,"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": 1708037623793.106, "dur": 37366.651, + "args": { + "External id": 4677440,"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": 1708037623806.478, "dur": 37343.807, + "args": { + "External id": 4677441,"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": 1708037623877.342, "dur": 12.952, + "args": { + "External id": 4677442,"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": 1708037623900.158, "dur": 37212.074, + "args": { + "External id": 4677443,"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": 1708037623902.544, "dur": 37208.960, + "args": { + "External id": 4677444,"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": 1708037623907.696, "dur": 5.290, + "args": { + "External id": 4677445,"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": 1708037623914.663, "dur": 37193.558, + "args": { + "External id": 4677446,"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": 1708037661247.886, "dur": 8.183, + "args": { + "External id": 4677447,"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": 1708037661250.387, "dur": 5.365, + "args": { + "External id": 4677448,"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": 1708037661283.849, "dur": 384.537, + "args": { + "External id": 4677449,"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": 1708037661317.464, "dur": 345.801, + "args": { + "External id": 4677450,"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": 1708037661330.152, "dur": 327.600, + "args": { + "External id": 4677451,"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": 1708037661691.730, "dur": 2.291, + "args": { + "External id": 4677452,"Record function id": 0, "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": 1708037661753.733, "dur": 6.204, + "args": { + "External id": 4677453,"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": 1708037661802.406, "dur": 1.674, + "args": { + "External id": 4677454,"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": 1708037661820.389, "dur": 3.590, + "args": { + "External id": 4677455,"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": 1708037661837.970, "dur": 1.253, + "args": { + "External id": 4677456,"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": 1708037661850.082, "dur": 0.803, + "args": { + "External id": 4677457,"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": 1708037661861.847, "dur": 0.874, + "args": { + "External id": 4677458,"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": 1708037661872.728, "dur": 3.361, + "args": { + "External id": 4677459,"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": 1708037661886.454, "dur": 3.101, + "args": { + "External id": 4677460,"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": 1708037661902.708, "dur": 0.995, + "args": { + "External id": 4677461,"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": 1708037662041.548, "dur": 2859.042, + "args": { + "External id": 4677462,"Record function id": 0, "Ev Idx": 1877 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1708037662063.161, "dur": 1122.202, + "args": { + "External id": 4677463,"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": 1708037662077.655, "dur": 326.257, + "args": { + "External id": 4677464,"Record function id": 0, "Ev Idx": 1879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708037662164.072, "dur": 4.932, + "args": { + "External id": 4677465,"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": 1708037662171.794, "dur": 1.477, + "args": { + "External id": 4677466,"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": 1708037662174.968, "dur": 3.209, + "args": { + "External id": 4677467,"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": 1708037662179.708, "dur": 1.188, + "args": { + "External id": 4677468,"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": 1708037662184.353, "dur": 0.959, + "args": { + "External id": 4677469,"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": 1708037662186.731, "dur": 1.205, + "args": { + "External id": 4677470,"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": 1708037662192.054, "dur": 2.801, + "args": { + "External id": 4677471,"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": 1708037662196.206, "dur": 1.096, + "args": { + "External id": 4677472,"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": 1708037662200.743, "dur": 0.838, + "args": { + "External id": 4677473,"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": 1708037662202.890, "dur": 0.790, + "args": { + "External id": 4677474,"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": 1708037662221.179, "dur": 152.265, + "args": { + "External id": 4677475,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037662238.891, "dur": 130.364, + "args": { + "External id": 4677476,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037662257.979, "dur": 16.253, + "args": { + "External id": 4677477,"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": 1708037662277.766, "dur": 64.750, + "args": { + "External id": 4677478,"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": 1708037662282.486, "dur": 59.741, + "args": { + "External id": 4677479,"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": 1708037662285.668, "dur": 5.150, + "args": { + "External id": 4677480,"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": 1708037662292.322, "dur": 49.137, + "args": { + "External id": 4677481,"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": 1708037662493.115, "dur": 682.963, + "args": { + "External id": 4677482,"Record function id": 0, "Ev Idx": 1897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1708037662508.054, "dur": 651.722, + "args": { + "External id": 4677483,"Record function id": 0, "Ev Idx": 1898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037662585.094, "dur": 6.082, + "args": { + "External id": 4677484,"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": 1708037662605.938, "dur": 37.127, + "args": { + "External id": 4677485,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037662612.595, "dur": 1.685, + "args": { + "External id": 4677486,"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": 1708037662617.399, "dur": 0.544, + "args": { + "External id": 4677487,"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": 1708037662618.546, "dur": 0.342, + "args": { + "External id": 4677488,"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": 1708037662620.994, "dur": 2.165, + "args": { + "External id": 4677489,"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": 1708037662623.915, "dur": 0.518, + "args": { + "External id": 4677490,"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": 1708037662626.579, "dur": 2.319, + "args": { + "External id": 4677491,"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": 1708037662631.928, "dur": 0.417, + "args": { + "External id": 4677492,"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": 1708037662632.993, "dur": 0.307, + "args": { + "External id": 4677493,"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": 1708037662636.119, "dur": 0.285, + "args": { + "External id": 4677494,"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": 1708037662652.907, "dur": 33.966, + "args": { + "External id": 4677495,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037662716.236, "dur": 151.230, + "args": { + "External id": 4677496,"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": 1708037662725.368, "dur": 3.423, + "args": { + "External id": 4677497,"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": 1708037662733.937, "dur": 12.195, + "args": { + "External id": 4677498,"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": 1708037662737.854, "dur": 7.814, + "args": { + "External id": 4677499,"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": 1708037662742.281, "dur": 2.085, + "args": { + "External id": 4677500,"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": 1708037662752.460, "dur": 71.899, + "args": { + "External id": 4677501,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037662753.663, "dur": 0.304, + "args": { + "External id": 4677502,"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": 1708037662756.746, "dur": 0.424, + "args": { + "External id": 4677503,"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": 1708037662798.891, "dur": 3.087, + "args": { + "External id": 4677504,"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": 1708037662806.614, "dur": 0.368, + "args": { + "External id": 4677505,"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": 1708037662807.737, "dur": 0.316, + "args": { + "External id": 4677506,"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": 1708037662808.651, "dur": 2.426, + "args": { + "External id": 4677507,"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": 1708037662813.792, "dur": 0.384, + "args": { + "External id": 4677508,"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": 1708037662814.792, "dur": 0.356, + "args": { + "External id": 4677509,"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": 1708037662817.701, "dur": 0.316, + "args": { + "External id": 4677510,"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": 1708037662837.053, "dur": 22.361, + "args": { + "External id": 4677511,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037662911.225, "dur": 174.552, + "args": { + "External id": 4677512,"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": 1708037662942.134, "dur": 139.696, + "args": { + "External id": 4677513,"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": 1708037662951.107, "dur": 125.381, + "args": { + "External id": 4677514,"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": 1708037663103.362, "dur": 1.982, + "args": { + "External id": 4677515,"Record function id": 0, "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": 1708037663193.076, "dur": 1682.179, + "args": { + "External id": 4677516,"Sequence number": 46526484, "Fwd thread 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": 1708037663193.076, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708037663308.800, "dur": 98.497, + "args": { + "External id": 4677517,"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": 1708037663448.198, "dur": 42.469, + "args": { + "External id": 4677518,"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": 1708037663506.216, "dur": 67.811, + "args": { + "External id": 4677519,"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": 1708037663587.199, "dur": 33.267, + "args": { + "External id": 4677520,"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": 1708037663629.093, "dur": 44.709, + "args": { + "External id": 4677521,"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": 1708037663680.251, "dur": 27.174, + "args": { + "External id": 4677522,"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": 1708037663723.070, "dur": 41.810, + "args": { + "External id": 4677523,"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": 1708037663794.128, "dur": 28.427, + "args": { + "External id": 4677524,"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": 1708037663848.795, "dur": 29.431, + "args": { + "External id": 4677525,"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": 1708037663900.976, "dur": 23.682, + "args": { + "External id": 4677526,"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": 1708037663941.899, "dur": 15.563, + "args": { + "External id": 4677527,"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": 1708037663966.610, "dur": 67.889, + "args": { + "External id": 4677528,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037664039.770, "dur": 34.859, + "args": { + "External id": 4677529,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037664105.721, "dur": 171.050, + "args": { + "External id": 4677530,"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": 1708037664183.718, "dur": 8.954, + "args": { + "External id": 4677531,"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": 1708037664194.433, "dur": 2.094, + "args": { + "External id": 4677532,"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": 1708037664313.930, "dur": 27.794, + "args": { + "External id": 4677533,"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": 1708037664355.961, "dur": 15.196, + "args": { + "External id": 4677534,"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": 1708037664379.375, "dur": 36.089, + "args": { + "External id": 4677535,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037664420.735, "dur": 34.064, + "args": { + "External id": 4677536,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037664463.252, "dur": 22.580, + "args": { + "External id": 4677537,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037664490.027, "dur": 64.828, + "args": { + "External id": 4677538,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037664572.454, "dur": 29.767, + "args": { + "External id": 4677539,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037664609.192, "dur": 35.475, + "args": { + "External id": 4677540,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037664669.071, "dur": 29.994, + "args": { + "External id": 4677541,"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": 1708037664720.025, "dur": 27.757, + "args": { + "External id": 4677542,"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": 1708037664764.493, "dur": 18.943, + "args": { + "External id": 4677543,"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": 1708037664802.456, "dur": 16.280, + "args": { + "External id": 4677544,"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": 1708037664832.379, "dur": 15.769, + "args": { + "External id": 4677545,"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": 1708037664922.847, "dur": 14.526, + "args": { + "External id": 4677546,"Record function id": 0, "Ev Idx": 1961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037664925.978, "dur": 10.437, + "args": { + "External id": 4677547,"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": 1708037664929.746, "dur": 5.729, + "args": { + "External id": 4677548,"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": 1708037664931.225, "dur": 4.126, + "args": { + "External id": 4677549,"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": 1708037664941.535, "dur": 6.045, + "args": { + "External id": 4677550,"Record function id": 0, "Ev Idx": 1965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037664944.331, "dur": 2.750, + "args": { + "External id": 4677551,"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": 1708037664945.215, "dur": 1.388, + "args": { + "External id": 4677552,"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": 1708037664945.675, "dur": 0.802, + "args": { + "External id": 4677553,"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": 1708037664950.827, "dur": 6.783, + "args": { + "External id": 4677554,"Record function id": 0, "Ev Idx": 1969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037664952.039, "dur": 5.142, + "args": { + "External id": 4677555,"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": 1708037664952.696, "dur": 3.821, + "args": { + "External id": 4677556,"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": 1708037664953.513, "dur": 2.932, + "args": { + "External id": 4677557,"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": 1708037664960.897, "dur": 4.598, + "args": { + "External id": 4677558,"Record function id": 0, "Ev Idx": 1973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037664962.120, "dur": 2.962, + "args": { + "External id": 4677559,"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": 1708037664963.053, "dur": 1.495, + "args": { + "External id": 4677560,"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": 1708037664963.582, "dur": 0.860, + "args": { + "External id": 4677561,"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": 1708037664968.694, "dur": 3.828, + "args": { + "External id": 4677562,"Record function id": 0, "Ev Idx": 1977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037664969.902, "dur": 2.208, + "args": { + "External id": 4677563,"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": 1708037664970.626, "dur": 1.074, + "args": { + "External id": 4677564,"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": 1708037664970.999, "dur": 0.599, + "args": { + "External id": 4677565,"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": 1708037664975.588, "dur": 3.746, + "args": { + "External id": 4677566,"Record function id": 0, "Ev Idx": 1981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037664976.608, "dur": 2.297, + "args": { + "External id": 4677567,"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": 1708037664977.185, "dur": 1.009, + "args": { + "External id": 4677568,"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": 1708037664977.578, "dur": 0.512, + "args": { + "External id": 4677569,"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": 1708037665017.229, "dur": 8.316, + "args": { + "External id": 4677570,"Record function id": 0, "Ev Idx": 1985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037665019.233, "dur": 5.608, + "args": { + "External id": 4677571,"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": 1708037665020.210, "dur": 3.849, + "args": { + "External id": 4677572,"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": 1708037665022.569, "dur": 1.251, + "args": { + "External id": 4677573,"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": 1708037665029.118, "dur": 4.010, + "args": { + "External id": 4677574,"Record function id": 0, "Ev Idx": 1989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037665030.210, "dur": 2.528, + "args": { + "External id": 4677575,"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": 1708037665030.910, "dur": 1.297, + "args": { + "External id": 4677576,"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": 1708037665031.529, "dur": 0.563, + "args": { + "External id": 4677577,"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": 1708037665036.185, "dur": 4.037, + "args": { + "External id": 4677578,"Record function id": 0, "Ev Idx": 1993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037665037.484, "dur": 2.314, + "args": { + "External id": 4677579,"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": 1708037665037.939, "dur": 1.292, + "args": { + "External id": 4677580,"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": 1708037665038.290, "dur": 0.837, + "args": { + "External id": 4677581,"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": 1708037665044.258, "dur": 37045.877, + "args": { + "External id": 4677582,"Record function id": 0, "Sequence number": 46526483, "Fwd thread id": 1, "Ev Idx": 1997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037665045.536, "dur": 37034.890, + "args": { + "External id": 4677583,"Sequence number": 46526483, "Fwd thread 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": 1708037665045.536, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.25)", "pid": 1336753, "tid": 1381210, + "ts": 1708037665076.277, "dur": 37.476, + "args": { + "External id": 4677584,"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": 1708037665121.862, "dur": 70.169, + "args": { + "External id": 4677585,"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": 1708037665201.573, "dur": 36869.991, + "args": { + "External id": 4677586,"Record function id": 0, "Ev Idx": 2001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037665289.820, "dur": 7.266, + "args": { + "External id": 4677587,"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": 1708037665307.539, "dur": 6.697, + "args": { + "External id": 4677588,"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": 1708037665327.961, "dur": 35849.304, + "args": { + "External id": 4677589,"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": 1708037665341.069, "dur": 35824.633, + "args": { + "External id": 4677590,"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": 1708037665397.673, "dur": 12.671, + "args": { + "External id": 4677591,"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": 1708037665418.610, "dur": 35699.952, + "args": { + "External id": 4677592,"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": 1708037665421.062, "dur": 35696.324, + "args": { + "External id": 4677593,"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": 1708037665424.306, "dur": 6.791, + "args": { + "External id": 4677594,"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": 1708037665432.757, "dur": 35679.694, + "args": { + "External id": 4677595,"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": 1708037701277.305, "dur": 10.077, + "args": { + "External id": 4677596,"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": 1708037701280.416, "dur": 6.635, + "args": { + "External id": 4677597,"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": 1708037701316.620, "dur": 409.664, + "args": { + "External id": 4677598,"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": 1708037701350.252, "dur": 371.021, + "args": { + "External id": 4677599,"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": 1708037701361.691, "dur": 353.456, + "args": { + "External id": 4677600,"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": 1708037701750.613, "dur": 2.422, + "args": { + "External id": 4677601,"Record function id": 0, "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": 1708037701812.134, "dur": 6.704, + "args": { + "External id": 4677602,"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": 1708037701863.007, "dur": 1.514, + "args": { + "External id": 4677603,"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": 1708037701883.350, "dur": 1.433, + "args": { + "External id": 4677604,"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": 1708037701899.750, "dur": 1.089, + "args": { + "External id": 4677605,"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": 1708037701911.041, "dur": 1.061, + "args": { + "External id": 4677606,"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": 1708037701921.917, "dur": 0.814, + "args": { + "External id": 4677607,"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": 1708037701935.363, "dur": 1.021, + "args": { + "External id": 4677608,"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": 1708037701951.700, "dur": 2.981, + "args": { + "External id": 4677609,"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": 1708037701963.760, "dur": 1.013, + "args": { + "External id": 4677610,"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": 1708037702106.595, "dur": 2849.518, + "args": { + "External id": 4677611,"Record function id": 0, "Ev Idx": 2026 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1708037702125.146, "dur": 1147.968, + "args": { + "External id": 4677612,"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": 1708037702141.246, "dur": 319.489, + "args": { + "External id": 4677613,"Record function id": 0, "Ev Idx": 2028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708037702225.951, "dur": 4.616, + "args": { + "External id": 4677614,"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": 1708037702233.618, "dur": 1.417, + "args": { + "External id": 4677615,"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": 1708037702238.857, "dur": 1.110, + "args": { + "External id": 4677616,"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": 1708037702241.262, "dur": 3.265, + "args": { + "External id": 4677617,"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": 1708037702245.987, "dur": 1.290, + "args": { + "External id": 4677618,"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": 1708037702248.387, "dur": 0.901, + "args": { + "External id": 4677619,"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": 1708037702252.533, "dur": 3.921, + "args": { + "External id": 4677620,"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": 1708037702257.747, "dur": 1.145, + "args": { + "External id": 4677621,"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": 1708037702262.103, "dur": 0.913, + "args": { + "External id": 4677622,"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": 1708037702264.309, "dur": 1.102, + "args": { + "External id": 4677623,"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": 1708037702285.005, "dur": 149.521, + "args": { + "External id": 4677624,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037702302.462, "dur": 128.221, + "args": { + "External id": 4677625,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037702323.155, "dur": 11.638, + "args": { + "External id": 4677626,"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": 1708037702337.974, "dur": 66.026, + "args": { + "External id": 4677627,"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": 1708037702340.678, "dur": 62.962, + "args": { + "External id": 4677628,"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": 1708037702344.022, "dur": 9.391, + "args": { + "External id": 4677629,"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": 1708037702354.830, "dur": 48.014, + "args": { + "External id": 4677630,"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": 1708037702565.674, "dur": 698.689, + "args": { + "External id": 4677631,"Record function id": 0, "Ev Idx": 2046 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1708037702581.819, "dur": 668.195, + "args": { + "External id": 4677632,"Record function id": 0, "Ev Idx": 2047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037702725.954, "dur": 6.989, + "args": { + "External id": 4677633,"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": 1708037702749.430, "dur": 34.986, + "args": { + "External id": 4677634,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037702756.241, "dur": 3.529, + "args": { + "External id": 4677635,"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": 1708037702760.869, "dur": 0.304, + "args": { + "External id": 4677636,"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": 1708037702761.727, "dur": 0.392, + "args": { + "External id": 4677637,"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": 1708037702766.348, "dur": 0.291, + "args": { + "External id": 4677638,"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": 1708037702767.133, "dur": 0.388, + "args": { + "External id": 4677639,"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": 1708037702767.979, "dur": 0.384, + "args": { + "External id": 4677640,"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": 1708037702771.783, "dur": 2.267, + "args": { + "External id": 4677641,"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": 1708037702774.604, "dur": 0.271, + "args": { + "External id": 4677642,"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": 1708037702775.939, "dur": 1.754, + "args": { + "External id": 4677643,"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": 1708037702795.098, "dur": 35.392, + "args": { + "External id": 4677644,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037702862.396, "dur": 107.775, + "args": { + "External id": 4677645,"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": 1708037702872.325, "dur": 3.937, + "args": { + "External id": 4677646,"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": 1708037702881.322, "dur": 9.460, + "args": { + "External id": 4677647,"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": 1708037702885.329, "dur": 5.030, + "args": { + "External id": 4677648,"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": 1708037702888.623, "dur": 0.460, + "args": { + "External id": 4677649,"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": 1708037702897.241, "dur": 31.087, + "args": { + "External id": 4677650,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037702899.388, "dur": 0.430, + "args": { + "External id": 4677651,"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": 1708037702901.342, "dur": 0.390, + "args": { + "External id": 4677652,"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": 1708037702902.948, "dur": 2.226, + "args": { + "External id": 4677653,"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": 1708037702906.640, "dur": 2.248, + "args": { + "External id": 4677654,"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": 1708037702910.218, "dur": 0.443, + "args": { + "External id": 4677655,"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": 1708037702914.434, "dur": 0.387, + "args": { + "External id": 4677656,"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": 1708037702916.214, "dur": 0.276, + "args": { + "External id": 4677657,"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": 1708037702917.987, "dur": 0.316, + "args": { + "External id": 4677658,"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": 1708037702921.520, "dur": 0.398, + "args": { + "External id": 4677659,"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": 1708037702943.198, "dur": 19.151, + "args": { + "External id": 4677660,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037703057.120, "dur": 121.471, + "args": { + "External id": 4677661,"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": 1708037703086.844, "dur": 88.118, + "args": { + "External id": 4677662,"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": 1708037703096.608, "dur": 73.732, + "args": { + "External id": 4677663,"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": 1708037703195.512, "dur": 1.612, + "args": { + "External id": 4677664,"Record function id": 0, "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": 1708037703281.331, "dur": 1651.326, + "args": { + "External id": 4677665,"Sequence number": 46526482, "Fwd thread 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": 1708037703281.331, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708037703391.572, "dur": 99.162, + "args": { + "External id": 4677666,"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": 1708037703556.359, "dur": 47.469, + "args": { + "External id": 4677667,"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": 1708037703622.537, "dur": 52.285, + "args": { + "External id": 4677668,"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": 1708037703688.131, "dur": 31.425, + "args": { + "External id": 4677669,"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": 1708037703728.424, "dur": 48.381, + "args": { + "External id": 4677670,"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": 1708037703784.114, "dur": 27.999, + "args": { + "External id": 4677671,"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": 1708037703819.642, "dur": 41.956, + "args": { + "External id": 4677672,"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": 1708037703888.490, "dur": 23.011, + "args": { + "External id": 4677673,"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": 1708037703935.200, "dur": 27.063, + "args": { + "External id": 4677674,"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": 1708037704015.204, "dur": 25.547, + "args": { + "External id": 4677675,"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": 1708037704061.028, "dur": 16.516, + "args": { + "External id": 4677676,"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": 1708037704086.594, "dur": 34.595, + "args": { + "External id": 4677677,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037704124.455, "dur": 32.546, + "args": { + "External id": 4677678,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037704189.942, "dur": 172.482, + "args": { + "External id": 4677679,"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": 1708037704269.633, "dur": 5.969, + "args": { + "External id": 4677680,"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": 1708037704277.448, "dur": 2.360, + "args": { + "External id": 4677681,"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": 1708037704397.414, "dur": 25.536, + "args": { + "External id": 4677682,"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": 1708037704434.946, "dur": 13.880, + "args": { + "External id": 4677683,"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": 1708037704455.937, "dur": 33.620, + "args": { + "External id": 4677684,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037704494.890, "dur": 65.523, + "args": { + "External id": 4677685,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037704580.226, "dur": 28.718, + "args": { + "External id": 4677686,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037704615.720, "dur": 32.597, + "args": { + "External id": 4677687,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037704653.308, "dur": 20.472, + "args": { + "External id": 4677688,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037704683.060, "dur": 32.900, + "args": { + "External id": 4677689,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037704736.755, "dur": 24.745, + "args": { + "External id": 4677690,"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": 1708037704782.754, "dur": 25.720, + "args": { + "External id": 4677691,"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": 1708037704824.825, "dur": 16.793, + "args": { + "External id": 4677692,"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": 1708037704859.851, "dur": 16.155, + "args": { + "External id": 4677693,"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": 1708037704890.624, "dur": 16.436, + "args": { + "External id": 4677694,"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": 1708037704978.048, "dur": 59.944, + "args": { + "External id": 4677695,"Record function id": 0, "Ev Idx": 2110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037705024.045, "dur": 12.268, + "args": { + "External id": 4677696,"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": 1708037705028.882, "dur": 5.946, + "args": { + "External id": 4677697,"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": 1708037705030.382, "dur": 4.179, + "args": { + "External id": 4677698,"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": 1708037705044.641, "dur": 5.475, + "args": { + "External id": 4677699,"Record function id": 0, "Ev Idx": 2114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037705046.553, "dur": 3.148, + "args": { + "External id": 4677700,"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": 1708037705047.705, "dur": 1.534, + "args": { + "External id": 4677701,"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": 1708037705048.377, "dur": 0.756, + "args": { + "External id": 4677702,"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": 1708037705053.609, "dur": 5.226, + "args": { + "External id": 4677703,"Record function id": 0, "Ev Idx": 2118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037705055.139, "dur": 3.251, + "args": { + "External id": 4677704,"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": 1708037705056.120, "dur": 1.826, + "args": { + "External id": 4677705,"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": 1708037705057.037, "dur": 0.843, + "args": { + "External id": 4677706,"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": 1708037705062.076, "dur": 6.461, + "args": { + "External id": 4677707,"Record function id": 0, "Ev Idx": 2122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037705063.580, "dur": 4.523, + "args": { + "External id": 4677708,"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": 1708037705064.334, "dur": 3.245, + "args": { + "External id": 4677709,"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": 1708037705064.927, "dur": 2.585, + "args": { + "External id": 4677710,"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": 1708037705071.870, "dur": 4.226, + "args": { + "External id": 4677711,"Record function id": 0, "Ev Idx": 2126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037705073.201, "dur": 2.487, + "args": { + "External id": 4677712,"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": 1708037705073.913, "dur": 1.250, + "args": { + "External id": 4677713,"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": 1708037705074.234, "dur": 0.865, + "args": { + "External id": 4677714,"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": 1708037705079.167, "dur": 4.290, + "args": { + "External id": 4677715,"Record function id": 0, "Ev Idx": 2130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037705080.624, "dur": 2.419, + "args": { + "External id": 4677716,"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": 1708037705081.078, "dur": 1.548, + "args": { + "External id": 4677717,"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": 1708037705081.671, "dur": 0.881, + "args": { + "External id": 4677718,"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": 1708037705086.752, "dur": 6.841, + "args": { + "External id": 4677719,"Record function id": 0, "Ev Idx": 2134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037705088.357, "dur": 4.806, + "args": { + "External id": 4677720,"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": 1708037705088.886, "dur": 3.852, + "args": { + "External id": 4677721,"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": 1708037705091.687, "dur": 0.984, + "args": { + "External id": 4677722,"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": 1708037705096.730, "dur": 4.594, + "args": { + "External id": 4677723,"Record function id": 0, "Ev Idx": 2138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037705098.189, "dur": 2.722, + "args": { + "External id": 4677724,"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": 1708037705098.993, "dur": 1.265, + "args": { + "External id": 4677725,"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": 1708037705099.621, "dur": 0.562, + "args": { + "External id": 4677726,"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": 1708037705104.379, "dur": 4.225, + "args": { + "External id": 4677727,"Record function id": 0, "Ev Idx": 2142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037705105.433, "dur": 2.739, + "args": { + "External id": 4677728,"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": 1708037705106.344, "dur": 1.186, + "args": { + "External id": 4677729,"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": 1708037705106.855, "dur": 0.606, + "args": { + "External id": 4677730,"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": 1708037705112.670, "dur": 36978.250, + "args": { + "External id": 4677731,"Record function id": 0, "Sequence number": 46526481, "Fwd thread id": 1, "Ev Idx": 2146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037705114.121, "dur": 36967.389, + "args": { + "External id": 4677732,"Sequence number": 46526481, "Fwd thread 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": 1708037705114.121, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.24)", "pid": 1336753, "tid": 1381210, + "ts": 1708037705142.277, "dur": 36.426, + "args": { + "External id": 4677733,"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": 1708037705186.532, "dur": 65.179, + "args": { + "External id": 4677734,"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": 1708037705260.035, "dur": 36812.412, + "args": { + "External id": 4677735,"Record function id": 0, "Ev Idx": 2150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037705354.735, "dur": 7.724, + "args": { + "External id": 4677736,"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": 1708037705372.210, "dur": 5.009, + "args": { + "External id": 4677737,"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": 1708037705391.136, "dur": 35838.446, + "args": { + "External id": 4677738,"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": 1708037705405.488, "dur": 35815.500, + "args": { + "External id": 4677739,"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": 1708037705462.512, "dur": 14.776, + "args": { + "External id": 4677740,"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": 1708037705484.187, "dur": 35698.143, + "args": { + "External id": 4677741,"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": 1708037705487.398, "dur": 35694.259, + "args": { + "External id": 4677742,"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": 1708037705491.416, "dur": 4.922, + "args": { + "External id": 4677743,"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": 1708037705498.000, "dur": 35680.250, + "args": { + "External id": 4677744,"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": 1708037741320.956, "dur": 8.153, + "args": { + "External id": 4677745,"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": 1708037741323.877, "dur": 4.932, + "args": { + "External id": 4677746,"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": 1708037741359.156, "dur": 365.373, + "args": { + "External id": 4677747,"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": 1708037741390.172, "dur": 329.311, + "args": { + "External id": 4677748,"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": 1708037741400.116, "dur": 313.691, + "args": { + "External id": 4677749,"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": 1708037741748.580, "dur": 2.221, + "args": { + "External id": 4677750,"Record function id": 0, "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": 1708037741807.737, "dur": 6.753, + "args": { + "External id": 4677751,"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": 1708037741860.448, "dur": 1.567, + "args": { + "External id": 4677752,"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": 1708037741879.270, "dur": 1.381, + "args": { + "External id": 4677753,"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": 1708037741892.984, "dur": 3.337, + "args": { + "External id": 4677754,"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": 1708037741909.595, "dur": 1.096, + "args": { + "External id": 4677755,"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": 1708037741921.984, "dur": 0.966, + "args": { + "External id": 4677756,"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": 1708037741934.911, "dur": 0.914, + "args": { + "External id": 4677757,"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": 1708037741947.736, "dur": 5.475, + "args": { + "External id": 4677758,"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": 1708037741966.615, "dur": 1.044, + "args": { + "External id": 4677759,"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": 1708037742106.955, "dur": 2809.988, + "args": { + "External id": 4677760,"Record function id": 0, "Ev Idx": 2175 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1708037742126.060, "dur": 1052.887, + "args": { + "External id": 4677761,"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": 1708037742141.082, "dur": 323.046, + "args": { + "External id": 4677762,"Record function id": 0, "Ev Idx": 2177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708037742228.513, "dur": 4.486, + "args": { + "External id": 4677763,"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": 1708037742236.090, "dur": 1.274, + "args": { + "External id": 4677764,"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": 1708037742239.413, "dur": 1.314, + "args": { + "External id": 4677765,"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": 1708037742242.650, "dur": 0.971, + "args": { + "External id": 4677766,"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": 1708037742247.806, "dur": 2.944, + "args": { + "External id": 4677767,"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": 1708037742252.465, "dur": 1.388, + "args": { + "External id": 4677768,"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": 1708037742255.822, "dur": 2.265, + "args": { + "External id": 4677769,"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": 1708037742259.481, "dur": 0.793, + "args": { + "External id": 4677770,"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": 1708037742263.494, "dur": 0.585, + "args": { + "External id": 4677771,"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": 1708037742265.586, "dur": 1.144, + "args": { + "External id": 4677772,"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": 1708037742283.913, "dur": 150.195, + "args": { + "External id": 4677773,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037742299.785, "dur": 130.332, + "args": { + "External id": 4677774,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037742319.534, "dur": 13.707, + "args": { + "External id": 4677775,"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": 1708037742336.361, "dur": 65.638, + "args": { + "External id": 4677776,"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": 1708037742339.294, "dur": 62.417, + "args": { + "External id": 4677777,"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": 1708037742343.015, "dur": 4.820, + "args": { + "External id": 4677778,"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": 1708037742351.714, "dur": 49.233, + "args": { + "External id": 4677779,"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": 1708037742579.577, "dur": 591.311, + "args": { + "External id": 4677780,"Record function id": 0, "Ev Idx": 2195 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1708037742597.700, "dur": 560.779, + "args": { + "External id": 4677781,"Record function id": 0, "Ev Idx": 2196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037742661.678, "dur": 7.390, + "args": { + "External id": 4677782,"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": 1708037742684.747, "dur": 33.375, + "args": { + "External id": 4677783,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037742690.029, "dur": 1.525, + "args": { + "External id": 4677784,"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": 1708037742694.557, "dur": 0.346, + "args": { + "External id": 4677785,"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": 1708037742696.318, "dur": 0.416, + "args": { + "External id": 4677786,"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": 1708037742698.363, "dur": 1.552, + "args": { + "External id": 4677787,"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": 1708037742701.473, "dur": 0.236, + "args": { + "External id": 4677788,"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": 1708037742703.486, "dur": 0.544, + "args": { + "External id": 4677789,"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": 1708037742706.688, "dur": 0.295, + "args": { + "External id": 4677790,"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": 1708037742708.652, "dur": 2.436, + "args": { + "External id": 4677791,"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": 1708037742712.670, "dur": 0.321, + "args": { + "External id": 4677792,"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": 1708037742728.771, "dur": 32.671, + "args": { + "External id": 4677793,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037742792.665, "dur": 96.287, + "args": { + "External id": 4677794,"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": 1708037742802.161, "dur": 3.512, + "args": { + "External id": 4677795,"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": 1708037742810.946, "dur": 10.646, + "args": { + "External id": 4677796,"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": 1708037742814.712, "dur": 6.422, + "args": { + "External id": 4677797,"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": 1708037742818.482, "dur": 1.493, + "args": { + "External id": 4677798,"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": 1708037742828.229, "dur": 25.922, + "args": { + "External id": 4677799,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037742830.722, "dur": 0.455, + "args": { + "External id": 4677800,"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": 1708037742832.635, "dur": 0.610, + "args": { + "External id": 4677801,"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": 1708037742834.672, "dur": 0.451, + "args": { + "External id": 4677802,"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": 1708037742838.094, "dur": 0.251, + "args": { + "External id": 4677803,"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": 1708037742840.170, "dur": 2.043, + "args": { + "External id": 4677804,"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": 1708037742843.788, "dur": 0.740, + "args": { + "External id": 4677805,"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": 1708037742845.768, "dur": 0.511, + "args": { + "External id": 4677806,"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": 1708037742847.495, "dur": 0.351, + "args": { + "External id": 4677807,"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": 1708037742849.531, "dur": 0.649, + "args": { + "External id": 4677808,"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": 1708037742863.497, "dur": 18.535, + "args": { + "External id": 4677809,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037742931.830, "dur": 154.057, + "args": { + "External id": 4677810,"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": 1708037742960.036, "dur": 122.344, + "args": { + "External id": 4677811,"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": 1708037742968.474, "dur": 109.239, + "args": { + "External id": 4677812,"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": 1708037743105.828, "dur": 2.303, + "args": { + "External id": 4677813,"Record function id": 0, "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": 1708037743187.216, "dur": 1706.564, + "args": { + "External id": 4677814,"Sequence number": 46526480, "Fwd thread 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": 1708037743187.216, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708037743294.579, "dur": 98.554, + "args": { + "External id": 4677815,"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": 1708037743434.482, "dur": 42.036, + "args": { + "External id": 4677816,"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": 1708037743492.215, "dur": 67.481, + "args": { + "External id": 4677817,"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": 1708037743572.949, "dur": 36.623, + "args": { + "External id": 4677818,"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": 1708037743618.804, "dur": 48.325, + "args": { + "External id": 4677819,"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": 1708037743675.011, "dur": 30.567, + "args": { + "External id": 4677820,"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": 1708037743712.448, "dur": 41.514, + "args": { + "External id": 4677821,"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": 1708037743780.335, "dur": 25.318, + "args": { + "External id": 4677822,"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": 1708037743826.181, "dur": 27.053, + "args": { + "External id": 4677823,"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": 1708037743875.890, "dur": 20.661, + "args": { + "External id": 4677824,"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": 1708037743908.921, "dur": 16.902, + "args": { + "External id": 4677825,"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": 1708037743937.169, "dur": 29.804, + "args": { + "External id": 4677826,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037743970.401, "dur": 95.837, + "args": { + "External id": 4677827,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037744103.734, "dur": 185.868, + "args": { + "External id": 4677828,"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": 1708037744191.749, "dur": 6.472, + "args": { + "External id": 4677829,"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": 1708037744200.241, "dur": 2.102, + "args": { + "External id": 4677830,"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": 1708037744324.719, "dur": 26.043, + "args": { + "External id": 4677831,"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": 1708037744362.723, "dur": 15.379, + "args": { + "External id": 4677832,"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": 1708037744386.556, "dur": 41.599, + "args": { + "External id": 4677833,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037744435.140, "dur": 34.971, + "args": { + "External id": 4677834,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037744488.389, "dur": 24.078, + "args": { + "External id": 4677835,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037744520.022, "dur": 63.788, + "args": { + "External id": 4677836,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037744602.280, "dur": 29.224, + "args": { + "External id": 4677837,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037744640.041, "dur": 31.626, + "args": { + "External id": 4677838,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037744694.329, "dur": 25.782, + "args": { + "External id": 4677839,"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": 1708037744737.967, "dur": 30.098, + "args": { + "External id": 4677840,"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": 1708037744783.096, "dur": 17.429, + "args": { + "External id": 4677841,"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": 1708037744816.223, "dur": 18.289, + "args": { + "External id": 4677842,"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": 1708037744848.692, "dur": 16.654, + "args": { + "External id": 4677843,"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": 1708037744940.009, "dur": 14.989, + "args": { + "External id": 4677844,"Record function id": 0, "Ev Idx": 2259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037744943.544, "dur": 10.535, + "args": { + "External id": 4677845,"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": 1708037744947.091, "dur": 5.813, + "args": { + "External id": 4677846,"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": 1708037744948.822, "dur": 3.960, + "args": { + "External id": 4677847,"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": 1708037744959.015, "dur": 5.287, + "args": { + "External id": 4677848,"Record function id": 0, "Ev Idx": 2263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037744960.414, "dur": 3.413, + "args": { + "External id": 4677849,"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": 1708037744961.228, "dur": 1.830, + "args": { + "External id": 4677850,"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": 1708037744961.972, "dur": 0.983, + "args": { + "External id": 4677851,"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": 1708037744967.582, "dur": 4.866, + "args": { + "External id": 4677852,"Record function id": 0, "Ev Idx": 2267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037744969.037, "dur": 3.012, + "args": { + "External id": 4677853,"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": 1708037744970.011, "dur": 1.431, + "args": { + "External id": 4677854,"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": 1708037744970.482, "dur": 0.885, + "args": { + "External id": 4677855,"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": 1708037744975.677, "dur": 38.581, + "args": { + "External id": 4677856,"Record function id": 0, "Ev Idx": 2271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037744976.901, "dur": 35.591, + "args": { + "External id": 4677857,"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": 1708037744977.462, "dur": 2.988, + "args": { + "External id": 4677858,"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": 1708037744977.907, "dur": 2.476, + "args": { + "External id": 4677859,"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": 1708037745020.265, "dur": 5.835, + "args": { + "External id": 4677860,"Record function id": 0, "Ev Idx": 2275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037745022.019, "dur": 3.643, + "args": { + "External id": 4677861,"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": 1708037745023.206, "dur": 2.051, + "args": { + "External id": 4677862,"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": 1708037745023.878, "dur": 1.308, + "args": { + "External id": 4677863,"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": 1708037745029.280, "dur": 4.963, + "args": { + "External id": 4677864,"Record function id": 0, "Ev Idx": 2279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037745031.030, "dur": 2.756, + "args": { + "External id": 4677865,"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": 1708037745031.591, "dur": 1.620, + "args": { + "External id": 4677866,"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": 1708037745032.486, "dur": 0.620, + "args": { + "External id": 4677867,"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": 1708037745037.635, "dur": 4.602, + "args": { + "External id": 4677868,"Record function id": 0, "Ev Idx": 2283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037745038.997, "dur": 2.811, + "args": { + "External id": 4677869,"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": 1708037745039.737, "dur": 1.551, + "args": { + "External id": 4677870,"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": 1708037745040.270, "dur": 0.940, + "args": { + "External id": 4677871,"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": 1708037745045.388, "dur": 4.757, + "args": { + "External id": 4677872,"Record function id": 0, "Ev Idx": 2287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037745046.861, "dur": 2.865, + "args": { + "External id": 4677873,"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": 1708037745047.819, "dur": 1.315, + "args": { + "External id": 4677874,"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": 1708037745048.285, "dur": 0.733, + "args": { + "External id": 4677875,"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": 1708037745053.351, "dur": 4.366, + "args": { + "External id": 4677876,"Record function id": 0, "Ev Idx": 2291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037745054.896, "dur": 2.372, + "args": { + "External id": 4677877,"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": 1708037745055.333, "dur": 1.394, + "args": { + "External id": 4677878,"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": 1708037745055.977, "dur": 0.637, + "args": { + "External id": 4677879,"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": 1708037745061.702, "dur": 36675.574, + "args": { + "External id": 4677880,"Record function id": 0, "Sequence number": 46526479, "Fwd thread id": 1, "Ev Idx": 2295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037745063.075, "dur": 36665.490, + "args": { + "External id": 4677881,"Sequence number": 46526479, "Fwd thread 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": 1708037745063.075, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.23)", "pid": 1336753, "tid": 1381210, + "ts": 1708037745094.264, "dur": 38.573, + "args": { + "External id": 4677882,"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": 1708037745140.439, "dur": 66.386, + "args": { + "External id": 4677883,"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": 1708037745212.149, "dur": 36508.064, + "args": { + "External id": 4677884,"Record function id": 0, "Ev Idx": 2299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037745307.411, "dur": 6.366, + "args": { + "External id": 4677885,"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": 1708037745322.791, "dur": 4.669, + "args": { + "External id": 4677886,"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": 1708037745341.866, "dur": 35689.810, + "args": { + "External id": 4677887,"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": 1708037745354.940, "dur": 35667.920, + "args": { + "External id": 4677888,"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": 1708037745406.549, "dur": 15.376, + "args": { + "External id": 4677889,"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": 1708037745428.220, "dur": 35529.850, + "args": { + "External id": 4677890,"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": 1708037745430.983, "dur": 35526.355, + "args": { + "External id": 4677891,"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": 1708037745434.936, "dur": 5.170, + "args": { + "External id": 4677892,"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": 1708037745441.908, "dur": 35512.397, + "args": { + "External id": 4677893,"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": 1708037781123.988, "dur": 8.806, + "args": { + "External id": 4677894,"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": 1708037781127.261, "dur": 5.131, + "args": { + "External id": 4677895,"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": 1708037781163.305, "dur": 240.658, + "args": { + "External id": 4677896,"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": 1708037781189.274, "dur": 210.373, + "args": { + "External id": 4677897,"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": 1708037781200.323, "dur": 193.879, + "args": { + "External id": 4677898,"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": 1708037781421.867, "dur": 1.895, + "args": { + "External id": 4677899,"Record function id": 0, "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": 1708037781473.256, "dur": 6.080, + "args": { + "External id": 4677900,"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": 1708037781523.115, "dur": 17.507, + "args": { + "External id": 4677901,"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": 1708037781564.066, "dur": 1.200, + "args": { + "External id": 4677902,"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": 1708037781581.529, "dur": 1.200, + "args": { + "External id": 4677903,"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": 1708037781597.011, "dur": 1.206, + "args": { + "External id": 4677904,"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": 1708037781609.427, "dur": 1.061, + "args": { + "External id": 4677905,"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": 1708037781622.817, "dur": 0.918, + "args": { + "External id": 4677906,"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": 1708037781639.513, "dur": 1.850, + "args": { + "External id": 4677907,"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": 1708037781656.378, "dur": 0.907, + "args": { + "External id": 4677908,"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": 1708037781752.936, "dur": 2849.490, + "args": { + "External id": 4677909,"Record function id": 0, "Ev Idx": 2324 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1708037781773.018, "dur": 1069.306, + "args": { + "External id": 4677910,"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": 1708037781788.971, "dur": 366.957, + "args": { + "External id": 4677911,"Record function id": 0, "Ev Idx": 2326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708037781873.416, "dur": 4.418, + "args": { + "External id": 4677912,"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": 1708037781880.738, "dur": 1.375, + "args": { + "External id": 4677913,"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": 1708037781883.946, "dur": 1.091, + "args": { + "External id": 4677914,"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": 1708037781886.762, "dur": 3.115, + "args": { + "External id": 4677915,"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": 1708037781891.610, "dur": 1.530, + "args": { + "External id": 4677916,"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": 1708037781894.857, "dur": 0.831, + "args": { + "External id": 4677917,"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": 1708037781897.428, "dur": 1.796, + "args": { + "External id": 4677918,"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": 1708037781900.948, "dur": 1.228, + "args": { + "External id": 4677919,"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": 1708037781903.834, "dur": 1.263, + "args": { + "External id": 4677920,"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": 1708037781906.603, "dur": 1.155, + "args": { + "External id": 4677921,"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": 1708037781925.460, "dur": 194.443, + "args": { + "External id": 4677922,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037781940.450, "dur": 174.513, + "args": { + "External id": 4677923,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037781962.697, "dur": 10.916, + "args": { + "External id": 4677924,"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": 1708037781976.929, "dur": 106.969, + "args": { + "External id": 4677925,"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": 1708037781979.868, "dur": 103.559, + "args": { + "External id": 4677926,"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": 1708037782020.184, "dur": 9.765, + "args": { + "External id": 4677927,"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": 1708037782032.153, "dur": 50.693, + "args": { + "External id": 4677928,"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": 1708037782254.392, "dur": 579.015, + "args": { + "External id": 4677929,"Record function id": 0, "Ev Idx": 2344 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1708037782271.426, "dur": 545.965, + "args": { + "External id": 4677930,"Record function id": 0, "Ev Idx": 2345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037782335.854, "dur": 4.899, + "args": { + "External id": 4677931,"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": 1708037782355.965, "dur": 34.960, + "args": { + "External id": 4677932,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037782361.170, "dur": 1.565, + "args": { + "External id": 4677933,"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": 1708037782365.165, "dur": 0.618, + "args": { + "External id": 4677934,"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": 1708037782367.681, "dur": 0.520, + "args": { + "External id": 4677935,"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": 1708037782369.889, "dur": 0.649, + "args": { + "External id": 4677936,"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": 1708037782372.749, "dur": 0.578, + "args": { + "External id": 4677937,"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": 1708037782375.225, "dur": 0.581, + "args": { + "External id": 4677938,"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": 1708037782377.582, "dur": 2.435, + "args": { + "External id": 4677939,"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": 1708037782381.956, "dur": 0.606, + "args": { + "External id": 4677940,"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": 1708037782384.776, "dur": 0.291, + "args": { + "External id": 4677941,"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": 1708037782406.664, "dur": 32.408, + "args": { + "External id": 4677942,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037782471.763, "dur": 122.896, + "args": { + "External id": 4677943,"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": 1708037782481.531, "dur": 2.891, + "args": { + "External id": 4677944,"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": 1708037782489.571, "dur": 10.033, + "args": { + "External id": 4677945,"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": 1708037782493.817, "dur": 5.372, + "args": { + "External id": 4677946,"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": 1708037782497.608, "dur": 0.464, + "args": { + "External id": 4677947,"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": 1708037782506.999, "dur": 43.941, + "args": { + "External id": 4677948,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037782509.164, "dur": 0.669, + "args": { + "External id": 4677949,"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": 1708037782511.433, "dur": 0.452, + "args": { + "External id": 4677950,"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": 1708037782513.799, "dur": 0.842, + "args": { + "External id": 4677951,"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": 1708037782516.508, "dur": 2.225, + "args": { + "External id": 4677952,"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": 1708037782520.645, "dur": 0.283, + "args": { + "External id": 4677953,"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": 1708037782522.710, "dur": 0.591, + "args": { + "External id": 4677954,"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": 1708037782541.053, "dur": 0.664, + "args": { + "External id": 4677955,"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": 1708037782543.356, "dur": 0.508, + "args": { + "External id": 4677956,"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": 1708037782545.757, "dur": 0.347, + "args": { + "External id": 4677957,"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": 1708037782564.857, "dur": 22.141, + "args": { + "External id": 4677958,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037782640.825, "dur": 109.132, + "args": { + "External id": 4677959,"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": 1708037782662.298, "dur": 84.117, + "args": { + "External id": 4677960,"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": 1708037782671.882, "dur": 70.219, + "args": { + "External id": 4677961,"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": 1708037782764.969, "dur": 1.793, + "args": { + "External id": 4677962,"Record function id": 0, "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": 1708037782849.847, "dur": 1730.467, + "args": { + "External id": 4677963,"Sequence number": 46526478, "Fwd thread 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": 1708037782849.847, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708037782955.331, "dur": 140.613, + "args": { + "External id": 4677964,"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": 1708037783140.291, "dur": 43.746, + "args": { + "External id": 4677965,"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": 1708037783203.204, "dur": 52.356, + "args": { + "External id": 4677966,"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": 1708037783265.454, "dur": 34.920, + "args": { + "External id": 4677967,"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": 1708037783310.038, "dur": 46.640, + "args": { + "External id": 4677968,"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": 1708037783364.643, "dur": 31.828, + "args": { + "External id": 4677969,"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": 1708037783404.188, "dur": 41.917, + "args": { + "External id": 4677970,"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": 1708037783471.069, "dur": 22.820, + "args": { + "External id": 4677971,"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": 1708037783537.909, "dur": 32.581, + "args": { + "External id": 4677972,"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": 1708037783595.178, "dur": 20.411, + "args": { + "External id": 4677973,"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": 1708037783630.465, "dur": 17.329, + "args": { + "External id": 4677974,"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": 1708037783659.140, "dur": 35.739, + "args": { + "External id": 4677975,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037783698.465, "dur": 34.038, + "args": { + "External id": 4677976,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037783760.834, "dur": 171.522, + "args": { + "External id": 4677977,"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": 1708037783839.564, "dur": 5.595, + "args": { + "External id": 4677978,"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": 1708037783847.159, "dur": 2.159, + "args": { + "External id": 4677979,"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": 1708037783964.903, "dur": 73.497, + "args": { + "External id": 4677980,"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": 1708037784052.757, "dur": 17.168, + "args": { + "External id": 4677981,"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": 1708037784080.189, "dur": 42.162, + "args": { + "External id": 4677982,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037784129.524, "dur": 36.829, + "args": { + "External id": 4677983,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037784175.394, "dur": 23.624, + "args": { + "External id": 4677984,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037784205.256, "dur": 48.117, + "args": { + "External id": 4677985,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037784266.601, "dur": 24.032, + "args": { + "External id": 4677986,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037784299.302, "dur": 30.455, + "args": { + "External id": 4677987,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037784351.036, "dur": 23.594, + "args": { + "External id": 4677988,"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": 1708037784391.941, "dur": 29.755, + "args": { + "External id": 4677989,"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": 1708037784437.484, "dur": 21.616, + "args": { + "External id": 4677990,"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": 1708037784476.089, "dur": 16.722, + "args": { + "External id": 4677991,"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": 1708037784516.021, "dur": 32.989, + "args": { + "External id": 4677992,"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": 1708037784625.243, "dur": 15.525, + "args": { + "External id": 4677993,"Record function id": 0, "Ev Idx": 2408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037784628.581, "dur": 11.285, + "args": { + "External id": 4677994,"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": 1708037784632.888, "dur": 6.046, + "args": { + "External id": 4677995,"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": 1708037784634.681, "dur": 4.133, + "args": { + "External id": 4677996,"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": 1708037784644.663, "dur": 5.730, + "args": { + "External id": 4677997,"Record function id": 0, "Ev Idx": 2412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037784646.207, "dur": 3.745, + "args": { + "External id": 4677998,"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": 1708037784647.336, "dur": 2.116, + "args": { + "External id": 4677999,"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": 1708037784648.102, "dur": 1.286, + "args": { + "External id": 4678000,"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": 1708037784653.626, "dur": 7.405, + "args": { + "External id": 4678001,"Record function id": 0, "Ev Idx": 2416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037784655.515, "dur": 5.103, + "args": { + "External id": 4678002,"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": 1708037784656.406, "dur": 3.638, + "args": { + "External id": 4678003,"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": 1708037784656.773, "dur": 3.174, + "args": { + "External id": 4678004,"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": 1708037784664.349, "dur": 5.223, + "args": { + "External id": 4678005,"Record function id": 0, "Ev Idx": 2420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037784666.197, "dur": 2.963, + "args": { + "External id": 4678006,"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": 1708037784666.849, "dur": 1.795, + "args": { + "External id": 4678007,"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": 1708037784667.556, "dur": 1.011, + "args": { + "External id": 4678008,"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": 1708037784673.365, "dur": 4.780, + "args": { + "External id": 4678009,"Record function id": 0, "Ev Idx": 2424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037784674.953, "dur": 2.753, + "args": { + "External id": 4678010,"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": 1708037784675.781, "dur": 1.265, + "args": { + "External id": 4678011,"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": 1708037784676.272, "dur": 0.700, + "args": { + "External id": 4678012,"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": 1708037784681.462, "dur": 4.780, + "args": { + "External id": 4678013,"Record function id": 0, "Ev Idx": 2428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037784682.843, "dur": 2.993, + "args": { + "External id": 4678014,"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": 1708037784683.827, "dur": 1.304, + "args": { + "External id": 4678015,"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": 1708037784684.285, "dur": 0.739, + "args": { + "External id": 4678016,"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": 1708037784689.518, "dur": 3.858, + "args": { + "External id": 4678017,"Record function id": 0, "Ev Idx": 2432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037784690.883, "dur": 2.079, + "args": { + "External id": 4678018,"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": 1708037784691.345, "dur": 1.213, + "args": { + "External id": 4678019,"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": 1708037784691.645, "dur": 0.813, + "args": { + "External id": 4678020,"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": 1708037784696.545, "dur": 4.331, + "args": { + "External id": 4678021,"Record function id": 0, "Ev Idx": 2436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037784697.751, "dur": 2.693, + "args": { + "External id": 4678022,"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": 1708037784698.802, "dur": 1.098, + "args": { + "External id": 4678023,"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": 1708037784699.104, "dur": 0.723, + "args": { + "External id": 4678024,"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": 1708037784704.047, "dur": 3.997, + "args": { + "External id": 4678025,"Record function id": 0, "Ev Idx": 2440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037784705.064, "dur": 2.569, + "args": { + "External id": 4678026,"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": 1708037784705.496, "dur": 1.468, + "args": { + "External id": 4678027,"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": 1708037784706.184, "dur": 0.699, + "args": { + "External id": 4678028,"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": 1708037784712.296, "dur": 37338.043, + "args": { + "External id": 4678029,"Record function id": 0, "Sequence number": 46526477, "Fwd thread id": 1, "Ev Idx": 2444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037784713.395, "dur": 37327.061, + "args": { + "External id": 4678030,"Sequence number": 46526477, "Fwd thread 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": 1708037784713.395, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.22)", "pid": 1336753, "tid": 1381210, + "ts": 1708037784742.022, "dur": 36.345, + "args": { + "External id": 4678031,"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": 1708037784786.288, "dur": 67.500, + "args": { + "External id": 4678032,"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": 1708037784860.225, "dur": 37170.651, + "args": { + "External id": 4678033,"Record function id": 0, "Ev Idx": 2448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037784945.752, "dur": 6.679, + "args": { + "External id": 4678034,"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": 1708037784962.097, "dur": 6.226, + "args": { + "External id": 4678035,"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": 1708037784982.800, "dur": 36164.438, + "args": { + "External id": 4678036,"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": 1708037785030.947, "dur": 36107.234, + "args": { + "External id": 4678037,"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": 1708037785129.967, "dur": 14.379, + "args": { + "External id": 4678038,"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": 1708037785151.110, "dur": 35946.191, + "args": { + "External id": 4678039,"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": 1708037785153.867, "dur": 35942.578, + "args": { + "External id": 4678040,"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": 1708037785158.641, "dur": 6.125, + "args": { + "External id": 4678041,"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": 1708037785166.810, "dur": 35926.039, + "args": { + "External id": 4678042,"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": 1708037821239.420, "dur": 8.996, + "args": { + "External id": 4678043,"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": 1708037821242.826, "dur": 5.210, + "args": { + "External id": 4678044,"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": 1708037821280.435, "dur": 409.932, + "args": { + "External id": 4678045,"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": 1708037821306.581, "dur": 378.428, + "args": { + "External id": 4678046,"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": 1708037821317.087, "dur": 361.959, + "args": { + "External id": 4678047,"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": 1708037821713.307, "dur": 2.502, + "args": { + "External id": 4678048,"Record function id": 0, "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": 1708037821777.517, "dur": 7.054, + "args": { + "External id": 4678049,"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": 1708037821828.378, "dur": 1.870, + "args": { + "External id": 4678050,"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": 1708037821848.187, "dur": 3.194, + "args": { + "External id": 4678051,"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": 1708037821865.168, "dur": 0.942, + "args": { + "External id": 4678052,"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": 1708037821879.188, "dur": 0.850, + "args": { + "External id": 4678053,"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": 1708037821893.284, "dur": 0.968, + "args": { + "External id": 4678054,"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": 1708037821907.100, "dur": 3.004, + "args": { + "External id": 4678055,"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": 1708037821923.046, "dur": 2.937, + "args": { + "External id": 4678056,"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": 1708037821937.831, "dur": 1.040, + "args": { + "External id": 4678057,"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": 1708037822067.462, "dur": 2832.598, + "args": { + "External id": 4678058,"Record function id": 0, "Ev Idx": 2473 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1708037822087.383, "dur": 1115.164, + "args": { + "External id": 4678059,"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": 1708037822103.078, "dur": 370.039, + "args": { + "External id": 4678060,"Record function id": 0, "Ev Idx": 2475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708037822191.240, "dur": 4.870, + "args": { + "External id": 4678061,"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": 1708037822199.720, "dur": 1.349, + "args": { + "External id": 4678062,"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": 1708037822203.368, "dur": 3.460, + "args": { + "External id": 4678063,"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": 1708037822208.513, "dur": 1.494, + "args": { + "External id": 4678064,"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": 1708037822211.885, "dur": 0.909, + "args": { + "External id": 4678065,"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": 1708037822214.746, "dur": 1.011, + "args": { + "External id": 4678066,"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": 1708037822217.556, "dur": 5.389, + "args": { + "External id": 4678067,"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": 1708037822224.693, "dur": 1.219, + "args": { + "External id": 4678068,"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": 1708037822227.417, "dur": 1.014, + "args": { + "External id": 4678069,"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": 1708037822229.913, "dur": 0.981, + "args": { + "External id": 4678070,"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": 1708037822249.114, "dur": 190.467, + "args": { + "External id": 4678071,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037822302.876, "dur": 132.039, + "args": { + "External id": 4678072,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037822321.543, "dur": 14.155, + "args": { + "External id": 4678073,"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": 1708037822339.391, "dur": 66.232, + "args": { + "External id": 4678074,"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": 1708037822342.343, "dur": 62.963, + "args": { + "External id": 4678075,"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": 1708037822346.789, "dur": 5.944, + "args": { + "External id": 4678076,"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": 1708037822354.803, "dur": 49.771, + "args": { + "External id": 4678077,"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": 1708037822591.129, "dur": 602.959, + "args": { + "External id": 4678078,"Record function id": 0, "Ev Idx": 2493 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1708037822609.168, "dur": 571.493, + "args": { + "External id": 4678079,"Record function id": 0, "Ev Idx": 2494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037822675.351, "dur": 5.641, + "args": { + "External id": 4678080,"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": 1708037822697.443, "dur": 34.584, + "args": { + "External id": 4678081,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037822702.701, "dur": 1.510, + "args": { + "External id": 4678082,"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": 1708037822706.744, "dur": 0.556, + "args": { + "External id": 4678083,"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": 1708037822709.103, "dur": 0.497, + "args": { + "External id": 4678084,"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": 1708037822712.100, "dur": 0.373, + "args": { + "External id": 4678085,"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": 1708037822714.473, "dur": 0.417, + "args": { + "External id": 4678086,"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": 1708037822716.619, "dur": 2.933, + "args": { + "External id": 4678087,"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": 1708037822721.174, "dur": 0.559, + "args": { + "External id": 4678088,"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": 1708037822723.848, "dur": 0.410, + "args": { + "External id": 4678089,"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": 1708037822726.053, "dur": 0.333, + "args": { + "External id": 4678090,"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": 1708037822743.179, "dur": 32.674, + "args": { + "External id": 4678091,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037822807.957, "dur": 101.555, + "args": { + "External id": 4678092,"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": 1708037822818.187, "dur": 3.121, + "args": { + "External id": 4678093,"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": 1708037822826.761, "dur": 10.326, + "args": { + "External id": 4678094,"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": 1708037822830.943, "dur": 5.737, + "args": { + "External id": 4678095,"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": 1708037822834.820, "dur": 0.722, + "args": { + "External id": 4678096,"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": 1708037822844.524, "dur": 27.243, + "args": { + "External id": 4678097,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037822846.711, "dur": 0.768, + "args": { + "External id": 4678098,"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": 1708037822849.635, "dur": 0.371, + "args": { + "External id": 4678099,"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": 1708037822852.150, "dur": 2.513, + "args": { + "External id": 4678100,"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": 1708037822856.661, "dur": 0.390, + "args": { + "External id": 4678101,"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": 1708037822858.704, "dur": 0.371, + "args": { + "External id": 4678102,"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": 1708037822860.784, "dur": 0.606, + "args": { + "External id": 4678103,"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": 1708037822862.851, "dur": 0.381, + "args": { + "External id": 4678104,"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": 1708037822865.325, "dur": 0.382, + "args": { + "External id": 4678105,"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": 1708037822867.095, "dur": 0.448, + "args": { + "External id": 4678106,"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": 1708037822882.398, "dur": 19.889, + "args": { + "External id": 4678107,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037822951.561, "dur": 160.784, + "args": { + "External id": 4678108,"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": 1708037822973.767, "dur": 134.688, + "args": { + "External id": 4678109,"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": 1708037823027.927, "dur": 76.207, + "args": { + "External id": 4678110,"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": 1708037823126.882, "dur": 1.875, + "args": { + "External id": 4678111,"Record function id": 0, "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": 1708037823211.964, "dur": 1666.622, + "args": { + "External id": 4678112,"Sequence number": 46526476, "Fwd thread 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": 1708037823211.964, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708037823321.996, "dur": 99.348, + "args": { + "External id": 4678113,"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": 1708037823458.334, "dur": 40.685, + "args": { + "External id": 4678114,"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": 1708037823517.046, "dur": 74.506, + "args": { + "External id": 4678115,"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": 1708037823607.045, "dur": 37.893, + "args": { + "External id": 4678116,"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": 1708037823652.197, "dur": 45.108, + "args": { + "External id": 4678117,"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": 1708037823706.008, "dur": 29.362, + "args": { + "External id": 4678118,"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": 1708037823743.011, "dur": 42.355, + "args": { + "External id": 4678119,"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": 1708037823810.440, "dur": 24.078, + "args": { + "External id": 4678120,"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": 1708037823853.276, "dur": 28.382, + "args": { + "External id": 4678121,"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": 1708037823899.423, "dur": 19.986, + "args": { + "External id": 4678122,"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": 1708037823932.953, "dur": 16.393, + "args": { + "External id": 4678123,"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": 1708037823960.217, "dur": 65.450, + "args": { + "External id": 4678124,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037824031.774, "dur": 38.213, + "args": { + "External id": 4678125,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037824101.343, "dur": 175.851, + "args": { + "External id": 4678126,"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": 1708037824179.107, "dur": 6.069, + "args": { + "External id": 4678127,"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": 1708037824187.347, "dur": 2.165, + "args": { + "External id": 4678128,"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": 1708037824334.049, "dur": 27.024, + "args": { + "External id": 4678129,"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": 1708037824374.520, "dur": 15.529, + "args": { + "External id": 4678130,"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": 1708037824399.118, "dur": 36.852, + "args": { + "External id": 4678131,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037824443.471, "dur": 35.298, + "args": { + "External id": 4678132,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037824499.208, "dur": 48.154, + "args": { + "External id": 4678133,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037824557.489, "dur": 37.169, + "args": { + "External id": 4678134,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037824603.115, "dur": 25.591, + "args": { + "External id": 4678135,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037824637.458, "dur": 30.509, + "args": { + "External id": 4678136,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037824692.088, "dur": 24.092, + "args": { + "External id": 4678137,"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": 1708037824733.045, "dur": 25.279, + "args": { + "External id": 4678138,"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": 1708037824772.657, "dur": 17.892, + "args": { + "External id": 4678139,"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": 1708037824804.673, "dur": 16.656, + "args": { + "External id": 4678140,"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": 1708037824834.680, "dur": 15.751, + "args": { + "External id": 4678141,"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": 1708037824922.500, "dur": 133.759, + "args": { + "External id": 4678142,"Record function id": 0, "Ev Idx": 2557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037824925.860, "dur": 128.582, + "args": { + "External id": 4678143,"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": 1708037824929.555, "dur": 122.967, + "args": { + "External id": 4678144,"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": 1708037825046.855, "dur": 5.205, + "args": { + "External id": 4678145,"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": 1708037825064.687, "dur": 9.166, + "args": { + "External id": 4678146,"Record function id": 0, "Ev Idx": 2561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037825066.857, "dur": 6.526, + "args": { + "External id": 4678147,"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": 1708037825068.301, "dur": 4.335, + "args": { + "External id": 4678148,"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": 1708037825069.161, "dur": 3.366, + "args": { + "External id": 4678149,"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": 1708037825077.228, "dur": 4.288, + "args": { + "External id": 4678150,"Record function id": 0, "Ev Idx": 2565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037825078.795, "dur": 2.317, + "args": { + "External id": 4678151,"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": 1708037825079.341, "dur": 1.319, + "args": { + "External id": 4678152,"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": 1708037825079.748, "dur": 0.840, + "args": { + "External id": 4678153,"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": 1708037825084.764, "dur": 4.220, + "args": { + "External id": 4678154,"Record function id": 0, "Ev Idx": 2569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037825086.166, "dur": 2.418, + "args": { + "External id": 4678155,"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": 1708037825086.876, "dur": 1.119, + "args": { + "External id": 4678156,"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": 1708037825087.187, "dur": 0.732, + "args": { + "External id": 4678157,"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": 1708037825092.047, "dur": 4.038, + "args": { + "External id": 4678158,"Record function id": 0, "Ev Idx": 2573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037825093.407, "dur": 2.240, + "args": { + "External id": 4678159,"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": 1708037825093.869, "dur": 1.137, + "args": { + "External id": 4678160,"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": 1708037825094.233, "dur": 0.697, + "args": { + "External id": 4678161,"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": 1708037825099.359, "dur": 4.121, + "args": { + "External id": 4678162,"Record function id": 0, "Ev Idx": 2577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037825100.533, "dur": 2.547, + "args": { + "External id": 4678163,"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": 1708037825101.198, "dur": 1.217, + "args": { + "External id": 4678164,"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": 1708037825101.610, "dur": 0.716, + "args": { + "External id": 4678165,"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": 1708037825106.672, "dur": 3.846, + "args": { + "External id": 4678166,"Record function id": 0, "Ev Idx": 2581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037825107.837, "dur": 2.236, + "args": { + "External id": 4678167,"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": 1708037825108.292, "dur": 1.140, + "args": { + "External id": 4678168,"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": 1708037825108.608, "dur": 0.748, + "args": { + "External id": 4678169,"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": 1708037825113.561, "dur": 6.057, + "args": { + "External id": 4678170,"Record function id": 0, "Ev Idx": 2585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037825114.892, "dur": 4.299, + "args": { + "External id": 4678171,"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": 1708037825115.726, "dur": 2.929, + "args": { + "External id": 4678172,"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": 1708037825117.866, "dur": 0.686, + "args": { + "External id": 4678173,"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": 1708037825122.756, "dur": 6.131, + "args": { + "External id": 4678174,"Record function id": 0, "Ev Idx": 2589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037825124.000, "dur": 4.434, + "args": { + "External id": 4678175,"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": 1708037825124.504, "dur": 3.307, + "args": { + "External id": 4678176,"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": 1708037825125.005, "dur": 2.715, + "args": { + "External id": 4678177,"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": 1708037825132.815, "dur": 37157.765, + "args": { + "External id": 4678178,"Record function id": 0, "Sequence number": 46526475, "Fwd thread id": 1, "Ev Idx": 2593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037825134.151, "dur": 37148.012, + "args": { + "External id": 4678179,"Sequence number": 46526475, "Fwd thread 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": 1708037825134.151, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.21)", "pid": 1336753, "tid": 1381210, + "ts": 1708037825167.423, "dur": 37.794, + "args": { + "External id": 4678180,"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": 1708037825217.087, "dur": 71.239, + "args": { + "External id": 4678181,"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": 1708037825294.454, "dur": 36979.628, + "args": { + "External id": 4678182,"Record function id": 0, "Ev Idx": 2597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037825382.173, "dur": 7.246, + "args": { + "External id": 4678183,"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": 1708037825399.053, "dur": 4.795, + "args": { + "External id": 4678184,"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": 1708037825422.542, "dur": 35972.131, + "args": { + "External id": 4678185,"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": 1708037825435.858, "dur": 35947.692, + "args": { + "External id": 4678186,"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": 1708037825491.034, "dur": 13.462, + "args": { + "External id": 4678187,"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": 1708037825510.977, "dur": 35829.414, + "args": { + "External id": 4678188,"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": 1708037825513.453, "dur": 35825.777, + "args": { + "External id": 4678189,"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": 1708037825517.608, "dur": 5.047, + "args": { + "External id": 4678190,"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": 1708037825540.197, "dur": 35794.402, + "args": { + "External id": 4678191,"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": 1708037861495.939, "dur": 10.588, + "args": { + "External id": 4678192,"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": 1708037861499.639, "dur": 6.452, + "args": { + "External id": 4678193,"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": 1708037861549.100, "dur": 377.578, + "args": { + "External id": 4678194,"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": 1708037861576.757, "dur": 344.825, + "args": { + "External id": 4678195,"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": 1708037861587.844, "dur": 326.317, + "args": { + "External id": 4678196,"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": 1708037861950.889, "dur": 2.571, + "args": { + "External id": 4678197,"Record function id": 0, "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": 1708037862048.094, "dur": 6.933, + "args": { + "External id": 4678198,"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": 1708037862100.769, "dur": 3.456, + "args": { + "External id": 4678199,"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": 1708037862122.035, "dur": 1.410, + "args": { + "External id": 4678200,"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": 1708037862136.975, "dur": 1.030, + "args": { + "External id": 4678201,"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": 1708037862152.062, "dur": 1.317, + "args": { + "External id": 4678202,"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": 1708037862165.959, "dur": 3.063, + "args": { + "External id": 4678203,"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": 1708037862181.889, "dur": 0.980, + "args": { + "External id": 4678204,"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": 1708037862195.245, "dur": 1.942, + "args": { + "External id": 4678205,"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": 1708037862210.022, "dur": 1.189, + "args": { + "External id": 4678206,"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": 1708037862306.398, "dur": 2850.350, + "args": { + "External id": 4678207,"Record function id": 0, "Ev Idx": 2622 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1708037862326.764, "dur": 1078.251, + "args": { + "External id": 4678208,"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": 1708037862341.359, "dur": 351.134, + "args": { + "External id": 4678209,"Record function id": 0, "Ev Idx": 2624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708037862426.439, "dur": 6.054, + "args": { + "External id": 4678210,"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": 1708037862435.915, "dur": 1.412, + "args": { + "External id": 4678211,"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": 1708037862439.080, "dur": 1.231, + "args": { + "External id": 4678212,"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": 1708037862442.091, "dur": 1.080, + "args": { + "External id": 4678213,"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": 1708037862444.663, "dur": 1.241, + "args": { + "External id": 4678214,"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": 1708037862447.476, "dur": 1.208, + "args": { + "External id": 4678215,"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": 1708037862450.461, "dur": 2.774, + "args": { + "External id": 4678216,"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": 1708037862454.616, "dur": 1.017, + "args": { + "External id": 4678217,"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": 1708037862457.513, "dur": 3.029, + "args": { + "External id": 4678218,"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": 1708037862462.230, "dur": 0.909, + "args": { + "External id": 4678219,"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": 1708037862483.423, "dur": 173.423, + "args": { + "External id": 4678220,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037862499.707, "dur": 151.886, + "args": { + "External id": 4678221,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037862522.885, "dur": 28.635, + "args": { + "External id": 4678222,"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": 1708037862555.920, "dur": 65.793, + "args": { + "External id": 4678223,"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": 1708037862558.463, "dur": 62.838, + "args": { + "External id": 4678224,"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": 1708037862562.990, "dur": 5.796, + "args": { + "External id": 4678225,"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": 1708037862570.624, "dur": 50.023, + "args": { + "External id": 4678226,"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": 1708037862786.371, "dur": 609.981, + "args": { + "External id": 4678227,"Record function id": 0, "Ev Idx": 2642 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1708037862804.171, "dur": 579.119, + "args": { + "External id": 4678228,"Record function id": 0, "Ev Idx": 2643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037862866.018, "dur": 4.596, + "args": { + "External id": 4678229,"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": 1708037862886.451, "dur": 33.308, + "args": { + "External id": 4678230,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037862891.257, "dur": 1.571, + "args": { + "External id": 4678231,"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": 1708037862894.994, "dur": 0.475, + "args": { + "External id": 4678232,"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": 1708037862897.497, "dur": 0.646, + "args": { + "External id": 4678233,"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": 1708037862900.392, "dur": 2.235, + "args": { + "External id": 4678234,"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": 1708037862904.853, "dur": 0.405, + "args": { + "External id": 4678235,"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": 1708037862907.175, "dur": 0.388, + "args": { + "External id": 4678236,"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": 1708037862909.252, "dur": 0.654, + "args": { + "External id": 4678237,"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": 1708037862911.653, "dur": 0.496, + "args": { + "External id": 4678238,"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": 1708037862914.114, "dur": 0.417, + "args": { + "External id": 4678239,"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": 1708037862929.798, "dur": 31.457, + "args": { + "External id": 4678240,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037863039.359, "dur": 120.243, + "args": { + "External id": 4678241,"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": 1708037863050.592, "dur": 5.068, + "args": { + "External id": 4678242,"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": 1708037863061.583, "dur": 11.840, + "args": { + "External id": 4678243,"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": 1708037863065.875, "dur": 7.133, + "args": { + "External id": 4678244,"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": 1708037863070.541, "dur": 0.726, + "args": { + "External id": 4678245,"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": 1708037863080.837, "dur": 30.485, + "args": { + "External id": 4678246,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037863083.668, "dur": 2.796, + "args": { + "External id": 4678247,"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": 1708037863088.696, "dur": 0.309, + "args": { + "External id": 4678248,"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": 1708037863090.797, "dur": 0.517, + "args": { + "External id": 4678249,"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": 1708037863093.275, "dur": 0.421, + "args": { + "External id": 4678250,"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": 1708037863096.049, "dur": 0.339, + "args": { + "External id": 4678251,"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": 1708037863098.182, "dur": 0.424, + "args": { + "External id": 4678252,"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": 1708037863100.409, "dur": 0.406, + "args": { + "External id": 4678253,"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": 1708037863102.693, "dur": 0.363, + "args": { + "External id": 4678254,"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": 1708037863104.766, "dur": 2.476, + "args": { + "External id": 4678255,"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": 1708037863124.221, "dur": 27.780, + "args": { + "External id": 4678256,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037863210.136, "dur": 111.288, + "args": { + "External id": 4678257,"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": 1708037863232.737, "dur": 85.389, + "args": { + "External id": 4678258,"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": 1708037863242.228, "dur": 71.824, + "args": { + "External id": 4678259,"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": 1708037863334.585, "dur": 1.580, + "args": { + "External id": 4678260,"Record function id": 0, "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": 1708037863411.534, "dur": 1719.358, + "args": { + "External id": 4678261,"Sequence number": 46526474, "Fwd thread 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": 1708037863411.534, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708037863518.435, "dur": 118.212, + "args": { + "External id": 4678262,"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": 1708037863682.707, "dur": 46.389, + "args": { + "External id": 4678263,"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": 1708037863751.314, "dur": 49.274, + "args": { + "External id": 4678264,"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": 1708037863810.065, "dur": 34.371, + "args": { + "External id": 4678265,"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": 1708037863852.477, "dur": 45.345, + "args": { + "External id": 4678266,"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": 1708037863906.595, "dur": 29.499, + "args": { + "External id": 4678267,"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": 1708037863946.132, "dur": 77.515, + "args": { + "External id": 4678268,"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": 1708037864053.117, "dur": 26.950, + "args": { + "External id": 4678269,"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": 1708037864099.741, "dur": 29.330, + "args": { + "External id": 4678270,"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": 1708037864149.002, "dur": 20.761, + "args": { + "External id": 4678271,"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": 1708037864183.706, "dur": 17.176, + "args": { + "External id": 4678272,"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": 1708037864214.229, "dur": 34.571, + "args": { + "External id": 4678273,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037864252.334, "dur": 33.601, + "args": { + "External id": 4678274,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037864313.377, "dur": 168.971, + "args": { + "External id": 4678275,"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": 1708037864387.736, "dur": 5.937, + "args": { + "External id": 4678276,"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": 1708037864395.788, "dur": 2.778, + "args": { + "External id": 4678277,"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": 1708037864516.490, "dur": 44.611, + "args": { + "External id": 4678278,"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": 1708037864574.690, "dur": 15.771, + "args": { + "External id": 4678279,"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": 1708037864600.943, "dur": 39.464, + "args": { + "External id": 4678280,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037864649.813, "dur": 35.782, + "args": { + "External id": 4678281,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037864693.531, "dur": 23.278, + "args": { + "External id": 4678282,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037864722.791, "dur": 47.855, + "args": { + "External id": 4678283,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037864782.945, "dur": 28.813, + "args": { + "External id": 4678284,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037864822.374, "dur": 34.644, + "args": { + "External id": 4678285,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037864875.340, "dur": 24.733, + "args": { + "External id": 4678286,"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": 1708037864919.865, "dur": 28.033, + "args": { + "External id": 4678287,"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": 1708037864964.252, "dur": 68.300, + "args": { + "External id": 4678288,"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": 1708037865053.138, "dur": 18.058, + "args": { + "External id": 4678289,"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": 1708037865084.475, "dur": 17.043, + "args": { + "External id": 4678290,"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": 1708037865179.358, "dur": 17.861, + "args": { + "External id": 4678291,"Record function id": 0, "Ev Idx": 2706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037865183.106, "dur": 13.184, + "args": { + "External id": 4678292,"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": 1708037865187.424, "dur": 7.899, + "args": { + "External id": 4678293,"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": 1708037865189.117, "dur": 6.080, + "args": { + "External id": 4678294,"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": 1708037865201.182, "dur": 4.904, + "args": { + "External id": 4678295,"Record function id": 0, "Ev Idx": 2710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037865202.760, "dur": 2.905, + "args": { + "External id": 4678296,"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": 1708037865203.434, "dur": 1.766, + "args": { + "External id": 4678297,"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": 1708037865204.003, "dur": 1.092, + "args": { + "External id": 4678298,"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": 1708037865209.261, "dur": 4.459, + "args": { + "External id": 4678299,"Record function id": 0, "Ev Idx": 2714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037865210.753, "dur": 2.562, + "args": { + "External id": 4678300,"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": 1708037865211.277, "dur": 1.578, + "args": { + "External id": 4678301,"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": 1708037865211.653, "dur": 1.140, + "args": { + "External id": 4678302,"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": 1708037865216.795, "dur": 4.207, + "args": { + "External id": 4678303,"Record function id": 0, "Ev Idx": 2718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037865218.613, "dur": 2.001, + "args": { + "External id": 4678304,"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": 1708037865219.117, "dur": 1.053, + "args": { + "External id": 4678305,"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": 1708037865219.430, "dur": 0.672, + "args": { + "External id": 4678306,"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": 1708037865224.621, "dur": 4.095, + "args": { + "External id": 4678307,"Record function id": 0, "Ev Idx": 2722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037865226.242, "dur": 2.057, + "args": { + "External id": 4678308,"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": 1708037865226.699, "dur": 1.163, + "args": { + "External id": 4678309,"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": 1708037865227.170, "dur": 0.616, + "args": { + "External id": 4678310,"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": 1708037865232.341, "dur": 4.413, + "args": { + "External id": 4678311,"Record function id": 0, "Ev Idx": 2726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037865234.128, "dur": 2.236, + "args": { + "External id": 4678312,"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": 1708037865234.603, "dur": 1.368, + "args": { + "External id": 4678313,"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": 1708037865235.076, "dur": 0.794, + "args": { + "External id": 4678314,"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": 1708037865240.135, "dur": 4.051, + "args": { + "External id": 4678315,"Record function id": 0, "Ev Idx": 2730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037865241.639, "dur": 2.165, + "args": { + "External id": 4678316,"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": 1708037865242.376, "dur": 1.012, + "args": { + "External id": 4678317,"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": 1708037865242.707, "dur": 0.601, + "args": { + "External id": 4678318,"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": 1708037865247.647, "dur": 6.647, + "args": { + "External id": 4678319,"Record function id": 0, "Ev Idx": 2734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037865249.488, "dur": 4.426, + "args": { + "External id": 4678320,"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": 1708037865250.043, "dur": 3.307, + "args": { + "External id": 4678321,"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": 1708037865250.452, "dur": 2.812, + "args": { + "External id": 4678322,"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": 1708037865257.579, "dur": 4.598, + "args": { + "External id": 4678323,"Record function id": 0, "Ev Idx": 2738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037865258.978, "dur": 2.787, + "args": { + "External id": 4678324,"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": 1708037865259.754, "dur": 1.293, + "args": { + "External id": 4678325,"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": 1708037865260.154, "dur": 0.794, + "args": { + "External id": 4678326,"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": 1708037865266.891, "dur": 38642.143, + "args": { + "External id": 4678327,"Record function id": 0, "Sequence number": 46526473, "Fwd thread id": 1, "Ev Idx": 2742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037865268.044, "dur": 38633.120, + "args": { + "External id": 4678328,"Sequence number": 46526473, "Fwd thread 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": 1708037865268.044, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.20)", "pid": 1336753, "tid": 1381210, + "ts": 1708037865299.464, "dur": 40.513, + "args": { + "External id": 4678329,"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": 1708037865347.701, "dur": 66.268, + "args": { + "External id": 4678330,"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": 1708037865419.629, "dur": 38473.154, + "args": { + "External id": 4678331,"Record function id": 0, "Ev Idx": 2746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037865504.872, "dur": 6.227, + "args": { + "External id": 4678332,"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": 1708037865520.398, "dur": 19.953, + "args": { + "External id": 4678333,"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": 1708037865557.803, "dur": 37477.820, + "args": { + "External id": 4678334,"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": 1708037865571.723, "dur": 37453.956, + "args": { + "External id": 4678335,"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": 1708037865660.105, "dur": 13.283, + "args": { + "External id": 4678336,"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": 1708037865680.004, "dur": 37285.096, + "args": { + "External id": 4678337,"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": 1708037865682.605, "dur": 37281.658, + "args": { + "External id": 4678338,"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": 1708037865687.068, "dur": 6.382, + "args": { + "External id": 4678339,"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": 1708037865695.363, "dur": 37265.475, + "args": { + "External id": 4678340,"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": 1708037903129.000, "dur": 8.846, + "args": { + "External id": 4678341,"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": 1708037903132.310, "dur": 5.216, + "args": { + "External id": 4678342,"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": 1708037903172.042, "dur": 409.921, + "args": { + "External id": 4678343,"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": 1708037903203.088, "dur": 373.532, + "args": { + "External id": 4678344,"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": 1708037903214.399, "dur": 355.605, + "args": { + "External id": 4678345,"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": 1708037903603.409, "dur": 2.718, + "args": { + "External id": 4678346,"Record function id": 0, "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": 1708037903672.841, "dur": 6.720, + "args": { + "External id": 4678347,"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": 1708037903727.318, "dur": 1.500, + "args": { + "External id": 4678348,"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": 1708037903747.044, "dur": 0.877, + "args": { + "External id": 4678349,"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": 1708037903761.045, "dur": 1.038, + "args": { + "External id": 4678350,"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": 1708037903773.636, "dur": 0.905, + "args": { + "External id": 4678351,"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": 1708037903787.739, "dur": 0.909, + "args": { + "External id": 4678352,"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": 1708037903802.396, "dur": 1.018, + "args": { + "External id": 4678353,"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": 1708037903816.467, "dur": 2.108, + "args": { + "External id": 4678354,"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": 1708037903830.888, "dur": 0.861, + "args": { + "External id": 4678355,"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": 1708037903923.662, "dur": 2902.897, + "args": { + "External id": 4678356,"Record function id": 0, "Ev Idx": 2771 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1708037903942.556, "dur": 1106.986, + "args": { + "External id": 4678357,"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": 1708037903958.038, "dur": 373.913, + "args": { + "External id": 4678358,"Record function id": 0, "Ev Idx": 2773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708037904080.571, "dur": 4.906, + "args": { + "External id": 4678359,"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": 1708037904088.978, "dur": 1.647, + "args": { + "External id": 4678360,"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": 1708037904092.577, "dur": 1.180, + "args": { + "External id": 4678361,"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": 1708037904095.498, "dur": 1.131, + "args": { + "External id": 4678362,"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": 1708037904098.375, "dur": 1.099, + "args": { + "External id": 4678363,"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": 1708037904107.420, "dur": 0.891, + "args": { + "External id": 4678364,"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": 1708037904110.258, "dur": 2.176, + "args": { + "External id": 4678365,"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": 1708037904114.407, "dur": 3.638, + "args": { + "External id": 4678366,"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": 1708037904119.777, "dur": 1.000, + "args": { + "External id": 4678367,"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": 1708037904122.504, "dur": 1.061, + "args": { + "External id": 4678368,"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": 1708037904143.058, "dur": 151.683, + "args": { + "External id": 4678369,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037904159.613, "dur": 130.720, + "args": { + "External id": 4678370,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037904176.766, "dur": 13.018, + "args": { + "External id": 4678371,"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": 1708037904193.031, "dur": 64.872, + "args": { + "External id": 4678372,"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": 1708037904195.615, "dur": 61.903, + "args": { + "External id": 4678373,"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": 1708037904199.981, "dur": 5.732, + "args": { + "External id": 4678374,"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": 1708037904207.646, "dur": 49.137, + "args": { + "External id": 4678375,"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": 1708037904427.036, "dur": 614.037, + "args": { + "External id": 4678376,"Record function id": 0, "Ev Idx": 2791 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1708037904445.540, "dur": 578.962, + "args": { + "External id": 4678377,"Record function id": 0, "Ev Idx": 2792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037904511.997, "dur": 4.406, + "args": { + "External id": 4678378,"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": 1708037904548.700, "dur": 33.895, + "args": { + "External id": 4678379,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037904553.855, "dur": 1.610, + "args": { + "External id": 4678380,"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": 1708037904558.256, "dur": 0.564, + "args": { + "External id": 4678381,"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": 1708037904560.909, "dur": 2.699, + "args": { + "External id": 4678382,"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": 1708037904565.552, "dur": 0.312, + "args": { + "External id": 4678383,"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": 1708037904567.938, "dur": 0.459, + "args": { + "External id": 4678384,"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": 1708037904570.492, "dur": 0.631, + "args": { + "External id": 4678385,"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": 1708037904572.966, "dur": 0.377, + "args": { + "External id": 4678386,"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": 1708037904575.345, "dur": 0.381, + "args": { + "External id": 4678387,"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": 1708037904577.336, "dur": 0.373, + "args": { + "External id": 4678388,"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": 1708037904593.938, "dur": 34.654, + "args": { + "External id": 4678389,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037904660.752, "dur": 108.164, + "args": { + "External id": 4678390,"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": 1708037904671.617, "dur": 3.925, + "args": { + "External id": 4678391,"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": 1708037904680.942, "dur": 12.093, + "args": { + "External id": 4678392,"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": 1708037904685.113, "dur": 7.517, + "args": { + "External id": 4678393,"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": 1708037904689.009, "dur": 2.272, + "args": { + "External id": 4678394,"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": 1708037904700.323, "dur": 29.631, + "args": { + "External id": 4678395,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037904702.753, "dur": 0.762, + "args": { + "External id": 4678396,"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": 1708037904705.768, "dur": 0.757, + "args": { + "External id": 4678397,"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": 1708037904708.407, "dur": 0.820, + "args": { + "External id": 4678398,"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": 1708037904711.278, "dur": 0.508, + "args": { + "External id": 4678399,"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": 1708037904713.445, "dur": 0.824, + "args": { + "External id": 4678400,"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": 1708037904716.037, "dur": 0.360, + "args": { + "External id": 4678401,"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": 1708037904718.093, "dur": 0.488, + "args": { + "External id": 4678402,"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": 1708037904720.638, "dur": 2.274, + "args": { + "External id": 4678403,"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": 1708037904724.766, "dur": 0.503, + "args": { + "External id": 4678404,"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": 1708037904740.850, "dur": 20.751, + "args": { + "External id": 4678405,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037904816.320, "dur": 109.525, + "args": { + "External id": 4678406,"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": 1708037904839.933, "dur": 82.470, + "args": { + "External id": 4678407,"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": 1708037904849.658, "dur": 68.173, + "args": { + "External id": 4678408,"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": 1708037904939.486, "dur": 1.822, + "args": { + "External id": 4678409,"Record function id": 0, "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": 1708037905058.267, "dur": 1745.418, + "args": { + "External id": 4678410,"Sequence number": 46526472, "Fwd thread 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": 1708037905058.267, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708037905167.999, "dur": 105.583, + "args": { + "External id": 4678411,"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": 1708037905315.653, "dur": 42.651, + "args": { + "External id": 4678412,"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": 1708037905378.978, "dur": 92.382, + "args": { + "External id": 4678413,"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": 1708037905486.613, "dur": 61.270, + "args": { + "External id": 4678414,"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": 1708037905558.461, "dur": 49.999, + "args": { + "External id": 4678415,"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": 1708037905617.253, "dur": 29.765, + "args": { + "External id": 4678416,"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": 1708037905658.542, "dur": 43.750, + "args": { + "External id": 4678417,"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": 1708037905729.127, "dur": 25.740, + "args": { + "External id": 4678418,"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": 1708037905774.149, "dur": 29.266, + "args": { + "External id": 4678419,"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": 1708037905823.575, "dur": 20.563, + "args": { + "External id": 4678420,"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": 1708037905857.675, "dur": 17.636, + "args": { + "External id": 4678421,"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": 1708037905890.767, "dur": 30.804, + "args": { + "External id": 4678422,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037905924.820, "dur": 36.443, + "args": { + "External id": 4678423,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037906029.938, "dur": 175.676, + "args": { + "External id": 4678424,"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": 1708037906107.027, "dur": 6.953, + "args": { + "External id": 4678425,"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": 1708037906116.274, "dur": 2.545, + "args": { + "External id": 4678426,"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": 1708037906241.938, "dur": 27.482, + "args": { + "External id": 4678427,"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": 1708037906281.410, "dur": 15.021, + "args": { + "External id": 4678428,"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": 1708037906308.040, "dur": 41.409, + "args": { + "External id": 4678429,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037906356.868, "dur": 36.276, + "args": { + "External id": 4678430,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037906400.094, "dur": 36.432, + "args": { + "External id": 4678431,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037906447.971, "dur": 37.859, + "args": { + "External id": 4678432,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037906495.685, "dur": 22.514, + "args": { + "External id": 4678433,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037906542.693, "dur": 38.784, + "args": { + "External id": 4678434,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037906601.522, "dur": 30.114, + "args": { + "External id": 4678435,"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": 1708037906650.404, "dur": 27.448, + "args": { + "External id": 4678436,"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": 1708037906693.836, "dur": 18.121, + "args": { + "External id": 4678437,"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": 1708037906727.804, "dur": 15.819, + "args": { + "External id": 4678438,"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": 1708037906756.406, "dur": 16.756, + "args": { + "External id": 4678439,"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": 1708037906849.326, "dur": 15.318, + "args": { + "External id": 4678440,"Record function id": 0, "Ev Idx": 2855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037906852.671, "dur": 11.039, + "args": { + "External id": 4678441,"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": 1708037906856.672, "dur": 6.046, + "args": { + "External id": 4678442,"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": 1708037906858.533, "dur": 4.037, + "args": { + "External id": 4678443,"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": 1708037906868.880, "dur": 5.570, + "args": { + "External id": 4678444,"Record function id": 0, "Ev Idx": 2859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037906870.266, "dur": 3.771, + "args": { + "External id": 4678445,"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": 1708037906871.224, "dur": 2.206, + "args": { + "External id": 4678446,"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": 1708037906872.283, "dur": 0.990, + "args": { + "External id": 4678447,"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": 1708037906877.963, "dur": 4.631, + "args": { + "External id": 4678448,"Record function id": 0, "Ev Idx": 2863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037906879.192, "dur": 2.980, + "args": { + "External id": 4678449,"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": 1708037906879.875, "dur": 1.617, + "args": { + "External id": 4678450,"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": 1708037906880.480, "dur": 0.936, + "args": { + "External id": 4678451,"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": 1708037906886.212, "dur": 4.763, + "args": { + "External id": 4678452,"Record function id": 0, "Ev Idx": 2867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037906887.880, "dur": 2.636, + "args": { + "External id": 4678453,"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": 1708037906888.613, "dur": 1.334, + "args": { + "External id": 4678454,"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": 1708037906889.017, "dur": 0.849, + "args": { + "External id": 4678455,"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": 1708037906894.190, "dur": 3.594, + "args": { + "External id": 4678456,"Record function id": 0, "Ev Idx": 2871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037906895.348, "dur": 2.032, + "args": { + "External id": 4678457,"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": 1708037906895.790, "dur": 1.205, + "args": { + "External id": 4678458,"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": 1708037906896.113, "dur": 0.806, + "args": { + "External id": 4678459,"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": 1708037906901.118, "dur": 3.592, + "args": { + "External id": 4678460,"Record function id": 0, "Ev Idx": 2875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037906902.161, "dur": 2.142, + "args": { + "External id": 4678461,"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": 1708037906902.637, "dur": 1.242, + "args": { + "External id": 4678462,"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": 1708037906903.059, "dur": 0.710, + "args": { + "External id": 4678463,"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": 1708037906908.121, "dur": 5.593, + "args": { + "External id": 4678464,"Record function id": 0, "Ev Idx": 2879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037906909.210, "dur": 4.080, + "args": { + "External id": 4678465,"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": 1708037906909.686, "dur": 3.221, + "args": { + "External id": 4678466,"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": 1708037906909.968, "dur": 2.851, + "args": { + "External id": 4678467,"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": 1708037906917.331, "dur": 4.419, + "args": { + "External id": 4678468,"Record function id": 0, "Ev Idx": 2883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037906918.564, "dur": 2.780, + "args": { + "External id": 4678469,"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": 1708037906919.080, "dur": 1.659, + "args": { + "External id": 4678470,"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": 1708037906919.591, "dur": 1.034, + "args": { + "External id": 4678471,"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": 1708037906925.307, "dur": 3.511, + "args": { + "External id": 4678472,"Record function id": 0, "Ev Idx": 2887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037906926.367, "dur": 2.037, + "args": { + "External id": 4678473,"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": 1708037906926.827, "dur": 1.127, + "args": { + "External id": 4678474,"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": 1708037906927.240, "dur": 0.625, + "args": { + "External id": 4678475,"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": 1708037906932.770, "dur": 35583.940, + "args": { + "External id": 4678476,"Record function id": 0, "Sequence number": 46526471, "Fwd thread id": 1, "Ev Idx": 2891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037906934.052, "dur": 35574.564, + "args": { + "External id": 4678477,"Sequence number": 46526471, "Fwd thread 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": 1708037906934.052, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 1336753, "tid": 1381210, + "ts": 1708037906960.929, "dur": 78.195, + "args": { + "External id": 4678478,"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": 1708037907049.370, "dur": 65.046, + "args": { + "External id": 4678479,"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": 1708037907119.943, "dur": 35380.833, + "args": { + "External id": 4678480,"Record function id": 0, "Ev Idx": 2895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037907205.567, "dur": 7.481, + "args": { + "External id": 4678481,"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": 1708037907223.315, "dur": 4.954, + "args": { + "External id": 4678482,"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": 1708037907243.208, "dur": 34433.199, + "args": { + "External id": 4678483,"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": 1708037907256.599, "dur": 34409.753, + "args": { + "External id": 4678484,"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": 1708037907350.619, "dur": 13.534, + "args": { + "External id": 4678485,"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": 1708037907370.886, "dur": 34253.003, + "args": { + "External id": 4678486,"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": 1708037907373.534, "dur": 34249.579, + "args": { + "External id": 4678487,"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": 1708037907377.645, "dur": 5.413, + "args": { + "External id": 4678488,"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": 1708037907385.156, "dur": 34234.903, + "args": { + "External id": 4678489,"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": 1708037941767.918, "dur": 9.066, + "args": { + "External id": 4678490,"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": 1708037941771.178, "dur": 5.444, + "args": { + "External id": 4678491,"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": 1708037941808.926, "dur": 388.562, + "args": { + "External id": 4678492,"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": 1708037941835.042, "dur": 357.421, + "args": { + "External id": 4678493,"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": 1708037941845.764, "dur": 340.717, + "args": { + "External id": 4678494,"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": 1708037942218.280, "dur": 2.282, + "args": { + "External id": 4678495,"Record function id": 0, "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": 1708037942280.913, "dur": 8.701, + "args": { + "External id": 4678496,"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": 1708037942334.209, "dur": 1.299, + "args": { + "External id": 4678497,"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": 1708037942352.603, "dur": 0.993, + "args": { + "External id": 4678498,"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": 1708037942367.400, "dur": 0.800, + "args": { + "External id": 4678499,"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": 1708037942381.269, "dur": 3.109, + "args": { + "External id": 4678500,"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": 1708037942396.296, "dur": 0.903, + "args": { + "External id": 4678501,"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": 1708037942410.138, "dur": 0.927, + "args": { + "External id": 4678502,"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": 1708037942423.599, "dur": 2.070, + "args": { + "External id": 4678503,"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": 1708037942437.910, "dur": 2.877, + "args": { + "External id": 4678504,"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": 1708037942546.944, "dur": 2842.225, + "args": { + "External id": 4678505,"Record function id": 0, "Ev Idx": 2920 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1708037942569.336, "dur": 1088.486, + "args": { + "External id": 4678506,"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": 1708037942584.004, "dur": 328.654, + "args": { + "External id": 4678507,"Record function id": 0, "Ev Idx": 2922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708037942668.366, "dur": 4.782, + "args": { + "External id": 4678508,"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": 1708037942676.217, "dur": 1.356, + "args": { + "External id": 4678509,"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": 1708037942679.218, "dur": 0.932, + "args": { + "External id": 4678510,"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": 1708037942681.831, "dur": 1.206, + "args": { + "External id": 4678511,"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": 1708037942684.636, "dur": 1.119, + "args": { + "External id": 4678512,"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": 1708037942687.326, "dur": 1.069, + "args": { + "External id": 4678513,"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": 1708037942689.866, "dur": 3.479, + "args": { + "External id": 4678514,"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": 1708037942694.940, "dur": 1.111, + "args": { + "External id": 4678515,"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": 1708037942697.841, "dur": 0.832, + "args": { + "External id": 4678516,"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": 1708037942700.522, "dur": 0.755, + "args": { + "External id": 4678517,"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": 1708037942722.519, "dur": 158.077, + "args": { + "External id": 4678518,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037942738.474, "dur": 137.133, + "args": { + "External id": 4678519,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037942762.913, "dur": 15.608, + "args": { + "External id": 4678520,"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": 1708037942781.488, "dur": 64.881, + "args": { + "External id": 4678521,"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": 1708037942784.128, "dur": 61.904, + "args": { + "External id": 4678522,"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": 1708037942788.598, "dur": 5.704, + "args": { + "External id": 4678523,"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": 1708037942796.288, "dur": 48.851, + "args": { + "External id": 4678524,"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": 1708037943054.885, "dur": 594.250, + "args": { + "External id": 4678525,"Record function id": 0, "Ev Idx": 2940 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1708037943074.200, "dur": 562.039, + "args": { + "External id": 4678526,"Record function id": 0, "Ev Idx": 2941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037943140.391, "dur": 5.635, + "args": { + "External id": 4678527,"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": 1708037943162.348, "dur": 37.110, + "args": { + "External id": 4678528,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037943167.762, "dur": 1.452, + "args": { + "External id": 4678529,"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": 1708037943171.911, "dur": 2.581, + "args": { + "External id": 4678530,"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": 1708037943176.350, "dur": 0.407, + "args": { + "External id": 4678531,"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": 1708037943178.374, "dur": 0.396, + "args": { + "External id": 4678532,"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": 1708037943180.637, "dur": 0.412, + "args": { + "External id": 4678533,"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": 1708037943182.859, "dur": 0.584, + "args": { + "External id": 4678534,"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": 1708037943190.183, "dur": 0.586, + "args": { + "External id": 4678535,"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": 1708037943192.785, "dur": 0.311, + "args": { + "External id": 4678536,"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": 1708037943194.831, "dur": 0.352, + "args": { + "External id": 4678537,"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": 1708037943209.608, "dur": 36.811, + "args": { + "External id": 4678538,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037943282.589, "dur": 108.279, + "args": { + "External id": 4678539,"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": 1708037943292.591, "dur": 5.410, + "args": { + "External id": 4678540,"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": 1708037943303.337, "dur": 10.090, + "args": { + "External id": 4678541,"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": 1708037943307.545, "dur": 5.485, + "args": { + "External id": 4678542,"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": 1708037943311.244, "dur": 0.572, + "args": { + "External id": 4678543,"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": 1708037943320.681, "dur": 26.624, + "args": { + "External id": 4678544,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037943323.051, "dur": 0.630, + "args": { + "External id": 4678545,"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": 1708037943325.471, "dur": 0.467, + "args": { + "External id": 4678546,"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": 1708037943327.877, "dur": 0.532, + "args": { + "External id": 4678547,"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": 1708037943330.255, "dur": 0.555, + "args": { + "External id": 4678548,"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": 1708037943332.569, "dur": 0.426, + "args": { + "External id": 4678549,"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": 1708037943334.760, "dur": 0.389, + "args": { + "External id": 4678550,"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": 1708037943336.829, "dur": 2.368, + "args": { + "External id": 4678551,"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": 1708037943340.811, "dur": 0.400, + "args": { + "External id": 4678552,"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": 1708037943343.058, "dur": 0.410, + "args": { + "External id": 4678553,"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": 1708037943361.868, "dur": 21.352, + "args": { + "External id": 4678554,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037943435.397, "dur": 131.253, + "args": { + "External id": 4678555,"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": 1708037943461.248, "dur": 101.532, + "args": { + "External id": 4678556,"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": 1708037943471.084, "dur": 86.613, + "args": { + "External id": 4678557,"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": 1708037943584.445, "dur": 1.943, + "args": { + "External id": 4678558,"Record function id": 0, "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": 1708037943664.995, "dur": 1703.531, + "args": { + "External id": 4678559,"Sequence number": 46526470, "Fwd thread 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": 1708037943664.995, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708037943770.783, "dur": 101.521, + "args": { + "External id": 4678560,"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": 1708037943911.973, "dur": 43.422, + "args": { + "External id": 4678561,"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": 1708037943976.941, "dur": 109.865, + "args": { + "External id": 4678562,"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": 1708037944103.764, "dur": 35.108, + "args": { + "External id": 4678563,"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": 1708037944147.127, "dur": 46.171, + "args": { + "External id": 4678564,"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": 1708037944203.342, "dur": 30.363, + "args": { + "External id": 4678565,"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": 1708037944243.327, "dur": 42.817, + "args": { + "External id": 4678566,"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": 1708037944313.020, "dur": 25.215, + "args": { + "External id": 4678567,"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": 1708037944359.961, "dur": 27.654, + "args": { + "External id": 4678568,"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": 1708037944407.734, "dur": 22.768, + "args": { + "External id": 4678569,"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": 1708037944443.639, "dur": 17.919, + "args": { + "External id": 4678570,"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": 1708037944474.539, "dur": 30.503, + "args": { + "External id": 4678571,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037944508.556, "dur": 49.023, + "args": { + "External id": 4678572,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037944588.878, "dur": 174.712, + "args": { + "External id": 4678573,"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": 1708037944667.464, "dur": 6.506, + "args": { + "External id": 4678574,"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": 1708037944676.239, "dur": 5.151, + "args": { + "External id": 4678575,"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": 1708037944796.732, "dur": 24.806, + "args": { + "External id": 4678576,"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": 1708037944832.451, "dur": 14.890, + "args": { + "External id": 4678577,"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": 1708037944856.076, "dur": 38.502, + "args": { + "External id": 4678578,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037944901.987, "dur": 35.372, + "args": { + "External id": 4678579,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037944945.016, "dur": 66.441, + "args": { + "External id": 4678580,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037945029.340, "dur": 45.548, + "args": { + "External id": 4678581,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037945083.829, "dur": 27.538, + "args": { + "External id": 4678582,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037945120.143, "dur": 30.330, + "args": { + "External id": 4678583,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037945173.296, "dur": 24.804, + "args": { + "External id": 4678584,"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": 1708037945215.661, "dur": 27.223, + "args": { + "External id": 4678585,"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": 1708037945258.646, "dur": 17.648, + "args": { + "External id": 4678586,"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": 1708037945291.806, "dur": 16.290, + "args": { + "External id": 4678587,"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": 1708037945323.143, "dur": 17.377, + "args": { + "External id": 4678588,"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": 1708037945412.512, "dur": 15.232, + "args": { + "External id": 4678589,"Record function id": 0, "Ev Idx": 3004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037945415.723, "dur": 11.074, + "args": { + "External id": 4678590,"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": 1708037945420.034, "dur": 5.923, + "args": { + "External id": 4678591,"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": 1708037945421.812, "dur": 4.011, + "args": { + "External id": 4678592,"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": 1708037945431.812, "dur": 5.200, + "args": { + "External id": 4678593,"Record function id": 0, "Ev Idx": 3008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037945433.067, "dur": 3.506, + "args": { + "External id": 4678594,"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": 1708037945434.119, "dur": 1.962, + "args": { + "External id": 4678595,"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": 1708037945434.916, "dur": 1.040, + "args": { + "External id": 4678596,"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": 1708037945440.507, "dur": 5.024, + "args": { + "External id": 4678597,"Record function id": 0, "Ev Idx": 3012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037945441.800, "dur": 3.328, + "args": { + "External id": 4678598,"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": 1708037945442.856, "dur": 1.842, + "args": { + "External id": 4678599,"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": 1708037945443.391, "dur": 1.218, + "args": { + "External id": 4678600,"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": 1708037945449.083, "dur": 6.715, + "args": { + "External id": 4678601,"Record function id": 0, "Ev Idx": 3016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037945450.613, "dur": 4.732, + "args": { + "External id": 4678602,"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": 1708037945451.159, "dur": 3.697, + "args": { + "External id": 4678603,"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": 1708037945451.935, "dur": 2.826, + "args": { + "External id": 4678604,"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": 1708037945459.176, "dur": 4.482, + "args": { + "External id": 4678605,"Record function id": 0, "Ev Idx": 3020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037945460.670, "dur": 2.538, + "args": { + "External id": 4678606,"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": 1708037945461.334, "dur": 1.438, + "args": { + "External id": 4678607,"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": 1708037945461.803, "dur": 0.880, + "args": { + "External id": 4678608,"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": 1708037945467.169, "dur": 3.797, + "args": { + "External id": 4678609,"Record function id": 0, "Ev Idx": 3024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037945468.328, "dur": 2.201, + "args": { + "External id": 4678610,"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": 1708037945468.821, "dur": 1.226, + "args": { + "External id": 4678611,"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": 1708037945469.314, "dur": 0.622, + "args": { + "External id": 4678612,"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": 1708037945474.287, "dur": 4.279, + "args": { + "External id": 4678613,"Record function id": 0, "Ev Idx": 3028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037945475.469, "dur": 2.678, + "args": { + "External id": 4678614,"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": 1708037945476.320, "dur": 1.401, + "args": { + "External id": 4678615,"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": 1708037945476.838, "dur": 0.787, + "args": { + "External id": 4678616,"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": 1708037945481.926, "dur": 3.947, + "args": { + "External id": 4678617,"Record function id": 0, "Ev Idx": 3032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037945483.034, "dur": 2.424, + "args": { + "External id": 4678618,"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": 1708037945483.880, "dur": 1.140, + "args": { + "External id": 4678619,"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": 1708037945484.185, "dur": 0.767, + "args": { + "External id": 4678620,"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": 1708037945489.155, "dur": 4.164, + "args": { + "External id": 4678621,"Record function id": 0, "Ev Idx": 3036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037945490.453, "dur": 2.448, + "args": { + "External id": 4678622,"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": 1708037945490.966, "dur": 1.436, + "args": { + "External id": 4678623,"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": 1708037945491.547, "dur": 0.759, + "args": { + "External id": 4678624,"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": 1708037945500.490, "dur": 36123.909, + "args": { + "External id": 4678625,"Record function id": 0, "Sequence number": 46526469, "Fwd thread id": 1, "Ev Idx": 3040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037945501.842, "dur": 36113.628, + "args": { + "External id": 4678626,"Sequence number": 46526469, "Fwd thread 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": 1708037945501.842, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 1336753, "tid": 1381210, + "ts": 1708037945545.080, "dur": 42.633, + "args": { + "External id": 4678627,"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": 1708037945596.567, "dur": 61.708, + "args": { + "External id": 4678628,"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": 1708037945664.269, "dur": 35941.861, + "args": { + "External id": 4678629,"Record function id": 0, "Ev Idx": 3044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037945752.293, "dur": 6.743, + "args": { + "External id": 4678630,"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": 1708037945768.852, "dur": 5.018, + "args": { + "External id": 4678631,"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": 1708037945788.447, "dur": 34990.615, + "args": { + "External id": 4678632,"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": 1708037945884.820, "dur": 34885.009, + "args": { + "External id": 4678633,"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": 1708037945933.777, "dur": 15.580, + "args": { + "External id": 4678634,"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": 1708037945959.256, "dur": 34771.635, + "args": { + "External id": 4678635,"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": 1708037945961.960, "dur": 34767.836, + "args": { + "External id": 4678636,"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": 1708037945966.228, "dur": 5.514, + "args": { + "External id": 4678637,"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": 1708037945973.481, "dur": 34753.085, + "args": { + "External id": 4678638,"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": 1708037980869.495, "dur": 9.200, + "args": { + "External id": 4678639,"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": 1708037980873.102, "dur": 5.274, + "args": { + "External id": 4678640,"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": 1708037980909.383, "dur": 374.579, + "args": { + "External id": 4678641,"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": 1708037980935.855, "dur": 343.111, + "args": { + "External id": 4678642,"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": 1708037980946.526, "dur": 326.353, + "args": { + "External id": 4678643,"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": 1708037981305.128, "dur": 2.403, + "args": { + "External id": 4678644,"Record function id": 0, "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": 1708037981366.443, "dur": 6.562, + "args": { + "External id": 4678645,"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": 1708037981416.162, "dur": 1.726, + "args": { + "External id": 4678646,"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": 1708037981435.940, "dur": 1.158, + "args": { + "External id": 4678647,"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": 1708037981452.689, "dur": 0.852, + "args": { + "External id": 4678648,"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": 1708037981466.578, "dur": 0.895, + "args": { + "External id": 4678649,"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": 1708037981478.902, "dur": 0.951, + "args": { + "External id": 4678650,"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": 1708037981492.839, "dur": 0.935, + "args": { + "External id": 4678651,"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": 1708037981508.371, "dur": 2.098, + "args": { + "External id": 4678652,"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": 1708037981522.444, "dur": 16.299, + "args": { + "External id": 4678653,"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": 1708037981641.699, "dur": 2931.119, + "args": { + "External id": 4678654,"Record function id": 0, "Ev Idx": 3069 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1708037981661.332, "dur": 1174.211, + "args": { + "External id": 4678655,"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": 1708037981676.361, "dur": 465.739, + "args": { + "External id": 4678656,"Record function id": 0, "Ev Idx": 3071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708037981841.776, "dur": 5.312, + "args": { + "External id": 4678657,"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": 1708037981851.004, "dur": 1.231, + "args": { + "External id": 4678658,"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": 1708037981854.297, "dur": 1.068, + "args": { + "External id": 4678659,"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": 1708037981857.175, "dur": 2.915, + "args": { + "External id": 4678660,"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": 1708037981862.067, "dur": 0.833, + "args": { + "External id": 4678661,"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": 1708037981866.228, "dur": 0.844, + "args": { + "External id": 4678662,"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": 1708037981868.815, "dur": 1.655, + "args": { + "External id": 4678663,"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": 1708037981871.965, "dur": 0.900, + "args": { + "External id": 4678664,"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": 1708037981874.380, "dur": 0.915, + "args": { + "External id": 4678665,"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": 1708037981877.036, "dur": 0.909, + "args": { + "External id": 4678666,"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": 1708037981900.188, "dur": 204.229, + "args": { + "External id": 4678667,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037981916.138, "dur": 183.530, + "args": { + "External id": 4678668,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037981934.007, "dur": 13.161, + "args": { + "External id": 4678669,"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": 1708037981953.780, "dur": 114.353, + "args": { + "External id": 4678670,"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": 1708037981956.352, "dur": 111.379, + "args": { + "External id": 4678671,"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": 1708037981960.372, "dur": 8.105, + "args": { + "External id": 4678672,"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": 1708037981970.438, "dur": 96.044, + "args": { + "External id": 4678673,"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": 1708037982243.185, "dur": 583.760, + "args": { + "External id": 4678674,"Record function id": 0, "Ev Idx": 3089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1708037982260.266, "dur": 554.129, + "args": { + "External id": 4678675,"Record function id": 0, "Ev Idx": 3090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037982328.557, "dur": 5.835, + "args": { + "External id": 4678676,"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": 1708037982349.745, "dur": 33.115, + "args": { + "External id": 4678677,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037982355.018, "dur": 1.832, + "args": { + "External id": 4678678,"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": 1708037982359.367, "dur": 0.507, + "args": { + "External id": 4678679,"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": 1708037982361.699, "dur": 0.484, + "args": { + "External id": 4678680,"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": 1708037982363.968, "dur": 0.462, + "args": { + "External id": 4678681,"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": 1708037982366.165, "dur": 0.464, + "args": { + "External id": 4678682,"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": 1708037982368.440, "dur": 0.671, + "args": { + "External id": 4678683,"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": 1708037982371.484, "dur": 2.470, + "args": { + "External id": 4678684,"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": 1708037982375.912, "dur": 0.337, + "args": { + "External id": 4678685,"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": 1708037982377.776, "dur": 0.444, + "args": { + "External id": 4678686,"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": 1708037982393.615, "dur": 31.719, + "args": { + "External id": 4678687,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037982455.588, "dur": 130.332, + "args": { + "External id": 4678688,"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": 1708037982465.768, "dur": 3.385, + "args": { + "External id": 4678689,"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": 1708037982474.069, "dur": 10.448, + "args": { + "External id": 4678690,"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": 1708037982478.239, "dur": 5.860, + "args": { + "External id": 4678691,"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": 1708037982482.187, "dur": 0.747, + "args": { + "External id": 4678692,"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": 1708037982491.227, "dur": 27.532, + "args": { + "External id": 4678693,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037982493.703, "dur": 0.634, + "args": { + "External id": 4678694,"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": 1708037982496.588, "dur": 0.591, + "args": { + "External id": 4678695,"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": 1708037982498.936, "dur": 0.374, + "args": { + "External id": 4678696,"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": 1708037982501.182, "dur": 2.445, + "args": { + "External id": 4678697,"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": 1708037982505.575, "dur": 0.408, + "args": { + "External id": 4678698,"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": 1708037982507.549, "dur": 0.452, + "args": { + "External id": 4678699,"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": 1708037982509.634, "dur": 0.456, + "args": { + "External id": 4678700,"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": 1708037982512.029, "dur": 0.427, + "args": { + "External id": 4678701,"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": 1708037982514.375, "dur": 0.404, + "args": { + "External id": 4678702,"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": 1708037982552.295, "dur": 25.057, + "args": { + "External id": 4678703,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037982634.556, "dur": 114.700, + "args": { + "External id": 4678704,"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": 1708037982660.666, "dur": 85.051, + "args": { + "External id": 4678705,"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": 1708037982670.136, "dur": 71.181, + "args": { + "External id": 4678706,"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": 1708037982765.835, "dur": 1.931, + "args": { + "External id": 4678707,"Record function id": 0, "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": 1708037982843.267, "dur": 1705.674, + "args": { + "External id": 4678708,"Sequence number": 46526468, "Fwd thread 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": 1708037982843.267, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708037982953.422, "dur": 138.856, + "args": { + "External id": 4678709,"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": 1708037983137.981, "dur": 42.572, + "args": { + "External id": 4678710,"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": 1708037983199.405, "dur": 55.373, + "args": { + "External id": 4678711,"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": 1708037983268.035, "dur": 35.332, + "args": { + "External id": 4678712,"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": 1708037983312.869, "dur": 47.208, + "args": { + "External id": 4678713,"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": 1708037983367.636, "dur": 30.649, + "args": { + "External id": 4678714,"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": 1708037983406.435, "dur": 42.466, + "args": { + "External id": 4678715,"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": 1708037983469.880, "dur": 23.296, + "args": { + "External id": 4678716,"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": 1708037983513.065, "dur": 45.846, + "args": { + "External id": 4678717,"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": 1708037983582.223, "dur": 20.547, + "args": { + "External id": 4678718,"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": 1708037983615.317, "dur": 16.243, + "args": { + "External id": 4678719,"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": 1708037983642.482, "dur": 35.015, + "args": { + "External id": 4678720,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037983681.170, "dur": 33.800, + "args": { + "External id": 4678721,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037983743.762, "dur": 173.747, + "args": { + "External id": 4678722,"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": 1708037983820.585, "dur": 5.822, + "args": { + "External id": 4678723,"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": 1708037983831.563, "dur": 2.409, + "args": { + "External id": 4678724,"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": 1708037983953.078, "dur": 25.695, + "args": { + "External id": 4678725,"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": 1708037984044.192, "dur": 19.867, + "args": { + "External id": 4678726,"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": 1708037984086.618, "dur": 49.205, + "args": { + "External id": 4678727,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037984146.539, "dur": 37.215, + "args": { + "External id": 4678728,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037984194.251, "dur": 22.614, + "args": { + "External id": 4678729,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037984222.625, "dur": 31.113, + "args": { + "External id": 4678730,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037984264.138, "dur": 21.910, + "args": { + "External id": 4678731,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037984294.197, "dur": 33.041, + "args": { + "External id": 4678732,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037984345.942, "dur": 24.792, + "args": { + "External id": 4678733,"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": 1708037984388.281, "dur": 25.360, + "args": { + "External id": 4678734,"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": 1708037984427.644, "dur": 17.708, + "args": { + "External id": 4678735,"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": 1708037984461.524, "dur": 15.200, + "args": { + "External id": 4678736,"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": 1708037984489.168, "dur": 17.900, + "args": { + "External id": 4678737,"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": 1708037984595.911, "dur": 15.920, + "args": { + "External id": 4678738,"Record function id": 0, "Ev Idx": 3153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037984599.336, "dur": 11.573, + "args": { + "External id": 4678739,"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": 1708037984603.414, "dur": 6.436, + "args": { + "External id": 4678740,"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": 1708037984605.603, "dur": 4.080, + "args": { + "External id": 4678741,"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": 1708037984615.898, "dur": 4.767, + "args": { + "External id": 4678742,"Record function id": 0, "Ev Idx": 3157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037984617.250, "dur": 2.955, + "args": { + "External id": 4678743,"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": 1708037984617.916, "dur": 1.821, + "args": { + "External id": 4678744,"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": 1708037984618.654, "dur": 0.988, + "args": { + "External id": 4678745,"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": 1708037984624.039, "dur": 6.759, + "args": { + "External id": 4678746,"Record function id": 0, "Ev Idx": 3161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037984625.264, "dur": 5.143, + "args": { + "External id": 4678747,"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": 1708037984626.070, "dur": 3.844, + "args": { + "External id": 4678748,"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": 1708037984626.564, "dur": 3.257, + "args": { + "External id": 4678749,"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": 1708037984634.150, "dur": 3.972, + "args": { + "External id": 4678750,"Record function id": 0, "Ev Idx": 3165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037984635.275, "dur": 2.415, + "args": { + "External id": 4678751,"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": 1708037984635.774, "dur": 1.360, + "args": { + "External id": 4678752,"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": 1708037984636.278, "dur": 0.784, + "args": { + "External id": 4678753,"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": 1708037984641.398, "dur": 3.897, + "args": { + "External id": 4678754,"Record function id": 0, "Ev Idx": 3169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037984642.428, "dur": 2.465, + "args": { + "External id": 4678755,"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": 1708037984642.933, "dur": 1.430, + "args": { + "External id": 4678756,"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": 1708037984643.321, "dur": 0.970, + "args": { + "External id": 4678757,"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": 1708037984648.818, "dur": 4.450, + "args": { + "External id": 4678758,"Record function id": 0, "Ev Idx": 3173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037984650.494, "dur": 2.381, + "args": { + "External id": 4678759,"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": 1708037984650.967, "dur": 1.466, + "args": { + "External id": 4678760,"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": 1708037984651.600, "dur": 0.733, + "args": { + "External id": 4678761,"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": 1708037984656.886, "dur": 4.193, + "args": { + "External id": 4678762,"Record function id": 0, "Ev Idx": 3177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037984658.420, "dur": 2.256, + "args": { + "External id": 4678763,"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": 1708037984659.009, "dur": 1.261, + "args": { + "External id": 4678764,"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": 1708037984659.511, "dur": 0.685, + "args": { + "External id": 4678765,"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": 1708037984664.320, "dur": 3.647, + "args": { + "External id": 4678766,"Record function id": 0, "Ev Idx": 3181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037984665.650, "dur": 1.903, + "args": { + "External id": 4678767,"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": 1708037984666.122, "dur": 1.016, + "args": { + "External id": 4678768,"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": 1708037984666.416, "dur": 0.648, + "args": { + "External id": 4678769,"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": 1708037984671.133, "dur": 3.929, + "args": { + "External id": 4678770,"Record function id": 0, "Ev Idx": 3185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708037984672.328, "dur": 2.351, + "args": { + "External id": 4678771,"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": 1708037984672.825, "dur": 1.441, + "args": { + "External id": 4678772,"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": 1708037984673.431, "dur": 0.739, + "args": { + "External id": 4678773,"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": 1708037984679.099, "dur": 37063.481, + "args": { + "External id": 4678774,"Record function id": 0, "Sequence number": 46526467, "Fwd thread id": 1, "Ev Idx": 3189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708037984680.399, "dur": 37054.031, + "args": { + "External id": 4678775,"Sequence number": 46526467, "Fwd thread 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": 1708037984680.399, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 1336753, "tid": 1381210, + "ts": 1708037984710.068, "dur": 37.576, + "args": { + "External id": 4678776,"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": 1708037984755.764, "dur": 70.534, + "args": { + "External id": 4678777,"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": 1708037984832.231, "dur": 36893.847, + "args": { + "External id": 4678778,"Record function id": 0, "Ev Idx": 3193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708037984919.865, "dur": 7.117, + "args": { + "External id": 4678779,"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": 1708037984936.706, "dur": 6.930, + "args": { + "External id": 4678780,"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": 1708037984958.787, "dur": 35905.226, + "args": { + "External id": 4678781,"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": 1708037984972.237, "dur": 35880.524, + "args": { + "External id": 4678782,"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": 1708037985062.575, "dur": 14.090, + "args": { + "External id": 4678783,"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": 1708037985083.029, "dur": 35727.476, + "args": { + "External id": 4678784,"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": 1708037985085.739, "dur": 35723.728, + "args": { + "External id": 4678785,"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": 1708037985089.998, "dur": 6.075, + "args": { + "External id": 4678786,"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": 1708037985098.077, "dur": 35707.373, + "args": { + "External id": 4678787,"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": 1708038020964.281, "dur": 10.866, + "args": { + "External id": 4678788,"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": 1708038020968.257, "dur": 6.551, + "args": { + "External id": 4678789,"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": 1708038021031.725, "dur": 357.081, + "args": { + "External id": 4678790,"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": 1708038021058.181, "dur": 325.351, + "args": { + "External id": 4678791,"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": 1708038021069.576, "dur": 308.197, + "args": { + "External id": 4678792,"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": 1708038021409.626, "dur": 2.639, + "args": { + "External id": 4678793,"Record function id": 0, "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": 1708038021477.923, "dur": 6.770, + "args": { + "External id": 4678794,"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": 1708038021546.587, "dur": 2.070, + "args": { + "External id": 4678795,"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": 1708038021572.447, "dur": 3.397, + "args": { + "External id": 4678796,"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": 1708038021588.918, "dur": 1.042, + "args": { + "External id": 4678797,"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": 1708038021602.298, "dur": 1.359, + "args": { + "External id": 4678798,"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": 1708038021615.113, "dur": 1.078, + "args": { + "External id": 4678799,"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": 1708038021632.631, "dur": 3.055, + "args": { + "External id": 4678800,"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": 1708038021648.849, "dur": 1.908, + "args": { + "External id": 4678801,"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": 1708038021663.528, "dur": 0.929, + "args": { + "External id": 4678802,"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": 1708038021758.319, "dur": 2856.664, + "args": { + "External id": 4678803,"Record function id": 0, "Ev Idx": 3218 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1708038021777.749, "dur": 1068.069, + "args": { + "External id": 4678804,"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": 1708038021793.710, "dur": 371.405, + "args": { + "External id": 4678805,"Record function id": 0, "Ev Idx": 3220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038021876.930, "dur": 4.309, + "args": { + "External id": 4678806,"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": 1708038021884.458, "dur": 0.985, + "args": { + "External id": 4678807,"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": 1708038021887.332, "dur": 3.571, + "args": { + "External id": 4678808,"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": 1708038021892.628, "dur": 1.210, + "args": { + "External id": 4678809,"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": 1708038021895.578, "dur": 1.032, + "args": { + "External id": 4678810,"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": 1708038021898.296, "dur": 1.122, + "args": { + "External id": 4678811,"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": 1708038021901.121, "dur": 1.939, + "args": { + "External id": 4678812,"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": 1708038021904.642, "dur": 1.172, + "args": { + "External id": 4678813,"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": 1708038021907.524, "dur": 0.748, + "args": { + "External id": 4678814,"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": 1708038021909.813, "dur": 1.230, + "args": { + "External id": 4678815,"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": 1708038021929.546, "dur": 199.548, + "args": { + "External id": 4678816,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038021945.437, "dur": 178.484, + "args": { + "External id": 4678817,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038021972.090, "dur": 50.407, + "args": { + "External id": 4678818,"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": 1708038022027.225, "dur": 67.087, + "args": { + "External id": 4678819,"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": 1708038022029.961, "dur": 63.961, + "args": { + "External id": 4678820,"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": 1708038022034.515, "dur": 6.229, + "args": { + "External id": 4678821,"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": 1708038022042.718, "dur": 50.567, + "args": { + "External id": 4678822,"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": 1708038022267.280, "dur": 566.937, + "args": { + "External id": 4678823,"Record function id": 0, "Ev Idx": 3238 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1708038022284.332, "dur": 536.938, + "args": { + "External id": 4678824,"Record function id": 0, "Ev Idx": 3239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038022348.137, "dur": 5.037, + "args": { + "External id": 4678825,"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": 1708038022368.675, "dur": 32.183, + "args": { + "External id": 4678826,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038022373.747, "dur": 1.460, + "args": { + "External id": 4678827,"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": 1708038022377.640, "dur": 0.620, + "args": { + "External id": 4678828,"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": 1708038022380.139, "dur": 0.486, + "args": { + "External id": 4678829,"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": 1708038022382.343, "dur": 0.609, + "args": { + "External id": 4678830,"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": 1708038022384.646, "dur": 0.408, + "args": { + "External id": 4678831,"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": 1708038022386.799, "dur": 2.623, + "args": { + "External id": 4678832,"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": 1708038022391.143, "dur": 0.511, + "args": { + "External id": 4678833,"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": 1708038022393.220, "dur": 0.588, + "args": { + "External id": 4678834,"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": 1708038022395.540, "dur": 0.441, + "args": { + "External id": 4678835,"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": 1708038022411.296, "dur": 32.351, + "args": { + "External id": 4678836,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038022474.891, "dur": 125.008, + "args": { + "External id": 4678837,"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": 1708038022484.643, "dur": 3.240, + "args": { + "External id": 4678838,"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": 1708038022492.995, "dur": 10.152, + "args": { + "External id": 4678839,"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": 1708038022497.098, "dur": 5.647, + "args": { + "External id": 4678840,"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": 1708038022501.069, "dur": 0.583, + "args": { + "External id": 4678841,"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": 1708038022510.034, "dur": 44.060, + "args": { + "External id": 4678842,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038022512.492, "dur": 0.544, + "args": { + "External id": 4678843,"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": 1708038022515.732, "dur": 0.467, + "args": { + "External id": 4678844,"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": 1708038022517.843, "dur": 2.109, + "args": { + "External id": 4678845,"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": 1708038022521.773, "dur": 0.465, + "args": { + "External id": 4678846,"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": 1708038022539.534, "dur": 0.812, + "args": { + "External id": 4678847,"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": 1708038022542.985, "dur": 0.340, + "args": { + "External id": 4678848,"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": 1708038022545.364, "dur": 0.384, + "args": { + "External id": 4678849,"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": 1708038022547.502, "dur": 0.404, + "args": { + "External id": 4678850,"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": 1708038022549.678, "dur": 0.557, + "args": { + "External id": 4678851,"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": 1708038022568.289, "dur": 24.165, + "args": { + "External id": 4678852,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038022646.923, "dur": 109.429, + "args": { + "External id": 4678853,"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": 1708038022669.827, "dur": 83.189, + "args": { + "External id": 4678854,"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": 1708038022679.596, "dur": 69.274, + "args": { + "External id": 4678855,"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": 1708038022769.242, "dur": 1.876, + "args": { + "External id": 4678856,"Record function id": 0, "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": 1708038022854.108, "dur": 1737.943, + "args": { + "External id": 4678857,"Sequence number": 46526466, "Fwd thread 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": 1708038022854.108, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038022962.367, "dur": 138.813, + "args": { + "External id": 4678858,"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": 1708038023143.175, "dur": 43.153, + "args": { + "External id": 4678859,"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": 1708038023205.795, "dur": 52.382, + "args": { + "External id": 4678860,"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": 1708038023270.212, "dur": 34.219, + "args": { + "External id": 4678861,"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": 1708038023312.377, "dur": 46.472, + "args": { + "External id": 4678862,"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": 1708038023384.269, "dur": 30.887, + "args": { + "External id": 4678863,"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": 1708038023424.369, "dur": 42.049, + "args": { + "External id": 4678864,"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": 1708038023490.663, "dur": 25.295, + "args": { + "External id": 4678865,"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": 1708038023551.307, "dur": 31.892, + "args": { + "External id": 4678866,"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": 1708038023611.166, "dur": 21.684, + "args": { + "External id": 4678867,"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": 1708038023647.603, "dur": 17.311, + "args": { + "External id": 4678868,"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": 1708038023675.598, "dur": 35.524, + "args": { + "External id": 4678869,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038023715.134, "dur": 33.655, + "args": { + "External id": 4678870,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038023777.826, "dur": 172.692, + "args": { + "External id": 4678871,"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": 1708038023856.539, "dur": 5.709, + "args": { + "External id": 4678872,"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": 1708038023864.327, "dur": 2.223, + "args": { + "External id": 4678873,"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": 1708038024022.983, "dur": 31.018, + "args": { + "External id": 4678874,"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": 1708038024067.682, "dur": 16.085, + "args": { + "External id": 4678875,"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": 1708038024094.555, "dur": 44.153, + "args": { + "External id": 4678876,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038024146.517, "dur": 50.229, + "args": { + "External id": 4678877,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038024212.948, "dur": 27.754, + "args": { + "External id": 4678878,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038024246.725, "dur": 33.516, + "args": { + "External id": 4678879,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038024286.277, "dur": 26.897, + "args": { + "External id": 4678880,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038024321.007, "dur": 30.186, + "args": { + "External id": 4678881,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038024374.534, "dur": 24.990, + "args": { + "External id": 4678882,"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": 1708038024420.863, "dur": 25.598, + "args": { + "External id": 4678883,"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": 1708038024461.897, "dur": 21.254, + "args": { + "External id": 4678884,"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": 1708038024497.780, "dur": 16.155, + "args": { + "External id": 4678885,"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": 1708038024541.352, "dur": 20.697, + "args": { + "External id": 4678886,"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": 1708038024638.571, "dur": 14.913, + "args": { + "External id": 4678887,"Record function id": 0, "Ev Idx": 3302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038024641.644, "dur": 10.766, + "args": { + "External id": 4678888,"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": 1708038024645.449, "dur": 5.936, + "args": { + "External id": 4678889,"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": 1708038024647.178, "dur": 4.085, + "args": { + "External id": 4678890,"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": 1708038024657.605, "dur": 7.839, + "args": { + "External id": 4678891,"Record function id": 0, "Ev Idx": 3306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038024659.358, "dur": 5.605, + "args": { + "External id": 4678892,"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": 1708038024660.596, "dur": 3.723, + "args": { + "External id": 4678893,"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": 1708038024661.420, "dur": 2.776, + "args": { + "External id": 4678894,"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": 1708038024668.891, "dur": 4.400, + "args": { + "External id": 4678895,"Record function id": 0, "Ev Idx": 3310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038024670.311, "dur": 2.586, + "args": { + "External id": 4678896,"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": 1708038024670.853, "dur": 1.595, + "args": { + "External id": 4678897,"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": 1708038024671.380, "dur": 0.973, + "args": { + "External id": 4678898,"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": 1708038024676.598, "dur": 4.606, + "args": { + "External id": 4678899,"Record function id": 0, "Ev Idx": 3314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038024678.122, "dur": 2.677, + "args": { + "External id": 4678900,"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": 1708038024678.929, "dur": 1.480, + "args": { + "External id": 4678901,"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": 1708038024679.629, "dur": 0.705, + "args": { + "External id": 4678902,"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": 1708038024684.584, "dur": 4.191, + "args": { + "External id": 4678903,"Record function id": 0, "Ev Idx": 3318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038024685.823, "dur": 2.535, + "args": { + "External id": 4678904,"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": 1708038024686.378, "dur": 1.234, + "args": { + "External id": 4678905,"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": 1708038024686.840, "dur": 0.700, + "args": { + "External id": 4678906,"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": 1708038024692.042, "dur": 3.969, + "args": { + "External id": 4678907,"Record function id": 0, "Ev Idx": 3322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038024693.232, "dur": 2.367, + "args": { + "External id": 4678908,"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": 1708038024693.819, "dur": 1.226, + "args": { + "External id": 4678909,"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": 1708038024694.314, "dur": 0.626, + "args": { + "External id": 4678910,"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": 1708038024699.220, "dur": 3.604, + "args": { + "External id": 4678911,"Record function id": 0, "Ev Idx": 3326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038024700.307, "dur": 2.135, + "args": { + "External id": 4678912,"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": 1708038024700.881, "dur": 1.029, + "args": { + "External id": 4678913,"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": 1708038024701.161, "dur": 0.657, + "args": { + "External id": 4678914,"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": 1708038024705.978, "dur": 4.537, + "args": { + "External id": 4678915,"Record function id": 0, "Ev Idx": 3330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038024707.353, "dur": 2.760, + "args": { + "External id": 4678916,"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": 1708038024708.101, "dur": 1.565, + "args": { + "External id": 4678917,"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": 1708038024708.941, "dur": 0.647, + "args": { + "External id": 4678918,"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": 1708038024713.618, "dur": 5.913, + "args": { + "External id": 4678919,"Record function id": 0, "Ev Idx": 3334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038024714.855, "dur": 4.263, + "args": { + "External id": 4678920,"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": 1708038024715.502, "dur": 3.181, + "args": { + "External id": 4678921,"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": 1708038024716.091, "dur": 2.507, + "args": { + "External id": 4678922,"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": 1708038024723.379, "dur": 37464.186, + "args": { + "External id": 4678923,"Record function id": 0, "Sequence number": 46526465, "Fwd thread id": 1, "Ev Idx": 3338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038024724.887, "dur": 37454.014, + "args": { + "External id": 4678924,"Sequence number": 46526465, "Fwd thread 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": 1708038024724.887, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 1336753, "tid": 1381210, + "ts": 1708038024752.333, "dur": 37.784, + "args": { + "External id": 4678925,"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": 1708038024797.806, "dur": 67.013, + "args": { + "External id": 4678926,"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": 1708038024870.619, "dur": 37299.678, + "args": { + "External id": 4678927,"Record function id": 0, "Ev Idx": 3342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038024956.721, "dur": 6.633, + "args": { + "External id": 4678928,"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": 1708038024972.773, "dur": 4.628, + "args": { + "External id": 4678929,"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": 1708038025028.337, "dur": 36272.205, + "args": { + "External id": 4678930,"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": 1708038025042.940, "dur": 36247.643, + "args": { + "External id": 4678931,"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": 1708038025108.704, "dur": 13.821, + "args": { + "External id": 4678932,"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": 1708038025128.837, "dur": 36123.385, + "args": { + "External id": 4678933,"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": 1708038025131.734, "dur": 36119.599, + "args": { + "External id": 4678934,"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": 1708038025135.841, "dur": 6.470, + "args": { + "External id": 4678935,"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": 1708038025144.382, "dur": 36103.362, + "args": { + "External id": 4678936,"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": 1708038061395.524, "dur": 10.066, + "args": { + "External id": 4678937,"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": 1708038061399.393, "dur": 5.804, + "args": { + "External id": 4678938,"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": 1708038061440.092, "dur": 357.868, + "args": { + "External id": 4678939,"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": 1708038061466.814, "dur": 326.246, + "args": { + "External id": 4678940,"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": 1708038061477.836, "dur": 308.984, + "args": { + "External id": 4678941,"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": 1708038061829.084, "dur": 2.329, + "args": { + "External id": 4678942,"Record function id": 0, "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": 1708038061892.515, "dur": 6.719, + "args": { + "External id": 4678943,"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": 1708038061945.505, "dur": 3.753, + "args": { + "External id": 4678944,"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": 1708038061967.650, "dur": 0.921, + "args": { + "External id": 4678945,"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": 1708038062024.170, "dur": 2.029, + "args": { + "External id": 4678946,"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": 1708038062044.914, "dur": 1.052, + "args": { + "External id": 4678947,"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": 1708038062059.019, "dur": 2.406, + "args": { + "External id": 4678948,"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": 1708038062074.257, "dur": 0.967, + "args": { + "External id": 4678949,"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": 1708038062088.917, "dur": 2.208, + "args": { + "External id": 4678950,"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": 1708038062103.931, "dur": 0.799, + "args": { + "External id": 4678951,"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": 1708038062207.278, "dur": 2854.913, + "args": { + "External id": 4678952,"Record function id": 0, "Ev Idx": 3367 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1708038062226.858, "dur": 1072.639, + "args": { + "External id": 4678953,"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": 1708038062241.890, "dur": 337.283, + "args": { + "External id": 4678954,"Record function id": 0, "Ev Idx": 3369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038062322.076, "dur": 6.143, + "args": { + "External id": 4678955,"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": 1708038062331.172, "dur": 1.096, + "args": { + "External id": 4678956,"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": 1708038062334.357, "dur": 1.407, + "args": { + "External id": 4678957,"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": 1708038062337.180, "dur": 1.198, + "args": { + "External id": 4678958,"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": 1708038062340.203, "dur": 0.996, + "args": { + "External id": 4678959,"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": 1708038062342.824, "dur": 0.931, + "args": { + "External id": 4678960,"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": 1708038062345.563, "dur": 1.640, + "args": { + "External id": 4678961,"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": 1708038062348.808, "dur": 1.084, + "args": { + "External id": 4678962,"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": 1708038062351.712, "dur": 2.948, + "args": { + "External id": 4678963,"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": 1708038062356.209, "dur": 0.725, + "args": { + "External id": 4678964,"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": 1708038062375.218, "dur": 168.710, + "args": { + "External id": 4678965,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038062392.166, "dur": 130.258, + "args": { + "External id": 4678966,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038062413.960, "dur": 11.799, + "args": { + "External id": 4678967,"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": 1708038062429.293, "dur": 64.981, + "args": { + "External id": 4678968,"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": 1708038062431.929, "dur": 61.901, + "args": { + "External id": 4678969,"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": 1708038062436.096, "dur": 5.287, + "args": { + "External id": 4678970,"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": 1708038062443.235, "dur": 49.818, + "args": { + "External id": 4678971,"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": 1708038062685.079, "dur": 605.352, + "args": { + "External id": 4678972,"Record function id": 0, "Ev Idx": 3387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1708038062703.698, "dur": 573.756, + "args": { + "External id": 4678973,"Record function id": 0, "Ev Idx": 3388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038062771.030, "dur": 5.997, + "args": { + "External id": 4678974,"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": 1708038062792.646, "dur": 32.892, + "args": { + "External id": 4678975,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038062797.759, "dur": 1.606, + "args": { + "External id": 4678976,"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": 1708038062802.210, "dur": 0.595, + "args": { + "External id": 4678977,"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": 1708038062804.385, "dur": 0.639, + "args": { + "External id": 4678978,"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": 1708038062806.945, "dur": 2.589, + "args": { + "External id": 4678979,"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": 1708038062811.252, "dur": 0.485, + "args": { + "External id": 4678980,"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": 1708038062813.478, "dur": 0.514, + "args": { + "External id": 4678981,"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": 1708038062815.691, "dur": 0.433, + "args": { + "External id": 4678982,"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": 1708038062818.183, "dur": 0.355, + "args": { + "External id": 4678983,"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": 1708038062820.345, "dur": 0.381, + "args": { + "External id": 4678984,"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": 1708038062835.961, "dur": 34.608, + "args": { + "External id": 4678985,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038062901.288, "dur": 153.824, + "args": { + "External id": 4678986,"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": 1708038062911.069, "dur": 3.297, + "args": { + "External id": 4678987,"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": 1708038062919.673, "dur": 10.372, + "args": { + "External id": 4678988,"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": 1708038062923.819, "dur": 5.792, + "args": { + "External id": 4678989,"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": 1708038062927.955, "dur": 0.537, + "args": { + "External id": 4678990,"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": 1708038062937.233, "dur": 27.805, + "args": { + "External id": 4678991,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038062940.150, "dur": 2.608, + "args": { + "External id": 4678992,"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": 1708038062944.444, "dur": 0.431, + "args": { + "External id": 4678993,"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": 1708038062946.471, "dur": 0.371, + "args": { + "External id": 4678994,"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": 1708038062949.012, "dur": 0.534, + "args": { + "External id": 4678995,"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": 1708038062951.207, "dur": 0.389, + "args": { + "External id": 4678996,"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": 1708038062953.427, "dur": 0.350, + "args": { + "External id": 4678997,"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": 1708038062955.472, "dur": 0.516, + "args": { + "External id": 4678998,"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": 1708038062957.716, "dur": 0.361, + "args": { + "External id": 4678999,"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": 1708038062959.764, "dur": 2.198, + "args": { + "External id": 4679000,"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": 1708038062976.032, "dur": 69.409, + "args": { + "External id": 4679001,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038063107.226, "dur": 109.082, + "args": { + "External id": 4679002,"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": 1708038063130.919, "dur": 81.831, + "args": { + "External id": 4679003,"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": 1708038063140.171, "dur": 68.669, + "args": { + "External id": 4679004,"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": 1708038063228.855, "dur": 1.788, + "args": { + "External id": 4679005,"Record function id": 0, "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": 1708038063308.192, "dur": 1726.603, + "args": { + "External id": 4679006,"Sequence number": 46526464, "Fwd thread 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": 1708038063308.192, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038063423.702, "dur": 97.270, + "args": { + "External id": 4679007,"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": 1708038063578.744, "dur": 44.588, + "args": { + "External id": 4679008,"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": 1708038063644.986, "dur": 55.016, + "args": { + "External id": 4679009,"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": 1708038063709.703, "dur": 34.562, + "args": { + "External id": 4679010,"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": 1708038063752.003, "dur": 46.903, + "args": { + "External id": 4679011,"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": 1708038063807.133, "dur": 29.971, + "args": { + "External id": 4679012,"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": 1708038063847.296, "dur": 43.989, + "args": { + "External id": 4679013,"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": 1708038063912.130, "dur": 24.203, + "args": { + "External id": 4679014,"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": 1708038063954.432, "dur": 78.653, + "args": { + "External id": 4679015,"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": 1708038064058.003, "dur": 23.932, + "args": { + "External id": 4679016,"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": 1708038064095.988, "dur": 17.587, + "args": { + "External id": 4679017,"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": 1708038064125.101, "dur": 35.076, + "args": { + "External id": 4679018,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038064163.886, "dur": 35.618, + "args": { + "External id": 4679019,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038064248.799, "dur": 173.819, + "args": { + "External id": 4679020,"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": 1708038064328.716, "dur": 5.494, + "args": { + "External id": 4679021,"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": 1708038064336.083, "dur": 2.260, + "args": { + "External id": 4679022,"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": 1708038064456.758, "dur": 25.787, + "args": { + "External id": 4679023,"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": 1708038064493.834, "dur": 16.248, + "args": { + "External id": 4679024,"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": 1708038064517.975, "dur": 54.289, + "args": { + "External id": 4679025,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038064583.441, "dur": 50.765, + "args": { + "External id": 4679026,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038064647.761, "dur": 29.226, + "args": { + "External id": 4679027,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038064682.808, "dur": 33.244, + "args": { + "External id": 4679028,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038064722.109, "dur": 25.194, + "args": { + "External id": 4679029,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038064757.123, "dur": 30.136, + "args": { + "External id": 4679030,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038064808.926, "dur": 26.888, + "args": { + "External id": 4679031,"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": 1708038064852.776, "dur": 25.212, + "args": { + "External id": 4679032,"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": 1708038064892.400, "dur": 18.553, + "args": { + "External id": 4679033,"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": 1708038064924.892, "dur": 16.160, + "args": { + "External id": 4679034,"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": 1708038064954.030, "dur": 16.533, + "args": { + "External id": 4679035,"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": 1708038065085.617, "dur": 17.674, + "args": { + "External id": 4679036,"Record function id": 0, "Ev Idx": 3451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038065089.223, "dur": 13.149, + "args": { + "External id": 4679037,"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": 1708038065093.223, "dur": 8.039, + "args": { + "External id": 4679038,"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": 1708038065095.091, "dur": 6.043, + "args": { + "External id": 4679039,"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": 1708038065107.162, "dur": 5.536, + "args": { + "External id": 4679040,"Record function id": 0, "Ev Idx": 3455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038065108.657, "dur": 3.522, + "args": { + "External id": 4679041,"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": 1708038065109.580, "dur": 2.100, + "args": { + "External id": 4679042,"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": 1708038065110.431, "dur": 1.121, + "args": { + "External id": 4679043,"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": 1708038065116.214, "dur": 4.486, + "args": { + "External id": 4679044,"Record function id": 0, "Ev Idx": 3459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038065117.588, "dur": 2.696, + "args": { + "External id": 4679045,"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": 1708038065118.302, "dur": 1.482, + "args": { + "External id": 4679046,"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": 1708038065118.742, "dur": 0.957, + "args": { + "External id": 4679047,"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": 1708038065123.944, "dur": 4.633, + "args": { + "External id": 4679048,"Record function id": 0, "Ev Idx": 3463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038065125.402, "dur": 2.750, + "args": { + "External id": 4679049,"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": 1708038065126.127, "dur": 1.385, + "args": { + "External id": 4679050,"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": 1708038065126.444, "dur": 0.975, + "args": { + "External id": 4679051,"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": 1708038065131.787, "dur": 3.879, + "args": { + "External id": 4679052,"Record function id": 0, "Ev Idx": 3467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038065133.000, "dur": 2.204, + "args": { + "External id": 4679053,"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": 1708038065133.431, "dur": 1.035, + "args": { + "External id": 4679054,"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": 1708038065133.720, "dur": 0.681, + "args": { + "External id": 4679055,"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": 1708038065138.811, "dur": 3.817, + "args": { + "External id": 4679056,"Record function id": 0, "Ev Idx": 3471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038065139.910, "dur": 2.320, + "args": { + "External id": 4679057,"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": 1708038065140.539, "dur": 1.168, + "args": { + "External id": 4679058,"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": 1708038065140.994, "dur": 0.605, + "args": { + "External id": 4679059,"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": 1708038065145.749, "dur": 3.604, + "args": { + "External id": 4679060,"Record function id": 0, "Ev Idx": 3475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038065146.878, "dur": 2.071, + "args": { + "External id": 4679061,"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": 1708038065147.348, "dur": 1.171, + "args": { + "External id": 4679062,"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": 1708038065147.720, "dur": 0.717, + "args": { + "External id": 4679063,"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": 1708038065152.493, "dur": 5.979, + "args": { + "External id": 4679064,"Record function id": 0, "Ev Idx": 3479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038065153.679, "dur": 4.389, + "args": { + "External id": 4679065,"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": 1708038065154.456, "dur": 3.077, + "args": { + "External id": 4679066,"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": 1708038065154.964, "dur": 2.482, + "args": { + "External id": 4679067,"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": 1708038065161.633, "dur": 5.169, + "args": { + "External id": 4679068,"Record function id": 0, "Ev Idx": 3483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038065163.374, "dur": 3.032, + "args": { + "External id": 4679069,"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": 1708038065164.199, "dur": 1.813, + "args": { + "External id": 4679070,"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": 1708038065165.054, "dur": 0.860, + "args": { + "External id": 4679071,"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": 1708038065170.850, "dur": 37978.241, + "args": { + "External id": 4679072,"Record function id": 0, "Sequence number": 46526463, "Fwd thread id": 1, "Ev Idx": 3487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038065172.379, "dur": 37968.272, + "args": { + "External id": 4679073,"Sequence number": 46526463, "Fwd thread 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": 1708038065172.379, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 1336753, "tid": 1381210, + "ts": 1708038065201.404, "dur": 34.753, + "args": { + "External id": 4679074,"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": 1708038065243.214, "dur": 60.587, + "args": { + "External id": 4679075,"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": 1708038065309.824, "dur": 37822.887, + "args": { + "External id": 4679076,"Record function id": 0, "Ev Idx": 3491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038065391.921, "dur": 6.483, + "args": { + "External id": 4679077,"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": 1708038065408.365, "dur": 4.604, + "args": { + "External id": 4679078,"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": 1708038065427.839, "dur": 36997.307, + "args": { + "External id": 4679079,"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": 1708038065441.503, "dur": 36974.590, + "args": { + "External id": 4679080,"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": 1708038065504.350, "dur": 12.197, + "args": { + "External id": 4679081,"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": 1708038065522.866, "dur": 36852.024, + "args": { + "External id": 4679082,"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": 1708038065543.037, "dur": 36831.247, + "args": { + "External id": 4679083,"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": 1708038065547.545, "dur": 6.714, + "args": { + "External id": 4679084,"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": 1708038065556.377, "dur": 36814.901, + "args": { + "External id": 4679085,"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": 1708038102522.851, "dur": 20.671, + "args": { + "External id": 4679086,"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": 1708038102536.883, "dur": 6.088, + "args": { + "External id": 4679087,"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": 1708038102575.159, "dur": 238.910, + "args": { + "External id": 4679088,"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": 1708038102600.694, "dur": 208.888, + "args": { + "External id": 4679089,"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": 1708038102611.477, "dur": 192.770, + "args": { + "External id": 4679090,"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": 1708038102830.902, "dur": 2.093, + "args": { + "External id": 4679091,"Record function id": 0, "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": 1708038102885.192, "dur": 6.781, + "args": { + "External id": 4679092,"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": 1708038102936.395, "dur": 1.833, + "args": { + "External id": 4679093,"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": 1708038102955.827, "dur": 1.145, + "args": { + "External id": 4679094,"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": 1708038102970.053, "dur": 0.975, + "args": { + "External id": 4679095,"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": 1708038103013.537, "dur": 1.509, + "args": { + "External id": 4679096,"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": 1708038103033.368, "dur": 1.140, + "args": { + "External id": 4679097,"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": 1708038103045.243, "dur": 0.867, + "args": { + "External id": 4679098,"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": 1708038103057.625, "dur": 2.344, + "args": { + "External id": 4679099,"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": 1708038103069.812, "dur": 0.804, + "args": { + "External id": 4679100,"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": 1708038103165.537, "dur": 2902.770, + "args": { + "External id": 4679101,"Record function id": 0, "Ev Idx": 3516 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1708038103186.195, "dur": 1053.397, + "args": { + "External id": 4679102,"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": 1708038103202.403, "dur": 314.678, + "args": { + "External id": 4679103,"Record function id": 0, "Ev Idx": 3518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038103284.439, "dur": 3.989, + "args": { + "External id": 4679104,"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": 1708038103291.543, "dur": 1.399, + "args": { + "External id": 4679105,"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": 1708038103294.629, "dur": 1.256, + "args": { + "External id": 4679106,"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": 1708038103297.252, "dur": 1.209, + "args": { + "External id": 4679107,"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": 1708038103299.918, "dur": 1.320, + "args": { + "External id": 4679108,"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": 1708038103302.879, "dur": 0.878, + "args": { + "External id": 4679109,"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": 1708038103305.293, "dur": 1.574, + "args": { + "External id": 4679110,"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": 1708038103308.248, "dur": 3.000, + "args": { + "External id": 4679111,"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": 1708038103312.852, "dur": 1.048, + "args": { + "External id": 4679112,"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": 1708038103315.766, "dur": 1.496, + "args": { + "External id": 4679113,"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": 1708038103334.573, "dur": 151.136, + "args": { + "External id": 4679114,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038103350.363, "dur": 130.670, + "args": { + "External id": 4679115,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038103373.859, "dur": 11.588, + "args": { + "External id": 4679116,"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": 1708038103388.504, "dur": 62.171, + "args": { + "External id": 4679117,"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": 1708038103391.272, "dur": 59.062, + "args": { + "External id": 4679118,"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": 1708038103395.230, "dur": 5.008, + "args": { + "External id": 4679119,"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": 1708038103402.059, "dur": 47.681, + "args": { + "External id": 4679120,"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": 1708038103633.623, "dur": 596.403, + "args": { + "External id": 4679121,"Record function id": 0, "Ev Idx": 3536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1708038103654.001, "dur": 562.616, + "args": { + "External id": 4679122,"Record function id": 0, "Ev Idx": 3537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038103717.239, "dur": 5.508, + "args": { + "External id": 4679123,"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": 1708038103739.234, "dur": 30.106, + "args": { + "External id": 4679124,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038103743.925, "dur": 1.753, + "args": { + "External id": 4679125,"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": 1708038103748.043, "dur": 0.710, + "args": { + "External id": 4679126,"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": 1708038103750.592, "dur": 2.463, + "args": { + "External id": 4679127,"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": 1708038103754.420, "dur": 0.367, + "args": { + "External id": 4679128,"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": 1708038103756.398, "dur": 0.537, + "args": { + "External id": 4679129,"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": 1708038103758.871, "dur": 0.349, + "args": { + "External id": 4679130,"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": 1708038103760.924, "dur": 0.424, + "args": { + "External id": 4679131,"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": 1708038103763.081, "dur": 0.433, + "args": { + "External id": 4679132,"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": 1708038103764.967, "dur": 0.391, + "args": { + "External id": 4679133,"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": 1708038103779.716, "dur": 34.838, + "args": { + "External id": 4679134,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038103844.808, "dur": 108.663, + "args": { + "External id": 4679135,"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": 1708038103854.548, "dur": 3.143, + "args": { + "External id": 4679136,"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": 1708038103867.826, "dur": 12.158, + "args": { + "External id": 4679137,"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": 1708038103871.874, "dur": 7.677, + "args": { + "External id": 4679138,"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": 1708038103875.652, "dur": 2.765, + "args": { + "External id": 4679139,"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": 1708038103889.199, "dur": 24.455, + "args": { + "External id": 4679140,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038103891.535, "dur": 0.872, + "args": { + "External id": 4679141,"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": 1708038103893.932, "dur": 0.397, + "args": { + "External id": 4679142,"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": 1708038103895.843, "dur": 0.368, + "args": { + "External id": 4679143,"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": 1708038103897.646, "dur": 0.376, + "args": { + "External id": 4679144,"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": 1708038103899.593, "dur": 0.389, + "args": { + "External id": 4679145,"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": 1708038103901.388, "dur": 0.375, + "args": { + "External id": 4679146,"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": 1708038103903.482, "dur": 0.397, + "args": { + "External id": 4679147,"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": 1708038103905.397, "dur": 2.326, + "args": { + "External id": 4679148,"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": 1708038103909.173, "dur": 0.471, + "args": { + "External id": 4679149,"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": 1708038103925.781, "dur": 20.802, + "args": { + "External id": 4679150,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038104032.886, "dur": 113.634, + "args": { + "External id": 4679151,"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": 1708038104054.389, "dur": 88.622, + "args": { + "External id": 4679152,"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": 1708038104064.351, "dur": 74.436, + "args": { + "External id": 4679153,"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": 1708038104160.228, "dur": 1.894, + "args": { + "External id": 4679154,"Record function id": 0, "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": 1708038104247.471, "dur": 1799.345, + "args": { + "External id": 4679155,"Sequence number": 46526462, "Fwd thread 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": 1708038104247.471, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038104358.338, "dur": 98.578, + "args": { + "External id": 4679156,"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": 1708038104493.529, "dur": 60.479, + "args": { + "External id": 4679157,"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": 1708038104577.840, "dur": 52.877, + "args": { + "External id": 4679158,"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": 1708038104640.043, "dur": 34.338, + "args": { + "External id": 4679159,"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": 1708038104681.306, "dur": 45.786, + "args": { + "External id": 4679160,"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": 1708038104734.880, "dur": 28.893, + "args": { + "External id": 4679161,"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": 1708038104773.251, "dur": 42.636, + "args": { + "External id": 4679162,"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": 1708038104838.455, "dur": 23.896, + "args": { + "External id": 4679163,"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": 1708038104879.988, "dur": 28.158, + "args": { + "External id": 4679164,"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": 1708038104925.962, "dur": 20.930, + "args": { + "External id": 4679165,"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": 1708038104959.526, "dur": 15.579, + "args": { + "External id": 4679166,"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": 1708038105022.015, "dur": 36.935, + "args": { + "External id": 4679167,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038105062.734, "dur": 33.286, + "args": { + "External id": 4679168,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038105195.749, "dur": 189.481, + "args": { + "External id": 4679169,"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": 1708038105287.542, "dur": 5.985, + "args": { + "External id": 4679170,"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": 1708038105295.688, "dur": 2.101, + "args": { + "External id": 4679171,"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": 1708038105422.129, "dur": 27.245, + "args": { + "External id": 4679172,"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": 1708038105460.315, "dur": 15.991, + "args": { + "External id": 4679173,"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": 1708038105490.567, "dur": 55.062, + "args": { + "External id": 4679174,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038105554.958, "dur": 40.052, + "args": { + "External id": 4679175,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038105602.389, "dur": 23.535, + "args": { + "External id": 4679176,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038105632.154, "dur": 43.540, + "args": { + "External id": 4679177,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038105690.618, "dur": 28.985, + "args": { + "External id": 4679178,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038105728.139, "dur": 32.458, + "args": { + "External id": 4679179,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038105783.075, "dur": 26.274, + "args": { + "External id": 4679180,"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": 1708038105857.125, "dur": 27.458, + "args": { + "External id": 4679181,"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": 1708038105901.949, "dur": 19.479, + "args": { + "External id": 4679182,"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": 1708038105938.065, "dur": 15.558, + "args": { + "External id": 4679183,"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": 1708038105965.451, "dur": 47.840, + "args": { + "External id": 4679184,"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": 1708038106092.257, "dur": 15.381, + "args": { + "External id": 4679185,"Record function id": 0, "Ev Idx": 3600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038106096.139, "dur": 10.643, + "args": { + "External id": 4679186,"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": 1708038106100.049, "dur": 5.695, + "args": { + "External id": 4679187,"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": 1708038106101.526, "dur": 4.059, + "args": { + "External id": 4679188,"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": 1708038106111.509, "dur": 5.342, + "args": { + "External id": 4679189,"Record function id": 0, "Ev Idx": 3604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038106113.222, "dur": 3.202, + "args": { + "External id": 4679190,"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": 1708038106113.918, "dur": 1.880, + "args": { + "External id": 4679191,"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": 1708038106114.676, "dur": 1.030, + "args": { + "External id": 4679192,"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": 1708038106120.351, "dur": 4.602, + "args": { + "External id": 4679193,"Record function id": 0, "Ev Idx": 3608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038106121.742, "dur": 2.800, + "args": { + "External id": 4679194,"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": 1708038106122.454, "dur": 1.545, + "args": { + "External id": 4679195,"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": 1708038106122.792, "dur": 1.146, + "args": { + "External id": 4679196,"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": 1708038106128.142, "dur": 4.001, + "args": { + "External id": 4679197,"Record function id": 0, "Ev Idx": 3612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038106129.473, "dur": 2.268, + "args": { + "External id": 4679198,"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": 1708038106129.952, "dur": 1.208, + "args": { + "External id": 4679199,"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": 1708038106130.476, "dur": 0.612, + "args": { + "External id": 4679200,"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": 1708038106135.307, "dur": 3.734, + "args": { + "External id": 4679201,"Record function id": 0, "Ev Idx": 3616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038106136.612, "dur": 2.037, + "args": { + "External id": 4679202,"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": 1708038106137.044, "dur": 1.054, + "args": { + "External id": 4679203,"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": 1708038106137.356, "dur": 0.666, + "args": { + "External id": 4679204,"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": 1708038106142.337, "dur": 4.228, + "args": { + "External id": 4679205,"Record function id": 0, "Ev Idx": 3620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038106143.697, "dur": 2.477, + "args": { + "External id": 4679206,"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": 1708038106144.359, "dur": 1.302, + "args": { + "External id": 4679207,"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": 1708038106144.806, "dur": 0.764, + "args": { + "External id": 4679208,"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": 1708038106149.803, "dur": 6.211, + "args": { + "External id": 4679209,"Record function id": 0, "Ev Idx": 3624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038106151.026, "dur": 4.576, + "args": { + "External id": 4679210,"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": 1708038106151.973, "dur": 3.176, + "args": { + "External id": 4679211,"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": 1708038106152.240, "dur": 2.822, + "args": { + "External id": 4679212,"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": 1708038106159.347, "dur": 3.921, + "args": { + "External id": 4679213,"Record function id": 0, "Ev Idx": 3628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038106160.581, "dur": 2.264, + "args": { + "External id": 4679214,"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": 1708038106161.208, "dur": 1.220, + "args": { + "External id": 4679215,"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": 1708038106161.462, "dur": 0.880, + "args": { + "External id": 4679216,"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": 1708038106166.414, "dur": 4.143, + "args": { + "External id": 4679217,"Record function id": 0, "Ev Idx": 3632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038106167.726, "dur": 2.420, + "args": { + "External id": 4679218,"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": 1708038106168.362, "dur": 1.351, + "args": { + "External id": 4679219,"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": 1708038106169.013, "dur": 0.602, + "args": { + "External id": 4679220,"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": 1708038106174.186, "dur": 36184.559, + "args": { + "External id": 4679221,"Record function id": 0, "Sequence number": 46526461, "Fwd thread id": 1, "Ev Idx": 3636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038106175.517, "dur": 36174.440, + "args": { + "External id": 4679222,"Sequence number": 46526461, "Fwd thread 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": 1708038106175.517, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 1336753, "tid": 1381210, + "ts": 1708038106205.688, "dur": 40.137, + "args": { + "External id": 4679223,"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": 1708038106253.631, "dur": 65.945, + "args": { + "External id": 4679224,"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": 1708038106325.167, "dur": 36016.889, + "args": { + "External id": 4679225,"Record function id": 0, "Ev Idx": 3640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038106411.435, "dur": 6.898, + "args": { + "External id": 4679226,"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": 1708038106427.579, "dur": 4.703, + "args": { + "External id": 4679227,"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": 1708038106447.109, "dur": 35004.379, + "args": { + "External id": 4679228,"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": 1708038106460.339, "dur": 34975.975, + "args": { + "External id": 4679229,"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": 1708038106543.763, "dur": 14.420, + "args": { + "External id": 4679230,"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": 1708038106564.819, "dur": 34828.523, + "args": { + "External id": 4679231,"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": 1708038106567.724, "dur": 34824.673, + "args": { + "External id": 4679232,"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": 1708038106572.046, "dur": 6.490, + "args": { + "External id": 4679233,"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": 1708038106580.452, "dur": 34807.122, + "args": { + "External id": 4679234,"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": 1708038141570.093, "dur": 10.766, + "args": { + "External id": 4679235,"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": 1708038141573.759, "dur": 6.668, + "args": { + "External id": 4679236,"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": 1708038141613.065, "dur": 426.243, + "args": { + "External id": 4679237,"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": 1708038141644.109, "dur": 389.786, + "args": { + "External id": 4679238,"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": 1708038141655.204, "dur": 372.329, + "args": { + "External id": 4679239,"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": 1708038142061.867, "dur": 2.635, + "args": { + "External id": 4679240,"Record function id": 0, "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": 1708038142127.746, "dur": 8.348, + "args": { + "External id": 4679241,"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": 1708038142180.785, "dur": 1.354, + "args": { + "External id": 4679242,"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": 1708038142199.692, "dur": 1.078, + "args": { + "External id": 4679243,"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": 1708038142213.505, "dur": 1.124, + "args": { + "External id": 4679244,"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": 1708038142226.796, "dur": 3.378, + "args": { + "External id": 4679245,"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": 1708038142242.300, "dur": 0.880, + "args": { + "External id": 4679246,"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": 1708038142254.538, "dur": 0.926, + "args": { + "External id": 4679247,"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": 1708038142267.180, "dur": 1.655, + "args": { + "External id": 4679248,"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": 1708038142278.789, "dur": 2.588, + "args": { + "External id": 4679249,"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": 1708038142373.294, "dur": 2874.147, + "args": { + "External id": 4679250,"Record function id": 0, "Ev Idx": 3665 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1708038142392.313, "dur": 1115.764, + "args": { + "External id": 4679251,"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": 1708038142406.719, "dur": 414.095, + "args": { + "External id": 4679252,"Record function id": 0, "Ev Idx": 3667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038142492.553, "dur": 7.280, + "args": { + "External id": 4679253,"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": 1708038142502.549, "dur": 1.683, + "args": { + "External id": 4679254,"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": 1708038142505.825, "dur": 1.255, + "args": { + "External id": 4679255,"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": 1708038142508.439, "dur": 1.035, + "args": { + "External id": 4679256,"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": 1708038142510.810, "dur": 1.244, + "args": { + "External id": 4679257,"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": 1708038142513.413, "dur": 0.883, + "args": { + "External id": 4679258,"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": 1708038142515.882, "dur": 3.570, + "args": { + "External id": 4679259,"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": 1708038142520.903, "dur": 1.015, + "args": { + "External id": 4679260,"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": 1708038142523.129, "dur": 16.525, + "args": { + "External id": 4679261,"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": 1708038142543.596, "dur": 0.827, + "args": { + "External id": 4679262,"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": 1708038142565.753, "dur": 220.268, + "args": { + "External id": 4679263,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038142581.915, "dur": 199.071, + "args": { + "External id": 4679264,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038142660.489, "dur": 12.604, + "args": { + "External id": 4679265,"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": 1708038142676.167, "dur": 74.738, + "args": { + "External id": 4679266,"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": 1708038142678.931, "dur": 71.618, + "args": { + "External id": 4679267,"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": 1708038142686.524, "dur": 6.663, + "args": { + "External id": 4679268,"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": 1708038142695.183, "dur": 54.576, + "args": { + "External id": 4679269,"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": 1708038142917.458, "dur": 582.613, + "args": { + "External id": 4679270,"Record function id": 0, "Ev Idx": 3685 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1708038142935.629, "dur": 551.513, + "args": { + "External id": 4679271,"Record function id": 0, "Ev Idx": 3686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038143033.894, "dur": 6.960, + "args": { + "External id": 4679272,"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": 1708038143057.291, "dur": 30.311, + "args": { + "External id": 4679273,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038143062.471, "dur": 1.874, + "args": { + "External id": 4679274,"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": 1708038143066.785, "dur": 2.723, + "args": { + "External id": 4679275,"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": 1708038143071.036, "dur": 0.456, + "args": { + "External id": 4679276,"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": 1708038143073.010, "dur": 0.562, + "args": { + "External id": 4679277,"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": 1708038143075.116, "dur": 0.410, + "args": { + "External id": 4679278,"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": 1708038143077.095, "dur": 0.553, + "args": { + "External id": 4679279,"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": 1708038143079.068, "dur": 0.402, + "args": { + "External id": 4679280,"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": 1708038143081.126, "dur": 0.406, + "args": { + "External id": 4679281,"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": 1708038143083.135, "dur": 0.321, + "args": { + "External id": 4679282,"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": 1708038143098.574, "dur": 35.229, + "args": { + "External id": 4679283,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038143164.812, "dur": 104.287, + "args": { + "External id": 4679284,"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": 1708038143175.200, "dur": 5.857, + "args": { + "External id": 4679285,"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": 1708038143186.484, "dur": 10.173, + "args": { + "External id": 4679286,"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": 1708038143190.870, "dur": 5.375, + "args": { + "External id": 4679287,"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": 1708038143194.586, "dur": 0.533, + "args": { + "External id": 4679288,"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": 1708038143203.407, "dur": 23.884, + "args": { + "External id": 4679289,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038143205.896, "dur": 0.434, + "args": { + "External id": 4679290,"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": 1708038143208.003, "dur": 0.350, + "args": { + "External id": 4679291,"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": 1708038143209.758, "dur": 0.596, + "args": { + "External id": 4679292,"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": 1708038143212.004, "dur": 0.368, + "args": { + "External id": 4679293,"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": 1708038143213.942, "dur": 0.372, + "args": { + "External id": 4679294,"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": 1708038143216.096, "dur": 0.360, + "args": { + "External id": 4679295,"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": 1708038143217.835, "dur": 2.219, + "args": { + "External id": 4679296,"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": 1708038143221.607, "dur": 0.424, + "args": { + "External id": 4679297,"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": 1708038143223.764, "dur": 0.404, + "args": { + "External id": 4679298,"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": 1708038143241.197, "dur": 20.676, + "args": { + "External id": 4679299,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038143318.222, "dur": 108.878, + "args": { + "External id": 4679300,"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": 1708038143339.558, "dur": 84.070, + "args": { + "External id": 4679301,"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": 1708038143349.039, "dur": 70.409, + "args": { + "External id": 4679302,"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": 1708038143439.143, "dur": 1.728, + "args": { + "External id": 4679303,"Record function id": 0, "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": 1708038143515.160, "dur": 1710.869, + "args": { + "External id": 4679304,"Sequence number": 46526460, "Fwd thread 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": 1708038143515.160, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038143643.153, "dur": 106.798, + "args": { + "External id": 4679305,"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": 1708038143787.580, "dur": 41.778, + "args": { + "External id": 4679306,"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": 1708038143848.640, "dur": 46.088, + "args": { + "External id": 4679307,"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": 1708038143903.400, "dur": 33.473, + "args": { + "External id": 4679308,"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": 1708038143944.056, "dur": 96.102, + "args": { + "External id": 4679309,"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": 1708038144054.269, "dur": 34.262, + "args": { + "External id": 4679310,"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": 1708038144096.525, "dur": 43.146, + "args": { + "External id": 4679311,"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": 1708038144164.087, "dur": 24.621, + "args": { + "External id": 4679312,"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": 1708038144205.421, "dur": 28.974, + "args": { + "External id": 4679313,"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": 1708038144253.510, "dur": 19.386, + "args": { + "External id": 4679314,"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": 1708038144288.270, "dur": 15.429, + "args": { + "External id": 4679315,"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": 1708038144314.077, "dur": 30.206, + "args": { + "External id": 4679316,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038144347.593, "dur": 31.884, + "args": { + "External id": 4679317,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038144405.210, "dur": 184.295, + "args": { + "External id": 4679318,"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": 1708038144479.518, "dur": 6.096, + "args": { + "External id": 4679319,"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": 1708038144487.395, "dur": 4.190, + "args": { + "External id": 4679320,"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": 1708038144626.274, "dur": 27.061, + "args": { + "External id": 4679321,"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": 1708038144684.887, "dur": 16.850, + "args": { + "External id": 4679322,"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": 1708038144711.389, "dur": 43.675, + "args": { + "External id": 4679323,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038144762.107, "dur": 35.666, + "args": { + "External id": 4679324,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038144805.132, "dur": 36.915, + "args": { + "External id": 4679325,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038144854.567, "dur": 37.664, + "args": { + "External id": 4679326,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038144899.879, "dur": 22.492, + "args": { + "External id": 4679327,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038144930.018, "dur": 33.217, + "args": { + "External id": 4679328,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038145015.190, "dur": 30.297, + "args": { + "External id": 4679329,"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": 1708038145065.984, "dur": 27.185, + "args": { + "External id": 4679330,"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": 1708038145109.882, "dur": 18.612, + "args": { + "External id": 4679331,"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": 1708038145148.394, "dur": 16.949, + "args": { + "External id": 4679332,"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": 1708038145181.348, "dur": 17.268, + "args": { + "External id": 4679333,"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": 1708038145269.833, "dur": 15.607, + "args": { + "External id": 4679334,"Record function id": 0, "Ev Idx": 3749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038145273.373, "dur": 11.071, + "args": { + "External id": 4679335,"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": 1708038145277.261, "dur": 6.160, + "args": { + "External id": 4679336,"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": 1708038145279.025, "dur": 4.259, + "args": { + "External id": 4679337,"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": 1708038145289.405, "dur": 4.819, + "args": { + "External id": 4679338,"Record function id": 0, "Ev Idx": 3753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038145290.720, "dur": 3.081, + "args": { + "External id": 4679339,"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": 1708038145291.379, "dur": 1.993, + "args": { + "External id": 4679340,"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": 1708038145292.232, "dur": 1.043, + "args": { + "External id": 4679341,"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": 1708038145297.508, "dur": 8.115, + "args": { + "External id": 4679342,"Record function id": 0, "Ev Idx": 3757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038145299.047, "dur": 6.192, + "args": { + "External id": 4679343,"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": 1708038145299.551, "dur": 2.021, + "args": { + "External id": 4679344,"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": 1708038145300.359, "dur": 1.140, + "args": { + "External id": 4679345,"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": 1708038145308.735, "dur": 6.442, + "args": { + "External id": 4679346,"Record function id": 0, "Ev Idx": 3761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038145309.889, "dur": 4.885, + "args": { + "External id": 4679347,"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": 1708038145310.844, "dur": 3.486, + "args": { + "External id": 4679348,"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": 1708038145311.128, "dur": 3.142, + "args": { + "External id": 4679349,"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": 1708038145318.319, "dur": 3.832, + "args": { + "External id": 4679350,"Record function id": 0, "Ev Idx": 3765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038145319.562, "dur": 2.197, + "args": { + "External id": 4679351,"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": 1708038145320.330, "dur": 1.045, + "args": { + "External id": 4679352,"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": 1708038145320.614, "dur": 0.692, + "args": { + "External id": 4679353,"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": 1708038145325.236, "dur": 4.149, + "args": { + "External id": 4679354,"Record function id": 0, "Ev Idx": 3769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038145326.263, "dur": 2.730, + "args": { + "External id": 4679355,"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": 1708038145326.902, "dur": 1.441, + "args": { + "External id": 4679356,"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": 1708038145327.415, "dur": 0.820, + "args": { + "External id": 4679357,"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": 1708038145332.616, "dur": 3.553, + "args": { + "External id": 4679358,"Record function id": 0, "Ev Idx": 3773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038145333.652, "dur": 2.127, + "args": { + "External id": 4679359,"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": 1708038145334.113, "dur": 1.184, + "args": { + "External id": 4679360,"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": 1708038145334.599, "dur": 0.600, + "args": { + "External id": 4679361,"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": 1708038145339.476, "dur": 3.586, + "args": { + "External id": 4679362,"Record function id": 0, "Ev Idx": 3777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038145340.589, "dur": 2.067, + "args": { + "External id": 4679363,"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": 1708038145341.083, "dur": 1.099, + "args": { + "External id": 4679364,"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": 1708038145341.478, "dur": 0.634, + "args": { + "External id": 4679365,"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": 1708038145346.237, "dur": 4.088, + "args": { + "External id": 4679366,"Record function id": 0, "Ev Idx": 3781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038145347.461, "dur": 2.474, + "args": { + "External id": 4679367,"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": 1708038145347.900, "dur": 1.513, + "args": { + "External id": 4679368,"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": 1708038145348.639, "dur": 0.686, + "args": { + "External id": 4679369,"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": 1708038145354.313, "dur": 35768.825, + "args": { + "External id": 4679370,"Record function id": 0, "Sequence number": 46526459, "Fwd thread id": 1, "Ev Idx": 3785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038145355.622, "dur": 35758.408, + "args": { + "External id": 4679371,"Sequence number": 46526459, "Fwd thread 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": 1708038145355.622, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 1336753, "tid": 1381210, + "ts": 1708038145389.263, "dur": 35.493, + "args": { + "External id": 4679372,"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": 1708038145432.424, "dur": 62.516, + "args": { + "External id": 4679373,"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": 1708038145500.892, "dur": 35604.788, + "args": { + "External id": 4679374,"Record function id": 0, "Ev Idx": 3789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038145608.195, "dur": 7.051, + "args": { + "External id": 4679375,"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": 1708038145625.403, "dur": 5.080, + "args": { + "External id": 4679376,"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": 1708038145645.303, "dur": 34640.052, + "args": { + "External id": 4679377,"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": 1708038145659.028, "dur": 34617.327, + "args": { + "External id": 4679378,"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": 1708038145719.335, "dur": 15.221, + "args": { + "External id": 4679379,"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": 1708038145740.583, "dur": 34495.768, + "args": { + "External id": 4679380,"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": 1708038145743.078, "dur": 34492.654, + "args": { + "External id": 4679381,"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": 1708038145747.053, "dur": 5.443, + "args": { + "External id": 4679382,"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": 1708038145754.613, "dur": 34477.858, + "args": { + "External id": 4679383,"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": 1708038180377.018, "dur": 8.576, + "args": { + "External id": 4679384,"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": 1708038180380.136, "dur": 5.153, + "args": { + "External id": 4679385,"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": 1708038180418.641, "dur": 349.448, + "args": { + "External id": 4679386,"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": 1708038180443.904, "dur": 318.805, + "args": { + "External id": 4679387,"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": 1708038180455.094, "dur": 301.015, + "args": { + "External id": 4679388,"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": 1708038180787.674, "dur": 2.479, + "args": { + "External id": 4679389,"Record function id": 0, "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": 1708038180850.101, "dur": 6.551, + "args": { + "External id": 4679390,"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": 1708038180900.143, "dur": 1.323, + "args": { + "External id": 4679391,"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": 1708038180919.149, "dur": 0.908, + "args": { + "External id": 4679392,"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": 1708038180935.641, "dur": 0.851, + "args": { + "External id": 4679393,"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": 1708038180948.517, "dur": 0.981, + "args": { + "External id": 4679394,"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": 1708038180963.754, "dur": 0.893, + "args": { + "External id": 4679395,"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": 1708038180977.391, "dur": 1.065, + "args": { + "External id": 4679396,"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": 1708038181028.999, "dur": 2.581, + "args": { + "External id": 4679397,"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": 1708038181042.842, "dur": 1.013, + "args": { + "External id": 4679398,"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": 1708038181138.363, "dur": 2744.020, + "args": { + "External id": 4679399,"Record function id": 0, "Ev Idx": 3814 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1708038181157.880, "dur": 1060.519, + "args": { + "External id": 4679400,"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": 1708038181171.370, "dur": 328.845, + "args": { + "External id": 4679401,"Record function id": 0, "Ev Idx": 3816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038181257.998, "dur": 4.020, + "args": { + "External id": 4679402,"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": 1708038181265.005, "dur": 1.034, + "args": { + "External id": 4679403,"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": 1708038181267.621, "dur": 0.911, + "args": { + "External id": 4679404,"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": 1708038181270.225, "dur": 2.851, + "args": { + "External id": 4679405,"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": 1708038181274.461, "dur": 1.472, + "args": { + "External id": 4679406,"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": 1708038181280.918, "dur": 0.811, + "args": { + "External id": 4679407,"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": 1708038181283.354, "dur": 1.765, + "args": { + "External id": 4679408,"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": 1708038181286.720, "dur": 0.819, + "args": { + "External id": 4679409,"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": 1708038181289.127, "dur": 0.867, + "args": { + "External id": 4679410,"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": 1708038181291.702, "dur": 0.856, + "args": { + "External id": 4679411,"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": 1708038181310.042, "dur": 160.084, + "args": { + "External id": 4679412,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038181325.107, "dur": 140.339, + "args": { + "External id": 4679413,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038181350.459, "dur": 11.788, + "args": { + "External id": 4679414,"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": 1708038181365.607, "dur": 68.732, + "args": { + "External id": 4679415,"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": 1708038181368.331, "dur": 65.633, + "args": { + "External id": 4679416,"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": 1708038181372.599, "dur": 7.134, + "args": { + "External id": 4679417,"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": 1708038181381.590, "dur": 51.682, + "args": { + "External id": 4679418,"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": 1708038181618.370, "dur": 591.287, + "args": { + "External id": 4679419,"Record function id": 0, "Ev Idx": 3834 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1708038181636.778, "dur": 559.110, + "args": { + "External id": 4679420,"Record function id": 0, "Ev Idx": 3835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038181701.973, "dur": 6.073, + "args": { + "External id": 4679421,"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": 1708038181724.040, "dur": 30.657, + "args": { + "External id": 4679422,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038181728.681, "dur": 1.551, + "args": { + "External id": 4679423,"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": 1708038181732.405, "dur": 0.464, + "args": { + "External id": 4679424,"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": 1708038181734.751, "dur": 0.607, + "args": { + "External id": 4679425,"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": 1708038181737.651, "dur": 0.416, + "args": { + "External id": 4679426,"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": 1708038181739.866, "dur": 0.566, + "args": { + "External id": 4679427,"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": 1708038181741.862, "dur": 0.609, + "args": { + "External id": 4679428,"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": 1708038181744.264, "dur": 2.423, + "args": { + "External id": 4679429,"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": 1708038181748.562, "dur": 0.516, + "args": { + "External id": 4679430,"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": 1708038181750.682, "dur": 0.381, + "args": { + "External id": 4679431,"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": 1708038181765.975, "dur": 33.644, + "args": { + "External id": 4679432,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038181829.757, "dur": 99.319, + "args": { + "External id": 4679433,"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": 1708038181839.599, "dur": 3.359, + "args": { + "External id": 4679434,"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": 1708038181848.062, "dur": 10.212, + "args": { + "External id": 4679435,"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": 1708038181852.292, "dur": 5.576, + "args": { + "External id": 4679436,"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": 1708038181856.216, "dur": 0.509, + "args": { + "External id": 4679437,"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": 1708038181864.713, "dur": 25.905, + "args": { + "External id": 4679438,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038181866.797, "dur": 0.655, + "args": { + "External id": 4679439,"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": 1708038181869.049, "dur": 0.384, + "args": { + "External id": 4679440,"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": 1708038181871.379, "dur": 0.405, + "args": { + "External id": 4679441,"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": 1708038181873.365, "dur": 2.836, + "args": { + "External id": 4679442,"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": 1708038181878.125, "dur": 0.745, + "args": { + "External id": 4679443,"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": 1708038181880.330, "dur": 0.371, + "args": { + "External id": 4679444,"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": 1708038181882.409, "dur": 0.677, + "args": { + "External id": 4679445,"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": 1708038181885.132, "dur": 0.576, + "args": { + "External id": 4679446,"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": 1708038181887.517, "dur": 0.365, + "args": { + "External id": 4679447,"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": 1708038181902.435, "dur": 19.614, + "args": { + "External id": 4679448,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038181977.510, "dur": 151.293, + "args": { + "External id": 4679449,"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": 1708038182037.753, "dur": 87.400, + "args": { + "External id": 4679450,"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": 1708038182048.161, "dur": 72.999, + "args": { + "External id": 4679451,"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": 1708038182142.183, "dur": 1.742, + "args": { + "External id": 4679452,"Record function id": 0, "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": 1708038182225.648, "dur": 1636.454, + "args": { + "External id": 4679453,"Sequence number": 46526458, "Fwd thread 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": 1708038182225.648, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038182334.292, "dur": 98.369, + "args": { + "External id": 4679454,"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": 1708038182471.031, "dur": 42.037, + "args": { + "External id": 4679455,"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": 1708038182548.063, "dur": 52.629, + "args": { + "External id": 4679456,"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": 1708038182611.068, "dur": 34.368, + "args": { + "External id": 4679457,"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": 1708038182654.622, "dur": 46.551, + "args": { + "External id": 4679458,"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": 1708038182709.502, "dur": 30.226, + "args": { + "External id": 4679459,"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": 1708038182747.658, "dur": 41.742, + "args": { + "External id": 4679460,"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": 1708038182811.354, "dur": 23.243, + "args": { + "External id": 4679461,"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": 1708038182855.230, "dur": 29.348, + "args": { + "External id": 4679462,"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": 1708038182903.947, "dur": 21.227, + "args": { + "External id": 4679463,"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": 1708038182939.577, "dur": 15.664, + "args": { + "External id": 4679464,"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": 1708038182963.679, "dur": 72.919, + "args": { + "External id": 4679465,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038183042.375, "dur": 36.651, + "args": { + "External id": 4679466,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038183109.489, "dur": 165.929, + "args": { + "External id": 4679467,"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": 1708038183185.091, "dur": 6.098, + "args": { + "External id": 4679468,"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": 1708038183193.065, "dur": 2.301, + "args": { + "External id": 4679469,"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": 1708038183308.891, "dur": 29.480, + "args": { + "External id": 4679470,"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": 1708038183349.204, "dur": 15.096, + "args": { + "External id": 4679471,"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": 1708038183375.726, "dur": 35.149, + "args": { + "External id": 4679472,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038183417.978, "dur": 34.605, + "args": { + "External id": 4679473,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038183461.951, "dur": 22.431, + "args": { + "External id": 4679474,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038183490.261, "dur": 62.792, + "args": { + "External id": 4679475,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038183571.555, "dur": 33.601, + "args": { + "External id": 4679476,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038183614.165, "dur": 31.984, + "args": { + "External id": 4679477,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038183667.473, "dur": 25.928, + "args": { + "External id": 4679478,"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": 1708038183710.826, "dur": 28.362, + "args": { + "External id": 4679479,"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": 1708038183753.582, "dur": 18.856, + "args": { + "External id": 4679480,"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": 1708038183788.188, "dur": 16.259, + "args": { + "External id": 4679481,"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": 1708038183817.187, "dur": 17.536, + "args": { + "External id": 4679482,"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": 1708038183903.613, "dur": 14.727, + "args": { + "External id": 4679483,"Record function id": 0, "Ev Idx": 3898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038183906.947, "dur": 10.508, + "args": { + "External id": 4679484,"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": 1708038183910.694, "dur": 5.743, + "args": { + "External id": 4679485,"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": 1708038183912.349, "dur": 3.960, + "args": { + "External id": 4679486,"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": 1708038183922.367, "dur": 5.446, + "args": { + "External id": 4679487,"Record function id": 0, "Ev Idx": 3902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038183923.860, "dur": 3.505, + "args": { + "External id": 4679488,"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": 1708038183924.913, "dur": 1.884, + "args": { + "External id": 4679489,"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": 1708038183925.661, "dur": 1.031, + "args": { + "External id": 4679490,"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": 1708038183931.153, "dur": 7.255, + "args": { + "External id": 4679491,"Record function id": 0, "Ev Idx": 3906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038183932.867, "dur": 5.110, + "args": { + "External id": 4679492,"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": 1708038183933.670, "dur": 3.760, + "args": { + "External id": 4679493,"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": 1708038183934.145, "dur": 3.214, + "args": { + "External id": 4679494,"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": 1708038183941.853, "dur": 3.908, + "args": { + "External id": 4679495,"Record function id": 0, "Ev Idx": 3910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038183943.000, "dur": 2.339, + "args": { + "External id": 4679496,"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": 1708038183943.491, "dur": 1.438, + "args": { + "External id": 4679497,"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": 1708038183943.980, "dur": 0.880, + "args": { + "External id": 4679498,"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": 1708038183948.936, "dur": 3.750, + "args": { + "External id": 4679499,"Record function id": 0, "Ev Idx": 3914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038183949.996, "dur": 2.281, + "args": { + "External id": 4679500,"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": 1708038183950.730, "dur": 1.130, + "args": { + "External id": 4679501,"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": 1708038183951.205, "dur": 0.577, + "args": { + "External id": 4679502,"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": 1708038183955.804, "dur": 4.309, + "args": { + "External id": 4679503,"Record function id": 0, "Ev Idx": 3918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038183957.184, "dur": 2.501, + "args": { + "External id": 4679504,"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": 1708038183957.936, "dur": 1.233, + "args": { + "External id": 4679505,"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": 1708038183958.428, "dur": 0.621, + "args": { + "External id": 4679506,"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": 1708038183963.355, "dur": 3.823, + "args": { + "External id": 4679507,"Record function id": 0, "Ev Idx": 3922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038183964.374, "dur": 2.395, + "args": { + "External id": 4679508,"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": 1708038183965.133, "dur": 1.031, + "args": { + "External id": 4679509,"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": 1708038183965.526, "dur": 0.556, + "args": { + "External id": 4679510,"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": 1708038183970.426, "dur": 4.245, + "args": { + "External id": 4679511,"Record function id": 0, "Ev Idx": 3926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038183971.518, "dur": 2.713, + "args": { + "External id": 4679512,"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": 1708038183972.373, "dur": 1.232, + "args": { + "External id": 4679513,"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": 1708038183972.700, "dur": 0.831, + "args": { + "External id": 4679514,"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": 1708038183977.704, "dur": 52.172, + "args": { + "External id": 4679515,"Record function id": 0, "Ev Idx": 3930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038183978.882, "dur": 49.906, + "args": { + "External id": 4679516,"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": 1708038183979.588, "dur": 48.065, + "args": { + "External id": 4679517,"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": 1708038184025.397, "dur": 1.882, + "args": { + "External id": 4679518,"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": 1708038184035.721, "dur": 37808.849, + "args": { + "External id": 4679519,"Record function id": 0, "Sequence number": 46526457, "Fwd thread id": 1, "Ev Idx": 3934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038184037.226, "dur": 37799.201, + "args": { + "External id": 4679520,"Sequence number": 46526457, "Fwd thread 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": 1708038184037.226, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 1336753, "tid": 1381210, + "ts": 1708038184068.594, "dur": 36.090, + "args": { + "External id": 4679521,"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": 1708038184112.014, "dur": 64.830, + "args": { + "External id": 4679522,"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": 1708038184182.839, "dur": 37645.763, + "args": { + "External id": 4679523,"Record function id": 0, "Ev Idx": 3938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038184267.499, "dur": 7.339, + "args": { + "External id": 4679524,"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": 1708038184283.340, "dur": 6.624, + "args": { + "External id": 4679525,"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": 1708038184303.768, "dur": 36674.548, + "args": { + "External id": 4679526,"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": 1708038184316.903, "dur": 36652.505, + "args": { + "External id": 4679527,"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": 1708038184374.768, "dur": 12.961, + "args": { + "External id": 4679528,"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": 1708038184393.983, "dur": 36533.975, + "args": { + "External id": 4679529,"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": 1708038184396.788, "dur": 36530.409, + "args": { + "External id": 4679530,"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": 1708038184400.743, "dur": 5.996, + "args": { + "External id": 4679531,"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": 1708038184408.815, "dur": 36514.944, + "args": { + "External id": 4679532,"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": 1708038221089.062, "dur": 9.185, + "args": { + "External id": 4679533,"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": 1708038221092.170, "dur": 5.605, + "args": { + "External id": 4679534,"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": 1708038221126.351, "dur": 394.886, + "args": { + "External id": 4679535,"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": 1708038221152.126, "dur": 364.389, + "args": { + "External id": 4679536,"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": 1708038221162.173, "dur": 348.458, + "args": { + "External id": 4679537,"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": 1708038221556.775, "dur": 3.131, + "args": { + "External id": 4679538,"Record function id": 0, "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": 1708038221619.300, "dur": 6.921, + "args": { + "External id": 4679539,"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": 1708038221675.098, "dur": 1.429, + "args": { + "External id": 4679540,"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": 1708038221692.617, "dur": 3.394, + "args": { + "External id": 4679541,"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": 1708038221708.267, "dur": 1.008, + "args": { + "External id": 4679542,"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": 1708038221721.199, "dur": 1.182, + "args": { + "External id": 4679543,"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": 1708038221732.712, "dur": 0.976, + "args": { + "External id": 4679544,"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": 1708038221744.571, "dur": 3.022, + "args": { + "External id": 4679545,"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": 1708038221758.845, "dur": 1.893, + "args": { + "External id": 4679546,"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": 1708038221771.156, "dur": 0.890, + "args": { + "External id": 4679547,"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": 1708038221860.394, "dur": 2751.679, + "args": { + "External id": 4679548,"Record function id": 0, "Ev Idx": 3963 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1708038221880.289, "dur": 1021.415, + "args": { + "External id": 4679549,"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": 1708038221895.361, "dur": 365.546, + "args": { + "External id": 4679550,"Record function id": 0, "Ev Idx": 3965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038221979.603, "dur": 40.482, + "args": { + "External id": 4679551,"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": 1708038222025.792, "dur": 1.478, + "args": { + "External id": 4679552,"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": 1708038222029.005, "dur": 3.035, + "args": { + "External id": 4679553,"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": 1708038222033.965, "dur": 0.819, + "args": { + "External id": 4679554,"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": 1708038222036.336, "dur": 0.784, + "args": { + "External id": 4679555,"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": 1708038222038.604, "dur": 0.984, + "args": { + "External id": 4679556,"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": 1708038222040.940, "dur": 1.423, + "args": { + "External id": 4679557,"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": 1708038222043.790, "dur": 0.971, + "args": { + "External id": 4679558,"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": 1708038222048.071, "dur": 0.700, + "args": { + "External id": 4679559,"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": 1708038222050.084, "dur": 0.682, + "args": { + "External id": 4679560,"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": 1708038222072.175, "dur": 153.165, + "args": { + "External id": 4679561,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038222087.817, "dur": 133.292, + "args": { + "External id": 4679562,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038222106.554, "dur": 13.993, + "args": { + "External id": 4679563,"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": 1708038222123.673, "dur": 65.003, + "args": { + "External id": 4679564,"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": 1708038222126.324, "dur": 61.922, + "args": { + "External id": 4679565,"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": 1708038222130.513, "dur": 5.529, + "args": { + "External id": 4679566,"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": 1708038222137.759, "dur": 49.828, + "args": { + "External id": 4679567,"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": 1708038222351.814, "dur": 542.145, + "args": { + "External id": 4679568,"Record function id": 0, "Ev Idx": 3983 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1708038222367.755, "dur": 513.198, + "args": { + "External id": 4679569,"Record function id": 0, "Ev Idx": 3984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038222430.243, "dur": 4.114, + "args": { + "External id": 4679570,"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": 1708038222449.266, "dur": 29.564, + "args": { + "External id": 4679571,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038222454.359, "dur": 1.799, + "args": { + "External id": 4679572,"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": 1708038222458.217, "dur": 0.673, + "args": { + "External id": 4679573,"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": 1708038222460.575, "dur": 0.539, + "args": { + "External id": 4679574,"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": 1708038222462.626, "dur": 0.418, + "args": { + "External id": 4679575,"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": 1708038222464.499, "dur": 0.411, + "args": { + "External id": 4679576,"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": 1708038222466.862, "dur": 2.497, + "args": { + "External id": 4679577,"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": 1708038222471.115, "dur": 0.359, + "args": { + "External id": 4679578,"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": 1708038222473.240, "dur": 0.580, + "args": { + "External id": 4679579,"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": 1708038222475.237, "dur": 0.436, + "args": { + "External id": 4679580,"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": 1708038222489.245, "dur": 31.961, + "args": { + "External id": 4679581,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038222569.686, "dur": 102.534, + "args": { + "External id": 4679582,"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": 1708038222579.853, "dur": 4.712, + "args": { + "External id": 4679583,"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": 1708038222590.007, "dur": 10.620, + "args": { + "External id": 4679584,"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": 1708038222594.237, "dur": 5.976, + "args": { + "External id": 4679585,"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": 1708038222597.883, "dur": 0.852, + "args": { + "External id": 4679586,"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": 1708038222607.573, "dur": 23.611, + "args": { + "External id": 4679587,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038222609.834, "dur": 0.518, + "args": { + "External id": 4679588,"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": 1708038222612.116, "dur": 0.434, + "args": { + "External id": 4679589,"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": 1708038222614.204, "dur": 2.501, + "args": { + "External id": 4679590,"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": 1708038222618.473, "dur": 0.554, + "args": { + "External id": 4679591,"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": 1708038222620.607, "dur": 0.438, + "args": { + "External id": 4679592,"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": 1708038222622.596, "dur": 0.410, + "args": { + "External id": 4679593,"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": 1708038222624.572, "dur": 0.360, + "args": { + "External id": 4679594,"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": 1708038222626.367, "dur": 0.389, + "args": { + "External id": 4679595,"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": 1708038222628.319, "dur": 0.321, + "args": { + "External id": 4679596,"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": 1708038222641.626, "dur": 23.312, + "args": { + "External id": 4679597,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038222717.773, "dur": 104.806, + "args": { + "External id": 4679598,"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": 1708038222738.530, "dur": 80.906, + "args": { + "External id": 4679599,"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": 1708038222747.462, "dur": 67.860, + "args": { + "External id": 4679600,"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": 1708038222834.652, "dur": 1.667, + "args": { + "External id": 4679601,"Record function id": 0, "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": 1708038222912.284, "dur": 1675.098, + "args": { + "External id": 4679602,"Sequence number": 46526456, "Fwd thread 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": 1708038222912.284, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038223064.220, "dur": 103.143, + "args": { + "External id": 4679603,"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": 1708038223205.775, "dur": 43.460, + "args": { + "External id": 4679604,"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": 1708038223264.919, "dur": 47.761, + "args": { + "External id": 4679605,"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": 1708038223323.696, "dur": 33.455, + "args": { + "External id": 4679606,"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": 1708038223364.166, "dur": 45.991, + "args": { + "External id": 4679607,"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": 1708038223417.800, "dur": 29.453, + "args": { + "External id": 4679608,"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": 1708038223454.857, "dur": 42.830, + "args": { + "External id": 4679609,"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": 1708038223520.049, "dur": 41.087, + "args": { + "External id": 4679610,"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": 1708038223580.902, "dur": 27.264, + "args": { + "External id": 4679611,"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": 1708038223628.945, "dur": 20.480, + "args": { + "External id": 4679612,"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": 1708038223662.662, "dur": 16.465, + "args": { + "External id": 4679613,"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": 1708038223688.870, "dur": 34.807, + "args": { + "External id": 4679614,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038223727.255, "dur": 35.214, + "args": { + "External id": 4679615,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038223790.036, "dur": 176.704, + "args": { + "External id": 4679616,"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": 1708038223871.032, "dur": 5.914, + "args": { + "External id": 4679617,"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": 1708038223878.670, "dur": 2.123, + "args": { + "External id": 4679618,"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": 1708038224039.991, "dur": 30.094, + "args": { + "External id": 4679619,"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": 1708038224081.190, "dur": 16.248, + "args": { + "External id": 4679620,"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": 1708038224107.121, "dur": 41.771, + "args": { + "External id": 4679621,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038224156.475, "dur": 35.807, + "args": { + "External id": 4679622,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038224201.023, "dur": 22.340, + "args": { + "External id": 4679623,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038224228.759, "dur": 31.041, + "args": { + "External id": 4679624,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038224279.058, "dur": 31.080, + "args": { + "External id": 4679625,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038224319.047, "dur": 33.983, + "args": { + "External id": 4679626,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038224372.173, "dur": 27.227, + "args": { + "External id": 4679627,"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": 1708038224416.000, "dur": 28.586, + "args": { + "External id": 4679628,"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": 1708038224459.754, "dur": 17.981, + "args": { + "External id": 4679629,"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": 1708038224491.783, "dur": 15.975, + "args": { + "External id": 4679630,"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": 1708038224519.445, "dur": 35.789, + "args": { + "External id": 4679631,"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": 1708038224634.066, "dur": 14.825, + "args": { + "External id": 4679632,"Record function id": 0, "Ev Idx": 4047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038224637.125, "dur": 10.729, + "args": { + "External id": 4679633,"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": 1708038224641.200, "dur": 5.602, + "args": { + "External id": 4679634,"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": 1708038224642.794, "dur": 3.871, + "args": { + "External id": 4679635,"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": 1708038224653.062, "dur": 7.403, + "args": { + "External id": 4679636,"Record function id": 0, "Ev Idx": 4051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038224654.479, "dur": 5.554, + "args": { + "External id": 4679637,"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": 1708038224655.686, "dur": 3.837, + "args": { + "External id": 4679638,"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": 1708038224656.397, "dur": 3.047, + "args": { + "External id": 4679639,"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": 1708038224663.729, "dur": 4.813, + "args": { + "External id": 4679640,"Record function id": 0, "Ev Idx": 4055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038224665.004, "dur": 3.146, + "args": { + "External id": 4679641,"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": 1708038224665.686, "dur": 1.805, + "args": { + "External id": 4679642,"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": 1708038224666.307, "dur": 1.110, + "args": { + "External id": 4679643,"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": 1708038224671.757, "dur": 4.624, + "args": { + "External id": 4679644,"Record function id": 0, "Ev Idx": 4059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038224673.352, "dur": 2.621, + "args": { + "External id": 4679645,"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": 1708038224674.060, "dur": 1.479, + "args": { + "External id": 4679646,"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": 1708038224674.681, "dur": 0.796, + "args": { + "External id": 4679647,"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": 1708038224679.490, "dur": 3.887, + "args": { + "External id": 4679648,"Record function id": 0, "Ev Idx": 4063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038224680.720, "dur": 2.264, + "args": { + "External id": 4679649,"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": 1708038224681.557, "dur": 0.985, + "args": { + "External id": 4679650,"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": 1708038224681.853, "dur": 0.616, + "args": { + "External id": 4679651,"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": 1708038224686.519, "dur": 4.016, + "args": { + "External id": 4679652,"Record function id": 0, "Ev Idx": 4067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038224687.526, "dur": 2.547, + "args": { + "External id": 4679653,"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": 1708038224688.145, "dur": 1.278, + "args": { + "External id": 4679654,"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": 1708038224688.608, "dur": 0.709, + "args": { + "External id": 4679655,"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": 1708038224693.792, "dur": 3.997, + "args": { + "External id": 4679656,"Record function id": 0, "Ev Idx": 4071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038224695.038, "dur": 2.324, + "args": { + "External id": 4679657,"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": 1708038224695.690, "dur": 1.033, + "args": { + "External id": 4679658,"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": 1708038224696.002, "dur": 0.647, + "args": { + "External id": 4679659,"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": 1708038224700.931, "dur": 4.750, + "args": { + "External id": 4679660,"Record function id": 0, "Ev Idx": 4075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038224702.283, "dur": 2.979, + "args": { + "External id": 4679661,"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": 1708038224703.312, "dur": 1.268, + "args": { + "External id": 4679662,"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": 1708038224703.766, "dur": 0.710, + "args": { + "External id": 4679663,"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": 1708038224708.781, "dur": 6.418, + "args": { + "External id": 4679664,"Record function id": 0, "Ev Idx": 4079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038224710.067, "dur": 4.682, + "args": { + "External id": 4679665,"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": 1708038224710.781, "dur": 3.315, + "args": { + "External id": 4679666,"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": 1708038224711.512, "dur": 2.463, + "args": { + "External id": 4679667,"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": 1708038224718.893, "dur": 35836.161, + "args": { + "External id": 4679668,"Record function id": 0, "Sequence number": 46526455, "Fwd thread id": 1, "Ev Idx": 4083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038224720.365, "dur": 35825.397, + "args": { + "External id": 4679669,"Sequence number": 46526455, "Fwd thread 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": 1708038224720.365, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 1336753, "tid": 1381210, + "ts": 1708038224747.626, "dur": 37.671, + "args": { + "External id": 4679670,"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": 1708038224792.548, "dur": 64.154, + "args": { + "External id": 4679671,"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": 1708038224862.327, "dur": 35659.880, + "args": { + "External id": 4679672,"Record function id": 0, "Ev Idx": 4087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038224947.278, "dur": 6.660, + "args": { + "External id": 4679673,"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": 1708038224963.152, "dur": 4.671, + "args": { + "External id": 4679674,"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": 1708038225017.675, "dur": 34704.823, + "args": { + "External id": 4679675,"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": 1708038225032.551, "dur": 34680.915, + "args": { + "External id": 4679676,"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": 1708038225100.037, "dur": 13.992, + "args": { + "External id": 4679677,"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": 1708038225120.781, "dur": 34552.695, + "args": { + "External id": 4679678,"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": 1708038225123.594, "dur": 34548.728, + "args": { + "External id": 4679679,"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": 1708038225127.694, "dur": 6.027, + "args": { + "External id": 4679680,"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": 1708038225205.218, "dur": 34463.848, + "args": { + "External id": 4679681,"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": 1708038259814.148, "dur": 8.839, + "args": { + "External id": 4679682,"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": 1708038259817.244, "dur": 5.406, + "args": { + "External id": 4679683,"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": 1708038259857.020, "dur": 368.918, + "args": { + "External id": 4679684,"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": 1708038259882.455, "dur": 338.156, + "args": { + "External id": 4679685,"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": 1708038259895.891, "dur": 318.129, + "args": { + "External id": 4679686,"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": 1708038260245.949, "dur": 2.447, + "args": { + "External id": 4679687,"Record function id": 0, "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": 1708038260306.711, "dur": 6.262, + "args": { + "External id": 4679688,"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": 1708038260359.631, "dur": 3.566, + "args": { + "External id": 4679689,"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": 1708038260379.550, "dur": 0.925, + "args": { + "External id": 4679690,"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": 1708038260392.036, "dur": 3.805, + "args": { + "External id": 4679691,"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": 1708038260407.715, "dur": 0.900, + "args": { + "External id": 4679692,"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": 1708038260419.750, "dur": 3.000, + "args": { + "External id": 4679693,"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": 1708038260438.406, "dur": 0.912, + "args": { + "External id": 4679694,"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": 1708038260451.945, "dur": 1.965, + "args": { + "External id": 4679695,"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": 1708038260463.993, "dur": 0.915, + "args": { + "External id": 4679696,"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": 1708038260570.991, "dur": 2891.877, + "args": { + "External id": 4679697,"Record function id": 0, "Ev Idx": 4112 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1708038260591.981, "dur": 1118.319, + "args": { + "External id": 4679698,"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": 1708038260606.841, "dur": 353.831, + "args": { + "External id": 4679699,"Record function id": 0, "Ev Idx": 4114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038260693.145, "dur": 6.046, + "args": { + "External id": 4679700,"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": 1708038260702.149, "dur": 1.116, + "args": { + "External id": 4679701,"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": 1708038260704.979, "dur": 1.529, + "args": { + "External id": 4679702,"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": 1708038260708.139, "dur": 0.838, + "args": { + "External id": 4679703,"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": 1708038260710.397, "dur": 1.026, + "args": { + "External id": 4679704,"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": 1708038260713.292, "dur": 0.780, + "args": { + "External id": 4679705,"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": 1708038260715.374, "dur": 1.311, + "args": { + "External id": 4679706,"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": 1708038260718.125, "dur": 1.012, + "args": { + "External id": 4679707,"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": 1708038260720.663, "dur": 2.418, + "args": { + "External id": 4679708,"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": 1708038260724.708, "dur": 1.024, + "args": { + "External id": 4679709,"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": 1708038260742.863, "dur": 180.125, + "args": { + "External id": 4679710,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038260762.234, "dur": 156.016, + "args": { + "External id": 4679711,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038260800.674, "dur": 16.271, + "args": { + "External id": 4679712,"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": 1708038260820.059, "dur": 65.201, + "args": { + "External id": 4679713,"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": 1708038260822.893, "dur": 62.020, + "args": { + "External id": 4679714,"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": 1708038260827.362, "dur": 5.567, + "args": { + "External id": 4679715,"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": 1708038260834.816, "dur": 49.486, + "args": { + "External id": 4679716,"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": 1708038261105.446, "dur": 596.213, + "args": { + "External id": 4679717,"Record function id": 0, "Ev Idx": 4132 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1708038261123.316, "dur": 564.860, + "args": { + "External id": 4679718,"Record function id": 0, "Ev Idx": 4133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038261189.649, "dur": 5.823, + "args": { + "External id": 4679719,"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": 1708038261211.469, "dur": 31.998, + "args": { + "External id": 4679720,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038261216.472, "dur": 1.799, + "args": { + "External id": 4679721,"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": 1708038261220.221, "dur": 0.412, + "args": { + "External id": 4679722,"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": 1708038261222.151, "dur": 0.354, + "args": { + "External id": 4679723,"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": 1708038261224.092, "dur": 2.510, + "args": { + "External id": 4679724,"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": 1708038261227.932, "dur": 0.412, + "args": { + "External id": 4679725,"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": 1708038261229.653, "dur": 0.409, + "args": { + "External id": 4679726,"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": 1708038261236.382, "dur": 0.397, + "args": { + "External id": 4679727,"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": 1708038261238.188, "dur": 0.429, + "args": { + "External id": 4679728,"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": 1708038261240.037, "dur": 0.416, + "args": { + "External id": 4679729,"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": 1708038261254.415, "dur": 35.473, + "args": { + "External id": 4679730,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038261320.839, "dur": 106.083, + "args": { + "External id": 4679731,"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": 1708038261330.610, "dur": 3.123, + "args": { + "External id": 4679732,"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": 1708038261339.258, "dur": 10.279, + "args": { + "External id": 4679733,"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": 1708038261343.401, "dur": 5.697, + "args": { + "External id": 4679734,"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": 1708038261347.350, "dur": 0.602, + "args": { + "External id": 4679735,"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": 1708038261359.276, "dur": 28.092, + "args": { + "External id": 4679736,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038261361.524, "dur": 2.628, + "args": { + "External id": 4679737,"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": 1708038261365.603, "dur": 0.431, + "args": { + "External id": 4679738,"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": 1708038261367.628, "dur": 0.482, + "args": { + "External id": 4679739,"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": 1708038261369.466, "dur": 0.590, + "args": { + "External id": 4679740,"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": 1708038261371.689, "dur": 0.358, + "args": { + "External id": 4679741,"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": 1708038261373.489, "dur": 0.365, + "args": { + "External id": 4679742,"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": 1708038261375.290, "dur": 0.499, + "args": { + "External id": 4679743,"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": 1708038261377.238, "dur": 0.338, + "args": { + "External id": 4679744,"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": 1708038261378.823, "dur": 2.551, + "args": { + "External id": 4679745,"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": 1708038261398.869, "dur": 20.240, + "args": { + "External id": 4679746,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038261474.601, "dur": 140.562, + "args": { + "External id": 4679747,"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": 1708038261495.317, "dur": 116.070, + "args": { + "External id": 4679748,"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": 1708038261508.844, "dur": 97.604, + "args": { + "External id": 4679749,"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": 1708038261634.392, "dur": 1.917, + "args": { + "External id": 4679750,"Record function id": 0, "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": 1708038261717.470, "dur": 1723.983, + "args": { + "External id": 4679751,"Sequence number": 46526454, "Fwd thread 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": 1708038261717.470, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038261827.259, "dur": 99.786, + "args": { + "External id": 4679752,"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": 1708038261964.331, "dur": 85.361, + "args": { + "External id": 4679753,"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": 1708038262074.765, "dur": 55.673, + "args": { + "External id": 4679754,"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": 1708038262139.920, "dur": 33.484, + "args": { + "External id": 4679755,"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": 1708038262180.246, "dur": 45.178, + "args": { + "External id": 4679756,"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": 1708038262233.020, "dur": 28.737, + "args": { + "External id": 4679757,"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": 1708038262271.542, "dur": 41.912, + "args": { + "External id": 4679758,"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": 1708038262336.718, "dur": 25.423, + "args": { + "External id": 4679759,"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": 1708038262418.217, "dur": 30.879, + "args": { + "External id": 4679760,"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": 1708038262471.712, "dur": 21.333, + "args": { + "External id": 4679761,"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": 1708038262508.540, "dur": 32.623, + "args": { + "External id": 4679762,"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": 1708038262555.121, "dur": 37.377, + "args": { + "External id": 4679763,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038262596.312, "dur": 35.380, + "args": { + "External id": 4679764,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038262659.521, "dur": 175.407, + "args": { + "External id": 4679765,"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": 1708038262734.857, "dur": 5.746, + "args": { + "External id": 4679766,"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": 1708038262742.540, "dur": 2.227, + "args": { + "External id": 4679767,"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": 1708038262870.388, "dur": 26.133, + "args": { + "External id": 4679768,"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": 1708038262907.234, "dur": 14.759, + "args": { + "External id": 4679769,"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": 1708038262929.982, "dur": 33.409, + "args": { + "External id": 4679770,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038262972.540, "dur": 90.441, + "args": { + "External id": 4679771,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038263081.458, "dur": 30.237, + "args": { + "External id": 4679772,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038263118.026, "dur": 35.033, + "args": { + "External id": 4679773,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038263159.547, "dur": 21.800, + "args": { + "External id": 4679774,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038263191.420, "dur": 33.424, + "args": { + "External id": 4679775,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038263243.839, "dur": 28.869, + "args": { + "External id": 4679776,"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": 1708038263289.849, "dur": 25.748, + "args": { + "External id": 4679777,"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": 1708038263334.658, "dur": 18.940, + "args": { + "External id": 4679778,"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": 1708038263367.449, "dur": 16.329, + "args": { + "External id": 4679779,"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": 1708038263396.394, "dur": 16.869, + "args": { + "External id": 4679780,"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": 1708038263485.073, "dur": 17.141, + "args": { + "External id": 4679781,"Record function id": 0, "Ev Idx": 4196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038263488.223, "dur": 13.112, + "args": { + "External id": 4679782,"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": 1708038263492.455, "dur": 8.021, + "args": { + "External id": 4679783,"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": 1708038263494.220, "dur": 6.145, + "args": { + "External id": 4679784,"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": 1708038263506.229, "dur": 4.859, + "args": { + "External id": 4679785,"Record function id": 0, "Ev Idx": 4200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038263507.443, "dur": 3.244, + "args": { + "External id": 4679786,"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": 1708038263508.148, "dur": 1.858, + "args": { + "External id": 4679787,"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": 1708038263508.939, "dur": 0.980, + "args": { + "External id": 4679788,"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": 1708038263514.403, "dur": 4.455, + "args": { + "External id": 4679789,"Record function id": 0, "Ev Idx": 4204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038263515.762, "dur": 2.719, + "args": { + "External id": 4679790,"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": 1708038263516.464, "dur": 1.547, + "args": { + "External id": 4679791,"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": 1708038263517.047, "dur": 0.879, + "args": { + "External id": 4679792,"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": 1708038263522.004, "dur": 22.150, + "args": { + "External id": 4679793,"Record function id": 0, "Ev Idx": 4208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038263523.088, "dur": 20.087, + "args": { + "External id": 4679794,"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": 1708038263540.197, "dur": 2.130, + "args": { + "External id": 4679795,"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": 1708038263540.841, "dur": 1.239, + "args": { + "External id": 4679796,"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": 1708038263549.148, "dur": 4.958, + "args": { + "External id": 4679797,"Record function id": 0, "Ev Idx": 4212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038263550.821, "dur": 2.871, + "args": { + "External id": 4679798,"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": 1708038263551.819, "dur": 1.303, + "args": { + "External id": 4679799,"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": 1708038263552.208, "dur": 0.838, + "args": { + "External id": 4679800,"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": 1708038263557.333, "dur": 4.555, + "args": { + "External id": 4679801,"Record function id": 0, "Ev Idx": 4216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038263558.684, "dur": 2.777, + "args": { + "External id": 4679802,"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": 1708038263559.272, "dur": 1.580, + "args": { + "External id": 4679803,"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": 1708038263559.829, "dur": 0.917, + "args": { + "External id": 4679804,"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": 1708038263565.188, "dur": 4.082, + "args": { + "External id": 4679805,"Record function id": 0, "Ev Idx": 4220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038263566.480, "dur": 2.388, + "args": { + "External id": 4679806,"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": 1708038263567.121, "dur": 1.356, + "args": { + "External id": 4679807,"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": 1708038263567.549, "dur": 0.850, + "args": { + "External id": 4679808,"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": 1708038263572.422, "dur": 5.736, + "args": { + "External id": 4679809,"Record function id": 0, "Ev Idx": 4224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038263573.356, "dur": 4.374, + "args": { + "External id": 4679810,"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": 1708038263573.937, "dur": 3.362, + "args": { + "External id": 4679811,"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": 1708038263574.212, "dur": 3.019, + "args": { + "External id": 4679812,"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": 1708038263581.283, "dur": 4.169, + "args": { + "External id": 4679813,"Record function id": 0, "Ev Idx": 4228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038263582.585, "dur": 2.468, + "args": { + "External id": 4679814,"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": 1708038263583.184, "dur": 1.467, + "args": { + "External id": 4679815,"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": 1708038263583.645, "dur": 0.912, + "args": { + "External id": 4679816,"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": 1708038263589.298, "dur": 35738.297, + "args": { + "External id": 4679817,"Record function id": 0, "Sequence number": 46526453, "Fwd thread id": 1, "Ev Idx": 4232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038263590.357, "dur": 35728.514, + "args": { + "External id": 4679818,"Sequence number": 46526453, "Fwd thread 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": 1708038263590.357, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 1336753, "tid": 1381210, + "ts": 1708038263618.054, "dur": 35.916, + "args": { + "External id": 4679819,"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": 1708038263661.488, "dur": 65.486, + "args": { + "External id": 4679820,"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": 1708038263732.690, "dur": 35578.286, + "args": { + "External id": 4679821,"Record function id": 0, "Ev Idx": 4236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038263818.088, "dur": 6.770, + "args": { + "External id": 4679822,"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": 1708038263833.794, "dur": 4.770, + "args": { + "External id": 4679823,"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": 1708038263854.101, "dur": 34643.618, + "args": { + "External id": 4679824,"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": 1708038263867.046, "dur": 34619.748, + "args": { + "External id": 4679825,"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": 1708038263948.626, "dur": 13.866, + "args": { + "External id": 4679826,"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": 1708038263968.777, "dur": 34474.935, + "args": { + "External id": 4679827,"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": 1708038263971.283, "dur": 34471.522, + "args": { + "External id": 4679828,"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": 1708038263975.423, "dur": 5.196, + "args": { + "External id": 4679829,"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": 1708038263982.530, "dur": 34456.031, + "args": { + "External id": 4679830,"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": 1708038298608.936, "dur": 10.717, + "args": { + "External id": 4679831,"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": 1708038298612.567, "dur": 6.627, + "args": { + "External id": 4679832,"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": 1708038298652.304, "dur": 371.632, + "args": { + "External id": 4679833,"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": 1708038298677.524, "dur": 341.481, + "args": { + "External id": 4679834,"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": 1708038298688.068, "dur": 324.071, + "args": { + "External id": 4679835,"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": 1708038299045.064, "dur": 2.706, + "args": { + "External id": 4679836,"Record function id": 0, "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": 1708038299107.637, "dur": 6.476, + "args": { + "External id": 4679837,"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": 1708038299160.307, "dur": 1.290, + "args": { + "External id": 4679838,"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": 1708038299177.692, "dur": 0.907, + "args": { + "External id": 4679839,"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": 1708038299189.989, "dur": 1.159, + "args": { + "External id": 4679840,"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": 1708038299202.280, "dur": 0.732, + "args": { + "External id": 4679841,"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": 1708038299215.070, "dur": 1.062, + "args": { + "External id": 4679842,"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": 1708038299227.674, "dur": 0.858, + "args": { + "External id": 4679843,"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": 1708038299238.934, "dur": 1.586, + "args": { + "External id": 4679844,"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": 1708038299250.300, "dur": 0.801, + "args": { + "External id": 4679845,"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": 1708038299341.304, "dur": 2781.844, + "args": { + "External id": 4679846,"Record function id": 0, "Ev Idx": 4261 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1708038299359.188, "dur": 1061.582, + "args": { + "External id": 4679847,"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": 1708038299373.455, "dur": 333.304, + "args": { + "External id": 4679848,"Record function id": 0, "Ev Idx": 4263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038299452.447, "dur": 4.107, + "args": { + "External id": 4679849,"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": 1708038299459.816, "dur": 1.096, + "args": { + "External id": 4679850,"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": 1708038299463.262, "dur": 0.813, + "args": { + "External id": 4679851,"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": 1708038299465.690, "dur": 1.289, + "args": { + "External id": 4679852,"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": 1708038299468.468, "dur": 1.249, + "args": { + "External id": 4679853,"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": 1708038299471.268, "dur": 1.149, + "args": { + "External id": 4679854,"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": 1708038299475.864, "dur": 1.270, + "args": { + "External id": 4679855,"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": 1708038299478.616, "dur": 3.203, + "args": { + "External id": 4679856,"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": 1708038299483.540, "dur": 0.919, + "args": { + "External id": 4679857,"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": 1708038299485.854, "dur": 0.712, + "args": { + "External id": 4679858,"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": 1708038299506.594, "dur": 169.950, + "args": { + "External id": 4679859,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038299522.011, "dur": 150.185, + "args": { + "External id": 4679860,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038299556.237, "dur": 11.964, + "args": { + "External id": 4679861,"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": 1708038299571.441, "dur": 69.221, + "args": { + "External id": 4679862,"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": 1708038299574.134, "dur": 66.195, + "args": { + "External id": 4679863,"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": 1708038299577.870, "dur": 9.177, + "args": { + "External id": 4679864,"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": 1708038299590.661, "dur": 49.037, + "args": { + "External id": 4679865,"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": 1708038299803.112, "dur": 609.613, + "args": { + "External id": 4679866,"Record function id": 0, "Ev Idx": 4281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1708038299819.288, "dur": 581.516, + "args": { + "External id": 4679867,"Record function id": 0, "Ev Idx": 4282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038299883.818, "dur": 4.251, + "args": { + "External id": 4679868,"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": 1708038299909.911, "dur": 29.392, + "args": { + "External id": 4679869,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038299914.304, "dur": 1.970, + "args": { + "External id": 4679870,"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": 1708038299917.832, "dur": 0.636, + "args": { + "External id": 4679871,"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": 1708038299919.218, "dur": 2.196, + "args": { + "External id": 4679872,"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": 1708038299923.262, "dur": 0.339, + "args": { + "External id": 4679873,"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": 1708038299925.163, "dur": 0.375, + "args": { + "External id": 4679874,"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": 1708038299927.190, "dur": 0.479, + "args": { + "External id": 4679875,"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": 1708038299928.904, "dur": 0.274, + "args": { + "External id": 4679876,"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": 1708038299930.702, "dur": 0.425, + "args": { + "External id": 4679877,"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": 1708038299932.479, "dur": 0.361, + "args": { + "External id": 4679878,"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": 1708038299950.120, "dur": 67.353, + "args": { + "External id": 4679879,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038300055.408, "dur": 119.582, + "args": { + "External id": 4679880,"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": 1708038300065.966, "dur": 5.037, + "args": { + "External id": 4679881,"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": 1708038300076.192, "dur": 16.576, + "args": { + "External id": 4679882,"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": 1708038300080.449, "dur": 11.875, + "args": { + "External id": 4679883,"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": 1708038300087.738, "dur": 2.673, + "args": { + "External id": 4679884,"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": 1708038300100.167, "dur": 28.179, + "args": { + "External id": 4679885,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038300102.517, "dur": 0.465, + "args": { + "External id": 4679886,"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": 1708038300104.817, "dur": 0.433, + "args": { + "External id": 4679887,"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": 1708038300106.816, "dur": 0.428, + "args": { + "External id": 4679888,"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": 1708038300109.017, "dur": 0.414, + "args": { + "External id": 4679889,"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": 1708038300111.100, "dur": 0.394, + "args": { + "External id": 4679890,"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": 1708038300113.192, "dur": 0.382, + "args": { + "External id": 4679891,"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": 1708038300114.893, "dur": 0.343, + "args": { + "External id": 4679892,"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": 1708038300116.803, "dur": 2.638, + "args": { + "External id": 4679893,"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": 1708038300120.646, "dur": 0.544, + "args": { + "External id": 4679894,"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": 1708038300140.554, "dur": 26.323, + "args": { + "External id": 4679895,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038300219.270, "dur": 115.394, + "args": { + "External id": 4679896,"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": 1708038300248.229, "dur": 83.334, + "args": { + "External id": 4679897,"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": 1708038300257.269, "dur": 70.339, + "args": { + "External id": 4679898,"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": 1708038300351.647, "dur": 1.888, + "args": { + "External id": 4679899,"Record function id": 0, "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": 1708038300428.223, "dur": 1671.419, + "args": { + "External id": 4679900,"Sequence number": 46526452, "Fwd thread 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": 1708038300428.223, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038300553.116, "dur": 103.977, + "args": { + "External id": 4679901,"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": 1708038300701.904, "dur": 42.135, + "args": { + "External id": 4679902,"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": 1708038300762.928, "dur": 46.538, + "args": { + "External id": 4679903,"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": 1708038300819.104, "dur": 30.914, + "args": { + "External id": 4679904,"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": 1708038300855.563, "dur": 43.573, + "args": { + "External id": 4679905,"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": 1708038300905.314, "dur": 26.327, + "args": { + "External id": 4679906,"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": 1708038300941.622, "dur": 78.885, + "args": { + "External id": 4679907,"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": 1708038301048.995, "dur": 26.227, + "args": { + "External id": 4679908,"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": 1708038301097.141, "dur": 26.956, + "args": { + "External id": 4679909,"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": 1708038301144.902, "dur": 19.708, + "args": { + "External id": 4679910,"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": 1708038301181.154, "dur": 16.262, + "args": { + "External id": 4679911,"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": 1708038301207.211, "dur": 34.088, + "args": { + "External id": 4679912,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038301244.397, "dur": 31.077, + "args": { + "External id": 4679913,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038301300.490, "dur": 165.778, + "args": { + "External id": 4679914,"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": 1708038301378.635, "dur": 5.390, + "args": { + "External id": 4679915,"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": 1708038301386.084, "dur": 1.996, + "args": { + "External id": 4679916,"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": 1708038301501.620, "dur": 41.120, + "args": { + "External id": 4679917,"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": 1708038301556.636, "dur": 16.277, + "args": { + "External id": 4679918,"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": 1708038301584.744, "dur": 38.618, + "args": { + "External id": 4679919,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038301628.748, "dur": 36.904, + "args": { + "External id": 4679920,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038301671.810, "dur": 22.680, + "args": { + "External id": 4679921,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038301705.254, "dur": 28.704, + "args": { + "External id": 4679922,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038301741.063, "dur": 24.415, + "args": { + "External id": 4679923,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038301772.445, "dur": 48.502, + "args": { + "External id": 4679924,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038301849.967, "dur": 23.925, + "args": { + "External id": 4679925,"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": 1708038301891.175, "dur": 25.084, + "args": { + "External id": 4679926,"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": 1708038301943.082, "dur": 22.208, + "args": { + "External id": 4679927,"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": 1708038302014.106, "dur": 20.494, + "args": { + "External id": 4679928,"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": 1708038302050.134, "dur": 19.994, + "args": { + "External id": 4679929,"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": 1708038302145.143, "dur": 15.024, + "args": { + "External id": 4679930,"Record function id": 0, "Ev Idx": 4345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038302148.516, "dur": 10.761, + "args": { + "External id": 4679931,"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": 1708038302152.351, "dur": 6.103, + "args": { + "External id": 4679932,"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": 1708038302153.973, "dur": 4.379, + "args": { + "External id": 4679933,"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": 1708038302164.153, "dur": 5.546, + "args": { + "External id": 4679934,"Record function id": 0, "Ev Idx": 4349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038302165.829, "dur": 3.414, + "args": { + "External id": 4679935,"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": 1708038302167.060, "dur": 1.730, + "args": { + "External id": 4679936,"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": 1708038302167.976, "dur": 0.740, + "args": { + "External id": 4679937,"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": 1708038302172.964, "dur": 4.854, + "args": { + "External id": 4679938,"Record function id": 0, "Ev Idx": 4353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038302174.439, "dur": 2.968, + "args": { + "External id": 4679939,"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": 1708038302175.389, "dur": 1.320, + "args": { + "External id": 4679940,"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": 1708038302175.782, "dur": 0.856, + "args": { + "External id": 4679941,"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": 1708038302181.095, "dur": 4.812, + "args": { + "External id": 4679942,"Record function id": 0, "Ev Idx": 4357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038302182.443, "dur": 3.001, + "args": { + "External id": 4679943,"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": 1708038302183.230, "dur": 1.608, + "args": { + "External id": 4679944,"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": 1708038302184.044, "dur": 0.697, + "args": { + "External id": 4679945,"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": 1708038302189.224, "dur": 4.440, + "args": { + "External id": 4679946,"Record function id": 0, "Ev Idx": 4361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038302190.798, "dur": 2.431, + "args": { + "External id": 4679947,"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": 1708038302191.456, "dur": 1.361, + "args": { + "External id": 4679948,"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": 1708038302191.907, "dur": 0.840, + "args": { + "External id": 4679949,"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": 1708038302196.991, "dur": 3.649, + "args": { + "External id": 4679950,"Record function id": 0, "Ev Idx": 4365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038302198.068, "dur": 2.153, + "args": { + "External id": 4679951,"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": 1708038302198.628, "dur": 1.065, + "args": { + "External id": 4679952,"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": 1708038302198.972, "dur": 0.629, + "args": { + "External id": 4679953,"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": 1708038302203.887, "dur": 7.745, + "args": { + "External id": 4679954,"Record function id": 0, "Ev Idx": 4369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038302205.330, "dur": 5.871, + "args": { + "External id": 4679955,"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": 1708038302205.783, "dur": 5.041, + "args": { + "External id": 4679956,"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": 1708038302208.068, "dur": 2.683, + "args": { + "External id": 4679957,"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": 1708038302214.803, "dur": 4.461, + "args": { + "External id": 4679958,"Record function id": 0, "Ev Idx": 4373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038302216.194, "dur": 2.653, + "args": { + "External id": 4679959,"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": 1708038302217.061, "dur": 1.260, + "args": { + "External id": 4679960,"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": 1708038302217.473, "dur": 0.775, + "args": { + "External id": 4679961,"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": 1708038302222.448, "dur": 3.740, + "args": { + "External id": 4679962,"Record function id": 0, "Ev Idx": 4377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038302223.880, "dur": 1.868, + "args": { + "External id": 4679963,"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": 1708038302224.325, "dur": 1.046, + "args": { + "External id": 4679964,"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": 1708038302224.617, "dur": 0.681, + "args": { + "External id": 4679965,"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": 1708038302229.786, "dur": 35662.220, + "args": { + "External id": 4679966,"Record function id": 0, "Sequence number": 46526451, "Fwd thread id": 1, "Ev Idx": 4381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038302231.178, "dur": 35652.787, + "args": { + "External id": 4679967,"Sequence number": 46526451, "Fwd thread 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": 1708038302231.178, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 1336753, "tid": 1381210, + "ts": 1708038302257.775, "dur": 39.202, + "args": { + "External id": 4679968,"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": 1708038302304.246, "dur": 64.768, + "args": { + "External id": 4679969,"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": 1708038302376.670, "dur": 35500.059, + "args": { + "External id": 4679970,"Record function id": 0, "Ev Idx": 4385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038302459.756, "dur": 6.644, + "args": { + "External id": 4679971,"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": 1708038302475.265, "dur": 4.693, + "args": { + "External id": 4679972,"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": 1708038302493.706, "dur": 34529.930, + "args": { + "External id": 4679973,"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": 1708038302507.152, "dur": 34507.065, + "args": { + "External id": 4679974,"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": 1708038302583.986, "dur": 13.764, + "args": { + "External id": 4679975,"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": 1708038302603.981, "dur": 34341.899, + "args": { + "External id": 4679976,"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": 1708038302606.621, "dur": 34338.661, + "args": { + "External id": 4679977,"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": 1708038302610.757, "dur": 5.850, + "args": { + "External id": 4679978,"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": 1708038302618.299, "dur": 34323.934, + "args": { + "External id": 4679979,"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": 1708038337116.974, "dur": 8.324, + "args": { + "External id": 4679980,"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": 1708038337119.559, "dur": 5.408, + "args": { + "External id": 4679981,"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": 1708038337156.194, "dur": 425.371, + "args": { + "External id": 4679982,"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": 1708038337192.106, "dur": 383.962, + "args": { + "External id": 4679983,"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": 1708038337202.341, "dur": 367.580, + "args": { + "External id": 4679984,"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": 1708038337607.111, "dur": 2.348, + "args": { + "External id": 4679985,"Record function id": 0, "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": 1708038337670.468, "dur": 8.731, + "args": { + "External id": 4679986,"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": 1708038337720.887, "dur": 1.277, + "args": { + "External id": 4679987,"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": 1708038337737.387, "dur": 1.263, + "args": { + "External id": 4679988,"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": 1708038337750.630, "dur": 1.391, + "args": { + "External id": 4679989,"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": 1708038337763.287, "dur": 2.891, + "args": { + "External id": 4679990,"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": 1708038337776.664, "dur": 1.233, + "args": { + "External id": 4679991,"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": 1708038337790.819, "dur": 1.189, + "args": { + "External id": 4679992,"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": 1708038337803.523, "dur": 0.952, + "args": { + "External id": 4679993,"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": 1708038337814.529, "dur": 3.172, + "args": { + "External id": 4679994,"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": 1708038337905.140, "dur": 2809.647, + "args": { + "External id": 4679995,"Record function id": 0, "Ev Idx": 4410 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1708038337924.771, "dur": 1120.367, + "args": { + "External id": 4679996,"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": 1708038337940.952, "dur": 359.203, + "args": { + "External id": 4679997,"Record function id": 0, "Ev Idx": 4412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038338061.533, "dur": 4.840, + "args": { + "External id": 4679998,"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": 1708038338069.786, "dur": 1.214, + "args": { + "External id": 4679999,"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": 1708038338074.700, "dur": 1.231, + "args": { + "External id": 4680000,"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": 1708038338077.815, "dur": 0.974, + "args": { + "External id": 4680001,"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": 1708038338080.262, "dur": 1.075, + "args": { + "External id": 4680002,"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": 1708038338082.953, "dur": 1.058, + "args": { + "External id": 4680003,"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": 1708038338087.490, "dur": 3.396, + "args": { + "External id": 4680004,"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": 1708038338092.364, "dur": 1.089, + "args": { + "External id": 4680005,"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": 1708038338094.987, "dur": 1.309, + "args": { + "External id": 4680006,"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": 1708038338097.742, "dur": 1.202, + "args": { + "External id": 4680007,"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": 1708038338120.704, "dur": 149.877, + "args": { + "External id": 4680008,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038338137.022, "dur": 129.140, + "args": { + "External id": 4680009,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038338157.383, "dur": 13.600, + "args": { + "External id": 4680010,"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": 1708038338173.777, "dur": 64.194, + "args": { + "External id": 4680011,"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": 1708038338176.375, "dur": 61.275, + "args": { + "External id": 4680012,"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": 1708038338180.357, "dur": 5.918, + "args": { + "External id": 4680013,"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": 1708038338187.985, "dur": 49.070, + "args": { + "External id": 4680014,"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": 1708038338399.148, "dur": 637.710, + "args": { + "External id": 4680015,"Record function id": 0, "Ev Idx": 4430 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1708038338417.262, "dur": 599.666, + "args": { + "External id": 4680016,"Record function id": 0, "Ev Idx": 4431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038338479.929, "dur": 4.246, + "args": { + "External id": 4680017,"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": 1708038338499.620, "dur": 48.440, + "args": { + "External id": 4680018,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038338503.645, "dur": 1.660, + "args": { + "External id": 4680019,"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": 1708038338507.755, "dur": 2.607, + "args": { + "External id": 4680020,"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": 1708038338512.014, "dur": 1.157, + "args": { + "External id": 4680021,"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": 1708038338514.935, "dur": 0.581, + "args": { + "External id": 4680022,"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": 1708038338516.988, "dur": 0.547, + "args": { + "External id": 4680023,"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": 1708038338519.875, "dur": 0.400, + "args": { + "External id": 4680024,"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": 1708038338521.884, "dur": 0.306, + "args": { + "External id": 4680025,"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": 1708038338538.735, "dur": 0.586, + "args": { + "External id": 4680026,"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": 1708038338541.960, "dur": 0.347, + "args": { + "External id": 4680027,"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": 1708038338559.604, "dur": 36.123, + "args": { + "External id": 4680028,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038338630.162, "dur": 117.233, + "args": { + "External id": 4680029,"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": 1708038338640.377, "dur": 6.478, + "args": { + "External id": 4680030,"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": 1708038338651.930, "dur": 9.726, + "args": { + "External id": 4680031,"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": 1708038338656.243, "dur": 5.017, + "args": { + "External id": 4680032,"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": 1708038338659.665, "dur": 0.497, + "args": { + "External id": 4680033,"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": 1708038338668.843, "dur": 29.137, + "args": { + "External id": 4680034,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038338671.147, "dur": 0.585, + "args": { + "External id": 4680035,"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": 1708038338673.363, "dur": 0.451, + "args": { + "External id": 4680036,"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": 1708038338675.886, "dur": 0.470, + "args": { + "External id": 4680037,"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": 1708038338677.589, "dur": 0.717, + "args": { + "External id": 4680038,"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": 1708038338679.761, "dur": 4.179, + "args": { + "External id": 4680039,"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": 1708038338685.333, "dur": 0.652, + "args": { + "External id": 4680040,"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": 1708038338687.223, "dur": 2.605, + "args": { + "External id": 4680041,"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": 1708038338691.304, "dur": 0.321, + "args": { + "External id": 4680042,"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": 1708038338693.146, "dur": 0.659, + "args": { + "External id": 4680043,"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": 1708038338715.385, "dur": 21.366, + "args": { + "External id": 4680044,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038338791.517, "dur": 119.376, + "args": { + "External id": 4680045,"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": 1708038338823.322, "dur": 84.212, + "args": { + "External id": 4680046,"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": 1708038338832.391, "dur": 71.034, + "args": { + "External id": 4680047,"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": 1708038338931.220, "dur": 1.854, + "args": { + "External id": 4680048,"Record function id": 0, "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": 1708038339053.221, "dur": 1642.195, + "args": { + "External id": 4680049,"Sequence number": 46526450, "Fwd thread 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": 1708038339053.221, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038339168.580, "dur": 102.630, + "args": { + "External id": 4680050,"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": 1708038339311.991, "dur": 41.049, + "args": { + "External id": 4680051,"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": 1708038339370.750, "dur": 48.459, + "args": { + "External id": 4680052,"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": 1708038339428.624, "dur": 32.733, + "args": { + "External id": 4680053,"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": 1708038339467.142, "dur": 44.908, + "args": { + "External id": 4680054,"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": 1708038339520.251, "dur": 46.966, + "args": { + "External id": 4680055,"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": 1708038339578.071, "dur": 42.834, + "args": { + "External id": 4680056,"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": 1708038339645.914, "dur": 28.399, + "args": { + "External id": 4680057,"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": 1708038339695.032, "dur": 27.746, + "args": { + "External id": 4680058,"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": 1708038339742.585, "dur": 19.404, + "args": { + "External id": 4680059,"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": 1708038339777.775, "dur": 16.289, + "args": { + "External id": 4680060,"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": 1708038339802.833, "dur": 29.808, + "args": { + "External id": 4680061,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038339835.802, "dur": 30.594, + "args": { + "External id": 4680062,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038339892.156, "dur": 205.975, + "args": { + "External id": 4680063,"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": 1708038339966.102, "dur": 5.613, + "args": { + "External id": 4680064,"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": 1708038339974.024, "dur": 4.426, + "args": { + "External id": 4680065,"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": 1708038340139.035, "dur": 26.512, + "args": { + "External id": 4680066,"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": 1708038340178.188, "dur": 14.726, + "args": { + "External id": 4680067,"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": 1708038340201.604, "dur": 50.242, + "args": { + "External id": 4680068,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038340257.648, "dur": 36.814, + "args": { + "External id": 4680069,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038340301.033, "dur": 22.331, + "args": { + "External id": 4680070,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038340329.533, "dur": 29.417, + "args": { + "External id": 4680071,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038340363.850, "dur": 38.300, + "args": { + "External id": 4680072,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038340414.860, "dur": 33.098, + "args": { + "External id": 4680073,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038340470.587, "dur": 28.132, + "args": { + "External id": 4680074,"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": 1708038340518.890, "dur": 43.682, + "args": { + "External id": 4680075,"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": 1708038340581.743, "dur": 18.179, + "args": { + "External id": 4680076,"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": 1708038340619.495, "dur": 16.052, + "args": { + "External id": 4680077,"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": 1708038340649.467, "dur": 15.979, + "args": { + "External id": 4680078,"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": 1708038340739.859, "dur": 14.674, + "args": { + "External id": 4680079,"Record function id": 0, "Ev Idx": 4494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038340743.012, "dur": 10.651, + "args": { + "External id": 4680080,"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": 1708038340747.142, "dur": 5.373, + "args": { + "External id": 4680081,"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": 1708038340748.390, "dur": 4.034, + "args": { + "External id": 4680082,"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": 1708038340758.448, "dur": 4.980, + "args": { + "External id": 4680083,"Record function id": 0, "Ev Idx": 4498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038340759.621, "dur": 3.323, + "args": { + "External id": 4680084,"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": 1708038340760.923, "dur": 1.569, + "args": { + "External id": 4680085,"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": 1708038340761.583, "dur": 0.843, + "args": { + "External id": 4680086,"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": 1708038340766.748, "dur": 4.399, + "args": { + "External id": 4680087,"Record function id": 0, "Ev Idx": 4502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038340768.194, "dur": 2.525, + "args": { + "External id": 4680088,"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": 1708038340768.917, "dur": 1.373, + "args": { + "External id": 4680089,"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": 1708038340769.357, "dur": 0.855, + "args": { + "External id": 4680090,"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": 1708038340774.361, "dur": 5.788, + "args": { + "External id": 4680091,"Record function id": 0, "Ev Idx": 4506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038340775.619, "dur": 4.107, + "args": { + "External id": 4680092,"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": 1708038340776.384, "dur": 2.893, + "args": { + "External id": 4680093,"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": 1708038340776.880, "dur": 2.318, + "args": { + "External id": 4680094,"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": 1708038340783.425, "dur": 7.055, + "args": { + "External id": 4680095,"Record function id": 0, "Ev Idx": 4510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038340787.790, "dur": 2.236, + "args": { + "External id": 4680096,"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": 1708038340788.569, "dur": 1.060, + "args": { + "External id": 4680097,"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": 1708038340788.843, "dur": 0.707, + "args": { + "External id": 4680098,"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": 1708038340793.667, "dur": 6.174, + "args": { + "External id": 4680099,"Record function id": 0, "Ev Idx": 4514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038340794.546, "dur": 4.836, + "args": { + "External id": 4680100,"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": 1708038340795.328, "dur": 3.346, + "args": { + "External id": 4680101,"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": 1708038340797.705, "dur": 0.872, + "args": { + "External id": 4680102,"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": 1708038340803.138, "dur": 4.147, + "args": { + "External id": 4680103,"Record function id": 0, "Ev Idx": 4518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038340804.336, "dur": 2.521, + "args": { + "External id": 4680104,"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": 1708038340805.174, "dur": 1.261, + "args": { + "External id": 4680105,"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": 1708038340805.569, "dur": 0.779, + "args": { + "External id": 4680106,"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": 1708038340810.472, "dur": 4.181, + "args": { + "External id": 4680107,"Record function id": 0, "Ev Idx": 4522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038340811.781, "dur": 2.431, + "args": { + "External id": 4680108,"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": 1708038340812.541, "dur": 1.243, + "args": { + "External id": 4680109,"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": 1708038340812.925, "dur": 0.785, + "args": { + "External id": 4680110,"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": 1708038340817.870, "dur": 4.293, + "args": { + "External id": 4680111,"Record function id": 0, "Ev Idx": 4526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038340819.033, "dur": 2.701, + "args": { + "External id": 4680112,"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": 1708038340819.923, "dur": 1.291, + "args": { + "External id": 4680113,"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": 1708038340820.270, "dur": 0.868, + "args": { + "External id": 4680114,"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": 1708038340826.215, "dur": 35133.112, + "args": { + "External id": 4680115,"Record function id": 0, "Sequence number": 46526449, "Fwd thread id": 1, "Ev Idx": 4530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038340828.123, "dur": 35122.292, + "args": { + "External id": 4680116,"Sequence number": 46526449, "Fwd thread 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": 1708038340828.123, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 1336753, "tid": 1381210, + "ts": 1708038340858.885, "dur": 35.636, + "args": { + "External id": 4680117,"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": 1708038340902.558, "dur": 68.765, + "args": { + "External id": 4680118,"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": 1708038340977.606, "dur": 34964.763, + "args": { + "External id": 4680119,"Record function id": 0, "Ev Idx": 4534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038341099.750, "dur": 7.501, + "args": { + "External id": 4680120,"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": 1708038341117.442, "dur": 5.254, + "args": { + "External id": 4680121,"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": 1708038341139.017, "dur": 34027.229, + "args": { + "External id": 4680122,"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": 1708038341153.170, "dur": 34004.420, + "args": { + "External id": 4680123,"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": 1708038341215.970, "dur": 15.028, + "args": { + "External id": 4680124,"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": 1708038341237.349, "dur": 33880.820, + "args": { + "External id": 4680125,"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": 1708038341240.138, "dur": 33877.322, + "args": { + "External id": 4680126,"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": 1708038341243.869, "dur": 8.849, + "args": { + "External id": 4680127,"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": 1708038341254.328, "dur": 33859.616, + "args": { + "External id": 4680128,"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": 1708038375250.633, "dur": 8.376, + "args": { + "External id": 4680129,"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": 1708038375253.244, "dur": 5.379, + "args": { + "External id": 4680130,"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": 1708038375288.968, "dur": 353.631, + "args": { + "External id": 4680131,"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": 1708038375321.496, "dur": 316.171, + "args": { + "External id": 4680132,"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": 1708038375331.822, "dur": 299.933, + "args": { + "External id": 4680133,"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": 1708038375665.211, "dur": 2.606, + "args": { + "External id": 4680134,"Record function id": 0, "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": 1708038375728.428, "dur": 6.739, + "args": { + "External id": 4680135,"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": 1708038375781.364, "dur": 1.647, + "args": { + "External id": 4680136,"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": 1708038375798.128, "dur": 1.295, + "args": { + "External id": 4680137,"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": 1708038375815.827, "dur": 0.831, + "args": { + "External id": 4680138,"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": 1708038375833.066, "dur": 1.087, + "args": { + "External id": 4680139,"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": 1708038375843.964, "dur": 0.970, + "args": { + "External id": 4680140,"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": 1708038375855.497, "dur": 0.892, + "args": { + "External id": 4680141,"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": 1708038375873.779, "dur": 1.062, + "args": { + "External id": 4680142,"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": 1708038375884.639, "dur": 0.956, + "args": { + "External id": 4680143,"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": 1708038375972.398, "dur": 2872.505, + "args": { + "External id": 4680144,"Record function id": 0, "Ev Idx": 4559 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1708038376025.799, "dur": 1134.065, + "args": { + "External id": 4680145,"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": 1708038376041.227, "dur": 327.963, + "args": { + "External id": 4680146,"Record function id": 0, "Ev Idx": 4561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038376130.046, "dur": 4.909, + "args": { + "External id": 4680147,"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": 1708038376138.472, "dur": 1.117, + "args": { + "External id": 4680148,"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": 1708038376141.383, "dur": 1.204, + "args": { + "External id": 4680149,"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": 1708038376145.855, "dur": 3.456, + "args": { + "External id": 4680150,"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": 1708038376151.031, "dur": 4.481, + "args": { + "External id": 4680151,"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": 1708038376157.296, "dur": 1.362, + "args": { + "External id": 4680152,"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": 1708038376160.147, "dur": 0.749, + "args": { + "External id": 4680153,"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": 1708038376164.295, "dur": 1.148, + "args": { + "External id": 4680154,"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": 1708038376166.791, "dur": 0.825, + "args": { + "External id": 4680155,"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": 1708038376169.077, "dur": 0.777, + "args": { + "External id": 4680156,"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": 1708038376187.549, "dur": 153.725, + "args": { + "External id": 4680157,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038376203.885, "dur": 133.003, + "args": { + "External id": 4680158,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038376226.847, "dur": 12.279, + "args": { + "External id": 4680159,"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": 1708038376242.090, "dur": 68.220, + "args": { + "External id": 4680160,"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": 1708038376244.942, "dur": 65.014, + "args": { + "External id": 4680161,"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": 1708038376249.040, "dur": 7.321, + "args": { + "External id": 4680162,"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": 1708038376258.134, "dur": 51.069, + "args": { + "External id": 4680163,"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": 1708038376462.556, "dur": 689.562, + "args": { + "External id": 4680164,"Record function id": 0, "Ev Idx": 4579 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1708038376477.218, "dur": 662.304, + "args": { + "External id": 4680165,"Record function id": 0, "Ev Idx": 4580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038376557.621, "dur": 6.141, + "args": { + "External id": 4680166,"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": 1708038376580.206, "dur": 32.961, + "args": { + "External id": 4680167,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038376584.759, "dur": 2.833, + "args": { + "External id": 4680168,"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": 1708038376589.806, "dur": 0.328, + "args": { + "External id": 4680169,"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": 1708038376591.547, "dur": 0.513, + "args": { + "External id": 4680170,"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": 1708038376594.486, "dur": 0.545, + "args": { + "External id": 4680171,"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": 1708038376596.628, "dur": 0.636, + "args": { + "External id": 4680172,"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": 1708038376598.634, "dur": 0.657, + "args": { + "External id": 4680173,"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": 1708038376601.124, "dur": 2.909, + "args": { + "External id": 4680174,"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": 1708038376605.377, "dur": 0.586, + "args": { + "External id": 4680175,"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": 1708038376607.988, "dur": 1.145, + "args": { + "External id": 4680176,"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": 1708038376624.390, "dur": 35.987, + "args": { + "External id": 4680177,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038376691.758, "dur": 171.454, + "args": { + "External id": 4680178,"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": 1708038376701.713, "dur": 3.458, + "args": { + "External id": 4680179,"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": 1708038376710.289, "dur": 10.468, + "args": { + "External id": 4680180,"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": 1708038376714.384, "dur": 5.970, + "args": { + "External id": 4680181,"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": 1708038376718.275, "dur": 0.822, + "args": { + "External id": 4680182,"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": 1708038376727.645, "dur": 24.482, + "args": { + "External id": 4680183,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038376730.009, "dur": 0.775, + "args": { + "External id": 4680184,"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": 1708038376732.714, "dur": 0.365, + "args": { + "External id": 4680185,"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": 1708038376734.793, "dur": 0.696, + "args": { + "External id": 4680186,"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": 1708038376737.187, "dur": 2.724, + "args": { + "External id": 4680187,"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": 1708038376741.402, "dur": 0.605, + "args": { + "External id": 4680188,"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": 1708038376743.575, "dur": 0.382, + "args": { + "External id": 4680189,"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": 1708038376745.511, "dur": 0.503, + "args": { + "External id": 4680190,"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": 1708038376747.374, "dur": 0.665, + "args": { + "External id": 4680191,"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": 1708038376749.372, "dur": 0.383, + "args": { + "External id": 4680192,"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": 1708038376830.914, "dur": 24.557, + "args": { + "External id": 4680193,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038376911.868, "dur": 153.730, + "args": { + "External id": 4680194,"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": 1708038376940.729, "dur": 120.896, + "args": { + "External id": 4680195,"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": 1708038376949.754, "dur": 106.965, + "args": { + "External id": 4680196,"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": 1708038377083.368, "dur": 1.924, + "args": { + "External id": 4680197,"Record function id": 0, "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": 1708038377168.178, "dur": 1655.454, + "args": { + "External id": 4680198,"Sequence number": 46526448, "Fwd thread 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": 1708038377168.178, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038377279.839, "dur": 103.206, + "args": { + "External id": 4680199,"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": 1708038377428.159, "dur": 41.559, + "args": { + "External id": 4680200,"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": 1708038377488.973, "dur": 68.718, + "args": { + "External id": 4680201,"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": 1708038377570.837, "dur": 36.470, + "args": { + "External id": 4680202,"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": 1708038377623.958, "dur": 44.384, + "args": { + "External id": 4680203,"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": 1708038377675.148, "dur": 27.615, + "args": { + "External id": 4680204,"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": 1708038377714.600, "dur": 40.695, + "args": { + "External id": 4680205,"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": 1708038377784.630, "dur": 23.447, + "args": { + "External id": 4680206,"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": 1708038377828.508, "dur": 30.953, + "args": { + "External id": 4680207,"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": 1708038377879.679, "dur": 21.266, + "args": { + "External id": 4680208,"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": 1708038377916.563, "dur": 21.646, + "args": { + "External id": 4680209,"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": 1708038377947.033, "dur": 29.467, + "args": { + "External id": 4680210,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038377979.473, "dur": 68.929, + "args": { + "External id": 4680211,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038378081.156, "dur": 170.699, + "args": { + "External id": 4680212,"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": 1708038378155.223, "dur": 6.114, + "args": { + "External id": 4680213,"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": 1708038378163.102, "dur": 2.380, + "args": { + "External id": 4680214,"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": 1708038378288.408, "dur": 29.443, + "args": { + "External id": 4680215,"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": 1708038378330.012, "dur": 14.335, + "args": { + "External id": 4680216,"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": 1708038378351.504, "dur": 38.756, + "args": { + "External id": 4680217,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038378395.294, "dur": 32.729, + "args": { + "External id": 4680218,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038378448.554, "dur": 31.937, + "args": { + "External id": 4680219,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038378485.602, "dur": 32.513, + "args": { + "External id": 4680220,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038378538.919, "dur": 29.714, + "args": { + "External id": 4680221,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038378577.626, "dur": 28.934, + "args": { + "External id": 4680222,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038378630.951, "dur": 24.961, + "args": { + "External id": 4680223,"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": 1708038378674.256, "dur": 24.376, + "args": { + "External id": 4680224,"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": 1708038378715.574, "dur": 17.173, + "args": { + "External id": 4680225,"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": 1708038378751.756, "dur": 16.298, + "args": { + "External id": 4680226,"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": 1708038378782.474, "dur": 15.613, + "args": { + "External id": 4680227,"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": 1708038378866.555, "dur": 13.985, + "args": { + "External id": 4680228,"Record function id": 0, "Ev Idx": 4643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038378869.770, "dur": 9.938, + "args": { + "External id": 4680229,"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": 1708038378873.229, "dur": 5.671, + "args": { + "External id": 4680230,"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": 1708038378874.839, "dur": 3.953, + "args": { + "External id": 4680231,"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": 1708038378884.443, "dur": 4.631, + "args": { + "External id": 4680232,"Record function id": 0, "Ev Idx": 4647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038378886.096, "dur": 2.552, + "args": { + "External id": 4680233,"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": 1708038378886.687, "dur": 1.475, + "args": { + "External id": 4680234,"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": 1708038378887.308, "dur": 0.751, + "args": { + "External id": 4680235,"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": 1708038378892.253, "dur": 4.311, + "args": { + "External id": 4680236,"Record function id": 0, "Ev Idx": 4651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038378893.443, "dur": 2.734, + "args": { + "External id": 4680237,"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": 1708038378894.046, "dur": 1.593, + "args": { + "External id": 4680238,"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": 1708038378894.575, "dur": 0.994, + "args": { + "External id": 4680239,"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": 1708038378899.731, "dur": 4.515, + "args": { + "External id": 4680240,"Record function id": 0, "Ev Idx": 4655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038378901.071, "dur": 2.731, + "args": { + "External id": 4680241,"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": 1708038378901.873, "dur": 1.396, + "args": { + "External id": 4680242,"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": 1708038378902.464, "dur": 0.693, + "args": { + "External id": 4680243,"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": 1708038378907.376, "dur": 5.990, + "args": { + "External id": 4680244,"Record function id": 0, "Ev Idx": 4659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038378908.357, "dur": 4.556, + "args": { + "External id": 4680245,"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": 1708038378908.894, "dur": 3.529, + "args": { + "External id": 4680246,"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": 1708038378909.294, "dur": 3.032, + "args": { + "External id": 4680247,"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": 1708038378916.466, "dur": 4.040, + "args": { + "External id": 4680248,"Record function id": 0, "Ev Idx": 4663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038378917.756, "dur": 2.314, + "args": { + "External id": 4680249,"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": 1708038378918.246, "dur": 1.281, + "args": { + "External id": 4680250,"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": 1708038378918.639, "dur": 0.799, + "args": { + "External id": 4680251,"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": 1708038378923.725, "dur": 3.874, + "args": { + "External id": 4680252,"Record function id": 0, "Ev Idx": 4667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038378924.972, "dur": 2.210, + "args": { + "External id": 4680253,"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": 1708038378925.452, "dur": 1.158, + "args": { + "External id": 4680254,"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": 1708038378925.836, "dur": 0.687, + "args": { + "External id": 4680255,"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": 1708038378930.664, "dur": 4.036, + "args": { + "External id": 4680256,"Record function id": 0, "Ev Idx": 4671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038378932.200, "dur": 2.090, + "args": { + "External id": 4680257,"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": 1708038378932.723, "dur": 1.060, + "args": { + "External id": 4680258,"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": 1708038378933.124, "dur": 0.595, + "args": { + "External id": 4680259,"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": 1708038378937.797, "dur": 5.698, + "args": { + "External id": 4680260,"Record function id": 0, "Ev Idx": 4675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038378939.192, "dur": 3.851, + "args": { + "External id": 4680261,"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": 1708038378939.697, "dur": 2.921, + "args": { + "External id": 4680262,"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": 1708038378941.703, "dur": 0.842, + "args": { + "External id": 4680263,"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": 1708038378947.175, "dur": 35751.438, + "args": { + "External id": 4680264,"Record function id": 0, "Sequence number": 46526447, "Fwd thread id": 1, "Ev Idx": 4679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038378948.661, "dur": 35742.297, + "args": { + "External id": 4680265,"Sequence number": 46526447, "Fwd thread 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": 1708038378948.661, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 1336753, "tid": 1381210, + "ts": 1708038378974.413, "dur": 68.188, + "args": { + "External id": 4680266,"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": 1708038379051.762, "dur": 67.607, + "args": { + "External id": 4680267,"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": 1708038379125.080, "dur": 35558.259, + "args": { + "External id": 4680268,"Record function id": 0, "Ev Idx": 4683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038379208.512, "dur": 7.153, + "args": { + "External id": 4680269,"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": 1708038379225.846, "dur": 5.094, + "args": { + "External id": 4680270,"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": 1708038379245.737, "dur": 34733.454, + "args": { + "External id": 4680271,"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": 1708038379259.250, "dur": 34711.243, + "args": { + "External id": 4680272,"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": 1708038379317.793, "dur": 13.190, + "args": { + "External id": 4680273,"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": 1708038379336.825, "dur": 34593.875, + "args": { + "External id": 4680274,"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": 1708038379339.305, "dur": 34590.659, + "args": { + "External id": 4680275,"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": 1708038379343.274, "dur": 7.192, + "args": { + "External id": 4680276,"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": 1708038379351.977, "dur": 34574.396, + "args": { + "External id": 4680277,"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": 1708038414090.460, "dur": 8.304, + "args": { + "External id": 4680278,"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": 1708038414092.997, "dur": 5.387, + "args": { + "External id": 4680279,"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": 1708038414128.337, "dur": 246.252, + "args": { + "External id": 4680280,"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": 1708038414159.964, "dur": 210.425, + "args": { + "External id": 4680281,"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": 1708038414170.029, "dur": 195.452, + "args": { + "External id": 4680282,"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": 1708038414392.995, "dur": 1.966, + "args": { + "External id": 4680283,"Record function id": 0, "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": 1708038414444.831, "dur": 6.437, + "args": { + "External id": 4680284,"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": 1708038414497.473, "dur": 1.488, + "args": { + "External id": 4680285,"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": 1708038414515.237, "dur": 1.274, + "args": { + "External id": 4680286,"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": 1708038414550.930, "dur": 4.166, + "args": { + "External id": 4680287,"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": 1708038414567.192, "dur": 1.203, + "args": { + "External id": 4680288,"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": 1708038414578.502, "dur": 0.988, + "args": { + "External id": 4680289,"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": 1708038414589.863, "dur": 0.859, + "args": { + "External id": 4680290,"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": 1708038414606.727, "dur": 2.634, + "args": { + "External id": 4680291,"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": 1708038414619.389, "dur": 1.018, + "args": { + "External id": 4680292,"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": 1708038414712.993, "dur": 2879.020, + "args": { + "External id": 4680293,"Record function id": 0, "Ev Idx": 4708 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1708038414732.389, "dur": 1111.442, + "args": { + "External id": 4680294,"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": 1708038414749.089, "dur": 376.347, + "args": { + "External id": 4680295,"Record function id": 0, "Ev Idx": 4710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038414829.681, "dur": 4.091, + "args": { + "External id": 4680296,"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": 1708038414836.598, "dur": 1.401, + "args": { + "External id": 4680297,"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": 1708038414839.688, "dur": 1.026, + "args": { + "External id": 4680298,"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": 1708038414844.057, "dur": 0.715, + "args": { + "External id": 4680299,"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": 1708038414846.148, "dur": 2.802, + "args": { + "External id": 4680300,"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": 1708038414850.818, "dur": 0.731, + "args": { + "External id": 4680301,"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": 1708038414853.460, "dur": 0.881, + "args": { + "External id": 4680302,"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": 1708038414857.068, "dur": 0.980, + "args": { + "External id": 4680303,"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": 1708038414859.517, "dur": 0.899, + "args": { + "External id": 4680304,"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": 1708038414862.427, "dur": 0.747, + "args": { + "External id": 4680305,"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": 1708038414883.409, "dur": 209.380, + "args": { + "External id": 4680306,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038414899.252, "dur": 187.950, + "args": { + "External id": 4680307,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038414938.912, "dur": 11.693, + "args": { + "External id": 4680308,"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": 1708038414953.420, "dur": 105.186, + "args": { + "External id": 4680309,"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": 1708038414955.765, "dur": 102.394, + "args": { + "External id": 4680310,"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": 1708038414963.436, "dur": 5.907, + "args": { + "External id": 4680311,"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": 1708038414970.921, "dur": 86.132, + "args": { + "External id": 4680312,"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": 1708038415220.892, "dur": 614.656, + "args": { + "External id": 4680313,"Record function id": 0, "Ev Idx": 4728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1708038415241.529, "dur": 581.756, + "args": { + "External id": 4680314,"Record function id": 0, "Ev Idx": 4729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038415305.973, "dur": 7.600, + "args": { + "External id": 4680315,"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": 1708038415329.489, "dur": 29.995, + "args": { + "External id": 4680316,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038415334.200, "dur": 1.315, + "args": { + "External id": 4680317,"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": 1708038415338.113, "dur": 0.745, + "args": { + "External id": 4680318,"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": 1708038415341.233, "dur": 0.525, + "args": { + "External id": 4680319,"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": 1708038415343.191, "dur": 0.492, + "args": { + "External id": 4680320,"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": 1708038415345.270, "dur": 0.384, + "args": { + "External id": 4680321,"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": 1708038415348.169, "dur": 0.333, + "args": { + "External id": 4680322,"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": 1708038415350.082, "dur": 0.329, + "args": { + "External id": 4680323,"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": 1708038415352.073, "dur": 2.662, + "args": { + "External id": 4680324,"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": 1708038415356.253, "dur": 0.460, + "args": { + "External id": 4680325,"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": 1708038415370.581, "dur": 35.439, + "args": { + "External id": 4680326,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038415436.284, "dur": 160.234, + "args": { + "External id": 4680327,"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": 1708038415445.952, "dur": 3.989, + "args": { + "External id": 4680328,"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": 1708038415455.188, "dur": 9.701, + "args": { + "External id": 4680329,"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": 1708038415459.224, "dur": 5.253, + "args": { + "External id": 4680330,"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": 1708038415462.867, "dur": 0.476, + "args": { + "External id": 4680331,"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": 1708038415471.868, "dur": 30.742, + "args": { + "External id": 4680332,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038415474.500, "dur": 0.775, + "args": { + "External id": 4680333,"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": 1708038415477.017, "dur": 0.707, + "args": { + "External id": 4680334,"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": 1708038415482.129, "dur": 0.581, + "args": { + "External id": 4680335,"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": 1708038415483.909, "dur": 0.558, + "args": { + "External id": 4680336,"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": 1708038415485.992, "dur": 2.283, + "args": { + "External id": 4680337,"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": 1708038415489.608, "dur": 0.549, + "args": { + "External id": 4680338,"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": 1708038415491.392, "dur": 0.548, + "args": { + "External id": 4680339,"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": 1708038415493.380, "dur": 0.408, + "args": { + "External id": 4680340,"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": 1708038415495.035, "dur": 0.397, + "args": { + "External id": 4680341,"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": 1708038415562.174, "dur": 25.519, + "args": { + "External id": 4680342,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038415642.922, "dur": 115.622, + "args": { + "External id": 4680343,"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": 1708038415673.421, "dur": 81.958, + "args": { + "External id": 4680344,"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": 1708038415682.622, "dur": 68.742, + "args": { + "External id": 4680345,"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": 1708038415773.790, "dur": 1.738, + "args": { + "External id": 4680346,"Record function id": 0, "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": 1708038415851.246, "dur": 1718.058, + "args": { + "External id": 4680347,"Sequence number": 46526446, "Fwd thread 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": 1708038415851.246, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038415961.896, "dur": 138.514, + "args": { + "External id": 4680348,"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": 1708038416152.155, "dur": 46.903, + "args": { + "External id": 4680349,"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": 1708038416215.749, "dur": 52.777, + "args": { + "External id": 4680350,"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": 1708038416277.794, "dur": 36.243, + "args": { + "External id": 4680351,"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": 1708038416320.174, "dur": 44.342, + "args": { + "External id": 4680352,"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": 1708038416372.830, "dur": 27.460, + "args": { + "External id": 4680353,"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": 1708038416408.438, "dur": 40.947, + "args": { + "External id": 4680354,"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": 1708038416473.028, "dur": 25.048, + "args": { + "External id": 4680355,"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": 1708038416517.628, "dur": 48.371, + "args": { + "External id": 4680356,"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": 1708038416590.214, "dur": 21.466, + "args": { + "External id": 4680357,"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": 1708038416633.758, "dur": 16.537, + "args": { + "External id": 4680358,"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": 1708038416658.401, "dur": 38.258, + "args": { + "External id": 4680359,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038416699.759, "dur": 33.310, + "args": { + "External id": 4680360,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038416769.337, "dur": 165.007, + "args": { + "External id": 4680361,"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": 1708038416844.880, "dur": 7.476, + "args": { + "External id": 4680362,"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": 1708038416854.429, "dur": 2.182, + "args": { + "External id": 4680363,"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": 1708038416969.667, "dur": 73.562, + "args": { + "External id": 4680364,"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": 1708038417057.544, "dur": 15.308, + "args": { + "External id": 4680365,"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": 1708038417082.228, "dur": 42.887, + "args": { + "External id": 4680366,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038417131.115, "dur": 53.512, + "args": { + "External id": 4680367,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038417200.991, "dur": 26.667, + "args": { + "External id": 4680368,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038417234.397, "dur": 29.397, + "args": { + "External id": 4680369,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038417269.127, "dur": 25.013, + "args": { + "External id": 4680370,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038417302.259, "dur": 32.365, + "args": { + "External id": 4680371,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038417357.596, "dur": 24.948, + "args": { + "External id": 4680372,"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": 1708038417403.063, "dur": 26.946, + "args": { + "External id": 4680373,"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": 1708038417445.123, "dur": 17.688, + "args": { + "External id": 4680374,"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": 1708038417479.757, "dur": 16.086, + "args": { + "External id": 4680375,"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": 1708038417509.572, "dur": 29.261, + "args": { + "External id": 4680376,"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": 1708038417614.083, "dur": 14.375, + "args": { + "External id": 4680377,"Record function id": 0, "Ev Idx": 4792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038417617.396, "dur": 10.178, + "args": { + "External id": 4680378,"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": 1708038417621.166, "dur": 5.526, + "args": { + "External id": 4680379,"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": 1708038417622.770, "dur": 3.803, + "args": { + "External id": 4680380,"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": 1708038417632.262, "dur": 4.868, + "args": { + "External id": 4680381,"Record function id": 0, "Ev Idx": 4796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038417633.468, "dur": 3.223, + "args": { + "External id": 4680382,"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": 1708038417634.541, "dur": 1.672, + "args": { + "External id": 4680383,"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": 1708038417635.124, "dur": 0.967, + "args": { + "External id": 4680384,"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": 1708038417640.402, "dur": 4.381, + "args": { + "External id": 4680385,"Record function id": 0, "Ev Idx": 4800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038417641.759, "dur": 2.615, + "args": { + "External id": 4680386,"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": 1708038417642.516, "dur": 1.325, + "args": { + "External id": 4680387,"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": 1708038417643.111, "dur": 0.629, + "args": { + "External id": 4680388,"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": 1708038417647.927, "dur": 4.308, + "args": { + "External id": 4680389,"Record function id": 0, "Ev Idx": 4804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038417649.336, "dur": 2.498, + "args": { + "External id": 4680390,"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": 1708038417650.288, "dur": 1.025, + "args": { + "External id": 4680391,"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": 1708038417650.576, "dur": 0.641, + "args": { + "External id": 4680392,"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": 1708038417655.335, "dur": 5.309, + "args": { + "External id": 4680393,"Record function id": 0, "Ev Idx": 4808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038417656.377, "dur": 3.856, + "args": { + "External id": 4680394,"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": 1708038417656.906, "dur": 2.900, + "args": { + "External id": 4680395,"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": 1708038417657.187, "dur": 2.554, + "args": { + "External id": 4680396,"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": 1708038417663.784, "dur": 5.627, + "args": { + "External id": 4680397,"Record function id": 0, "Ev Idx": 4812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038417664.820, "dur": 4.131, + "args": { + "External id": 4680398,"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": 1708038417665.733, "dur": 2.762, + "args": { + "External id": 4680399,"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": 1708038417667.514, "dur": 0.844, + "args": { + "External id": 4680400,"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": 1708038417672.731, "dur": 3.307, + "args": { + "External id": 4680401,"Record function id": 0, "Ev Idx": 4816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038417673.772, "dur": 1.866, + "args": { + "External id": 4680402,"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": 1708038417674.255, "dur": 0.988, + "args": { + "External id": 4680403,"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": 1708038417674.612, "dur": 0.534, + "args": { + "External id": 4680404,"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": 1708038417679.179, "dur": 3.822, + "args": { + "External id": 4680405,"Record function id": 0, "Ev Idx": 4820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038417680.187, "dur": 2.396, + "args": { + "External id": 4680406,"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": 1708038417680.606, "dur": 1.443, + "args": { + "External id": 4680407,"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": 1708038417681.197, "dur": 0.751, + "args": { + "External id": 4680408,"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": 1708038417686.028, "dur": 4.082, + "args": { + "External id": 4680409,"Record function id": 0, "Ev Idx": 4824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038417687.264, "dur": 2.459, + "args": { + "External id": 4680410,"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": 1708038417687.897, "dur": 1.410, + "args": { + "External id": 4680411,"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": 1708038417688.558, "dur": 0.651, + "args": { + "External id": 4680412,"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": 1708038417693.705, "dur": 36550.196, + "args": { + "External id": 4680413,"Record function id": 0, "Sequence number": 46526445, "Fwd thread id": 1, "Ev Idx": 4828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038417695.191, "dur": 36535.624, + "args": { + "External id": 4680414,"Sequence number": 46526445, "Fwd thread 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": 1708038417695.191, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 1336753, "tid": 1381210, + "ts": 1708038417723.806, "dur": 36.144, + "args": { + "External id": 4680415,"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": 1708038417767.161, "dur": 77.169, + "args": { + "External id": 4680416,"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": 1708038417850.536, "dur": 36372.221, + "args": { + "External id": 4680417,"Record function id": 0, "Ev Idx": 4832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038417935.783, "dur": 6.935, + "args": { + "External id": 4680418,"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": 1708038417951.678, "dur": 4.688, + "args": { + "External id": 4680419,"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": 1708038417970.328, "dur": 35397.219, + "args": { + "External id": 4680420,"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": 1708038418017.448, "dur": 35341.012, + "args": { + "External id": 4680421,"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": 1708038418073.324, "dur": 13.866, + "args": { + "External id": 4680422,"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": 1708038418093.242, "dur": 35225.781, + "args": { + "External id": 4680423,"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": 1708038418096.078, "dur": 35222.222, + "args": { + "External id": 4680424,"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": 1708038418100.284, "dur": 7.802, + "args": { + "External id": 4680425,"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": 1708038418111.302, "dur": 35203.776, + "args": { + "External id": 4680426,"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": 1708038453452.825, "dur": 8.201, + "args": { + "External id": 4680427,"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": 1708038453455.348, "dur": 5.327, + "args": { + "External id": 4680428,"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": 1708038453492.686, "dur": 396.922, + "args": { + "External id": 4680429,"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": 1708038453521.264, "dur": 363.569, + "args": { + "External id": 4680430,"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": 1708038453543.350, "dur": 335.457, + "args": { + "External id": 4680431,"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": 1708038453910.321, "dur": 1.796, + "args": { + "External id": 4680432,"Record function id": 0, "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": 1708038453972.461, "dur": 6.753, + "args": { + "External id": 4680433,"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": 1708038454059.515, "dur": 2.169, + "args": { + "External id": 4680434,"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": 1708038454078.062, "dur": 1.696, + "args": { + "External id": 4680435,"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": 1708038454091.578, "dur": 3.402, + "args": { + "External id": 4680436,"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": 1708038454106.681, "dur": 1.169, + "args": { + "External id": 4680437,"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": 1708038454118.106, "dur": 0.913, + "args": { + "External id": 4680438,"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": 1708038454130.978, "dur": 0.760, + "args": { + "External id": 4680439,"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": 1708038454143.418, "dur": 3.129, + "args": { + "External id": 4680440,"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": 1708038454156.881, "dur": 0.719, + "args": { + "External id": 4680441,"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": 1708038454259.273, "dur": 2836.906, + "args": { + "External id": 4680442,"Record function id": 0, "Ev Idx": 4857 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1708038454279.716, "dur": 1067.303, + "args": { + "External id": 4680443,"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": 1708038454293.610, "dur": 350.315, + "args": { + "External id": 4680444,"Record function id": 0, "Ev Idx": 4859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038454388.091, "dur": 4.159, + "args": { + "External id": 4680445,"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": 1708038454395.296, "dur": 1.275, + "args": { + "External id": 4680446,"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": 1708038454399.822, "dur": 0.858, + "args": { + "External id": 4680447,"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": 1708038454402.495, "dur": 0.945, + "args": { + "External id": 4680448,"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": 1708038454405.149, "dur": 0.898, + "args": { + "External id": 4680449,"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": 1708038454407.486, "dur": 2.661, + "args": { + "External id": 4680450,"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": 1708038454412.963, "dur": 0.735, + "args": { + "External id": 4680451,"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": 1708038454415.471, "dur": 1.010, + "args": { + "External id": 4680452,"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": 1708038454418.036, "dur": 1.200, + "args": { + "External id": 4680453,"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": 1708038454420.840, "dur": 1.143, + "args": { + "External id": 4680454,"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": 1708038454444.575, "dur": 168.297, + "args": { + "External id": 4680455,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038454459.898, "dur": 148.191, + "args": { + "External id": 4680456,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038454478.973, "dur": 12.349, + "args": { + "External id": 4680457,"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": 1708038454494.382, "dur": 83.405, + "args": { + "External id": 4680458,"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": 1708038454496.826, "dur": 80.469, + "args": { + "External id": 4680459,"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": 1708038454504.108, "dur": 5.855, + "args": { + "External id": 4680460,"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": 1708038454511.649, "dur": 64.502, + "args": { + "External id": 4680461,"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": 1708038454739.652, "dur": 599.468, + "args": { + "External id": 4680462,"Record function id": 0, "Ev Idx": 4877 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1708038454759.182, "dur": 567.566, + "args": { + "External id": 4680463,"Record function id": 0, "Ev Idx": 4878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038454824.729, "dur": 5.788, + "args": { + "External id": 4680464,"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": 1708038454846.760, "dur": 31.178, + "args": { + "External id": 4680465,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038454851.582, "dur": 3.373, + "args": { + "External id": 4680466,"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": 1708038454857.940, "dur": 0.431, + "args": { + "External id": 4680467,"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": 1708038454860.008, "dur": 0.520, + "args": { + "External id": 4680468,"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": 1708038454861.973, "dur": 1.244, + "args": { + "External id": 4680469,"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": 1708038454864.479, "dur": 0.280, + "args": { + "External id": 4680470,"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": 1708038454866.038, "dur": 0.448, + "args": { + "External id": 4680471,"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": 1708038454868.972, "dur": 0.316, + "args": { + "External id": 4680472,"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": 1708038454870.549, "dur": 0.362, + "args": { + "External id": 4680473,"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": 1708038454872.499, "dur": 2.716, + "args": { + "External id": 4680474,"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": 1708038454888.825, "dur": 31.563, + "args": { + "External id": 4680475,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038454952.099, "dur": 151.134, + "args": { + "External id": 4680476,"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": 1708038454961.519, "dur": 3.288, + "args": { + "External id": 4680477,"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": 1708038454969.625, "dur": 9.795, + "args": { + "External id": 4680478,"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": 1708038454973.486, "dur": 5.528, + "args": { + "External id": 4680479,"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": 1708038454976.972, "dur": 0.948, + "args": { + "External id": 4680480,"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": 1708038455025.976, "dur": 30.503, + "args": { + "External id": 4680481,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038455028.851, "dur": 0.683, + "args": { + "External id": 4680482,"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": 1708038455031.632, "dur": 1.051, + "args": { + "External id": 4680483,"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": 1708038455034.399, "dur": 0.360, + "args": { + "External id": 4680484,"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": 1708038455036.297, "dur": 0.625, + "args": { + "External id": 4680485,"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": 1708038455038.316, "dur": 0.529, + "args": { + "External id": 4680486,"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": 1708038455040.212, "dur": 2.833, + "args": { + "External id": 4680487,"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": 1708038455044.385, "dur": 0.606, + "args": { + "External id": 4680488,"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": 1708038455046.694, "dur": 0.364, + "args": { + "External id": 4680489,"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": 1708038455048.876, "dur": 0.427, + "args": { + "External id": 4680490,"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": 1708038455070.994, "dur": 24.677, + "args": { + "External id": 4680491,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038455149.615, "dur": 111.817, + "args": { + "External id": 4680492,"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": 1708038455175.309, "dur": 82.833, + "args": { + "External id": 4680493,"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": 1708038455184.372, "dur": 69.081, + "args": { + "External id": 4680494,"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": 1708038455277.379, "dur": 1.938, + "args": { + "External id": 4680495,"Record function id": 0, "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": 1708038455354.901, "dur": 1719.726, + "args": { + "External id": 4680496,"Sequence number": 46526444, "Fwd thread 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": 1708038455354.901, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038455463.246, "dur": 117.968, + "args": { + "External id": 4680497,"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": 1708038455627.858, "dur": 43.223, + "args": { + "External id": 4680498,"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": 1708038455688.483, "dur": 51.708, + "args": { + "External id": 4680499,"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": 1708038455749.856, "dur": 32.006, + "args": { + "External id": 4680500,"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": 1708038455788.149, "dur": 48.261, + "args": { + "External id": 4680501,"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": 1708038455843.911, "dur": 31.107, + "args": { + "External id": 4680502,"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": 1708038455883.666, "dur": 41.923, + "args": { + "External id": 4680503,"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": 1708038455951.356, "dur": 23.821, + "args": { + "External id": 4680504,"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": 1708038456035.193, "dur": 33.670, + "args": { + "External id": 4680505,"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": 1708038456094.323, "dur": 21.622, + "args": { + "External id": 4680506,"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": 1708038456133.396, "dur": 19.510, + "args": { + "External id": 4680507,"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": 1708038456161.553, "dur": 34.498, + "args": { + "External id": 4680508,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038456199.583, "dur": 33.830, + "args": { + "External id": 4680509,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038456260.932, "dur": 168.702, + "args": { + "External id": 4680510,"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": 1708038456338.233, "dur": 7.820, + "args": { + "External id": 4680511,"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": 1708038456347.975, "dur": 2.930, + "args": { + "External id": 4680512,"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": 1708038456465.604, "dur": 26.836, + "args": { + "External id": 4680513,"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": 1708038456512.011, "dur": 32.385, + "args": { + "External id": 4680514,"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": 1708038456555.629, "dur": 42.342, + "args": { + "External id": 4680515,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038456603.933, "dur": 38.172, + "args": { + "External id": 4680516,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038456648.903, "dur": 24.548, + "args": { + "External id": 4680517,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038456680.388, "dur": 48.274, + "args": { + "External id": 4680518,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038456740.191, "dur": 27.856, + "args": { + "External id": 4680519,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038456774.857, "dur": 32.280, + "args": { + "External id": 4680520,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038456832.543, "dur": 25.229, + "args": { + "External id": 4680521,"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": 1708038456880.615, "dur": 28.023, + "args": { + "External id": 4680522,"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": 1708038456923.858, "dur": 20.810, + "args": { + "External id": 4680523,"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": 1708038456961.762, "dur": 15.584, + "args": { + "External id": 4680524,"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": 1708038457025.593, "dur": 19.778, + "args": { + "External id": 4680525,"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": 1708038457117.865, "dur": 14.580, + "args": { + "External id": 4680526,"Record function id": 0, "Ev Idx": 4941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038457121.030, "dur": 10.414, + "args": { + "External id": 4680527,"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": 1708038457125.012, "dur": 5.479, + "args": { + "External id": 4680528,"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": 1708038457126.594, "dur": 3.807, + "args": { + "External id": 4680529,"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": 1708038457136.421, "dur": 5.411, + "args": { + "External id": 4680530,"Record function id": 0, "Ev Idx": 4945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038457138.175, "dur": 3.215, + "args": { + "External id": 4680531,"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": 1708038457139.188, "dur": 1.664, + "args": { + "External id": 4680532,"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": 1708038457139.826, "dur": 0.933, + "args": { + "External id": 4680533,"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": 1708038457145.125, "dur": 4.878, + "args": { + "External id": 4680534,"Record function id": 0, "Ev Idx": 4949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038457146.463, "dur": 3.127, + "args": { + "External id": 4680535,"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": 1708038457147.333, "dur": 1.826, + "args": { + "External id": 4680536,"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": 1708038457148.375, "dur": 0.698, + "args": { + "External id": 4680537,"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": 1708038457153.396, "dur": 4.174, + "args": { + "External id": 4680538,"Record function id": 0, "Ev Idx": 4953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038457154.955, "dur": 2.208, + "args": { + "External id": 4680539,"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": 1708038457155.741, "dur": 0.989, + "args": { + "External id": 4680540,"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": 1708038457156.062, "dur": 0.594, + "args": { + "External id": 4680541,"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": 1708038457160.725, "dur": 5.651, + "args": { + "External id": 4680542,"Record function id": 0, "Ev Idx": 4957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038457161.643, "dur": 4.293, + "args": { + "External id": 4680543,"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": 1708038457162.321, "dur": 3.194, + "args": { + "External id": 4680544,"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": 1708038457162.615, "dur": 2.832, + "args": { + "External id": 4680545,"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": 1708038457169.459, "dur": 3.973, + "args": { + "External id": 4680546,"Record function id": 0, "Ev Idx": 4961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038457170.654, "dur": 2.355, + "args": { + "External id": 4680547,"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": 1708038457171.323, "dur": 1.153, + "args": { + "External id": 4680548,"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": 1708038457171.670, "dur": 0.735, + "args": { + "External id": 4680549,"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": 1708038457176.732, "dur": 4.502, + "args": { + "External id": 4680550,"Record function id": 0, "Ev Idx": 4965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038457177.682, "dur": 3.125, + "args": { + "External id": 4680551,"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": 1708038457178.136, "dur": 2.240, + "args": { + "External id": 4680552,"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": 1708038457179.663, "dur": 0.637, + "args": { + "External id": 4680553,"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": 1708038457184.362, "dur": 3.683, + "args": { + "External id": 4680554,"Record function id": 0, "Ev Idx": 4969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038457185.391, "dur": 2.226, + "args": { + "External id": 4680555,"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": 1708038457185.856, "dur": 1.359, + "args": { + "External id": 4680556,"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": 1708038457186.477, "dur": 0.664, + "args": { + "External id": 4680557,"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": 1708038457191.048, "dur": 3.334, + "args": { + "External id": 4680558,"Record function id": 0, "Ev Idx": 4973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038457192.002, "dur": 1.974, + "args": { + "External id": 4680559,"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": 1708038457192.418, "dur": 1.151, + "args": { + "External id": 4680560,"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": 1708038457192.829, "dur": 0.675, + "args": { + "External id": 4680561,"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": 1708038457198.041, "dur": 36324.246, + "args": { + "External id": 4680562,"Record function id": 0, "Sequence number": 46526443, "Fwd thread id": 1, "Ev Idx": 4977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038457199.205, "dur": 36314.233, + "args": { + "External id": 4680563,"Sequence number": 46526443, "Fwd thread 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": 1708038457199.205, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 1336753, "tid": 1381210, + "ts": 1708038457226.217, "dur": 35.697, + "args": { + "External id": 4680564,"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": 1708038457268.931, "dur": 63.850, + "args": { + "External id": 4680565,"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": 1708038457339.446, "dur": 36165.959, + "args": { + "External id": 4680566,"Record function id": 0, "Ev Idx": 4981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038457424.640, "dur": 6.502, + "args": { + "External id": 4680567,"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": 1708038457440.260, "dur": 4.667, + "args": { + "External id": 4680568,"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": 1708038457460.165, "dur": 35262.478, + "args": { + "External id": 4680569,"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": 1708038457473.724, "dur": 35239.626, + "args": { + "External id": 4680570,"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": 1708038457520.513, "dur": 30.216, + "args": { + "External id": 4680571,"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": 1708038457557.715, "dur": 35119.096, + "args": { + "External id": 4680572,"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": 1708038457560.036, "dur": 35116.175, + "args": { + "External id": 4680573,"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": 1708038457564.274, "dur": 8.072, + "args": { + "External id": 4680574,"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": 1708038457574.130, "dur": 35098.903, + "args": { + "External id": 4680575,"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": 1708038492810.405, "dur": 8.261, + "args": { + "External id": 4680576,"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": 1708038492813.037, "dur": 5.264, + "args": { + "External id": 4680577,"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": 1708038492846.359, "dur": 365.385, + "args": { + "External id": 4680578,"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": 1708038492873.209, "dur": 333.540, + "args": { + "External id": 4680579,"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": 1708038492882.713, "dur": 318.358, + "args": { + "External id": 4680580,"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": 1708038493237.697, "dur": 2.552, + "args": { + "External id": 4680581,"Record function id": 0, "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": 1708038493301.383, "dur": 6.314, + "args": { + "External id": 4680582,"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": 1708038493349.636, "dur": 1.363, + "args": { + "External id": 4680583,"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": 1708038493366.879, "dur": 1.300, + "args": { + "External id": 4680584,"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": 1708038493380.582, "dur": 3.148, + "args": { + "External id": 4680585,"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": 1708038493395.315, "dur": 0.840, + "args": { + "External id": 4680586,"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": 1708038493406.098, "dur": 1.143, + "args": { + "External id": 4680587,"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": 1708038493419.406, "dur": 1.204, + "args": { + "External id": 4680588,"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": 1708038493430.798, "dur": 3.541, + "args": { + "External id": 4680589,"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": 1708038493443.717, "dur": 0.941, + "args": { + "External id": 4680590,"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": 1708038493556.548, "dur": 2743.170, + "args": { + "External id": 4680591,"Record function id": 0, "Ev Idx": 5006 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1708038493577.313, "dur": 1046.919, + "args": { + "External id": 4680592,"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": 1708038493590.190, "dur": 323.148, + "args": { + "External id": 4680593,"Record function id": 0, "Ev Idx": 5008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038493675.878, "dur": 4.695, + "args": { + "External id": 4680594,"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": 1708038493687.470, "dur": 1.260, + "args": { + "External id": 4680595,"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": 1708038493692.294, "dur": 0.891, + "args": { + "External id": 4680596,"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": 1708038493694.793, "dur": 0.952, + "args": { + "External id": 4680597,"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": 1708038493697.249, "dur": 0.933, + "args": { + "External id": 4680598,"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": 1708038493699.514, "dur": 3.010, + "args": { + "External id": 4680599,"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": 1708038493705.264, "dur": 0.680, + "args": { + "External id": 4680600,"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": 1708038493707.506, "dur": 0.984, + "args": { + "External id": 4680601,"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": 1708038493710.206, "dur": 1.230, + "args": { + "External id": 4680602,"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": 1708038493713.268, "dur": 1.150, + "args": { + "External id": 4680603,"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": 1708038493734.784, "dur": 150.630, + "args": { + "External id": 4680604,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038493750.792, "dur": 130.676, + "args": { + "External id": 4680605,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038493772.522, "dur": 12.442, + "args": { + "External id": 4680606,"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": 1708038493787.706, "dur": 65.131, + "args": { + "External id": 4680607,"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": 1708038493790.233, "dur": 62.180, + "args": { + "External id": 4680608,"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": 1708038493793.958, "dur": 5.504, + "args": { + "External id": 4680609,"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": 1708038493801.024, "dur": 50.843, + "args": { + "External id": 4680610,"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": 1708038494041.730, "dur": 574.858, + "args": { + "External id": 4680611,"Record function id": 0, "Ev Idx": 5026 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1708038494059.889, "dur": 544.382, + "args": { + "External id": 4680612,"Record function id": 0, "Ev Idx": 5027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038494128.257, "dur": 5.805, + "args": { + "External id": 4680613,"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": 1708038494150.318, "dur": 28.962, + "args": { + "External id": 4680614,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038494155.025, "dur": 4.214, + "args": { + "External id": 4680615,"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": 1708038494161.523, "dur": 0.527, + "args": { + "External id": 4680616,"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": 1708038494163.353, "dur": 0.550, + "args": { + "External id": 4680617,"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": 1708038494165.077, "dur": 0.983, + "args": { + "External id": 4680618,"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": 1708038494166.963, "dur": 0.342, + "args": { + "External id": 4680619,"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": 1708038494168.695, "dur": 0.427, + "args": { + "External id": 4680620,"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": 1708038494170.827, "dur": 0.454, + "args": { + "External id": 4680621,"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": 1708038494172.637, "dur": 0.474, + "args": { + "External id": 4680622,"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": 1708038494174.329, "dur": 1.936, + "args": { + "External id": 4680623,"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": 1708038494190.017, "dur": 36.855, + "args": { + "External id": 4680624,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038494259.672, "dur": 100.619, + "args": { + "External id": 4680625,"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": 1708038494269.197, "dur": 3.210, + "args": { + "External id": 4680626,"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": 1708038494277.573, "dur": 10.370, + "args": { + "External id": 4680627,"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": 1708038494281.591, "dur": 5.902, + "args": { + "External id": 4680628,"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": 1708038494285.254, "dur": 1.101, + "args": { + "External id": 4680629,"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": 1708038494294.703, "dur": 27.522, + "args": { + "External id": 4680630,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038494296.375, "dur": 0.411, + "args": { + "External id": 4680631,"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": 1708038494298.466, "dur": 0.645, + "args": { + "External id": 4680632,"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": 1708038494300.265, "dur": 0.396, + "args": { + "External id": 4680633,"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": 1708038494302.270, "dur": 0.271, + "args": { + "External id": 4680634,"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": 1708038494303.530, "dur": 0.370, + "args": { + "External id": 4680635,"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": 1708038494304.805, "dur": 2.693, + "args": { + "External id": 4680636,"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": 1708038494308.381, "dur": 0.544, + "args": { + "External id": 4680637,"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": 1708038494310.119, "dur": 0.453, + "args": { + "External id": 4680638,"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": 1708038494311.968, "dur": 3.459, + "args": { + "External id": 4680639,"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": 1708038494333.324, "dur": 19.948, + "args": { + "External id": 4680640,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038494404.265, "dur": 111.795, + "args": { + "External id": 4680641,"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": 1708038494430.271, "dur": 82.736, + "args": { + "External id": 4680642,"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": 1708038494439.285, "dur": 69.237, + "args": { + "External id": 4680643,"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": 1708038494548.428, "dur": 2.923, + "args": { + "External id": 4680644,"Record function id": 0, "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": 1708038494632.425, "dur": 1646.415, + "args": { + "External id": 4680645,"Sequence number": 46526442, "Fwd thread 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": 1708038494632.425, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038494741.401, "dur": 104.234, + "args": { + "External id": 4680646,"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": 1708038494886.207, "dur": 42.068, + "args": { + "External id": 4680647,"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": 1708038494945.061, "dur": 86.411, + "args": { + "External id": 4680648,"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": 1708038495045.315, "dur": 37.211, + "args": { + "External id": 4680649,"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": 1708038495089.067, "dur": 46.161, + "args": { + "External id": 4680650,"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": 1708038495146.495, "dur": 27.688, + "args": { + "External id": 4680651,"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": 1708038495181.132, "dur": 43.843, + "args": { + "External id": 4680652,"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": 1708038495250.068, "dur": 27.872, + "args": { + "External id": 4680653,"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": 1708038495295.903, "dur": 28.434, + "args": { + "External id": 4680654,"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": 1708038495343.760, "dur": 20.161, + "args": { + "External id": 4680655,"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": 1708038495377.686, "dur": 18.221, + "args": { + "External id": 4680656,"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": 1708038495405.421, "dur": 30.254, + "args": { + "External id": 4680657,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038495439.054, "dur": 32.488, + "args": { + "External id": 4680658,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038495497.564, "dur": 187.581, + "args": { + "External id": 4680659,"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": 1708038495590.480, "dur": 6.268, + "args": { + "External id": 4680660,"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": 1708038495598.461, "dur": 3.725, + "args": { + "External id": 4680661,"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": 1708038495724.796, "dur": 25.840, + "args": { + "External id": 4680662,"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": 1708038495764.285, "dur": 14.516, + "args": { + "External id": 4680663,"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": 1708038495785.782, "dur": 38.008, + "args": { + "External id": 4680664,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038495829.226, "dur": 32.976, + "args": { + "External id": 4680665,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038495868.445, "dur": 21.803, + "args": { + "External id": 4680666,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038495896.640, "dur": 31.812, + "args": { + "External id": 4680667,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038495933.755, "dur": 21.228, + "args": { + "External id": 4680668,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038495961.421, "dur": 65.465, + "args": { + "External id": 4680669,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038496063.171, "dur": 29.858, + "args": { + "External id": 4680670,"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": 1708038496113.340, "dur": 25.487, + "args": { + "External id": 4680671,"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": 1708038496164.110, "dur": 17.708, + "args": { + "External id": 4680672,"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": 1708038496199.322, "dur": 20.427, + "args": { + "External id": 4680673,"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": 1708038496235.001, "dur": 15.853, + "args": { + "External id": 4680674,"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": 1708038496321.544, "dur": 14.426, + "args": { + "External id": 4680675,"Record function id": 0, "Ev Idx": 5090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038496324.770, "dur": 10.239, + "args": { + "External id": 4680676,"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": 1708038496328.516, "dur": 5.535, + "args": { + "External id": 4680677,"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": 1708038496329.919, "dur": 4.029, + "args": { + "External id": 4680678,"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": 1708038496339.836, "dur": 4.429, + "args": { + "External id": 4680679,"Record function id": 0, "Ev Idx": 5094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038496341.207, "dur": 2.634, + "args": { + "External id": 4680680,"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": 1708038496341.802, "dur": 1.469, + "args": { + "External id": 4680681,"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": 1708038496342.329, "dur": 0.874, + "args": { + "External id": 4680682,"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": 1708038496347.518, "dur": 3.951, + "args": { + "External id": 4680683,"Record function id": 0, "Ev Idx": 5098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038496348.557, "dur": 2.486, + "args": { + "External id": 4680684,"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": 1708038496349.085, "dur": 1.397, + "args": { + "External id": 4680685,"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": 1708038496349.638, "dur": 0.767, + "args": { + "External id": 4680686,"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": 1708038496354.629, "dur": 3.498, + "args": { + "External id": 4680687,"Record function id": 0, "Ev Idx": 5102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038496355.576, "dur": 2.143, + "args": { + "External id": 4680688,"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": 1708038496356.115, "dur": 1.115, + "args": { + "External id": 4680689,"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": 1708038496356.511, "dur": 0.646, + "args": { + "External id": 4680690,"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": 1708038496361.262, "dur": 5.577, + "args": { + "External id": 4680691,"Record function id": 0, "Ev Idx": 5106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038496362.236, "dur": 4.207, + "args": { + "External id": 4680692,"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": 1708038496362.703, "dur": 3.331, + "args": { + "External id": 4680693,"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": 1708038496362.995, "dur": 2.966, + "args": { + "External id": 4680694,"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": 1708038496369.882, "dur": 5.158, + "args": { + "External id": 4680695,"Record function id": 0, "Ev Idx": 5110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038496370.853, "dur": 3.754, + "args": { + "External id": 4680696,"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": 1708038496371.481, "dur": 2.720, + "args": { + "External id": 4680697,"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": 1708038496373.349, "dur": 0.786, + "args": { + "External id": 4680698,"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": 1708038496378.308, "dur": 3.706, + "args": { + "External id": 4680699,"Record function id": 0, "Ev Idx": 5114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038496379.258, "dur": 2.327, + "args": { + "External id": 4680700,"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": 1708038496379.729, "dur": 1.296, + "args": { + "External id": 4680701,"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": 1708038496380.011, "dur": 0.940, + "args": { + "External id": 4680702,"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": 1708038496385.089, "dur": 76.144, + "args": { + "External id": 4680703,"Record function id": 0, "Ev Idx": 5118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038496386.107, "dur": 74.517, + "args": { + "External id": 4680704,"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": 1708038496458.176, "dur": 1.821, + "args": { + "External id": 4680705,"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": 1708038496459.035, "dur": 0.875, + "args": { + "External id": 4680706,"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": 1708038496464.739, "dur": 5.471, + "args": { + "External id": 4680707,"Record function id": 0, "Ev Idx": 5122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038496465.944, "dur": 3.813, + "args": { + "External id": 4680708,"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": 1708038496466.515, "dur": 2.629, + "args": { + "External id": 4680709,"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": 1708038496468.365, "dur": 0.651, + "args": { + "External id": 4680710,"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": 1708038496474.300, "dur": 38344.302, + "args": { + "External id": 4680711,"Record function id": 0, "Sequence number": 46526441, "Fwd thread id": 1, "Ev Idx": 5126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038496475.570, "dur": 38334.125, + "args": { + "External id": 4680712,"Sequence number": 46526441, "Fwd thread 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": 1708038496475.570, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 1336753, "tid": 1381210, + "ts": 1708038496502.706, "dur": 53.040, + "args": { + "External id": 4680713,"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": 1708038496564.803, "dur": 65.011, + "args": { + "External id": 4680714,"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": 1708038496635.507, "dur": 38166.681, + "args": { + "External id": 4680715,"Record function id": 0, "Ev Idx": 5130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038496723.234, "dur": 7.945, + "args": { + "External id": 4680716,"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": 1708038496741.315, "dur": 4.790, + "args": { + "External id": 4680717,"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": 1708038496760.426, "dur": 37301.121, + "args": { + "External id": 4680718,"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": 1708038496773.253, "dur": 37279.662, + "args": { + "External id": 4680719,"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": 1708038496814.300, "dur": 13.099, + "args": { + "External id": 4680720,"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": 1708038496835.006, "dur": 37176.818, + "args": { + "External id": 4680721,"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": 1708038496837.237, "dur": 37173.863, + "args": { + "External id": 4680722,"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": 1708038496840.658, "dur": 7.711, + "args": { + "External id": 4680723,"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": 1708038496849.929, "dur": 37158.152, + "args": { + "External id": 4680724,"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": 1708038534149.776, "dur": 8.727, + "args": { + "External id": 4680725,"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": 1708038534152.424, "dur": 5.653, + "args": { + "External id": 4680726,"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": 1708038534188.748, "dur": 314.328, + "args": { + "External id": 4680727,"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": 1708038534220.633, "dur": 278.070, + "args": { + "External id": 4680728,"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": 1708038534230.190, "dur": 263.081, + "args": { + "External id": 4680729,"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": 1708038534521.446, "dur": 17.725, + "args": { + "External id": 4680730,"Record function id": 0, "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": 1708038534596.859, "dur": 6.734, + "args": { + "External id": 4680731,"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": 1708038534645.523, "dur": 1.674, + "args": { + "External id": 4680732,"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": 1708038534662.609, "dur": 1.788, + "args": { + "External id": 4680733,"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": 1708038534675.176, "dur": 3.367, + "args": { + "External id": 4680734,"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": 1708038534690.634, "dur": 0.737, + "args": { + "External id": 4680735,"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": 1708038534701.600, "dur": 1.179, + "args": { + "External id": 4680736,"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": 1708038534714.058, "dur": 1.359, + "args": { + "External id": 4680737,"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": 1708038534725.858, "dur": 3.307, + "args": { + "External id": 4680738,"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": 1708038534741.458, "dur": 0.765, + "args": { + "External id": 4680739,"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": 1708038534836.929, "dur": 2736.892, + "args": { + "External id": 4680740,"Record function id": 0, "Ev Idx": 5155 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1708038534855.738, "dur": 1048.044, + "args": { + "External id": 4680741,"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": 1708038534869.494, "dur": 364.438, + "args": { + "External id": 4680742,"Record function id": 0, "Ev Idx": 5157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038534947.821, "dur": 3.884, + "args": { + "External id": 4680743,"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": 1708038534954.567, "dur": 1.397, + "args": { + "External id": 4680744,"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": 1708038534959.386, "dur": 1.070, + "args": { + "External id": 4680745,"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": 1708038534962.159, "dur": 0.885, + "args": { + "External id": 4680746,"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": 1708038534964.457, "dur": 0.809, + "args": { + "External id": 4680747,"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": 1708038534966.773, "dur": 2.458, + "args": { + "External id": 4680748,"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": 1708038534971.756, "dur": 1.119, + "args": { + "External id": 4680749,"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": 1708038534974.279, "dur": 1.008, + "args": { + "External id": 4680750,"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": 1708038534976.562, "dur": 1.355, + "args": { + "External id": 4680751,"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": 1708038534979.152, "dur": 1.525, + "args": { + "External id": 4680752,"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": 1708038535036.308, "dur": 168.003, + "args": { + "External id": 4680753,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038535051.801, "dur": 147.872, + "args": { + "External id": 4680754,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038535086.779, "dur": 16.557, + "args": { + "External id": 4680755,"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": 1708038535106.454, "dur": 64.554, + "args": { + "External id": 4680756,"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": 1708038535108.816, "dur": 61.837, + "args": { + "External id": 4680757,"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": 1708038535112.557, "dur": 6.706, + "args": { + "External id": 4680758,"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": 1708038535121.006, "dur": 48.968, + "args": { + "External id": 4680759,"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": 1708038535329.140, "dur": 566.799, + "args": { + "External id": 4680760,"Record function id": 0, "Ev Idx": 5175 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1708038535346.110, "dur": 537.780, + "args": { + "External id": 4680761,"Record function id": 0, "Ev Idx": 5176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038535408.204, "dur": 4.753, + "args": { + "External id": 4680762,"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": 1708038535432.382, "dur": 25.835, + "args": { + "External id": 4680763,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038535436.691, "dur": 4.111, + "args": { + "External id": 4680764,"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": 1708038535442.336, "dur": 0.357, + "args": { + "External id": 4680765,"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": 1708038535443.872, "dur": 0.546, + "args": { + "External id": 4680766,"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": 1708038535446.401, "dur": 0.397, + "args": { + "External id": 4680767,"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": 1708038535447.576, "dur": 0.584, + "args": { + "External id": 4680768,"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": 1708038535448.880, "dur": 0.338, + "args": { + "External id": 4680769,"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": 1708038535450.718, "dur": 0.364, + "args": { + "External id": 4680770,"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": 1708038535451.764, "dur": 0.336, + "args": { + "External id": 4680771,"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": 1708038535452.907, "dur": 2.366, + "args": { + "External id": 4680772,"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": 1708038535468.340, "dur": 35.316, + "args": { + "External id": 4680773,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038535550.730, "dur": 107.771, + "args": { + "External id": 4680774,"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": 1708038535561.131, "dur": 4.595, + "args": { + "External id": 4680775,"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": 1708038535571.247, "dur": 10.493, + "args": { + "External id": 4680776,"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": 1708038535575.349, "dur": 5.993, + "args": { + "External id": 4680777,"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": 1708038535578.893, "dur": 0.907, + "args": { + "External id": 4680778,"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": 1708038535588.365, "dur": 24.547, + "args": { + "External id": 4680779,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038535590.703, "dur": 0.564, + "args": { + "External id": 4680780,"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": 1708038535592.563, "dur": 0.615, + "args": { + "External id": 4680781,"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": 1708038535594.436, "dur": 0.628, + "args": { + "External id": 4680782,"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": 1708038535595.911, "dur": 0.306, + "args": { + "External id": 4680783,"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": 1708038535597.305, "dur": 0.327, + "args": { + "External id": 4680784,"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": 1708038535599.354, "dur": 2.378, + "args": { + "External id": 4680785,"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": 1708038535602.502, "dur": 0.323, + "args": { + "External id": 4680786,"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": 1708038535603.688, "dur": 0.261, + "args": { + "External id": 4680787,"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": 1708038535605.316, "dur": 0.516, + "args": { + "External id": 4680788,"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": 1708038535628.677, "dur": 22.604, + "args": { + "External id": 4680789,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038535705.176, "dur": 114.209, + "args": { + "External id": 4680790,"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": 1708038535729.431, "dur": 86.795, + "args": { + "External id": 4680791,"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": 1708038535737.864, "dur": 74.076, + "args": { + "External id": 4680792,"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": 1708038535833.626, "dur": 1.951, + "args": { + "External id": 4680793,"Record function id": 0, "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": 1708038535911.509, "dur": 1638.858, + "args": { + "External id": 4680794,"Sequence number": 46526440, "Fwd thread 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": 1708038535911.509, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038536057.294, "dur": 103.921, + "args": { + "External id": 4680795,"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": 1708038536204.366, "dur": 42.916, + "args": { + "External id": 4680796,"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": 1708038536263.866, "dur": 47.294, + "args": { + "External id": 4680797,"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": 1708038536320.876, "dur": 31.176, + "args": { + "External id": 4680798,"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": 1708038536358.685, "dur": 43.420, + "args": { + "External id": 4680799,"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": 1708038536410.952, "dur": 27.900, + "args": { + "External id": 4680800,"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": 1708038536446.173, "dur": 41.222, + "args": { + "External id": 4680801,"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": 1708038536509.137, "dur": 41.612, + "args": { + "External id": 4680802,"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": 1708038536573.035, "dur": 28.985, + "args": { + "External id": 4680803,"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": 1708038536623.391, "dur": 21.586, + "args": { + "External id": 4680804,"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": 1708038536660.350, "dur": 19.323, + "args": { + "External id": 4680805,"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": 1708038536689.443, "dur": 33.282, + "args": { + "External id": 4680806,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038536725.788, "dur": 35.137, + "args": { + "External id": 4680807,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038536787.800, "dur": 164.527, + "args": { + "External id": 4680808,"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": 1708038536861.618, "dur": 6.253, + "args": { + "External id": 4680809,"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": 1708038536869.577, "dur": 2.287, + "args": { + "External id": 4680810,"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": 1708038537023.427, "dur": 28.636, + "args": { + "External id": 4680811,"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": 1708038537064.956, "dur": 14.967, + "args": { + "External id": 4680812,"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": 1708038537091.477, "dur": 39.866, + "args": { + "External id": 4680813,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038537136.897, "dur": 34.047, + "args": { + "External id": 4680814,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038537177.359, "dur": 22.017, + "args": { + "External id": 4680815,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038537203.701, "dur": 28.429, + "args": { + "External id": 4680816,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038537239.656, "dur": 21.239, + "args": { + "External id": 4680817,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038537268.686, "dur": 46.894, + "args": { + "External id": 4680818,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038537340.695, "dur": 25.216, + "args": { + "External id": 4680819,"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": 1708038537385.229, "dur": 29.284, + "args": { + "External id": 4680820,"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": 1708038537430.248, "dur": 21.116, + "args": { + "External id": 4680821,"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": 1708038537465.616, "dur": 16.390, + "args": { + "External id": 4680822,"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": 1708038537493.404, "dur": 16.046, + "args": { + "External id": 4680823,"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": 1708038537596.099, "dur": 18.176, + "args": { + "External id": 4680824,"Record function id": 0, "Ev Idx": 5239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038537599.574, "dur": 13.667, + "args": { + "External id": 4680825,"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": 1708038537604.000, "dur": 8.020, + "args": { + "External id": 4680826,"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": 1708038537605.678, "dur": 6.205, + "args": { + "External id": 4680827,"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": 1708038537618.267, "dur": 5.645, + "args": { + "External id": 4680828,"Record function id": 0, "Ev Idx": 5243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038537619.878, "dur": 3.387, + "args": { + "External id": 4680829,"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": 1708038537620.625, "dur": 1.934, + "args": { + "External id": 4680830,"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": 1708038537621.574, "dur": 0.910, + "args": { + "External id": 4680831,"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": 1708038537627.157, "dur": 4.778, + "args": { + "External id": 4680832,"Record function id": 0, "Ev Idx": 5247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038537628.695, "dur": 2.823, + "args": { + "External id": 4680833,"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": 1708038537629.504, "dur": 1.554, + "args": { + "External id": 4680834,"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": 1708038537629.943, "dur": 1.047, + "args": { + "External id": 4680835,"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": 1708038537635.112, "dur": 4.320, + "args": { + "External id": 4680836,"Record function id": 0, "Ev Idx": 5251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038537636.358, "dur": 2.657, + "args": { + "External id": 4680837,"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": 1708038537637.338, "dur": 1.249, + "args": { + "External id": 4680838,"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": 1708038537637.863, "dur": 0.663, + "args": { + "External id": 4680839,"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": 1708038537642.596, "dur": 3.406, + "args": { + "External id": 4680840,"Record function id": 0, "Ev Idx": 5255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038537643.686, "dur": 1.918, + "args": { + "External id": 4680841,"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": 1708038537644.144, "dur": 1.058, + "args": { + "External id": 4680842,"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": 1708038537644.486, "dur": 0.643, + "args": { + "External id": 4680843,"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": 1708038537649.149, "dur": 4.299, + "args": { + "External id": 4680844,"Record function id": 0, "Ev Idx": 5259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038537650.362, "dur": 2.678, + "args": { + "External id": 4680845,"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": 1708038537651.221, "dur": 1.405, + "args": { + "External id": 4680846,"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": 1708038537651.892, "dur": 0.633, + "args": { + "External id": 4680847,"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": 1708038537656.722, "dur": 3.759, + "args": { + "External id": 4680848,"Record function id": 0, "Ev Idx": 5263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038537657.755, "dur": 2.300, + "args": { + "External id": 4680849,"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": 1708038537658.429, "dur": 1.046, + "args": { + "External id": 4680850,"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": 1708038537658.818, "dur": 0.559, + "args": { + "External id": 4680851,"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": 1708038537663.585, "dur": 9.826, + "args": { + "External id": 4680852,"Record function id": 0, "Ev Idx": 5267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038537665.246, "dur": 7.745, + "args": { + "External id": 4680853,"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": 1708038537669.515, "dur": 3.037, + "args": { + "External id": 4680854,"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": 1708038537669.933, "dur": 2.531, + "args": { + "External id": 4680855,"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": 1708038537676.584, "dur": 5.570, + "args": { + "External id": 4680856,"Record function id": 0, "Ev Idx": 5271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038537678.058, "dur": 3.688, + "args": { + "External id": 4680857,"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": 1708038537678.881, "dur": 2.253, + "args": { + "External id": 4680858,"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": 1708038537680.228, "dur": 0.804, + "args": { + "External id": 4680859,"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": 1708038537685.936, "dur": 36075.326, + "args": { + "External id": 4680860,"Record function id": 0, "Sequence number": 46526439, "Fwd thread id": 1, "Ev Idx": 5275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038537687.133, "dur": 36065.843, + "args": { + "External id": 4680861,"Sequence number": 46526439, "Fwd thread 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": 1708038537687.133, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 1336753, "tid": 1381210, + "ts": 1708038537714.891, "dur": 36.613, + "args": { + "External id": 4680862,"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": 1708038537759.309, "dur": 67.277, + "args": { + "External id": 4680863,"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": 1708038537832.513, "dur": 35911.526, + "args": { + "External id": 4680864,"Record function id": 0, "Ev Idx": 5279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038537919.543, "dur": 6.652, + "args": { + "External id": 4680865,"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": 1708038537935.225, "dur": 4.808, + "args": { + "External id": 4680866,"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": 1708038537954.540, "dur": 34957.373, + "args": { + "External id": 4680867,"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": 1708038537967.838, "dur": 34934.886, + "args": { + "External id": 4680868,"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": 1708038538061.875, "dur": 13.778, + "args": { + "External id": 4680869,"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": 1708038538081.905, "dur": 34781.951, + "args": { + "External id": 4680870,"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": 1708038538084.251, "dur": 34778.908, + "args": { + "External id": 4680871,"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": 1708038538088.188, "dur": 6.624, + "args": { + "External id": 4680872,"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": 1708038538097.326, "dur": 34762.733, + "args": { + "External id": 4680873,"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": 1708038573028.085, "dur": 11.153, + "args": { + "External id": 4680874,"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": 1708038573032.647, "dur": 6.025, + "args": { + "External id": 4680875,"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": 1708038573067.967, "dur": 370.397, + "args": { + "External id": 4680876,"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": 1708038573098.799, "dur": 335.005, + "args": { + "External id": 4680877,"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": 1708038573109.784, "dur": 318.408, + "args": { + "External id": 4680878,"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": 1708038573456.403, "dur": 5.053, + "args": { + "External id": 4680879,"Record function id": 0, "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": 1708038573519.843, "dur": 21.141, + "args": { + "External id": 4680880,"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": 1708038573586.382, "dur": 1.773, + "args": { + "External id": 4680881,"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": 1708038573604.369, "dur": 3.219, + "args": { + "External id": 4680882,"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": 1708038573618.721, "dur": 1.001, + "args": { + "External id": 4680883,"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": 1708038573630.453, "dur": 1.070, + "args": { + "External id": 4680884,"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": 1708038573642.685, "dur": 1.160, + "args": { + "External id": 4680885,"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": 1708038573655.387, "dur": 2.895, + "args": { + "External id": 4680886,"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": 1708038573672.951, "dur": 1.196, + "args": { + "External id": 4680887,"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": 1708038573684.147, "dur": 0.910, + "args": { + "External id": 4680888,"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": 1708038573777.005, "dur": 2827.911, + "args": { + "External id": 4680889,"Record function id": 0, "Ev Idx": 5304 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1708038573797.156, "dur": 1090.531, + "args": { + "External id": 4680890,"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": 1708038573812.872, "dur": 364.887, + "args": { + "External id": 4680891,"Record function id": 0, "Ev Idx": 5306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038573898.370, "dur": 4.006, + "args": { + "External id": 4680892,"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": 1708038573905.623, "dur": 1.215, + "args": { + "External id": 4680893,"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": 1708038573908.544, "dur": 1.064, + "args": { + "External id": 4680894,"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": 1708038573911.644, "dur": 2.807, + "args": { + "External id": 4680895,"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": 1708038573916.010, "dur": 0.775, + "args": { + "External id": 4680896,"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": 1708038573918.479, "dur": 0.928, + "args": { + "External id": 4680897,"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": 1708038573921.995, "dur": 1.121, + "args": { + "External id": 4680898,"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": 1708038573924.378, "dur": 1.178, + "args": { + "External id": 4680899,"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": 1708038573927.057, "dur": 1.305, + "args": { + "External id": 4680900,"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": 1708038573929.765, "dur": 1.012, + "args": { + "External id": 4680901,"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": 1708038573953.120, "dur": 190.073, + "args": { + "External id": 4680902,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038573969.234, "dur": 168.988, + "args": { + "External id": 4680903,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038574023.598, "dur": 11.964, + "args": { + "External id": 4680904,"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": 1708038574038.838, "dur": 71.000, + "args": { + "External id": 4680905,"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": 1708038574041.434, "dur": 68.076, + "args": { + "External id": 4680906,"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": 1708038574045.006, "dur": 9.064, + "args": { + "External id": 4680907,"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": 1708038574055.869, "dur": 52.947, + "args": { + "External id": 4680908,"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": 1708038574275.640, "dur": 601.365, + "args": { + "External id": 4680909,"Record function id": 0, "Ev Idx": 5324 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1708038574294.236, "dur": 570.531, + "args": { + "External id": 4680910,"Record function id": 0, "Ev Idx": 5325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038574357.001, "dur": 4.393, + "args": { + "External id": 4680911,"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": 1708038574413.730, "dur": 29.022, + "args": { + "External id": 4680912,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038574419.566, "dur": 1.489, + "args": { + "External id": 4680913,"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": 1708038574423.474, "dur": 0.416, + "args": { + "External id": 4680914,"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": 1708038574425.063, "dur": 0.682, + "args": { + "External id": 4680915,"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": 1708038574427.458, "dur": 0.547, + "args": { + "External id": 4680916,"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": 1708038574429.923, "dur": 0.584, + "args": { + "External id": 4680917,"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": 1708038574431.898, "dur": 0.668, + "args": { + "External id": 4680918,"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": 1708038574433.924, "dur": 2.438, + "args": { + "External id": 4680919,"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": 1708038574437.723, "dur": 0.339, + "args": { + "External id": 4680920,"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": 1708038574439.397, "dur": 0.479, + "args": { + "External id": 4680921,"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": 1708038574453.816, "dur": 33.953, + "args": { + "External id": 4680922,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038574517.887, "dur": 125.432, + "args": { + "External id": 4680923,"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": 1708038574545.458, "dur": 4.618, + "args": { + "External id": 4680924,"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": 1708038574555.671, "dur": 10.547, + "args": { + "External id": 4680925,"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": 1708038574559.944, "dur": 5.876, + "args": { + "External id": 4680926,"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": 1708038574563.730, "dur": 0.586, + "args": { + "External id": 4680927,"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": 1708038574573.533, "dur": 28.964, + "args": { + "External id": 4680928,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038574575.807, "dur": 0.356, + "args": { + "External id": 4680929,"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": 1708038574577.981, "dur": 0.426, + "args": { + "External id": 4680930,"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": 1708038574579.571, "dur": 0.585, + "args": { + "External id": 4680931,"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": 1708038574581.644, "dur": 2.432, + "args": { + "External id": 4680932,"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": 1708038574585.758, "dur": 0.356, + "args": { + "External id": 4680933,"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": 1708038574586.985, "dur": 0.384, + "args": { + "External id": 4680934,"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": 1708038574591.634, "dur": 0.602, + "args": { + "External id": 4680935,"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": 1708038574593.202, "dur": 0.501, + "args": { + "External id": 4680936,"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": 1708038574595.162, "dur": 0.417, + "args": { + "External id": 4680937,"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": 1708038574613.426, "dur": 22.596, + "args": { + "External id": 4680938,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038574690.179, "dur": 111.789, + "args": { + "External id": 4680939,"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": 1708038574716.869, "dur": 81.631, + "args": { + "External id": 4680940,"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": 1708038574725.677, "dur": 68.509, + "args": { + "External id": 4680941,"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": 1708038574816.053, "dur": 1.677, + "args": { + "External id": 4680942,"Record function id": 0, "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": 1708038574895.413, "dur": 1690.116, + "args": { + "External id": 4680943,"Sequence number": 46526438, "Fwd thread 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": 1708038574895.413, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038575046.262, "dur": 105.654, + "args": { + "External id": 4680944,"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": 1708038575196.460, "dur": 42.034, + "args": { + "External id": 4680945,"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": 1708038575255.027, "dur": 47.549, + "args": { + "External id": 4680946,"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": 1708038575312.874, "dur": 32.341, + "args": { + "External id": 4680947,"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": 1708038575351.418, "dur": 44.123, + "args": { + "External id": 4680948,"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": 1708038575403.898, "dur": 28.440, + "args": { + "External id": 4680949,"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": 1708038575439.537, "dur": 41.401, + "args": { + "External id": 4680950,"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": 1708038575502.620, "dur": 40.111, + "args": { + "External id": 4680951,"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": 1708038575563.219, "dur": 30.866, + "args": { + "External id": 4680952,"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": 1708038575619.013, "dur": 21.096, + "args": { + "External id": 4680953,"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": 1708038575654.890, "dur": 20.905, + "args": { + "External id": 4680954,"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": 1708038575686.759, "dur": 34.573, + "args": { + "External id": 4680955,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038575724.449, "dur": 36.295, + "args": { + "External id": 4680956,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038575791.634, "dur": 165.070, + "args": { + "External id": 4680957,"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": 1708038575866.460, "dur": 6.109, + "args": { + "External id": 4680958,"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": 1708038575874.507, "dur": 1.993, + "args": { + "External id": 4680959,"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": 1708038576026.338, "dur": 31.263, + "args": { + "External id": 4680960,"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": 1708038576069.992, "dur": 16.194, + "args": { + "External id": 4680961,"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": 1708038576098.196, "dur": 44.293, + "args": { + "External id": 4680962,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038576149.725, "dur": 37.919, + "args": { + "External id": 4680963,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038576194.508, "dur": 23.028, + "args": { + "External id": 4680964,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038576222.808, "dur": 45.687, + "args": { + "External id": 4680965,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038576282.959, "dur": 26.458, + "args": { + "External id": 4680966,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038576317.430, "dur": 31.653, + "args": { + "External id": 4680967,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038576370.679, "dur": 24.460, + "args": { + "External id": 4680968,"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": 1708038576412.223, "dur": 30.725, + "args": { + "External id": 4680969,"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": 1708038576457.927, "dur": 18.370, + "args": { + "External id": 4680970,"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": 1708038576490.074, "dur": 17.084, + "args": { + "External id": 4680971,"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": 1708038576519.841, "dur": 35.362, + "args": { + "External id": 4680972,"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": 1708038576626.933, "dur": 14.603, + "args": { + "External id": 4680973,"Record function id": 0, "Ev Idx": 5388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038576629.954, "dur": 10.569, + "args": { + "External id": 4680974,"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": 1708038576634.019, "dur": 5.493, + "args": { + "External id": 4680975,"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": 1708038576635.579, "dur": 3.811, + "args": { + "External id": 4680976,"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": 1708038576645.492, "dur": 5.389, + "args": { + "External id": 4680977,"Record function id": 0, "Ev Idx": 5392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038576646.721, "dur": 3.719, + "args": { + "External id": 4680978,"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": 1708038576647.825, "dur": 2.091, + "args": { + "External id": 4680979,"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": 1708038576648.658, "dur": 1.172, + "args": { + "External id": 4680980,"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": 1708038576654.152, "dur": 4.652, + "args": { + "External id": 4680981,"Record function id": 0, "Ev Idx": 5396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038576655.485, "dur": 2.902, + "args": { + "External id": 4680982,"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": 1708038576656.261, "dur": 1.664, + "args": { + "External id": 4680983,"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": 1708038576656.751, "dur": 1.102, + "args": { + "External id": 4680984,"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": 1708038576662.085, "dur": 6.714, + "args": { + "External id": 4680985,"Record function id": 0, "Ev Idx": 5400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038576663.099, "dur": 5.302, + "args": { + "External id": 4680986,"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": 1708038576663.966, "dur": 3.846, + "args": { + "External id": 4680987,"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": 1708038576664.371, "dur": 3.370, + "args": { + "External id": 4680988,"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": 1708038576671.988, "dur": 4.556, + "args": { + "External id": 4680989,"Record function id": 0, "Ev Idx": 5404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038576673.315, "dur": 2.779, + "args": { + "External id": 4680990,"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": 1708038576674.062, "dur": 1.570, + "args": { + "External id": 4680991,"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": 1708038576674.665, "dur": 0.905, + "args": { + "External id": 4680992,"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": 1708038576679.724, "dur": 4.282, + "args": { + "External id": 4680993,"Record function id": 0, "Ev Idx": 5408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038576681.079, "dur": 2.511, + "args": { + "External id": 4680994,"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": 1708038576681.842, "dur": 1.274, + "args": { + "External id": 4680995,"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": 1708038576682.303, "dur": 0.710, + "args": { + "External id": 4680996,"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": 1708038576687.339, "dur": 4.629, + "args": { + "External id": 4680997,"Record function id": 0, "Ev Idx": 5412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038576688.665, "dur": 2.907, + "args": { + "External id": 4680998,"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": 1708038576689.390, "dur": 1.650, + "args": { + "External id": 4680999,"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": 1708038576690.231, "dur": 0.714, + "args": { + "External id": 4681000,"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": 1708038576695.249, "dur": 3.633, + "args": { + "External id": 4681001,"Record function id": 0, "Ev Idx": 5416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038576696.256, "dur": 2.216, + "args": { + "External id": 4681002,"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": 1708038576696.906, "dur": 1.096, + "args": { + "External id": 4681003,"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": 1708038576697.216, "dur": 0.673, + "args": { + "External id": 4681004,"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": 1708038576701.958, "dur": 3.734, + "args": { + "External id": 4681005,"Record function id": 0, "Ev Idx": 5420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038576702.995, "dur": 2.285, + "args": { + "External id": 4681006,"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": 1708038576703.503, "dur": 1.349, + "args": { + "External id": 4681007,"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": 1708038576704.052, "dur": 0.689, + "args": { + "External id": 4681008,"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": 1708038576709.379, "dur": 36318.546, + "args": { + "External id": 4681009,"Record function id": 0, "Sequence number": 46526437, "Fwd thread id": 1, "Ev Idx": 5424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038576710.744, "dur": 36307.417, + "args": { + "External id": 4681010,"Sequence number": 46526437, "Fwd thread 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": 1708038576710.744, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 1336753, "tid": 1381210, + "ts": 1708038576739.100, "dur": 37.300, + "args": { + "External id": 4681011,"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": 1708038576784.038, "dur": 64.694, + "args": { + "External id": 4681012,"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": 1708038576854.259, "dur": 36125.177, + "args": { + "External id": 4681013,"Record function id": 0, "Ev Idx": 5428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038576940.295, "dur": 6.476, + "args": { + "External id": 4681014,"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": 1708038576955.623, "dur": 4.742, + "args": { + "External id": 4681015,"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": 1708038576975.042, "dur": 35235.237, + "args": { + "External id": 4681016,"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": 1708038577022.467, "dur": 35178.955, + "args": { + "External id": 4681017,"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": 1708038577081.330, "dur": 13.757, + "args": { + "External id": 4681018,"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": 1708038577101.409, "dur": 35061.457, + "args": { + "External id": 4681019,"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": 1708038577103.979, "dur": 35058.170, + "args": { + "External id": 4681020,"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": 1708038577108.225, "dur": 8.488, + "args": { + "External id": 4681021,"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": 1708038577118.612, "dur": 35040.502, + "args": { + "External id": 4681022,"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": 1708038612295.484, "dur": 9.799, + "args": { + "External id": 4681023,"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": 1708038612297.939, "dur": 7.048, + "args": { + "External id": 4681024,"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": 1708038612333.999, "dur": 359.526, + "args": { + "External id": 4681025,"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": 1708038612361.361, "dur": 327.447, + "args": { + "External id": 4681026,"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": 1708038612371.567, "dur": 311.525, + "args": { + "External id": 4681027,"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": 1708038612712.031, "dur": 2.382, + "args": { + "External id": 4681028,"Record function id": 0, "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": 1708038612770.785, "dur": 6.779, + "args": { + "External id": 4681029,"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": 1708038612822.911, "dur": 1.592, + "args": { + "External id": 4681030,"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": 1708038612843.607, "dur": 0.929, + "args": { + "External id": 4681031,"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": 1708038612856.817, "dur": 3.114, + "args": { + "External id": 4681032,"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": 1708038612871.638, "dur": 1.212, + "args": { + "External id": 4681033,"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": 1708038612882.932, "dur": 0.955, + "args": { + "External id": 4681034,"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": 1708038612894.843, "dur": 1.585, + "args": { + "External id": 4681035,"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": 1708038612908.003, "dur": 2.836, + "args": { + "External id": 4681036,"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": 1708038612921.280, "dur": 0.934, + "args": { + "External id": 4681037,"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": 1708038613043.664, "dur": 2750.250, + "args": { + "External id": 4681038,"Record function id": 0, "Ev Idx": 5453 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1708038613064.535, "dur": 1053.562, + "args": { + "External id": 4681039,"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": 1708038613078.400, "dur": 325.967, + "args": { + "External id": 4681040,"Record function id": 0, "Ev Idx": 5455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038613176.060, "dur": 4.504, + "args": { + "External id": 4681041,"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": 1708038613183.669, "dur": 0.932, + "args": { + "External id": 4681042,"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": 1708038613186.393, "dur": 0.911, + "args": { + "External id": 4681043,"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": 1708038613189.240, "dur": 0.935, + "args": { + "External id": 4681044,"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": 1708038613191.713, "dur": 0.887, + "args": { + "External id": 4681045,"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": 1708038613193.793, "dur": 0.906, + "args": { + "External id": 4681046,"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": 1708038613196.561, "dur": 3.246, + "args": { + "External id": 4681047,"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": 1708038613201.615, "dur": 1.181, + "args": { + "External id": 4681048,"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": 1708038613204.011, "dur": 1.383, + "args": { + "External id": 4681049,"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": 1708038613206.983, "dur": 1.051, + "args": { + "External id": 4681050,"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": 1708038613230.425, "dur": 146.778, + "args": { + "External id": 4681051,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038613245.982, "dur": 127.202, + "args": { + "External id": 4681052,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038613262.254, "dur": 11.738, + "args": { + "External id": 4681053,"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": 1708038613276.681, "dur": 67.859, + "args": { + "External id": 4681054,"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": 1708038613279.240, "dur": 64.957, + "args": { + "External id": 4681055,"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": 1708038613286.536, "dur": 6.557, + "args": { + "External id": 4681056,"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": 1708038613294.646, "dur": 49.046, + "args": { + "External id": 4681057,"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": 1708038613512.822, "dur": 597.310, + "args": { + "External id": 4681058,"Record function id": 0, "Ev Idx": 5473 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1708038613550.606, "dur": 546.869, + "args": { + "External id": 4681059,"Record function id": 0, "Ev Idx": 5474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038613624.604, "dur": 5.652, + "args": { + "External id": 4681060,"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": 1708038613645.917, "dur": 27.408, + "args": { + "External id": 4681061,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038613650.778, "dur": 1.516, + "args": { + "External id": 4681062,"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": 1708038613654.491, "dur": 0.423, + "args": { + "External id": 4681063,"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": 1708038613656.311, "dur": 3.111, + "args": { + "External id": 4681064,"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": 1708038613660.511, "dur": 0.652, + "args": { + "External id": 4681065,"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": 1708038613662.279, "dur": 0.309, + "args": { + "External id": 4681066,"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": 1708038613664.222, "dur": 0.340, + "args": { + "External id": 4681067,"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": 1708038613665.660, "dur": 0.484, + "args": { + "External id": 4681068,"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": 1708038613667.771, "dur": 0.409, + "args": { + "External id": 4681069,"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": 1708038613669.769, "dur": 0.476, + "args": { + "External id": 4681070,"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": 1708038613683.713, "dur": 33.592, + "args": { + "External id": 4681071,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038613746.264, "dur": 95.115, + "args": { + "External id": 4681072,"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": 1708038613755.975, "dur": 2.900, + "args": { + "External id": 4681073,"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": 1708038613763.742, "dur": 11.514, + "args": { + "External id": 4681074,"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": 1708038613767.727, "dur": 7.127, + "args": { + "External id": 4681075,"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": 1708038613770.990, "dur": 2.459, + "args": { + "External id": 4681076,"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": 1708038613782.241, "dur": 23.848, + "args": { + "External id": 4681077,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708038613783.835, "dur": 0.590, + "args": { + "External id": 4681078,"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": 1708038613786.211, "dur": 0.492, + "args": { + "External id": 4681079,"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": 1708038613787.835, "dur": 0.653, + "args": { + "External id": 4681080,"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": 1708038613789.724, "dur": 0.564, + "args": { + "External id": 4681081,"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": 1708038613791.705, "dur": 0.338, + "args": { + "External id": 4681082,"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": 1708038613793.118, "dur": 0.382, + "args": { + "External id": 4681083,"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": 1708038613794.870, "dur": 0.400, + "args": { + "External id": 4681084,"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": 1708038613796.460, "dur": 2.317, + "args": { + "External id": 4681085,"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": 1708038613799.736, "dur": 0.498, + "args": { + "External id": 4681086,"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": 1708038613815.893, "dur": 18.421, + "args": { + "External id": 4681087,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708038613884.504, "dur": 142.058, + "args": { + "External id": 4681088,"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": 1708038613906.488, "dur": 116.364, + "args": { + "External id": 4681089,"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": 1708038613915.598, "dur": 101.151, + "args": { + "External id": 4681090,"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": 1708038614043.408, "dur": 2.604, + "args": { + "External id": 4681091,"Record function id": 0, "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": 1708038614125.291, "dur": 1647.362, + "args": { + "External id": 4681092,"Sequence number": 46526436, "Fwd thread 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": 1708038614125.291, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038614235.356, "dur": 101.660, + "args": { + "External id": 4681093,"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": 1708038614375.868, "dur": 44.732, + "args": { + "External id": 4681094,"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": 1708038614436.753, "dur": 50.170, + "args": { + "External id": 4681095,"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": 1708038614498.453, "dur": 49.421, + "args": { + "External id": 4681096,"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": 1708038614557.227, "dur": 47.427, + "args": { + "External id": 4681097,"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": 1708038614611.074, "dur": 27.937, + "args": { + "External id": 4681098,"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": 1708038614646.722, "dur": 41.273, + "args": { + "External id": 4681099,"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": 1708038614711.700, "dur": 26.021, + "args": { + "External id": 4681100,"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": 1708038614761.662, "dur": 29.532, + "args": { + "External id": 4681101,"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": 1708038614813.173, "dur": 24.477, + "args": { + "External id": 4681102,"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": 1708038614852.172, "dur": 17.346, + "args": { + "External id": 4681103,"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": 1708038614878.241, "dur": 33.459, + "args": { + "External id": 4681104,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038614915.162, "dur": 32.939, + "args": { + "External id": 4681105,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038614979.529, "dur": 208.247, + "args": { + "External id": 4681106,"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": 1708038615090.858, "dur": 6.678, + "args": { + "External id": 4681107,"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": 1708038615099.667, "dur": 2.182, + "args": { + "External id": 4681108,"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": 1708038615225.549, "dur": 27.134, + "args": { + "External id": 4681109,"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": 1708038615267.658, "dur": 15.333, + "args": { + "External id": 4681110,"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": 1708038615291.394, "dur": 41.699, + "args": { + "External id": 4681111,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038615339.459, "dur": 35.717, + "args": { + "External id": 4681112,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038615384.116, "dur": 22.745, + "args": { + "External id": 4681113,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038615411.759, "dur": 29.274, + "args": { + "External id": 4681114,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038615446.727, "dur": 22.570, + "args": { + "External id": 4681115,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038615476.172, "dur": 44.318, + "args": { + "External id": 4681116,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038615563.171, "dur": 27.907, + "args": { + "External id": 4681117,"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": 1708038615614.823, "dur": 27.585, + "args": { + "External id": 4681118,"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": 1708038615658.008, "dur": 17.713, + "args": { + "External id": 4681119,"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": 1708038615691.446, "dur": 20.579, + "args": { + "External id": 4681120,"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": 1708038615725.452, "dur": 16.683, + "args": { + "External id": 4681121,"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": 1708038615815.023, "dur": 17.057, + "args": { + "External id": 4681122,"Record function id": 0, "Ev Idx": 5537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038615818.444, "dur": 12.754, + "args": { + "External id": 4681123,"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": 1708038615822.332, "dur": 8.023, + "args": { + "External id": 4681124,"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": 1708038615824.130, "dur": 6.108, + "args": { + "External id": 4681125,"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": 1708038615835.858, "dur": 5.529, + "args": { + "External id": 4681126,"Record function id": 0, "Ev Idx": 5541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038615837.251, "dur": 3.695, + "args": { + "External id": 4681127,"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": 1708038615838.144, "dur": 2.154, + "args": { + "External id": 4681128,"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": 1708038615839.170, "dur": 1.067, + "args": { + "External id": 4681129,"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": 1708038615844.654, "dur": 4.457, + "args": { + "External id": 4681130,"Record function id": 0, "Ev Idx": 5545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038615845.988, "dur": 2.722, + "args": { + "External id": 4681131,"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": 1708038615846.598, "dur": 1.460, + "args": { + "External id": 4681132,"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": 1708038615846.918, "dur": 1.066, + "args": { + "External id": 4681133,"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": 1708038615852.350, "dur": 4.056, + "args": { + "External id": 4681134,"Record function id": 0, "Ev Idx": 5549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038615853.510, "dur": 2.456, + "args": { + "External id": 4681135,"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": 1708038615854.223, "dur": 1.094, + "args": { + "External id": 4681136,"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": 1708038615854.542, "dur": 0.708, + "args": { + "External id": 4681137,"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": 1708038615859.465, "dur": 4.305, + "args": { + "External id": 4681138,"Record function id": 0, "Ev Idx": 5553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038615860.869, "dur": 2.501, + "args": { + "External id": 4681139,"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": 1708038615861.545, "dur": 1.367, + "args": { + "External id": 4681140,"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": 1708038615862.021, "dur": 0.824, + "args": { + "External id": 4681141,"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": 1708038615866.991, "dur": 3.945, + "args": { + "External id": 4681142,"Record function id": 0, "Ev Idx": 5557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038615868.037, "dur": 2.470, + "args": { + "External id": 4681143,"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": 1708038615868.504, "dur": 1.409, + "args": { + "External id": 4681144,"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": 1708038615868.991, "dur": 0.818, + "args": { + "External id": 4681145,"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": 1708038615874.245, "dur": 3.624, + "args": { + "External id": 4681146,"Record function id": 0, "Ev Idx": 5561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038615875.420, "dur": 2.038, + "args": { + "External id": 4681147,"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": 1708038615875.923, "dur": 1.023, + "args": { + "External id": 4681148,"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": 1708038615876.208, "dur": 0.639, + "args": { + "External id": 4681149,"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": 1708038615881.017, "dur": 5.638, + "args": { + "External id": 4681150,"Record function id": 0, "Ev Idx": 5565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038615882.356, "dur": 3.880, + "args": { + "External id": 4681151,"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": 1708038615882.838, "dur": 3.001, + "args": { + "External id": 4681152,"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": 1708038615883.152, "dur": 2.606, + "args": { + "External id": 4681153,"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": 1708038615889.712, "dur": 4.305, + "args": { + "External id": 4681154,"Record function id": 0, "Ev Idx": 5569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038615890.819, "dur": 2.776, + "args": { + "External id": 4681155,"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": 1708038615891.294, "dur": 1.691, + "args": { + "External id": 4681156,"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": 1708038615892.005, "dur": 0.864, + "args": { + "External id": 4681157,"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": 1708038615897.932, "dur": 38189.413, + "args": { + "External id": 4681158,"Record function id": 0, "Sequence number": 46526435, "Fwd thread id": 1, "Ev Idx": 5573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038615899.354, "dur": 38176.289, + "args": { + "External id": 4681159,"Sequence number": 46526435, "Fwd thread 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": 1708038615899.354, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 1336753, "tid": 1381210, + "ts": 1708038615925.527, "dur": 33.452, + "args": { + "External id": 4681160,"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": 1708038615966.144, "dur": 105.820, + "args": { + "External id": 4681161,"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": 1708038616079.581, "dur": 37984.242, + "args": { + "External id": 4681162,"Record function id": 0, "Ev Idx": 5577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038616165.506, "dur": 6.729, + "args": { + "External id": 4681163,"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": 1708038616181.950, "dur": 4.891, + "args": { + "External id": 4681164,"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": 1708038616201.259, "dur": 36893.772, + "args": { + "External id": 4681165,"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": 1708038616214.249, "dur": 36863.800, + "args": { + "External id": 4681166,"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": 1708038616262.879, "dur": 13.389, + "args": { + "External id": 4681167,"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": 1708038616282.206, "dur": 36728.020, + "args": { + "External id": 4681168,"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": 1708038616284.676, "dur": 36723.544, + "args": { + "External id": 4681169,"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": 1708038616288.664, "dur": 5.700, + "args": { + "External id": 4681170,"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": 1708038616295.999, "dur": 36677.351, + "args": { + "External id": 4681171,"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": 1708038653225.833, "dur": 17.989, + "args": { + "External id": 4681172,"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": 1708038653233.337, "dur": 10.006, + "args": { + "External id": 4681173,"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": 1708038653279.928, "dur": 426.034, + "args": { + "External id": 4681174,"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": 1708038653308.685, "dur": 391.864, + "args": { + "External id": 4681175,"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": 1708038653319.877, "dur": 374.137, + "args": { + "External id": 4681176,"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": 1708038653731.853, "dur": 3.157, + "args": { + "External id": 4681177,"Record function id": 0, "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": 1708038653804.809, "dur": 7.170, + "args": { + "External id": 4681178,"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": 1708038653855.774, "dur": 1.546, + "args": { + "External id": 4681179,"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": 1708038653873.306, "dur": 4.084, + "args": { + "External id": 4681180,"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": 1708038653889.714, "dur": 0.918, + "args": { + "External id": 4681181,"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": 1708038653902.801, "dur": 1.083, + "args": { + "External id": 4681182,"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": 1708038653913.545, "dur": 1.024, + "args": { + "External id": 4681183,"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": 1708038653925.946, "dur": 3.100, + "args": { + "External id": 4681184,"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": 1708038653940.783, "dur": 1.744, + "args": { + "External id": 4681185,"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": 1708038653952.853, "dur": 1.192, + "args": { + "External id": 4681186,"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": 1708038654108.772, "dur": 3357.950, + "args": { + "External id": 4681187,"Record function id": 0, "Ev Idx": 5602 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1708038654135.876, "dur": 1037.129, + "args": { + "External id": 4681188,"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": 1708038654155.876, "dur": 868.853, + "args": { + "External id": 4681189,"Record function id": 0, "Ev Idx": 5604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1381210, + "ts": 1708038654290.870, "dur": 10.247, + "args": { + "External id": 4681190,"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": 1708038654306.210, "dur": 1.316, + "args": { + "External id": 4681191,"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": 1708038654309.901, "dur": 1.708, + "args": { + "External id": 4681192,"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": 1708038654314.544, "dur": 1.810, + "args": { + "External id": 4681193,"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": 1708038654319.277, "dur": 3.943, + "args": { + "External id": 4681194,"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": 1708038654325.727, "dur": 1.152, + "args": { + "External id": 4681195,"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": 1708038654330.450, "dur": 1.541, + "args": { + "External id": 4681196,"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": 1708038654334.795, "dur": 1.302, + "args": { + "External id": 4681197,"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": 1708038654338.351, "dur": 1.385, + "args": { + "External id": 4681198,"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": 1708038654342.133, "dur": 1.355, + "args": { + "External id": 4681199,"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": 1708038654411.957, "dur": 530.612, + "args": { + "External id": 4681200,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038654614.761, "dur": 321.336, + "args": { + "External id": 4681201,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708038654795.917, "dur": 16.249, + "args": { + "External id": 4681202,"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": 1708038654816.475, "dur": 85.800, + "args": { + "External id": 4681203,"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": 1708038654819.717, "dur": 82.050, + "args": { + "External id": 4681204,"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": 1708038654825.249, "dur": 9.435, + "args": { + "External id": 4681205,"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": 1708038654837.661, "dur": 63.219, + "args": { + "External id": 4681206,"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": 1708038655183.533, "dur": 2258.567, + "args": { + "External id": 4681207,"Sequence number": 46526434, "Fwd thread 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": 1708038655183.533, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1381210, + "ts": 1708038655306.704, "dur": 106.280, + "args": { + "External id": 4681208,"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": 1708038655457.079, "dur": 44.552, + "args": { + "External id": 4681209,"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": 1708038655519.859, "dur": 73.520, + "args": { + "External id": 4681210,"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": 1708038655607.785, "dur": 34.820, + "args": { + "External id": 4681211,"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": 1708038655652.173, "dur": 44.990, + "args": { + "External id": 4681212,"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": 1708038655705.188, "dur": 29.105, + "args": { + "External id": 4681213,"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": 1708038655741.995, "dur": 41.489, + "args": { + "External id": 4681214,"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": 1708038655807.603, "dur": 24.105, + "args": { + "External id": 4681215,"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": 1708038655849.416, "dur": 30.497, + "args": { + "External id": 4681216,"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": 1708038655971.474, "dur": 66.523, + "args": { + "External id": 4681217,"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": 1708038656063.075, "dur": 20.823, + "args": { + "External id": 4681218,"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": 1708038656098.199, "dur": 41.139, + "args": { + "External id": 4681219,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038656143.074, "dur": 35.410, + "args": { + "External id": 4681220,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038656208.912, "dur": 204.817, + "args": { + "External id": 4681221,"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": 1708038656287.129, "dur": 7.899, + "args": { + "External id": 4681222,"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": 1708038656297.925, "dur": 4.858, + "args": { + "External id": 4681223,"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": 1708038656654.250, "dur": 217.664, + "args": { + "External id": 4681224,"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": 1708038656895.198, "dur": 18.419, + "args": { + "External id": 4681225,"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": 1708038656932.696, "dur": 100.410, + "args": { + "External id": 4681226,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038657046.308, "dur": 47.573, + "args": { + "External id": 4681227,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038657102.579, "dur": 22.853, + "args": { + "External id": 4681228,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038657132.991, "dur": 30.406, + "args": { + "External id": 4681229,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038657170.127, "dur": 21.290, + "args": { + "External id": 4681230,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038657199.748, "dur": 30.320, + "args": { + "External id": 4681231,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708038657250.322, "dur": 24.719, + "args": { + "External id": 4681232,"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": 1708038657292.884, "dur": 28.420, + "args": { + "External id": 4681233,"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": 1708038657336.038, "dur": 17.956, + "args": { + "External id": 4681234,"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": 1708038657367.571, "dur": 16.801, + "args": { + "External id": 4681235,"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": 1708038657396.197, "dur": 16.260, + "args": { + "External id": 4681236,"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": 1708038657489.312, "dur": 16.806, + "args": { + "External id": 4681237,"Record function id": 0, "Ev Idx": 5652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038657492.642, "dur": 12.556, + "args": { + "External id": 4681238,"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": 1708038657496.682, "dur": 7.601, + "args": { + "External id": 4681239,"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": 1708038657498.007, "dur": 6.149, + "args": { + "External id": 4681240,"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": 1708038657510.091, "dur": 5.612, + "args": { + "External id": 4681241,"Record function id": 0, "Ev Idx": 5656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038657511.541, "dur": 3.715, + "args": { + "External id": 4681242,"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": 1708038657512.574, "dur": 2.209, + "args": { + "External id": 4681243,"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": 1708038657513.220, "dur": 1.491, + "args": { + "External id": 4681244,"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": 1708038657518.905, "dur": 20.129, + "args": { + "External id": 4681245,"Record function id": 0, "Ev Idx": 5660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038657520.703, "dur": 16.265, + "args": { + "External id": 4681246,"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": 1708038657521.188, "dur": 1.476, + "args": { + "External id": 4681247,"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": 1708038657521.696, "dur": 0.884, + "args": { + "External id": 4681248,"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": 1708038657544.888, "dur": 6.169, + "args": { + "External id": 4681249,"Record function id": 0, "Ev Idx": 5664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038657546.709, "dur": 3.937, + "args": { + "External id": 4681250,"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": 1708038657548.051, "dur": 1.991, + "args": { + "External id": 4681251,"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": 1708038657548.527, "dur": 1.413, + "args": { + "External id": 4681252,"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": 1708038657554.014, "dur": 4.780, + "args": { + "External id": 4681253,"Record function id": 0, "Ev Idx": 5668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038657555.678, "dur": 2.736, + "args": { + "External id": 4681254,"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": 1708038657556.469, "dur": 1.223, + "args": { + "External id": 4681255,"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": 1708038657557.041, "dur": 0.588, + "args": { + "External id": 4681256,"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": 1708038657561.895, "dur": 4.616, + "args": { + "External id": 4681257,"Record function id": 0, "Ev Idx": 5672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038657563.214, "dur": 2.853, + "args": { + "External id": 4681258,"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": 1708038657564.211, "dur": 1.363, + "args": { + "External id": 4681259,"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": 1708038657564.796, "dur": 0.677, + "args": { + "External id": 4681260,"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": 1708038657569.627, "dur": 4.306, + "args": { + "External id": 4681261,"Record function id": 0, "Ev Idx": 5676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038657570.935, "dur": 2.371, + "args": { + "External id": 4681262,"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": 1708038657571.514, "dur": 1.359, + "args": { + "External id": 4681263,"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": 1708038657571.915, "dur": 0.878, + "args": { + "External id": 4681264,"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": 1708038657576.854, "dur": 7.155, + "args": { + "External id": 4681265,"Record function id": 0, "Ev Idx": 5680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038657578.597, "dur": 4.991, + "args": { + "External id": 4681266,"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": 1708038657579.600, "dur": 3.563, + "args": { + "External id": 4681267,"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": 1708038657580.451, "dur": 2.645, + "args": { + "External id": 4681268,"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": 1708038657586.861, "dur": 4.873, + "args": { + "External id": 4681269,"Record function id": 0, "Ev Idx": 5684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038657588.185, "dur": 3.134, + "args": { + "External id": 4681270,"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": 1708038657588.894, "dur": 2.008, + "args": { + "External id": 4681271,"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": 1708038657589.588, "dur": 1.220, + "args": { + "External id": 4681272,"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": 1708038657595.495, "dur": 34733.470, + "args": { + "External id": 4681273,"Record function id": 0, "Sequence number": 46526433, "Fwd thread id": 1, "Ev Idx": 5688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038657596.866, "dur": 34723.896, + "args": { + "External id": 4681274,"Sequence number": 46526433, "Fwd thread 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": 1708038657596.866, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 1336753, "tid": 1381210, + "ts": 1708038657628.259, "dur": 39.192, + "args": { + "External id": 4681275,"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": 1708038657675.726, "dur": 75.950, + "args": { + "External id": 4681276,"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": 1708038657758.155, "dur": 34554.936, + "args": { + "External id": 4681277,"Record function id": 0, "Ev Idx": 5692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038657848.919, "dur": 6.737, + "args": { + "External id": 4681278,"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": 1708038657864.899, "dur": 5.039, + "args": { + "External id": 4681279,"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": 1708038657885.154, "dur": 33618.075, + "args": { + "External id": 4681280,"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": 1708038657899.621, "dur": 33593.666, + "args": { + "External id": 4681281,"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": 1708038657952.495, "dur": 13.268, + "args": { + "External id": 4681282,"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": 1708038657973.352, "dur": 33480.884, + "args": { + "External id": 4681283,"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": 1708038657975.892, "dur": 33477.533, + "args": { + "External id": 4681284,"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": 1708038657979.549, "dur": 53.192, + "args": { + "External id": 4681285,"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": 1708038658036.379, "dur": 33413.425, + "args": { + "External id": 4681286,"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": 1708038691609.364, "dur": 13.075, + "args": { + "External id": 4681287,"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": 1708038691615.529, "dur": 6.433, + "args": { + "External id": 4681288,"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": 1708038691653.910, "dur": 372.133, + "args": { + "External id": 4681289,"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": 1708038691681.430, "dur": 339.680, + "args": { + "External id": 4681290,"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": 1708038691691.933, "dur": 322.046, + "args": { + "External id": 4681291,"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": 1708038692046.310, "dur": 2.752, + "args": { + "External id": 4681292,"Record function id": 0, "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": 1708038692107.527, "dur": 6.534, + "args": { + "External id": 4681293,"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": 1708038692159.602, "dur": 1.465, + "args": { + "External id": 4681294,"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": 1708038692176.502, "dur": 3.365, + "args": { + "External id": 4681295,"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": 1708038692191.600, "dur": 0.980, + "args": { + "External id": 4681296,"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": 1708038692205.853, "dur": 1.187, + "args": { + "External id": 4681297,"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": 1708038692217.178, "dur": 1.423, + "args": { + "External id": 4681298,"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": 1708038692229.565, "dur": 2.867, + "args": { + "External id": 4681299,"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": 1708038692243.380, "dur": 1.009, + "args": { + "External id": 4681300,"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": 1708038692253.553, "dur": 0.827, + "args": { + "External id": 4681301,"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": 1708038692343.770, "dur": 313.632, + "args": { + "External id": 4681302,"Record function id": 0, "Sequence number": 46526432, "Fwd thread id": 1, "Ev Idx": 5717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336753, "tid": 1381210, + "ts": 1708038692346.606, "dur": 301.395, + "args": { + "External id": 4681303,"Sequence number": 46526432, "Fwd thread 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": 1708038692346.606, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 1336753, "tid": 1381210, + "ts": 1708038692463.300, "dur": 49.885, + "args": { + "External id": 4681304,"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": 1708038692551.753, "dur": 36.849, + "args": { + "External id": 4681305,"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": 1708038692607.068, "dur": 23.107, + "args": { + "External id": 4681306,"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": 1708038692669.794, "dur": 15.094, + "args": { + "External id": 4681307,"Record function id": 0, "Ev Idx": 5722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336753, "tid": 1381210, + "ts": 1708038692673.217, "dur": 10.823, + "args": { + "External id": 4681308,"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": 1708038692677.211, "dur": 5.988, + "args": { + "External id": 4681309,"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": 1708038692678.637, "dur": 4.433, + "args": { + "External id": 4681310,"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": 1708038692707.749, "dur": 9995.131, + "args": { + "External id": 4681311,"Record function id": 0, "Ev Idx": 5726 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 1336753, "tid": 1381210, + "ts": 1708038692727.617, "dur": 42.318, + "args": { + "External id": 4681312,"Record function id": 0, "Ev Idx": 5727 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 1336753, "tid": 1381210, + "ts": 1708038692776.836, "dur": 354.325, + "args": { + "External id": 4681313,"Record function id": 0, "Ev Idx": 5728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 1336753, "tid": 1381210, + "ts": 1708038693142.435, "dur": 9256.427, + "args": { + "External id": 4681314,"Record function id": 0, "Ev Idx": 5729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1381210, + "ts": 1708038693293.120, "dur": 9.470, + "args": { + "External id": 4681315,"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": 1708038693316.011, "dur": 6.330, + "args": { + "External id": 4681316,"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": 1708038693354.350, "dur": 7795.045, + "args": { + "External id": 4681317,"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": 1708038693377.547, "dur": 7758.698, + "args": { + "External id": 4681318,"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": 1708038693956.445, "dur": 21.838, + "args": { + "External id": 4681319,"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": 1708038694127.955, "dur": 6958.239, + "args": { + "External id": 4681320,"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": 1708038694131.724, "dur": 6953.489, + "args": { + "External id": 4681321,"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": 1708038694138.636, "dur": 17.911, + "args": { + "External id": 4681322,"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": 1708038694159.153, "dur": 6919.045, + "args": { + "External id": 4681323,"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": 1708038701293.352, "dur": 11.635, + "args": { + "External id": 4681324,"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": 1708038701296.644, "dur": 7.946, + "args": { + "External id": 4681325,"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": 1708038701335.861, "dur": 371.434, + "args": { + "External id": 4681326,"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": 1708038701360.176, "dur": 342.442, + "args": { + "External id": 4681327,"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": 1708038701374.889, "dur": 322.154, + "args": { + "External id": 4681328,"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": 1708038701725.266, "dur": 2.335, + "args": { + "External id": 4681329,"Record function id": 0, "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": 1708038701781.843, "dur": 6.770, + "args": { + "External id": 4681330,"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": 1708038701829.434, "dur": 1.528, + "args": { + "External id": 4681331,"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": 1708038701844.977, "dur": 1.298, + "args": { + "External id": 4681332,"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": 1708038701858.648, "dur": 3.799, + "args": { + "External id": 4681333,"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": 1708038701873.778, "dur": 1.512, + "args": { + "External id": 4681334,"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": 1708038701886.113, "dur": 1.206, + "args": { + "External id": 4681335,"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": 1708038701901.274, "dur": 1.422, + "args": { + "External id": 4681336,"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": 1708038701913.069, "dur": 2.932, + "args": { + "External id": 4681337,"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": 1708038701926.633, "dur": 1.095, + "args": { + "External id": 4681338,"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": 1708038701938.050, "dur": 1.254, + "args": { + "External id": 4681339,"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": 1708038701950.518, "dur": 1.079, + "args": { + "External id": 4681340,"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": 1708038701961.346, "dur": 3.310, + "args": { + "External id": 4681341,"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": 1708038701975.796, "dur": 1.160, + "args": { + "External id": 4681342,"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": 1708038702026.618, "dur": 2.023, + "args": { + "External id": 4681343,"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": 1708038702040.134, "dur": 1.275, + "args": { + "External id": 4681344,"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": 1708038702051.471, "dur": 3.263, + "args": { + "External id": 4681345,"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": 1708038702064.717, "dur": 1.292, + "args": { + "External id": 4681346,"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": 1708038702076.662, "dur": 1.632, + "args": { + "External id": 4681347,"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": 1708038702088.793, "dur": 1.217, + "args": { + "External id": 4681348,"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": 1708038702100.148, "dur": 3.260, + "args": { + "External id": 4681349,"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": 1708038702114.855, "dur": 1.484, + "args": { + "External id": 4681350,"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": 1708038702127.630, "dur": 1.343, + "args": { + "External id": 4681351,"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": 1708038702139.199, "dur": 1.382, + "args": { + "External id": 4681352,"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": 1708038702151.363, "dur": 3.345, + "args": { + "External id": 4681353,"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": 1708038702164.325, "dur": 1.342, + "args": { + "External id": 4681354,"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": 1708038702175.791, "dur": 1.664, + "args": { + "External id": 4681355,"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": 1708038702187.528, "dur": 1.715, + "args": { + "External id": 4681356,"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": 1708038702200.248, "dur": 3.026, + "args": { + "External id": 4681357,"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": 1708038702213.839, "dur": 1.378, + "args": { + "External id": 4681358,"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": 1708038702226.045, "dur": 1.184, + "args": { + "External id": 4681359,"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": 1708038702238.555, "dur": 1.255, + "args": { + "External id": 4681360,"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": 1708038702250.539, "dur": 2.895, + "args": { + "External id": 4681361,"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": 1708038702264.129, "dur": 1.217, + "args": { + "External id": 4681362,"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": 1708038702275.405, "dur": 1.064, + "args": { + "External id": 4681363,"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": 1708038702287.170, "dur": 1.438, + "args": { + "External id": 4681364,"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": 1708038702299.438, "dur": 2.993, + "args": { + "External id": 4681365,"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": 1708038702312.466, "dur": 1.425, + "args": { + "External id": 4681366,"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": 1708038702324.389, "dur": 1.266, + "args": { + "External id": 4681367,"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": 1708038702335.422, "dur": 1.349, + "args": { + "External id": 4681368,"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#193535", "pid": 1336753, "tid": 1336753, + "ts": 1708036593887.624, "dur": 2127236.278, + "args": { + "External id": 4670465,"Record function id": 0, "Ev Idx": 5784 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.zero_grad#AdamW.zero_grad", "pid": 1336753, "tid": 1336753, + "ts": 1708036593926.840, "dur": 766.268, + "args": { + "External id": 4670466,"Record function id": 0, "Ev Idx": 5785 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 1336753, "tid": 1336753, + "ts": 1708036594737.945, "dur": 2241.357, + "args": { + "External id": 4670467,"Record function id": 0, "Ev Idx": 5786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036595869.793, "dur": 7.388, + "args": { + "External id": 4670468,"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": 1708036595918.259, "dur": 6.718, + "args": { + "External id": 4670469,"Sequence number": 46526432, "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": 1708036596434.471, "dur": 2.510, + "args": { + "External id": 4670470,"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": 1708036596447.276, "dur": 2.488, + "args": { + "External id": 4670471,"Sequence number": 46526432, "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": 1708036596877.817, "dur": 1.900, + "args": { + "External id": 4670472,"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": 1708036596884.253, "dur": 2.104, + "args": { + "External id": 4670473,"Sequence number": 46526432, "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": 1708036597885.388, "dur": 17.225, + "args": { + "External id": 4670474,"Sequence number": 46526432, "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": 1708036597896.363, "dur": 2.334, + "args": { + "External id": 4670475,"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": 1708036597904.314, "dur": 4.319, + "args": { + "External id": 4670476,"Sequence number": 46526432, "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": 1708036597906.413, "dur": 1.146, + "args": { + "External id": 4670477,"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": 1708036597937.283, "dur": 658.255, + "args": { + "External id": 4670478,"Sequence number": 46526432, "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": 1708036597944.033, "dur": 650.717, + "args": { + "External id": 4670479,"Sequence number": 46526432, "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": 1708036597952.583, "dur": 10.612, + "args": { + "External id": 4670480,"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": 1708036597965.597, "dur": 627.066, + "args": { + "External id": 4670481,"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": 1708036597975.396, "dur": 0.545, + "args": { + "External id": 4670482,"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": 1708036597978.983, "dur": 33.694, + "args": { + "External id": 4670483,"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": 1708036598008.116, "dur": 4.346, + "args": { + "External id": 4670484,"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": 1708036598011.178, "dur": 0.792, + "args": { + "External id": 4670485,"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": 1708036598015.673, "dur": 291.641, + "args": { + "External id": 4670486,"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": 1708036598019.985, "dur": 286.915, + "args": { + "External id": 4670487,"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": 1708036598022.050, "dur": 17.896, + "args": { + "External id": 4670488,"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": 1708036598024.164, "dur": 15.271, + "args": { + "External id": 4670489,"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": 1708036598040.918, "dur": 265.313, + "args": { + "External id": 4670490,"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": 1708036598309.930, "dur": 278.431, + "args": { + "External id": 4670491,"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": 1708036598613.452, "dur": 766.670, + "args": { + "External id": 4670492,"Sequence number": 46526432, "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": 1708036598615.524, "dur": 763.870, + "args": { + "External id": 4670493,"Sequence number": 46526432, "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": 1708036598624.712, "dur": 9.766, + "args": { + "External id": 4670494,"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": 1708036598635.490, "dur": 738.949, + "args": { + "External id": 4670495,"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": 1708036599411.098, "dur": 51.993, + "args": { + "External id": 4670496,"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": 1708036599417.441, "dur": 5.436, + "args": { + "External id": 4670497,"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": 1708036599425.806, "dur": 36.790, + "args": { + "External id": 4670498,"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": 1708036599430.367, "dur": 6.372, + "args": { + "External id": 4670499,"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": 1708036599474.310, "dur": 95.281, + "args": { + "External id": 4670500,"Sequence number": 46526432, "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": 1708036599481.348, "dur": 7.631, + "args": { + "External id": 4670501,"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": 1708036599486.668, "dur": 1.860, + "args": { + "External id": 4670502,"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": 1708036599489.910, "dur": 5.373, + "args": { + "External id": 4670503,"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": 1708036599498.584, "dur": 4.754, + "args": { + "External id": 4670504,"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": 1708036599506.159, "dur": 5.039, + "args": { + "External id": 4670505,"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": 1708036599510.569, "dur": 0.511, + "args": { + "External id": 4670506,"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": 1708036599512.059, "dur": 4.088, + "args": { + "External id": 4670507,"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": 1708036599515.229, "dur": 0.829, + "args": { + "External id": 4670508,"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": 1708036599518.563, "dur": 5.146, + "args": { + "External id": 4670509,"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": 1708036599521.034, "dur": 2.576, + "args": { + "External id": 4670510,"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": 1708036599522.752, "dur": 0.765, + "args": { + "External id": 4670511,"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": 1708036599539.403, "dur": 29.325, + "args": { + "External id": 4670512,"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": 1708036599578.976, "dur": 27.726, + "args": { + "External id": 4670513,"Sequence number": 46526432, "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": 1708036599580.620, "dur": 25.910, + "args": { + "External id": 4670514,"Sequence number": 46526432, "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": 1708036599586.256, "dur": 3.466, + "args": { + "External id": 4670515,"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": 1708036599590.556, "dur": 15.618, + "args": { + "External id": 4670516,"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": 1708036599734.263, "dur": 151.666, + "args": { + "External id": 4670517,"Record function id": 0, "Ev Idx": 5836 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 1336753, "tid": 1336753, + "ts": 1708036599820.097, "dur": 54.117, + "args": { + "External id": 4670518,"Record function id": 0, "Ev Idx": 5837 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036599894.417, "dur": 45.327, + "args": { + "External id": 4670519,"Record function id": 0, "Ev Idx": 5838 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 1336753, "tid": 1336753, + "ts": 1708036599949.886, "dur": 8214.841, + "args": { + "External id": 4670520,"Record function id": 0, "Ev Idx": 5839 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 1336753, "tid": 1336753, + "ts": 1708036599960.306, "dur": 1422.246, + "args": { + "External id": 4670521,"Record function id": 0, "Ev Idx": 5840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036600125.821, "dur": 8.104, + "args": { + "External id": 4670522,"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": 1708036600159.197, "dur": 142.503, + "args": { + "External id": 4670523,"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": 1708036600164.783, "dur": 1.828, + "args": { + "External id": 4670524,"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": 1708036600171.793, "dur": 0.444, + "args": { + "External id": 4670525,"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": 1708036600172.930, "dur": 0.408, + "args": { + "External id": 4670526,"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": 1708036600174.087, "dur": 2.841, + "args": { + "External id": 4670527,"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": 1708036600181.677, "dur": 0.398, + "args": { + "External id": 4670528,"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": 1708036600182.800, "dur": 0.466, + "args": { + "External id": 4670529,"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": 1708036600183.991, "dur": 2.320, + "args": { + "External id": 4670530,"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": 1708036600189.529, "dur": 0.301, + "args": { + "External id": 4670531,"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": 1708036600190.491, "dur": 0.359, + "args": { + "External id": 4670532,"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": 1708036600195.160, "dur": 0.276, + "args": { + "External id": 4670533,"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": 1708036600195.933, "dur": 0.695, + "args": { + "External id": 4670534,"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": 1708036600197.462, "dur": 2.425, + "args": { + "External id": 4670535,"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": 1708036600203.995, "dur": 0.372, + "args": { + "External id": 4670536,"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": 1708036600205.004, "dur": 0.625, + "args": { + "External id": 4670537,"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": 1708036600206.303, "dur": 1.931, + "args": { + "External id": 4670538,"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": 1708036600211.270, "dur": 0.279, + "args": { + "External id": 4670539,"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": 1708036600211.978, "dur": 0.377, + "args": { + "External id": 4670540,"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": 1708036600216.848, "dur": 0.248, + "args": { + "External id": 4670541,"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": 1708036600217.779, "dur": 0.448, + "args": { + "External id": 4670542,"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": 1708036600218.892, "dur": 2.610, + "args": { + "External id": 4670543,"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": 1708036600225.682, "dur": 0.552, + "args": { + "External id": 4670544,"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": 1708036600226.801, "dur": 0.491, + "args": { + "External id": 4670545,"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": 1708036600227.929, "dur": 2.009, + "args": { + "External id": 4670546,"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": 1708036600232.782, "dur": 0.311, + "args": { + "External id": 4670547,"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": 1708036600233.693, "dur": 0.350, + "args": { + "External id": 4670548,"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": 1708036600239.001, "dur": 0.352, + "args": { + "External id": 4670549,"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": 1708036600239.984, "dur": 0.549, + "args": { + "External id": 4670550,"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": 1708036600241.302, "dur": 2.260, + "args": { + "External id": 4670551,"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": 1708036600248.336, "dur": 0.603, + "args": { + "External id": 4670552,"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": 1708036600249.644, "dur": 0.565, + "args": { + "External id": 4670553,"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": 1708036600250.934, "dur": 2.019, + "args": { + "External id": 4670554,"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": 1708036600255.754, "dur": 0.446, + "args": { + "External id": 4670555,"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": 1708036600256.867, "dur": 0.319, + "args": { + "External id": 4670556,"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": 1708036600261.721, "dur": 0.228, + "args": { + "External id": 4670557,"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": 1708036600262.718, "dur": 0.284, + "args": { + "External id": 4670558,"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": 1708036600263.593, "dur": 2.769, + "args": { + "External id": 4670559,"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": 1708036600270.046, "dur": 0.456, + "args": { + "External id": 4670560,"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": 1708036600270.971, "dur": 0.296, + "args": { + "External id": 4670561,"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": 1708036600271.693, "dur": 2.379, + "args": { + "External id": 4670562,"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": 1708036600328.210, "dur": 86.594, + "args": { + "External id": 4670563,"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": 1708036600492.963, "dur": 303.471, + "args": { + "External id": 4670564,"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": 1708036600509.244, "dur": 4.012, + "args": { + "External id": 4670565,"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": 1708036600522.229, "dur": 36.470, + "args": { + "External id": 4670566,"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": 1708036600547.779, "dur": 10.525, + "args": { + "External id": 4670567,"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": 1708036600553.108, "dur": 0.764, + "args": { + "External id": 4670568,"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": 1708036600567.874, "dur": 120.987, + "args": { + "External id": 4670569,"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": 1708036600569.600, "dur": 0.535, + "args": { + "External id": 4670570,"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": 1708036600571.354, "dur": 0.316, + "args": { + "External id": 4670571,"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": 1708036600574.388, "dur": 3.026, + "args": { + "External id": 4670572,"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": 1708036600577.904, "dur": 0.800, + "args": { + "External id": 4670573,"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": 1708036600580.798, "dur": 0.411, + "args": { + "External id": 4670574,"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": 1708036600581.873, "dur": 0.471, + "args": { + "External id": 4670575,"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": 1708036600583.283, "dur": 0.299, + "args": { + "External id": 4670576,"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": 1708036600585.999, "dur": 0.460, + "args": { + "External id": 4670577,"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": 1708036600587.110, "dur": 0.671, + "args": { + "External id": 4670578,"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": 1708036600588.524, "dur": 0.310, + "args": { + "External id": 4670579,"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": 1708036600591.833, "dur": 2.699, + "args": { + "External id": 4670580,"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": 1708036600595.254, "dur": 0.553, + "args": { + "External id": 4670581,"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": 1708036600599.278, "dur": 1.784, + "args": { + "External id": 4670582,"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": 1708036600601.848, "dur": 0.474, + "args": { + "External id": 4670583,"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": 1708036600602.788, "dur": 0.556, + "args": { + "External id": 4670584,"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": 1708036600608.195, "dur": 0.293, + "args": { + "External id": 4670585,"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": 1708036600609.161, "dur": 0.504, + "args": { + "External id": 4670586,"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": 1708036600610.202, "dur": 0.260, + "args": { + "External id": 4670587,"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": 1708036600615.008, "dur": 2.247, + "args": { + "External id": 4670588,"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": 1708036600617.803, "dur": 0.324, + "args": { + "External id": 4670589,"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": 1708036600619.857, "dur": 1.721, + "args": { + "External id": 4670590,"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": 1708036600622.420, "dur": 0.227, + "args": { + "External id": 4670591,"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": 1708036600623.161, "dur": 0.314, + "args": { + "External id": 4670592,"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": 1708036600627.447, "dur": 0.326, + "args": { + "External id": 4670593,"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": 1708036600628.299, "dur": 0.563, + "args": { + "External id": 4670594,"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": 1708036600629.620, "dur": 0.249, + "args": { + "External id": 4670595,"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": 1708036600634.276, "dur": 2.310, + "args": { + "External id": 4670596,"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": 1708036600637.122, "dur": 0.244, + "args": { + "External id": 4670597,"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": 1708036600640.609, "dur": 1.622, + "args": { + "External id": 4670598,"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": 1708036600642.911, "dur": 0.297, + "args": { + "External id": 4670599,"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": 1708036600643.798, "dur": 0.237, + "args": { + "External id": 4670600,"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": 1708036600648.064, "dur": 0.302, + "args": { + "External id": 4670601,"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": 1708036600648.993, "dur": 0.605, + "args": { + "External id": 4670602,"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": 1708036600650.102, "dur": 0.280, + "args": { + "External id": 4670603,"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": 1708036600654.644, "dur": 2.025, + "args": { + "External id": 4670604,"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": 1708036600657.118, "dur": 0.455, + "args": { + "External id": 4670605,"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": 1708036600660.147, "dur": 1.911, + "args": { + "External id": 4670606,"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": 1708036600662.654, "dur": 0.516, + "args": { + "External id": 4670607,"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": 1708036600663.720, "dur": 0.597, + "args": { + "External id": 4670608,"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": 1708036600712.379, "dur": 64.955, + "args": { + "External id": 4670609,"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": 1708036600858.552, "dur": 399.841, + "args": { + "External id": 4670610,"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": 1708036600893.608, "dur": 359.261, + "args": { + "External id": 4670611,"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": 1708036600903.993, "dur": 342.728, + "args": { + "External id": 4670612,"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": 1708036601288.418, "dur": 2.247, + "args": { + "External id": 4670613,"Record function id": 0, "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": 1708036601399.583, "dur": 6523.890, + "args": { + "External id": 4670614,"Record function id": 0, "Ev Idx": 5933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036601652.110, "dur": 7.459, + "args": { + "External id": 4670615,"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": 1708036601664.059, "dur": 1.018, + "args": { + "External id": 4670616,"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": 1708036601666.589, "dur": 1.410, + "args": { + "External id": 4670617,"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": 1708036601669.864, "dur": 2.735, + "args": { + "External id": 4670618,"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": 1708036601673.971, "dur": 1.006, + "args": { + "External id": 4670619,"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": 1708036601676.392, "dur": 0.854, + "args": { + "External id": 4670620,"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": 1708036601680.291, "dur": 1.137, + "args": { + "External id": 4670621,"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": 1708036601682.872, "dur": 3.300, + "args": { + "External id": 4670622,"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": 1708036601689.399, "dur": 0.697, + "args": { + "External id": 4670623,"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": 1708036601691.223, "dur": 0.929, + "args": { + "External id": 4670624,"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": 1708036601695.602, "dur": 0.788, + "args": { + "External id": 4670625,"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": 1708036601697.647, "dur": 2.457, + "args": { + "External id": 4670626,"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": 1708036601701.573, "dur": 0.798, + "args": { + "External id": 4670627,"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": 1708036601703.455, "dur": 0.872, + "args": { + "External id": 4670628,"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": 1708036601706.697, "dur": 1.142, + "args": { + "External id": 4670629,"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": 1708036601709.169, "dur": 3.260, + "args": { + "External id": 4670630,"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": 1708036601716.939, "dur": 0.877, + "args": { + "External id": 4670631,"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": 1708036601719.172, "dur": 0.958, + "args": { + "External id": 4670632,"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": 1708036601722.695, "dur": 1.069, + "args": { + "External id": 4670633,"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": 1708036601725.206, "dur": 2.680, + "args": { + "External id": 4670634,"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": 1708036601729.501, "dur": 0.745, + "args": { + "External id": 4670635,"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": 1708036601731.506, "dur": 0.995, + "args": { + "External id": 4670636,"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": 1708036601735.383, "dur": 1.071, + "args": { + "External id": 4670637,"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": 1708036601737.986, "dur": 2.557, + "args": { + "External id": 4670638,"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": 1708036601758.416, "dur": 0.658, + "args": { + "External id": 4670639,"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": 1708036601760.456, "dur": 0.870, + "args": { + "External id": 4670640,"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": 1708036601764.148, "dur": 1.062, + "args": { + "External id": 4670641,"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": 1708036601766.687, "dur": 3.171, + "args": { + "External id": 4670642,"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": 1708036601771.352, "dur": 0.720, + "args": { + "External id": 4670643,"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": 1708036601773.325, "dur": 0.913, + "args": { + "External id": 4670644,"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": 1708036601776.842, "dur": 0.934, + "args": { + "External id": 4670645,"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": 1708036601779.173, "dur": 3.074, + "args": { + "External id": 4670646,"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": 1708036601785.671, "dur": 0.707, + "args": { + "External id": 4670647,"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": 1708036601787.626, "dur": 1.105, + "args": { + "External id": 4670648,"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": 1708036601791.269, "dur": 1.023, + "args": { + "External id": 4670649,"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": 1708036601793.571, "dur": 3.215, + "args": { + "External id": 4670650,"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": 1708036601797.935, "dur": 0.730, + "args": { + "External id": 4670651,"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": 1708036601799.891, "dur": 0.984, + "args": { + "External id": 4670652,"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": 1708036601803.385, "dur": 0.860, + "args": { + "External id": 4670653,"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": 1708036601805.471, "dur": 3.490, + "args": { + "External id": 4670654,"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": 1708036601841.108, "dur": 6026.634, + "args": { + "External id": 4670655,"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": 1708036601868.712, "dur": 5990.277, + "args": { + "External id": 4670656,"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": 1708036601892.899, "dur": 5.482, + "args": { + "External id": 4670657,"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": 1708036601904.113, "dur": 5912.275, + "args": { + "External id": 4670658,"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": 1708036601906.745, "dur": 5908.958, + "args": { + "External id": 4670659,"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": 1708036601913.773, "dur": 5.258, + "args": { + "External id": 4670660,"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": 1708036601922.368, "dur": 5890.600, + "args": { + "External id": 4670661,"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": 1708036608256.924, "dur": 36.064, + "args": { + "External id": 4670662,"Record function id": 0, "Ev Idx": 5981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 1336753, "tid": 1336753, + "ts": 1708036608294.424, "dur": 261.291, + "args": { + "External id": 4670663,"Record function id": 0, "Ev Idx": 5982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036608344.377, "dur": 199.371, + "args": { + "External id": 4670664,"Sequence number": 46526432, "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": 1708036608344.377, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036608422.823, "dur": 59.060, + "args": { + "External id": 4670665,"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": 1708036608621.620, "dur": 54.755, + "args": { + "External id": 4670666,"Record function id": 0, "Ev Idx": 5985 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 1336753, "tid": 1336753, + "ts": 1708036608688.219, "dur": 7516.775, + "args": { + "External id": 4670667,"Record function id": 0, "Ev Idx": 5986 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 1336753, "tid": 1336753, + "ts": 1708036608696.697, "dur": 888.223, + "args": { + "External id": 4670668,"Record function id": 0, "Ev Idx": 5987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036608770.858, "dur": 10.990, + "args": { + "External id": 4670669,"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": 1708036608795.954, "dur": 42.868, + "args": { + "External id": 4670670,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036608804.442, "dur": 2.393, + "args": { + "External id": 4670671,"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": 1708036608808.412, "dur": 0.622, + "args": { + "External id": 4670672,"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": 1708036608810.037, "dur": 2.001, + "args": { + "External id": 4670673,"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": 1708036608814.795, "dur": 0.483, + "args": { + "External id": 4670674,"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": 1708036608815.858, "dur": 0.369, + "args": { + "External id": 4670675,"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": 1708036608820.534, "dur": 0.167, + "args": { + "External id": 4670676,"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": 1708036608821.297, "dur": 0.478, + "args": { + "External id": 4670677,"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": 1708036608822.516, "dur": 2.212, + "args": { + "External id": 4670678,"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": 1708036608828.758, "dur": 0.636, + "args": { + "External id": 4670679,"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": 1708036608849.326, "dur": 38.527, + "args": { + "External id": 4670680,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036608919.277, "dur": 157.563, + "args": { + "External id": 4670681,"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": 1708036608929.724, "dur": 4.169, + "args": { + "External id": 4670682,"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": 1708036608938.984, "dur": 11.320, + "args": { + "External id": 4670683,"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": 1708036608943.201, "dur": 6.681, + "args": { + "External id": 4670684,"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": 1708036608948.186, "dur": 0.461, + "args": { + "External id": 4670685,"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": 1708036608956.508, "dur": 69.173, + "args": { + "External id": 4670686,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036608957.774, "dur": 0.483, + "args": { + "External id": 4670687,"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": 1708036608961.406, "dur": 0.457, + "args": { + "External id": 4670688,"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": 1708036608964.901, "dur": 0.528, + "args": { + "External id": 4670689,"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": 1708036608968.683, "dur": 0.484, + "args": { + "External id": 4670690,"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": 1708036608969.722, "dur": 4.152, + "args": { + "External id": 4670691,"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": 1708036608974.912, "dur": 0.509, + "args": { + "External id": 4670692,"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": 1708036608978.955, "dur": 0.235, + "args": { + "External id": 4670693,"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": 1708036608981.751, "dur": 0.349, + "args": { + "External id": 4670694,"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": 1708036609017.289, "dur": 0.824, + "args": { + "External id": 4670695,"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": 1708036609040.117, "dur": 27.326, + "args": { + "External id": 4670696,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036609127.611, "dur": 347.587, + "args": { + "External id": 4670697,"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": 1708036609157.585, "dur": 312.432, + "args": { + "External id": 4670698,"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": 1708036609166.279, "dur": 297.954, + "args": { + "External id": 4670699,"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": 1708036609496.851, "dur": 2.342, + "args": { + "External id": 4670700,"Record function id": 0, "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": 1708036609608.177, "dur": 6331.466, + "args": { + "External id": 4670701,"Record function id": 0, "Ev Idx": 6020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036609713.642, "dur": 6.384, + "args": { + "External id": 4670702,"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": 1708036609723.091, "dur": 1.050, + "args": { + "External id": 4670703,"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": 1708036609725.790, "dur": 1.119, + "args": { + "External id": 4670704,"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": 1708036609728.688, "dur": 2.977, + "args": { + "External id": 4670705,"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": 1708036609735.017, "dur": 0.872, + "args": { + "External id": 4670706,"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": 1708036609737.395, "dur": 1.207, + "args": { + "External id": 4670707,"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": 1708036609739.947, "dur": 0.938, + "args": { + "External id": 4670708,"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": 1708036609743.800, "dur": 3.438, + "args": { + "External id": 4670709,"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": 1708036609750.247, "dur": 0.943, + "args": { + "External id": 4670710,"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": 1708036609752.425, "dur": 0.753, + "args": { + "External id": 4670711,"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": 1708036609769.418, "dur": 6134.323, + "args": { + "External id": 4670712,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036609786.222, "dur": 6111.273, + "args": { + "External id": 4670713,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036609816.321, "dur": 13.732, + "args": { + "External id": 4670714,"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": 1708036609834.147, "dur": 6030.892, + "args": { + "External id": 4670715,"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": 1708036609838.776, "dur": 6025.647, + "args": { + "External id": 4670716,"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": 1708036609843.999, "dur": 8.439, + "args": { + "External id": 4670717,"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": 1708036609854.095, "dur": 6007.504, + "args": { + "External id": 4670718,"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": 1708036616147.019, "dur": 31.203, + "args": { + "External id": 4670719,"Sequence number": 46526433, "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": 1708036616147.019, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036616164.405, "dur": 8.951, + "args": { + "External id": 4670720,"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": 1708036616168.910, "dur": 4.135, + "args": { + "External id": 4670721,"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": 1708036616247.169, "dur": 156.761, + "args": { + "External id": 4670722,"Record function id": 0, "Ev Idx": 6041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036616405.748, "dur": 1297.550, + "args": { + "External id": 4670723,"Record function id": 0, "Ev Idx": 6042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036616449.459, "dur": 1239.968, + "args": { + "External id": 4670724,"Sequence number": 46526434, "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": 1708036616449.459, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036616554.413, "dur": 53.702, + "args": { + "External id": 4670725,"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": 1708036616625.071, "dur": 129.478, + "args": { + "External id": 4670726,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036616766.788, "dur": 36.953, + "args": { + "External id": 4670727,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036616811.631, "dur": 30.395, + "args": { + "External id": 4670728,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036616869.112, "dur": 29.308, + "args": { + "External id": 4670729,"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": 1708036616921.632, "dur": 15.394, + "args": { + "External id": 4670730,"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": 1708036616959.502, "dur": 226.324, + "args": { + "External id": 4670731,"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": 1708036617100.041, "dur": 11.444, + "args": { + "External id": 4670732,"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": 1708036617104.812, "dur": 5.738, + "args": { + "External id": 4670733,"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": 1708036617114.216, "dur": 3.609, + "args": { + "External id": 4670734,"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": 1708036617121.736, "dur": 1.007, + "args": { + "External id": 4670735,"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": 1708036617125.554, "dur": 4.162, + "args": { + "External id": 4670736,"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": 1708036617197.705, "dur": 49.392, + "args": { + "External id": 4670737,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036617278.908, "dur": 36.155, + "args": { + "External id": 4670738,"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": 1708036617322.293, "dur": 41.812, + "args": { + "External id": 4670739,"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": 1708036617374.132, "dur": 35.097, + "args": { + "External id": 4670740,"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": 1708036617433.179, "dur": 29.814, + "args": { + "External id": 4670741,"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": 1708036617468.603, "dur": 35.942, + "args": { + "External id": 4670742,"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": 1708036617565.573, "dur": 27.257, + "args": { + "External id": 4670743,"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": 1708036617768.028, "dur": 85.693, + "args": { + "External id": 4670744,"Record function id": 0, "Ev Idx": 6063 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036617932.386, "dur": 44.798, + "args": { + "External id": 4670745,"Record function id": 0, "Ev Idx": 6064 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 1336753, "tid": 1336753, + "ts": 1708036618085.642, "dur": 19276.197, + "args": { + "External id": 4670746,"Record function id": 0, "Ev Idx": 6065 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 1336753, "tid": 1336753, + "ts": 1708036618098.900, "dur": 977.387, + "args": { + "External id": 4670747,"Record function id": 0, "Ev Idx": 6066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036618181.599, "dur": 9.511, + "args": { + "External id": 4670748,"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": 1708036618205.125, "dur": 45.185, + "args": { + "External id": 4670749,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036618212.117, "dur": 3.867, + "args": { + "External id": 4670750,"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": 1708036618217.705, "dur": 0.676, + "args": { + "External id": 4670751,"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": 1708036618221.281, "dur": 1.415, + "args": { + "External id": 4670752,"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": 1708036618225.190, "dur": 0.435, + "args": { + "External id": 4670753,"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": 1708036618226.337, "dur": 2.748, + "args": { + "External id": 4670754,"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": 1708036618231.937, "dur": 0.374, + "args": { + "External id": 4670755,"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": 1708036618233.634, "dur": 0.282, + "args": { + "External id": 4670756,"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": 1708036618234.485, "dur": 0.543, + "args": { + "External id": 4670757,"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": 1708036618238.190, "dur": 2.433, + "args": { + "External id": 4670758,"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": 1708036618260.883, "dur": 46.543, + "args": { + "External id": 4670759,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036618340.355, "dur": 120.304, + "args": { + "External id": 4670760,"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": 1708036618353.118, "dur": 4.182, + "args": { + "External id": 4670761,"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": 1708036618362.675, "dur": 9.585, + "args": { + "External id": 4670762,"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": 1708036618367.089, "dur": 4.726, + "args": { + "External id": 4670763,"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": 1708036618369.971, "dur": 0.607, + "args": { + "External id": 4670764,"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": 1708036618378.291, "dur": 32.534, + "args": { + "External id": 4670765,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036618381.435, "dur": 0.496, + "args": { + "External id": 4670766,"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": 1708036618382.801, "dur": 2.306, + "args": { + "External id": 4670767,"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": 1708036618385.800, "dur": 2.375, + "args": { + "External id": 4670768,"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": 1708036618390.742, "dur": 0.542, + "args": { + "External id": 4670769,"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": 1708036618391.927, "dur": 0.306, + "args": { + "External id": 4670770,"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": 1708036618394.853, "dur": 0.287, + "args": { + "External id": 4670771,"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": 1708036618398.307, "dur": 0.363, + "args": { + "External id": 4670772,"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": 1708036618399.362, "dur": 0.573, + "args": { + "External id": 4670773,"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": 1708036618404.285, "dur": 0.277, + "args": { + "External id": 4670774,"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": 1708036618424.070, "dur": 26.049, + "args": { + "External id": 4670775,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036618511.495, "dur": 409.875, + "args": { + "External id": 4670776,"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": 1708036618575.692, "dur": 339.795, + "args": { + "External id": 4670777,"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": 1708036618586.175, "dur": 323.599, + "args": { + "External id": 4670778,"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": 1708036618944.270, "dur": 2.298, + "args": { + "External id": 4670779,"Record function id": 0, "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": 1708036619098.927, "dur": 18065.938, + "args": { + "External id": 4670780,"Record function id": 0, "Ev Idx": 6099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036619203.524, "dur": 6.526, + "args": { + "External id": 4670781,"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": 1708036619213.477, "dur": 1.224, + "args": { + "External id": 4670782,"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": 1708036619216.408, "dur": 1.076, + "args": { + "External id": 4670783,"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": 1708036619219.160, "dur": 0.830, + "args": { + "External id": 4670784,"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": 1708036619221.361, "dur": 1.704, + "args": { + "External id": 4670785,"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": 1708036619226.070, "dur": 1.039, + "args": { + "External id": 4670786,"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": 1708036619230.876, "dur": 1.316, + "args": { + "External id": 4670787,"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": 1708036619233.365, "dur": 5.252, + "args": { + "External id": 4670788,"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": 1708036619239.868, "dur": 0.946, + "args": { + "External id": 4670789,"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": 1708036619244.109, "dur": 6.874, + "args": { + "External id": 4670790,"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": 1708036619267.879, "dur": 17858.142, + "args": { + "External id": 4670791,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036619285.999, "dur": 17833.716, + "args": { + "External id": 4670792,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036619313.197, "dur": 12.221, + "args": { + "External id": 4670793,"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": 1708036619328.945, "dur": 17756.656, + "args": { + "External id": 4670794,"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": 1708036619331.476, "dur": 17753.663, + "args": { + "External id": 4670795,"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": 1708036619336.859, "dur": 4.701, + "args": { + "External id": 4670796,"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": 1708036619343.151, "dur": 17738.938, + "args": { + "External id": 4670797,"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": 1708036637305.756, "dur": 32.043, + "args": { + "External id": 4670798,"Sequence number": 46526435, "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": 1708036637305.756, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036637323.733, "dur": 9.697, + "args": { + "External id": 4670799,"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": 1708036637329.212, "dur": 4.026, + "args": { + "External id": 4670800,"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": 1708036637403.754, "dur": 94.678, + "args": { + "External id": 4670801,"Record function id": 0, "Ev Idx": 6120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036637500.015, "dur": 1124.069, + "args": { + "External id": 4670802,"Record function id": 0, "Ev Idx": 6121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036637557.694, "dur": 1052.788, + "args": { + "External id": 4670803,"Sequence number": 46526436, "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": 1708036637557.694, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036637641.096, "dur": 44.470, + "args": { + "External id": 4670804,"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": 1708036637701.325, "dur": 110.259, + "args": { + "External id": 4670805,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036637818.608, "dur": 36.750, + "args": { + "External id": 4670806,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036637860.608, "dur": 31.107, + "args": { + "External id": 4670807,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036637922.420, "dur": 27.170, + "args": { + "External id": 4670808,"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": 1708036637970.598, "dur": 56.939, + "args": { + "External id": 4670809,"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": 1708036638047.613, "dur": 137.752, + "args": { + "External id": 4670810,"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": 1708036638102.943, "dur": 13.396, + "args": { + "External id": 4670811,"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": 1708036638107.524, "dur": 8.093, + "args": { + "External id": 4670812,"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": 1708036638121.105, "dur": 5.000, + "args": { + "External id": 4670813,"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": 1708036638127.274, "dur": 2.648, + "args": { + "External id": 4670814,"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": 1708036638132.142, "dur": 3.034, + "args": { + "External id": 4670815,"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": 1708036638196.369, "dur": 48.822, + "args": { + "External id": 4670816,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036638276.529, "dur": 27.755, + "args": { + "External id": 4670817,"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": 1708036638313.707, "dur": 41.092, + "args": { + "External id": 4670818,"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": 1708036638360.881, "dur": 34.604, + "args": { + "External id": 4670819,"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": 1708036638419.613, "dur": 24.809, + "args": { + "External id": 4670820,"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": 1708036638450.139, "dur": 34.270, + "args": { + "External id": 4670821,"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": 1708036638502.282, "dur": 37.180, + "args": { + "External id": 4670822,"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": 1708036638687.567, "dur": 75.294, + "args": { + "External id": 4670823,"Record function id": 0, "Ev Idx": 6142 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036638839.879, "dur": 46.757, + "args": { + "External id": 4670824,"Record function id": 0, "Ev Idx": 6143 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 1336753, "tid": 1336753, + "ts": 1708036638896.024, "dur": 18564.939, + "args": { + "External id": 4670825,"Record function id": 0, "Ev Idx": 6144 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 1336753, "tid": 1336753, + "ts": 1708036638905.561, "dur": 918.612, + "args": { + "External id": 4670826,"Record function id": 0, "Ev Idx": 6145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036639024.965, "dur": 9.280, + "args": { + "External id": 4670827,"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": 1708036639051.907, "dur": 42.166, + "args": { + "External id": 4670828,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036639057.101, "dur": 2.347, + "args": { + "External id": 4670829,"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": 1708036639063.020, "dur": 0.423, + "args": { + "External id": 4670830,"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": 1708036639067.025, "dur": 0.591, + "args": { + "External id": 4670831,"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": 1708036639068.618, "dur": 0.468, + "args": { + "External id": 4670832,"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": 1708036639071.690, "dur": 0.525, + "args": { + "External id": 4670833,"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": 1708036639075.185, "dur": 0.826, + "args": { + "External id": 4670834,"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": 1708036639076.773, "dur": 4.797, + "args": { + "External id": 4670835,"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": 1708036639084.006, "dur": 0.329, + "args": { + "External id": 4670836,"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": 1708036639085.219, "dur": 0.541, + "args": { + "External id": 4670837,"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": 1708036639104.514, "dur": 45.142, + "args": { + "External id": 4670838,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036639186.125, "dur": 119.433, + "args": { + "External id": 4670839,"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": 1708036639198.768, "dur": 3.855, + "args": { + "External id": 4670840,"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": 1708036639208.112, "dur": 10.158, + "args": { + "External id": 4670841,"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": 1708036639212.843, "dur": 5.017, + "args": { + "External id": 4670842,"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": 1708036639216.041, "dur": 0.584, + "args": { + "External id": 4670843,"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": 1708036639224.600, "dur": 36.232, + "args": { + "External id": 4670844,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036639228.198, "dur": 1.972, + "args": { + "External id": 4670845,"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": 1708036639231.059, "dur": 0.773, + "args": { + "External id": 4670846,"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": 1708036639232.551, "dur": 0.553, + "args": { + "External id": 4670847,"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": 1708036639238.178, "dur": 2.470, + "args": { + "External id": 4670848,"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": 1708036639241.574, "dur": 0.580, + "args": { + "External id": 4670849,"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": 1708036639244.792, "dur": 0.559, + "args": { + "External id": 4670850,"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": 1708036639247.842, "dur": 0.556, + "args": { + "External id": 4670851,"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": 1708036639249.117, "dur": 0.493, + "args": { + "External id": 4670852,"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": 1708036639251.983, "dur": 2.091, + "args": { + "External id": 4670853,"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": 1708036639271.598, "dur": 25.428, + "args": { + "External id": 4670854,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036639356.638, "dur": 372.213, + "args": { + "External id": 4670855,"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": 1708036639388.667, "dur": 334.875, + "args": { + "External id": 4670856,"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": 1708036639399.244, "dur": 316.568, + "args": { + "External id": 4670857,"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": 1708036639753.896, "dur": 2.550, + "args": { + "External id": 4670858,"Record function id": 0, "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": 1708036639843.688, "dur": 17425.531, + "args": { + "External id": 4670859,"Record function id": 0, "Ev Idx": 6178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036639942.318, "dur": 6.074, + "args": { + "External id": 4670860,"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": 1708036639951.705, "dur": 1.512, + "args": { + "External id": 4670861,"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": 1708036639954.909, "dur": 3.780, + "args": { + "External id": 4670862,"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": 1708036639962.127, "dur": 0.918, + "args": { + "External id": 4670863,"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": 1708036639964.505, "dur": 1.127, + "args": { + "External id": 4670864,"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": 1708036639966.832, "dur": 1.429, + "args": { + "External id": 4670865,"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": 1708036639969.883, "dur": 1.028, + "args": { + "External id": 4670866,"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": 1708036639973.331, "dur": 3.653, + "args": { + "External id": 4670867,"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": 1708036639978.369, "dur": 1.090, + "args": { + "External id": 4670868,"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": 1708036640018.932, "dur": 1.923, + "args": { + "External id": 4670869,"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": 1708036640044.493, "dur": 17185.409, + "args": { + "External id": 4670870,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036640060.053, "dur": 17163.402, + "args": { + "External id": 4670871,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036640088.495, "dur": 14.455, + "args": { + "External id": 4670872,"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": 1708036640106.135, "dur": 17084.491, + "args": { + "External id": 4670873,"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": 1708036640108.949, "dur": 17081.147, + "args": { + "External id": 4670874,"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": 1708036640114.825, "dur": 5.403, + "args": { + "External id": 4670875,"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": 1708036640121.979, "dur": 17065.363, + "args": { + "External id": 4670876,"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": 1708036657408.147, "dur": 29.148, + "args": { + "External id": 4670877,"Sequence number": 46526437, "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": 1708036657408.147, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036657425.676, "dur": 7.160, + "args": { + "External id": 4670878,"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": 1708036657428.610, "dur": 4.028, + "args": { + "External id": 4670879,"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": 1708036657498.809, "dur": 99.736, + "args": { + "External id": 4670880,"Record function id": 0, "Ev Idx": 6199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036657601.523, "dur": 1096.639, + "args": { + "External id": 4670881,"Record function id": 0, "Ev Idx": 6200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036657644.171, "dur": 1039.951, + "args": { + "External id": 4670882,"Sequence number": 46526438, "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": 1708036657644.171, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036657713.270, "dur": 42.247, + "args": { + "External id": 4670883,"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": 1708036657768.473, "dur": 106.487, + "args": { + "External id": 4670884,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036657884.818, "dur": 38.466, + "args": { + "External id": 4670885,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036657932.176, "dur": 31.676, + "args": { + "External id": 4670886,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036658031.537, "dur": 27.898, + "args": { + "External id": 4670887,"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": 1708036658079.131, "dur": 14.964, + "args": { + "External id": 4670888,"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": 1708036658113.346, "dur": 132.133, + "args": { + "External id": 4670889,"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": 1708036658164.573, "dur": 13.189, + "args": { + "External id": 4670890,"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": 1708036658171.137, "dur": 5.734, + "args": { + "External id": 4670891,"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": 1708036658180.221, "dur": 6.396, + "args": { + "External id": 4670892,"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": 1708036658187.846, "dur": 1.162, + "args": { + "External id": 4670893,"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": 1708036658191.238, "dur": 4.622, + "args": { + "External id": 4670894,"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": 1708036658256.196, "dur": 52.243, + "args": { + "External id": 4670895,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036658337.506, "dur": 29.790, + "args": { + "External id": 4670896,"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": 1708036658376.001, "dur": 41.491, + "args": { + "External id": 4670897,"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": 1708036658425.422, "dur": 34.287, + "args": { + "External id": 4670898,"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": 1708036658479.634, "dur": 25.252, + "args": { + "External id": 4670899,"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": 1708036658510.535, "dur": 51.427, + "args": { + "External id": 4670900,"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": 1708036658589.221, "dur": 18.067, + "args": { + "External id": 4670901,"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": 1708036658761.711, "dur": 74.680, + "args": { + "External id": 4670902,"Record function id": 0, "Ev Idx": 6221 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036658913.103, "dur": 48.589, + "args": { + "External id": 4670903,"Record function id": 0, "Ev Idx": 6222 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 1336753, "tid": 1336753, + "ts": 1708036658971.320, "dur": 18895.364, + "args": { + "External id": 4670904,"Record function id": 0, "Ev Idx": 6223 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 1336753, "tid": 1336753, + "ts": 1708036659019.186, "dur": 953.612, + "args": { + "External id": 4670905,"Record function id": 0, "Ev Idx": 6224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036659104.879, "dur": 9.415, + "args": { + "External id": 4670906,"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": 1708036659128.327, "dur": 64.670, + "args": { + "External id": 4670907,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036659133.904, "dur": 2.507, + "args": { + "External id": 4670908,"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": 1708036659143.269, "dur": 0.432, + "args": { + "External id": 4670909,"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": 1708036659144.565, "dur": 0.672, + "args": { + "External id": 4670910,"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": 1708036659163.406, "dur": 0.563, + "args": { + "External id": 4670911,"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": 1708036659169.075, "dur": 0.737, + "args": { + "External id": 4670912,"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": 1708036659170.764, "dur": 0.455, + "args": { + "External id": 4670913,"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": 1708036659174.668, "dur": 4.696, + "args": { + "External id": 4670914,"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": 1708036659180.116, "dur": 0.565, + "args": { + "External id": 4670915,"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": 1708036659181.316, "dur": 0.556, + "args": { + "External id": 4670916,"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": 1708036659207.197, "dur": 45.881, + "args": { + "External id": 4670917,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036659287.521, "dur": 154.766, + "args": { + "External id": 4670918,"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": 1708036659299.752, "dur": 4.191, + "args": { + "External id": 4670919,"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": 1708036659309.116, "dur": 10.136, + "args": { + "External id": 4670920,"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": 1708036659313.783, "dur": 5.076, + "args": { + "External id": 4670921,"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": 1708036659316.994, "dur": 0.620, + "args": { + "External id": 4670922,"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": 1708036659328.056, "dur": 36.609, + "args": { + "External id": 4670923,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036659329.712, "dur": 2.299, + "args": { + "External id": 4670924,"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": 1708036659333.060, "dur": 0.820, + "args": { + "External id": 4670925,"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": 1708036659337.587, "dur": 0.647, + "args": { + "External id": 4670926,"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": 1708036659340.493, "dur": 2.527, + "args": { + "External id": 4670927,"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": 1708036659345.552, "dur": 0.427, + "args": { + "External id": 4670928,"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": 1708036659346.945, "dur": 0.573, + "args": { + "External id": 4670929,"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": 1708036659349.631, "dur": 0.626, + "args": { + "External id": 4670930,"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": 1708036659353.216, "dur": 0.564, + "args": { + "External id": 4670931,"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": 1708036659354.456, "dur": 2.473, + "args": { + "External id": 4670932,"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": 1708036659406.287, "dur": 27.143, + "args": { + "External id": 4670933,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036659496.749, "dur": 380.155, + "args": { + "External id": 4670934,"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": 1708036659543.415, "dur": 328.305, + "args": { + "External id": 4670935,"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": 1708036659558.993, "dur": 306.717, + "args": { + "External id": 4670936,"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": 1708036659901.017, "dur": 2.370, + "args": { + "External id": 4670937,"Record function id": 0, "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": 1708036660029.829, "dur": 17626.543, + "args": { + "External id": 4670938,"Record function id": 0, "Ev Idx": 6257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036660131.432, "dur": 6.887, + "args": { + "External id": 4670939,"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": 1708036660141.631, "dur": 1.488, + "args": { + "External id": 4670940,"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": 1708036660144.924, "dur": 2.796, + "args": { + "External id": 4670941,"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": 1708036660149.657, "dur": 1.053, + "args": { + "External id": 4670942,"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": 1708036660152.264, "dur": 1.141, + "args": { + "External id": 4670943,"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": 1708036660154.626, "dur": 1.265, + "args": { + "External id": 4670944,"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": 1708036660159.232, "dur": 1.194, + "args": { + "External id": 4670945,"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": 1708036660161.986, "dur": 3.692, + "args": { + "External id": 4670946,"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": 1708036660166.928, "dur": 0.854, + "args": { + "External id": 4670947,"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": 1708036660168.966, "dur": 0.900, + "args": { + "External id": 4670948,"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": 1708036660190.951, "dur": 17424.823, + "args": { + "External id": 4670949,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036660206.810, "dur": 17402.602, + "args": { + "External id": 4670950,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036660229.506, "dur": 13.438, + "args": { + "External id": 4670951,"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": 1708036660245.898, "dur": 17330.729, + "args": { + "External id": 4670952,"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": 1708036660248.540, "dur": 17327.563, + "args": { + "External id": 4670953,"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": 1708036660255.758, "dur": 5.842, + "args": { + "External id": 4670954,"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": 1708036660263.370, "dur": 17310.015, + "args": { + "External id": 4670955,"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": 1708036677801.547, "dur": 39.035, + "args": { + "External id": 4670956,"Sequence number": 46526439, "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": 1708036677801.547, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036677828.089, "dur": 7.666, + "args": { + "External id": 4670957,"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": 1708036677831.238, "dur": 4.324, + "args": { + "External id": 4670958,"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": 1708036677906.474, "dur": 128.891, + "args": { + "External id": 4670959,"Record function id": 0, "Ev Idx": 6278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036678040.551, "dur": 1196.768, + "args": { + "External id": 4670960,"Record function id": 0, "Ev Idx": 6279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036678087.527, "dur": 1136.303, + "args": { + "External id": 4670961,"Sequence number": 46526440, "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": 1708036678087.527, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036678154.443, "dur": 44.654, + "args": { + "External id": 4670962,"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": 1708036678210.734, "dur": 106.119, + "args": { + "External id": 4670963,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036678330.062, "dur": 38.010, + "args": { + "External id": 4670964,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036678374.422, "dur": 31.479, + "args": { + "External id": 4670965,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036678433.225, "dur": 24.850, + "args": { + "External id": 4670966,"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": 1708036678474.045, "dur": 15.926, + "args": { + "External id": 4670967,"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": 1708036678508.762, "dur": 158.237, + "args": { + "External id": 4670968,"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": 1708036678586.417, "dur": 11.690, + "args": { + "External id": 4670969,"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": 1708036678591.281, "dur": 5.890, + "args": { + "External id": 4670970,"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": 1708036678600.603, "dur": 5.131, + "args": { + "External id": 4670971,"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": 1708036678607.074, "dur": 0.794, + "args": { + "External id": 4670972,"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": 1708036678612.647, "dur": 4.213, + "args": { + "External id": 4670973,"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": 1708036678678.473, "dur": 48.527, + "args": { + "External id": 4670974,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036678759.479, "dur": 31.261, + "args": { + "External id": 4670975,"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": 1708036678800.033, "dur": 40.383, + "args": { + "External id": 4670976,"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": 1708036678933.747, "dur": 38.238, + "args": { + "External id": 4670977,"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": 1708036679039.164, "dur": 27.567, + "args": { + "External id": 4670978,"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": 1708036679074.128, "dur": 40.734, + "args": { + "External id": 4670979,"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": 1708036679132.704, "dur": 21.954, + "args": { + "External id": 4670980,"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": 1708036679300.710, "dur": 74.648, + "args": { + "External id": 4670981,"Record function id": 0, "Ev Idx": 6300 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036679450.666, "dur": 45.239, + "args": { + "External id": 4670982,"Record function id": 0, "Ev Idx": 6301 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 1336753, "tid": 1336753, + "ts": 1708036679505.441, "dur": 18722.079, + "args": { + "External id": 4670983,"Record function id": 0, "Ev Idx": 6302 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 1336753, "tid": 1336753, + "ts": 1708036679514.571, "dur": 917.859, + "args": { + "External id": 4670984,"Record function id": 0, "Ev Idx": 6303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036679618.212, "dur": 9.157, + "args": { + "External id": 4670985,"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": 1708036679641.331, "dur": 42.843, + "args": { + "External id": 4670986,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036679647.958, "dur": 2.202, + "args": { + "External id": 4670987,"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": 1708036679653.803, "dur": 0.319, + "args": { + "External id": 4670988,"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": 1708036679654.858, "dur": 0.460, + "args": { + "External id": 4670989,"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": 1708036679658.373, "dur": 0.375, + "args": { + "External id": 4670990,"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": 1708036679661.427, "dur": 0.447, + "args": { + "External id": 4670991,"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": 1708036679664.613, "dur": 0.449, + "args": { + "External id": 4670992,"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": 1708036679665.760, "dur": 3.731, + "args": { + "External id": 4670993,"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": 1708036679670.621, "dur": 0.410, + "args": { + "External id": 4670994,"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": 1708036679673.978, "dur": 0.389, + "args": { + "External id": 4670995,"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": 1708036679695.821, "dur": 44.379, + "args": { + "External id": 4670996,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036679773.065, "dur": 118.492, + "args": { + "External id": 4670997,"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": 1708036679784.710, "dur": 3.663, + "args": { + "External id": 4670998,"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": 1708036679793.430, "dur": 11.235, + "args": { + "External id": 4670999,"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": 1708036679797.780, "dur": 6.509, + "args": { + "External id": 4671000,"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": 1708036679802.683, "dur": 0.443, + "args": { + "External id": 4671001,"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": 1708036679811.052, "dur": 34.987, + "args": { + "External id": 4671002,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036679812.774, "dur": 2.331, + "args": { + "External id": 4671003,"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": 1708036679818.433, "dur": 0.823, + "args": { + "External id": 4671004,"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": 1708036679819.908, "dur": 0.368, + "args": { + "External id": 4671005,"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": 1708036679824.986, "dur": 2.656, + "args": { + "External id": 4671006,"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": 1708036679828.160, "dur": 0.673, + "args": { + "External id": 4671007,"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": 1708036679829.774, "dur": 0.450, + "args": { + "External id": 4671008,"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": 1708036679835.399, "dur": 0.318, + "args": { + "External id": 4671009,"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": 1708036679836.924, "dur": 0.287, + "args": { + "External id": 4671010,"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": 1708036679837.710, "dur": 1.650, + "args": { + "External id": 4671011,"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": 1708036679858.442, "dur": 24.521, + "args": { + "External id": 4671012,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036679942.956, "dur": 392.117, + "args": { + "External id": 4671013,"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": 1708036679974.568, "dur": 355.363, + "args": { + "External id": 4671014,"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": 1708036680031.719, "dur": 292.403, + "args": { + "External id": 4671015,"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": 1708036680360.086, "dur": 2.210, + "args": { + "External id": 4671016,"Record function id": 0, "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": 1708036680453.595, "dur": 17577.891, + "args": { + "External id": 4671017,"Record function id": 0, "Ev Idx": 6336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036680572.656, "dur": 6.969, + "args": { + "External id": 4671018,"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": 1708036680583.266, "dur": 1.263, + "args": { + "External id": 4671019,"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": 1708036680586.228, "dur": 3.228, + "args": { + "External id": 4671020,"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": 1708036680591.354, "dur": 1.067, + "args": { + "External id": 4671021,"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": 1708036680593.825, "dur": 1.339, + "args": { + "External id": 4671022,"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": 1708036680596.431, "dur": 1.199, + "args": { + "External id": 4671023,"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": 1708036680600.968, "dur": 1.292, + "args": { + "External id": 4671024,"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": 1708036680604.843, "dur": 3.959, + "args": { + "External id": 4671025,"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": 1708036680610.243, "dur": 1.026, + "args": { + "External id": 4671026,"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": 1708036680612.725, "dur": 0.909, + "args": { + "External id": 4671027,"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": 1708036680633.809, "dur": 17331.347, + "args": { + "External id": 4671028,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036680650.274, "dur": 17308.375, + "args": { + "External id": 4671029,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036680672.694, "dur": 14.066, + "args": { + "External id": 4671030,"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": 1708036680689.750, "dur": 17237.058, + "args": { + "External id": 4671031,"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": 1708036680692.739, "dur": 17233.538, + "args": { + "External id": 4671032,"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": 1708036680697.938, "dur": 8.606, + "args": { + "External id": 4671033,"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": 1708036680708.408, "dur": 17215.071, + "args": { + "External id": 4671034,"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": 1708036698173.862, "dur": 29.411, + "args": { + "External id": 4671035,"Sequence number": 46526441, "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": 1708036698173.862, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036698189.186, "dur": 9.569, + "args": { + "External id": 4671036,"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": 1708036698194.226, "dur": 4.311, + "args": { + "External id": 4671037,"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": 1708036698266.795, "dur": 81.528, + "args": { + "External id": 4671038,"Record function id": 0, "Ev Idx": 6357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036698349.789, "dur": 1072.819, + "args": { + "External id": 4671039,"Record function id": 0, "Ev Idx": 6358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036698390.478, "dur": 1019.121, + "args": { + "External id": 4671040,"Sequence number": 46526442, "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": 1708036698390.478, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036698452.560, "dur": 40.522, + "args": { + "External id": 4671041,"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": 1708036698504.661, "dur": 119.594, + "args": { + "External id": 4671042,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036698637.307, "dur": 38.728, + "args": { + "External id": 4671043,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036698685.705, "dur": 30.505, + "args": { + "External id": 4671044,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036698741.311, "dur": 33.406, + "args": { + "External id": 4671045,"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": 1708036698792.638, "dur": 14.548, + "args": { + "External id": 4671046,"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": 1708036698824.423, "dur": 124.768, + "args": { + "External id": 4671047,"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": 1708036698872.388, "dur": 10.139, + "args": { + "External id": 4671048,"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": 1708036698877.090, "dur": 4.588, + "args": { + "External id": 4671049,"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": 1708036698884.998, "dur": 6.019, + "args": { + "External id": 4671050,"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": 1708036698893.567, "dur": 1.023, + "args": { + "External id": 4671051,"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": 1708036698897.119, "dur": 3.895, + "args": { + "External id": 4671052,"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": 1708036698959.275, "dur": 85.365, + "args": { + "External id": 4671053,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036699078.867, "dur": 28.860, + "args": { + "External id": 4671054,"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": 1708036699117.186, "dur": 43.735, + "args": { + "External id": 4671055,"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": 1708036699169.071, "dur": 34.599, + "args": { + "External id": 4671056,"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": 1708036699224.619, "dur": 29.954, + "args": { + "External id": 4671057,"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": 1708036699260.535, "dur": 34.013, + "args": { + "External id": 4671058,"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": 1708036699314.602, "dur": 18.673, + "args": { + "External id": 4671059,"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": 1708036699486.346, "dur": 96.179, + "args": { + "External id": 4671060,"Record function id": 0, "Ev Idx": 6379 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036699660.562, "dur": 47.403, + "args": { + "External id": 4671061,"Record function id": 0, "Ev Idx": 6380 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 1336753, "tid": 1336753, + "ts": 1708036699717.662, "dur": 19008.948, + "args": { + "External id": 4671062,"Record function id": 0, "Ev Idx": 6381 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 1336753, "tid": 1336753, + "ts": 1708036699727.375, "dur": 764.756, + "args": { + "External id": 4671063,"Record function id": 0, "Ev Idx": 6382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036699808.578, "dur": 8.884, + "args": { + "External id": 4671064,"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": 1708036699831.115, "dur": 40.939, + "args": { + "External id": 4671065,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036699838.241, "dur": 2.021, + "args": { + "External id": 4671066,"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": 1708036699844.575, "dur": 0.308, + "args": { + "External id": 4671067,"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": 1708036699847.340, "dur": 0.397, + "args": { + "External id": 4671068,"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": 1708036699848.364, "dur": 0.585, + "args": { + "External id": 4671069,"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": 1708036699851.542, "dur": 0.681, + "args": { + "External id": 4671070,"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": 1708036699854.205, "dur": 0.665, + "args": { + "External id": 4671071,"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": 1708036699855.593, "dur": 3.557, + "args": { + "External id": 4671072,"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": 1708036699859.757, "dur": 0.318, + "args": { + "External id": 4671073,"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": 1708036699862.364, "dur": 0.402, + "args": { + "External id": 4671074,"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": 1708036699883.049, "dur": 42.596, + "args": { + "External id": 4671075,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036699957.305, "dur": 163.402, + "args": { + "External id": 4671076,"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": 1708036699970.634, "dur": 3.343, + "args": { + "External id": 4671077,"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": 1708036699978.925, "dur": 49.975, + "args": { + "External id": 4671078,"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": 1708036700022.236, "dur": 6.134, + "args": { + "External id": 4671079,"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": 1708036700025.559, "dur": 0.984, + "args": { + "External id": 4671080,"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": 1708036700037.242, "dur": 33.241, + "args": { + "External id": 4671081,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036700040.521, "dur": 2.435, + "args": { + "External id": 4671082,"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": 1708036700043.980, "dur": 0.416, + "args": { + "External id": 4671083,"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": 1708036700045.159, "dur": 0.610, + "args": { + "External id": 4671084,"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": 1708036700050.163, "dur": 2.014, + "args": { + "External id": 4671085,"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": 1708036700053.023, "dur": 0.400, + "args": { + "External id": 4671086,"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": 1708036700053.969, "dur": 0.586, + "args": { + "External id": 4671087,"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": 1708036700057.493, "dur": 0.493, + "args": { + "External id": 4671088,"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": 1708036700058.529, "dur": 0.389, + "args": { + "External id": 4671089,"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": 1708036700061.031, "dur": 1.913, + "args": { + "External id": 4671090,"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": 1708036700083.841, "dur": 28.323, + "args": { + "External id": 4671091,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036700176.065, "dur": 235.190, + "args": { + "External id": 4671092,"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": 1708036700207.276, "dur": 199.573, + "args": { + "External id": 4671093,"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": 1708036700221.465, "dur": 180.414, + "args": { + "External id": 4671094,"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": 1708036700430.916, "dur": 1.968, + "args": { + "External id": 4671095,"Record function id": 0, "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": 1708036700510.448, "dur": 18028.942, + "args": { + "External id": 4671096,"Record function id": 0, "Ev Idx": 6415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036700629.119, "dur": 6.114, + "args": { + "External id": 4671097,"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": 1708036700638.566, "dur": 1.190, + "args": { + "External id": 4671098,"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": 1708036700641.292, "dur": 3.982, + "args": { + "External id": 4671099,"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": 1708036700646.762, "dur": 0.899, + "args": { + "External id": 4671100,"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": 1708036700648.998, "dur": 1.175, + "args": { + "External id": 4671101,"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": 1708036700651.294, "dur": 1.289, + "args": { + "External id": 4671102,"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": 1708036700657.568, "dur": 1.246, + "args": { + "External id": 4671103,"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": 1708036700660.027, "dur": 4.190, + "args": { + "External id": 4671104,"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": 1708036700665.532, "dur": 0.987, + "args": { + "External id": 4671105,"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": 1708036700667.914, "dur": 0.688, + "args": { + "External id": 4671106,"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": 1708036700687.143, "dur": 17801.553, + "args": { + "External id": 4671107,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036700711.527, "dur": 17770.534, + "args": { + "External id": 4671108,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036700732.182, "dur": 14.667, + "args": { + "External id": 4671109,"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": 1708036700749.633, "dur": 17699.917, + "args": { + "External id": 4671110,"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": 1708036700752.194, "dur": 17696.691, + "args": { + "External id": 4671111,"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": 1708036700757.250, "dur": 4.979, + "args": { + "External id": 4671112,"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": 1708036700766.720, "dur": 17679.379, + "args": { + "External id": 4671113,"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": 1708036718674.871, "dur": 27.984, + "args": { + "External id": 4671114,"Sequence number": 46526443, "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": 1708036718674.871, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036718690.578, "dur": 8.031, + "args": { + "External id": 4671115,"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": 1708036718694.308, "dur": 4.079, + "args": { + "External id": 4671116,"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": 1708036718763.705, "dur": 79.224, + "args": { + "External id": 4671117,"Record function id": 0, "Ev Idx": 6436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036718844.444, "dur": 1081.755, + "args": { + "External id": 4671118,"Record function id": 0, "Ev Idx": 6437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036718884.664, "dur": 1028.810, + "args": { + "External id": 4671119,"Sequence number": 46526444, "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": 1708036718884.664, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036718947.988, "dur": 87.637, + "args": { + "External id": 4671120,"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": 1708036719051.788, "dur": 102.954, + "args": { + "External id": 4671121,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036719166.353, "dur": 38.911, + "args": { + "External id": 4671122,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036719212.996, "dur": 31.037, + "args": { + "External id": 4671123,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036719269.800, "dur": 26.975, + "args": { + "External id": 4671124,"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": 1708036719314.414, "dur": 14.534, + "args": { + "External id": 4671125,"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": 1708036719358.190, "dur": 125.693, + "args": { + "External id": 4671126,"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": 1708036719407.418, "dur": 10.734, + "args": { + "External id": 4671127,"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": 1708036719412.340, "dur": 5.193, + "args": { + "External id": 4671128,"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": 1708036719420.638, "dur": 4.481, + "args": { + "External id": 4671129,"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": 1708036719426.280, "dur": 1.126, + "args": { + "External id": 4671130,"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": 1708036719430.475, "dur": 4.557, + "args": { + "External id": 4671131,"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": 1708036719494.216, "dur": 64.343, + "args": { + "External id": 4671132,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036719593.103, "dur": 33.547, + "args": { + "External id": 4671133,"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": 1708036719635.395, "dur": 44.257, + "args": { + "External id": 4671134,"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": 1708036719688.960, "dur": 34.807, + "args": { + "External id": 4671135,"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": 1708036719743.716, "dur": 25.269, + "args": { + "External id": 4671136,"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": 1708036719774.408, "dur": 32.720, + "args": { + "External id": 4671137,"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": 1708036719828.991, "dur": 16.800, + "args": { + "External id": 4671138,"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": 1708036720024.514, "dur": 79.529, + "args": { + "External id": 4671139,"Record function id": 0, "Ev Idx": 6458 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036720183.892, "dur": 47.881, + "args": { + "External id": 4671140,"Record function id": 0, "Ev Idx": 6459 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 1336753, "tid": 1336753, + "ts": 1708036720241.889, "dur": 18972.437, + "args": { + "External id": 4671141,"Record function id": 0, "Ev Idx": 6460 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 1336753, "tid": 1336753, + "ts": 1708036720250.483, "dur": 1000.922, + "args": { + "External id": 4671142,"Record function id": 0, "Ev Idx": 6461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036720334.886, "dur": 8.565, + "args": { + "External id": 4671143,"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": 1708036720359.734, "dur": 47.297, + "args": { + "External id": 4671144,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036720365.289, "dur": 2.199, + "args": { + "External id": 4671145,"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": 1708036720371.963, "dur": 0.523, + "args": { + "External id": 4671146,"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": 1708036720374.344, "dur": 0.397, + "args": { + "External id": 4671147,"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": 1708036720376.695, "dur": 0.661, + "args": { + "External id": 4671148,"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": 1708036720380.678, "dur": 0.613, + "args": { + "External id": 4671149,"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": 1708036720383.082, "dur": 0.714, + "args": { + "External id": 4671150,"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": 1708036720389.521, "dur": 3.657, + "args": { + "External id": 4671151,"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": 1708036720394.487, "dur": 0.838, + "args": { + "External id": 4671152,"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": 1708036720396.551, "dur": 0.385, + "args": { + "External id": 4671153,"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": 1708036720421.399, "dur": 41.665, + "args": { + "External id": 4671154,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036720495.646, "dur": 144.110, + "args": { + "External id": 4671155,"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": 1708036720507.924, "dur": 3.709, + "args": { + "External id": 4671156,"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": 1708036720516.601, "dur": 28.587, + "args": { + "External id": 4671157,"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": 1708036720521.164, "dur": 23.476, + "args": { + "External id": 4671158,"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": 1708036720541.708, "dur": 0.780, + "args": { + "External id": 4671159,"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": 1708036720554.044, "dur": 35.341, + "args": { + "External id": 4671160,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036720556.435, "dur": 1.775, + "args": { + "External id": 4671161,"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": 1708036720560.700, "dur": 0.447, + "args": { + "External id": 4671162,"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": 1708036720562.911, "dur": 0.615, + "args": { + "External id": 4671163,"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": 1708036720567.312, "dur": 2.163, + "args": { + "External id": 4671164,"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": 1708036720570.932, "dur": 0.459, + "args": { + "External id": 4671165,"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": 1708036720573.098, "dur": 0.276, + "args": { + "External id": 4671166,"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": 1708036720576.102, "dur": 0.545, + "args": { + "External id": 4671167,"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": 1708036720578.291, "dur": 0.766, + "args": { + "External id": 4671168,"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": 1708036720580.677, "dur": 1.768, + "args": { + "External id": 4671169,"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": 1708036720601.394, "dur": 29.404, + "args": { + "External id": 4671170,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036720697.089, "dur": 448.299, + "args": { + "External id": 4671171,"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": 1708036720728.548, "dur": 411.053, + "args": { + "External id": 4671172,"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": 1708036720739.012, "dur": 394.332, + "args": { + "External id": 4671173,"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": 1708036721172.583, "dur": 2.892, + "args": { + "External id": 4671174,"Record function id": 0, "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": 1708036721271.981, "dur": 17740.247, + "args": { + "External id": 4671175,"Record function id": 0, "Ev Idx": 6494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036721371.056, "dur": 6.720, + "args": { + "External id": 4671176,"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": 1708036721382.109, "dur": 1.247, + "args": { + "External id": 4671177,"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": 1708036721385.740, "dur": 2.934, + "args": { + "External id": 4671178,"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": 1708036721390.841, "dur": 1.287, + "args": { + "External id": 4671179,"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": 1708036721393.673, "dur": 0.865, + "args": { + "External id": 4671180,"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": 1708036721396.238, "dur": 1.209, + "args": { + "External id": 4671181,"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": 1708036721401.096, "dur": 1.218, + "args": { + "External id": 4671182,"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": 1708036721403.739, "dur": 3.728, + "args": { + "External id": 4671183,"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": 1708036721409.153, "dur": 1.336, + "args": { + "External id": 4671184,"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": 1708036721411.976, "dur": 0.801, + "args": { + "External id": 4671185,"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": 1708036721432.749, "dur": 17511.371, + "args": { + "External id": 4671186,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036721448.479, "dur": 17489.049, + "args": { + "External id": 4671187,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036721470.610, "dur": 15.230, + "args": { + "External id": 4671188,"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": 1708036721488.473, "dur": 17416.769, + "args": { + "External id": 4671189,"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": 1708036721491.232, "dur": 17413.424, + "args": { + "External id": 4671190,"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": 1708036721497.530, "dur": 5.182, + "args": { + "External id": 4671191,"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": 1708036721504.283, "dur": 17397.535, + "args": { + "External id": 4671192,"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": 1708036739159.385, "dur": 28.319, + "args": { + "External id": 4671193,"Sequence number": 46526445, "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": 1708036739159.385, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036739175.037, "dur": 8.050, + "args": { + "External id": 4671194,"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": 1708036739178.689, "dur": 4.136, + "args": { + "External id": 4671195,"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": 1708036739254.061, "dur": 76.018, + "args": { + "External id": 4671196,"Record function id": 0, "Ev Idx": 6515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036739331.670, "dur": 1081.894, + "args": { + "External id": 4671197,"Record function id": 0, "Ev Idx": 6516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036739372.409, "dur": 1024.496, + "args": { + "External id": 4671198,"Sequence number": 46526446, "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": 1708036739372.409, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036739434.809, "dur": 42.814, + "args": { + "External id": 4671199,"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": 1708036739489.107, "dur": 120.593, + "args": { + "External id": 4671200,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036739624.992, "dur": 38.898, + "args": { + "External id": 4671201,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036739672.049, "dur": 31.612, + "args": { + "External id": 4671202,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036739729.129, "dur": 26.442, + "args": { + "External id": 4671203,"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": 1708036739772.486, "dur": 14.868, + "args": { + "External id": 4671204,"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": 1708036739806.856, "dur": 125.365, + "args": { + "External id": 4671205,"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": 1708036739853.603, "dur": 11.907, + "args": { + "External id": 4671206,"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": 1708036739858.312, "dur": 6.423, + "args": { + "External id": 4671207,"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": 1708036739868.263, "dur": 5.451, + "args": { + "External id": 4671208,"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": 1708036739875.157, "dur": 0.867, + "args": { + "External id": 4671209,"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": 1708036739878.851, "dur": 4.312, + "args": { + "External id": 4671210,"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": 1708036739942.753, "dur": 79.608, + "args": { + "External id": 4671211,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036740063.652, "dur": 35.541, + "args": { + "External id": 4671212,"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": 1708036740109.544, "dur": 47.109, + "args": { + "External id": 4671213,"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": 1708036740164.352, "dur": 34.592, + "args": { + "External id": 4671214,"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": 1708036740224.907, "dur": 26.079, + "args": { + "External id": 4671215,"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": 1708036740256.383, "dur": 33.854, + "args": { + "External id": 4671216,"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": 1708036740308.019, "dur": 17.289, + "args": { + "External id": 4671217,"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": 1708036740479.558, "dur": 94.871, + "args": { + "External id": 4671218,"Record function id": 0, "Ev Idx": 6537 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036740652.319, "dur": 48.653, + "args": { + "External id": 4671219,"Record function id": 0, "Ev Idx": 6538 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 1336753, "tid": 1336753, + "ts": 1708036740711.036, "dur": 18949.990, + "args": { + "External id": 4671220,"Record function id": 0, "Ev Idx": 6539 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 1336753, "tid": 1336753, + "ts": 1708036740720.692, "dur": 953.877, + "args": { + "External id": 4671221,"Record function id": 0, "Ev Idx": 6540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036740802.143, "dur": 8.688, + "args": { + "External id": 4671222,"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": 1708036740824.882, "dur": 47.059, + "args": { + "External id": 4671223,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036740831.091, "dur": 2.236, + "args": { + "External id": 4671224,"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": 1708036740837.574, "dur": 0.407, + "args": { + "External id": 4671225,"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": 1708036740839.908, "dur": 0.334, + "args": { + "External id": 4671226,"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": 1708036740841.699, "dur": 0.592, + "args": { + "External id": 4671227,"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": 1708036740845.211, "dur": 0.612, + "args": { + "External id": 4671228,"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": 1708036740847.405, "dur": 0.709, + "args": { + "External id": 4671229,"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": 1708036740850.087, "dur": 4.117, + "args": { + "External id": 4671230,"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": 1708036740855.944, "dur": 6.087, + "args": { + "External id": 4671231,"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": 1708036740863.649, "dur": 0.624, + "args": { + "External id": 4671232,"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": 1708036740884.079, "dur": 42.142, + "args": { + "External id": 4671233,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036740959.571, "dur": 184.098, + "args": { + "External id": 4671234,"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": 1708036740971.695, "dur": 3.854, + "args": { + "External id": 4671235,"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": 1708036740980.478, "dur": 65.232, + "args": { + "External id": 4671236,"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": 1708036741037.255, "dur": 8.054, + "args": { + "External id": 4671237,"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": 1708036741042.044, "dur": 1.262, + "args": { + "External id": 4671238,"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": 1708036741055.987, "dur": 35.009, + "args": { + "External id": 4671239,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036741058.660, "dur": 2.450, + "args": { + "External id": 4671240,"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": 1708036741062.580, "dur": 0.310, + "args": { + "External id": 4671241,"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": 1708036741064.980, "dur": 0.773, + "args": { + "External id": 4671242,"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": 1708036741068.868, "dur": 2.348, + "args": { + "External id": 4671243,"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": 1708036741072.702, "dur": 0.571, + "args": { + "External id": 4671244,"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": 1708036741074.958, "dur": 0.374, + "args": { + "External id": 4671245,"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": 1708036741078.372, "dur": 0.547, + "args": { + "External id": 4671246,"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": 1708036741080.109, "dur": 0.325, + "args": { + "External id": 4671247,"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": 1708036741082.162, "dur": 2.099, + "args": { + "External id": 4671248,"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": 1708036741104.164, "dur": 30.285, + "args": { + "External id": 4671249,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036741199.245, "dur": 374.841, + "args": { + "External id": 4671250,"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": 1708036741232.267, "dur": 336.612, + "args": { + "External id": 4671251,"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": 1708036741243.789, "dur": 318.551, + "args": { + "External id": 4671252,"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": 1708036741599.824, "dur": 2.537, + "args": { + "External id": 4671253,"Record function id": 0, "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": 1708036741695.600, "dur": 17749.156, + "args": { + "External id": 4671254,"Record function id": 0, "Ev Idx": 6573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036741819.124, "dur": 6.691, + "args": { + "External id": 4671255,"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": 1708036741829.772, "dur": 1.504, + "args": { + "External id": 4671256,"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": 1708036741833.258, "dur": 3.101, + "args": { + "External id": 4671257,"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": 1708036741842.780, "dur": 1.276, + "args": { + "External id": 4671258,"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": 1708036741845.686, "dur": 1.306, + "args": { + "External id": 4671259,"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": 1708036741848.576, "dur": 0.962, + "args": { + "External id": 4671260,"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": 1708036741851.249, "dur": 1.425, + "args": { + "External id": 4671261,"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": 1708036741855.786, "dur": 3.634, + "args": { + "External id": 4671262,"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": 1708036741861.054, "dur": 1.272, + "args": { + "External id": 4671263,"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": 1708036741863.824, "dur": 0.825, + "args": { + "External id": 4671264,"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": 1708036741884.823, "dur": 17511.913, + "args": { + "External id": 4671265,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036741903.950, "dur": 17486.153, + "args": { + "External id": 4671266,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036741923.982, "dur": 13.653, + "args": { + "External id": 4671267,"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": 1708036741942.632, "dur": 17415.455, + "args": { + "External id": 4671268,"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": 1708036741945.120, "dur": 17412.313, + "args": { + "External id": 4671269,"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": 1708036741951.134, "dur": 4.657, + "args": { + "External id": 4671270,"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": 1708036741960.878, "dur": 17393.681, + "args": { + "External id": 4671271,"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": 1708036759605.287, "dur": 29.615, + "args": { + "External id": 4671272,"Sequence number": 46526447, "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": 1708036759605.287, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036759622.492, "dur": 7.608, + "args": { + "External id": 4671273,"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": 1708036759625.586, "dur": 4.186, + "args": { + "External id": 4671274,"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": 1708036759700.386, "dur": 75.043, + "args": { + "External id": 4671275,"Record function id": 0, "Ev Idx": 6594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036759777.414, "dur": 1079.085, + "args": { + "External id": 4671276,"Record function id": 0, "Ev Idx": 6595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036759817.729, "dur": 1025.942, + "args": { + "External id": 4671277,"Sequence number": 46526448, "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": 1708036759817.729, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036759886.201, "dur": 42.056, + "args": { + "External id": 4671278,"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": 1708036759939.733, "dur": 135.368, + "args": { + "External id": 4671279,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036760089.113, "dur": 41.031, + "args": { + "External id": 4671280,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036760139.251, "dur": 32.111, + "args": { + "External id": 4671281,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036760196.649, "dur": 27.977, + "args": { + "External id": 4671282,"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": 1708036760241.792, "dur": 14.052, + "args": { + "External id": 4671283,"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": 1708036760274.962, "dur": 138.888, + "args": { + "External id": 4671284,"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": 1708036760322.302, "dur": 13.932, + "args": { + "External id": 4671285,"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": 1708036760326.962, "dur": 8.539, + "args": { + "External id": 4671286,"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": 1708036760339.181, "dur": 6.839, + "args": { + "External id": 4671287,"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": 1708036760353.682, "dur": 1.608, + "args": { + "External id": 4671288,"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": 1708036760357.908, "dur": 4.514, + "args": { + "External id": 4671289,"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": 1708036760424.369, "dur": 42.885, + "args": { + "External id": 4671290,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036760498.925, "dur": 42.152, + "args": { + "External id": 4671291,"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": 1708036760553.388, "dur": 44.673, + "args": { + "External id": 4671292,"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": 1708036760605.550, "dur": 34.667, + "args": { + "External id": 4671293,"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": 1708036760662.495, "dur": 26.970, + "args": { + "External id": 4671294,"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": 1708036760695.332, "dur": 33.808, + "args": { + "External id": 4671295,"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": 1708036760750.938, "dur": 20.976, + "args": { + "External id": 4671296,"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": 1708036760918.526, "dur": 112.707, + "args": { + "External id": 4671297,"Record function id": 0, "Ev Idx": 6616 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036761112.906, "dur": 48.881, + "args": { + "External id": 4671298,"Record function id": 0, "Ev Idx": 6617 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 1336753, "tid": 1336753, + "ts": 1708036761171.888, "dur": 18808.133, + "args": { + "External id": 4671299,"Record function id": 0, "Ev Idx": 6618 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 1336753, "tid": 1336753, + "ts": 1708036761180.504, "dur": 947.284, + "args": { + "External id": 4671300,"Record function id": 0, "Ev Idx": 6619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036761260.705, "dur": 8.369, + "args": { + "External id": 4671301,"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": 1708036761283.676, "dur": 42.804, + "args": { + "External id": 4671302,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036761289.077, "dur": 2.288, + "args": { + "External id": 4671303,"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": 1708036761296.564, "dur": 0.551, + "args": { + "External id": 4671304,"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": 1708036761298.692, "dur": 0.456, + "args": { + "External id": 4671305,"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": 1708036761300.933, "dur": 0.559, + "args": { + "External id": 4671306,"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": 1708036761304.501, "dur": 0.507, + "args": { + "External id": 4671307,"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": 1708036761307.056, "dur": 0.447, + "args": { + "External id": 4671308,"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": 1708036761308.821, "dur": 2.951, + "args": { + "External id": 4671309,"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": 1708036761313.791, "dur": 1.001, + "args": { + "External id": 4671310,"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": 1708036761316.786, "dur": 0.748, + "args": { + "External id": 4671311,"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": 1708036761337.483, "dur": 45.131, + "args": { + "External id": 4671312,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036761417.591, "dur": 138.538, + "args": { + "External id": 4671313,"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": 1708036761429.418, "dur": 3.953, + "args": { + "External id": 4671314,"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": 1708036761438.263, "dur": 10.398, + "args": { + "External id": 4671315,"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": 1708036761442.577, "dur": 5.689, + "args": { + "External id": 4671316,"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": 1708036761446.349, "dur": 0.621, + "args": { + "External id": 4671317,"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": 1708036761455.301, "dur": 37.297, + "args": { + "External id": 4671318,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036761457.738, "dur": 2.817, + "args": { + "External id": 4671319,"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": 1708036761462.191, "dur": 0.733, + "args": { + "External id": 4671320,"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": 1708036761464.368, "dur": 0.335, + "args": { + "External id": 4671321,"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": 1708036761468.323, "dur": 2.403, + "args": { + "External id": 4671322,"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": 1708036761472.933, "dur": 0.562, + "args": { + "External id": 4671323,"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": 1708036761474.866, "dur": 0.405, + "args": { + "External id": 4671324,"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": 1708036761479.047, "dur": 0.600, + "args": { + "External id": 4671325,"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": 1708036761481.648, "dur": 0.748, + "args": { + "External id": 4671326,"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": 1708036761483.838, "dur": 2.173, + "args": { + "External id": 4671327,"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": 1708036761502.697, "dur": 43.289, + "args": { + "External id": 4671328,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036761610.977, "dur": 411.646, + "args": { + "External id": 4671329,"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": 1708036761642.017, "dur": 375.116, + "args": { + "External id": 4671330,"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": 1708036761652.924, "dur": 323.996, + "args": { + "External id": 4671331,"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": 1708036762049.687, "dur": 2.938, + "args": { + "External id": 4671332,"Record function id": 0, "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": 1708036762151.386, "dur": 17636.825, + "args": { + "External id": 4671333,"Record function id": 0, "Ev Idx": 6652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036762256.252, "dur": 7.003, + "args": { + "External id": 4671334,"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": 1708036762267.541, "dur": 1.647, + "args": { + "External id": 4671335,"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": 1708036762271.034, "dur": 3.121, + "args": { + "External id": 4671336,"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": 1708036762275.976, "dur": 0.870, + "args": { + "External id": 4671337,"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": 1708036762278.640, "dur": 0.681, + "args": { + "External id": 4671338,"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": 1708036762280.956, "dur": 1.422, + "args": { + "External id": 4671339,"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": 1708036762285.594, "dur": 0.995, + "args": { + "External id": 4671340,"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": 1708036762288.009, "dur": 3.261, + "args": { + "External id": 4671341,"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": 1708036762292.788, "dur": 0.873, + "args": { + "External id": 4671342,"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": 1708036762295.209, "dur": 0.653, + "args": { + "External id": 4671343,"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": 1708036762326.494, "dur": 17413.256, + "args": { + "External id": 4671344,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036762341.996, "dur": 17390.751, + "args": { + "External id": 4671345,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036762361.143, "dur": 13.884, + "args": { + "External id": 4671346,"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": 1708036762378.035, "dur": 17323.080, + "args": { + "External id": 4671347,"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": 1708036762380.558, "dur": 17319.868, + "args": { + "External id": 4671348,"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": 1708036762386.940, "dur": 4.894, + "args": { + "External id": 4671349,"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": 1708036762393.463, "dur": 17304.109, + "args": { + "External id": 4671350,"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": 1708036779928.049, "dur": 28.333, + "args": { + "External id": 4671351,"Sequence number": 46526449, "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": 1708036779928.049, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036779944.200, "dur": 7.761, + "args": { + "External id": 4671352,"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": 1708036779947.586, "dur": 4.146, + "args": { + "External id": 4671353,"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": 1708036780048.112, "dur": 77.282, + "args": { + "External id": 4671354,"Record function id": 0, "Ev Idx": 6673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036780127.738, "dur": 1084.353, + "args": { + "External id": 4671355,"Record function id": 0, "Ev Idx": 6674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036780170.307, "dur": 1027.818, + "args": { + "External id": 4671356,"Sequence number": 46526450, "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": 1708036780170.307, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036780235.683, "dur": 43.721, + "args": { + "External id": 4671357,"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": 1708036780292.586, "dur": 108.256, + "args": { + "External id": 4671358,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036780409.825, "dur": 41.254, + "args": { + "External id": 4671359,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036780460.566, "dur": 31.511, + "args": { + "External id": 4671360,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036780515.678, "dur": 41.059, + "args": { + "External id": 4671361,"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": 1708036780578.002, "dur": 16.291, + "args": { + "External id": 4671362,"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": 1708036780614.380, "dur": 126.430, + "args": { + "External id": 4671363,"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": 1708036780662.444, "dur": 11.708, + "args": { + "External id": 4671364,"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": 1708036780667.950, "dur": 5.525, + "args": { + "External id": 4671365,"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": 1708036780676.837, "dur": 6.533, + "args": { + "External id": 4671366,"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": 1708036780684.783, "dur": 1.127, + "args": { + "External id": 4671367,"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": 1708036780688.431, "dur": 4.271, + "args": { + "External id": 4671368,"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": 1708036780751.277, "dur": 51.440, + "args": { + "External id": 4671369,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036780835.270, "dur": 27.584, + "args": { + "External id": 4671370,"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": 1708036780871.480, "dur": 40.673, + "args": { + "External id": 4671371,"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": 1708036780920.254, "dur": 34.395, + "args": { + "External id": 4671372,"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": 1708036780976.449, "dur": 64.406, + "args": { + "External id": 4671373,"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": 1708036781048.756, "dur": 39.043, + "args": { + "External id": 4671374,"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": 1708036781109.114, "dur": 17.914, + "args": { + "External id": 4671375,"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": 1708036781276.205, "dur": 84.141, + "args": { + "External id": 4671376,"Record function id": 0, "Ev Idx": 6695 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036781439.914, "dur": 50.429, + "args": { + "External id": 4671377,"Record function id": 0, "Ev Idx": 6696 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 1336753, "tid": 1336753, + "ts": 1708036781500.306, "dur": 18866.545, + "args": { + "External id": 4671378,"Record function id": 0, "Ev Idx": 6697 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 1336753, "tid": 1336753, + "ts": 1708036781509.338, "dur": 946.681, + "args": { + "External id": 4671379,"Record function id": 0, "Ev Idx": 6698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036781609.758, "dur": 8.995, + "args": { + "External id": 4671380,"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": 1708036781633.435, "dur": 38.143, + "args": { + "External id": 4671381,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036781638.938, "dur": 2.399, + "args": { + "External id": 4671382,"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": 1708036781645.232, "dur": 0.705, + "args": { + "External id": 4671383,"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": 1708036781647.124, "dur": 0.721, + "args": { + "External id": 4671384,"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": 1708036781649.397, "dur": 0.294, + "args": { + "External id": 4671385,"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": 1708036781653.306, "dur": 0.451, + "args": { + "External id": 4671386,"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": 1708036781655.573, "dur": 0.462, + "args": { + "External id": 4671387,"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": 1708036781657.584, "dur": 2.687, + "args": { + "External id": 4671388,"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": 1708036781661.150, "dur": 0.467, + "args": { + "External id": 4671389,"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": 1708036781662.524, "dur": 0.397, + "args": { + "External id": 4671390,"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": 1708036781682.708, "dur": 42.603, + "args": { + "External id": 4671391,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036781758.898, "dur": 158.139, + "args": { + "External id": 4671392,"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": 1708036781774.410, "dur": 3.680, + "args": { + "External id": 4671393,"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": 1708036781783.339, "dur": 10.172, + "args": { + "External id": 4671394,"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": 1708036781787.829, "dur": 5.301, + "args": { + "External id": 4671395,"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": 1708036781791.102, "dur": 0.751, + "args": { + "External id": 4671396,"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": 1708036781799.739, "dur": 32.819, + "args": { + "External id": 4671397,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036781801.515, "dur": 2.076, + "args": { + "External id": 4671398,"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": 1708036781808.780, "dur": 0.606, + "args": { + "External id": 4671399,"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": 1708036781810.340, "dur": 0.697, + "args": { + "External id": 4671400,"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": 1708036781813.540, "dur": 2.498, + "args": { + "External id": 4671401,"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": 1708036781817.296, "dur": 0.494, + "args": { + "External id": 4671402,"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": 1708036781818.828, "dur": 1.425, + "args": { + "External id": 4671403,"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": 1708036781821.362, "dur": 0.454, + "args": { + "External id": 4671404,"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": 1708036781822.944, "dur": 0.467, + "args": { + "External id": 4671405,"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": 1708036781826.399, "dur": 0.485, + "args": { + "External id": 4671406,"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": 1708036781883.037, "dur": 24.806, + "args": { + "External id": 4671407,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036781970.647, "dur": 390.486, + "args": { + "External id": 4671408,"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": 1708036782034.831, "dur": 321.494, + "args": { + "External id": 4671409,"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": 1708036782048.345, "dur": 302.773, + "args": { + "External id": 4671410,"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": 1708036782384.255, "dur": 2.011, + "args": { + "External id": 4671411,"Record function id": 0, "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": 1708036782476.667, "dur": 17691.975, + "args": { + "External id": 4671412,"Record function id": 0, "Ev Idx": 6731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036782600.008, "dur": 7.019, + "args": { + "External id": 4671413,"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": 1708036782611.165, "dur": 1.212, + "args": { + "External id": 4671414,"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": 1708036782614.038, "dur": 3.357, + "args": { + "External id": 4671415,"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": 1708036782619.406, "dur": 1.218, + "args": { + "External id": 4671416,"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": 1708036782622.086, "dur": 1.123, + "args": { + "External id": 4671417,"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": 1708036782624.647, "dur": 0.792, + "args": { + "External id": 4671418,"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": 1708036782628.514, "dur": 1.150, + "args": { + "External id": 4671419,"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": 1708036782631.179, "dur": 2.848, + "args": { + "External id": 4671420,"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": 1708036782635.532, "dur": 0.751, + "args": { + "External id": 4671421,"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": 1708036782637.748, "dur": 1.055, + "args": { + "External id": 4671422,"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": 1708036782660.470, "dur": 17462.398, + "args": { + "External id": 4671423,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036782676.128, "dur": 17440.004, + "args": { + "External id": 4671424,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036782697.097, "dur": 13.608, + "args": { + "External id": 4671425,"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": 1708036782713.715, "dur": 17371.197, + "args": { + "External id": 4671426,"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": 1708036782716.466, "dur": 17367.924, + "args": { + "External id": 4671427,"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": 1708036782722.147, "dur": 6.126, + "args": { + "External id": 4671428,"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": 1708036782729.802, "dur": 17351.919, + "args": { + "External id": 4671429,"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": 1708036800309.691, "dur": 28.192, + "args": { + "External id": 4671430,"Sequence number": 46526451, "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": 1708036800309.691, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036800325.630, "dur": 7.553, + "args": { + "External id": 4671431,"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": 1708036800328.768, "dur": 4.224, + "args": { + "External id": 4671432,"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": 1708036800406.486, "dur": 72.035, + "args": { + "External id": 4671433,"Record function id": 0, "Ev Idx": 6752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036800480.249, "dur": 1085.781, + "args": { + "External id": 4671434,"Record function id": 0, "Ev Idx": 6753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036800519.733, "dur": 1032.366, + "args": { + "External id": 4671435,"Sequence number": 46526452, "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": 1708036800519.733, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036800601.060, "dur": 43.964, + "args": { + "External id": 4671436,"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": 1708036800658.117, "dur": 100.677, + "args": { + "External id": 4671437,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036800771.471, "dur": 38.527, + "args": { + "External id": 4671438,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036800817.811, "dur": 33.655, + "args": { + "External id": 4671439,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036800875.135, "dur": 25.243, + "args": { + "External id": 4671440,"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": 1708036800916.899, "dur": 13.543, + "args": { + "External id": 4671441,"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": 1708036800948.554, "dur": 168.241, + "args": { + "External id": 4671442,"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": 1708036801032.779, "dur": 12.082, + "args": { + "External id": 4671443,"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": 1708036801037.674, "dur": 6.193, + "args": { + "External id": 4671444,"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": 1708036801047.378, "dur": 5.703, + "args": { + "External id": 4671445,"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": 1708036801054.614, "dur": 1.189, + "args": { + "External id": 4671446,"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": 1708036801058.383, "dur": 5.527, + "args": { + "External id": 4671447,"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": 1708036801127.950, "dur": 50.290, + "args": { + "External id": 4671448,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036801207.808, "dur": 27.384, + "args": { + "External id": 4671449,"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": 1708036801254.274, "dur": 40.860, + "args": { + "External id": 4671450,"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": 1708036801302.658, "dur": 37.405, + "args": { + "External id": 4671451,"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": 1708036801362.472, "dur": 27.146, + "args": { + "External id": 4671452,"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": 1708036801395.119, "dur": 33.781, + "args": { + "External id": 4671453,"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": 1708036801447.336, "dur": 17.844, + "args": { + "External id": 4671454,"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": 1708036801629.859, "dur": 81.555, + "args": { + "External id": 4671455,"Record function id": 0, "Ev Idx": 6774 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036801783.532, "dur": 46.746, + "args": { + "External id": 4671456,"Record function id": 0, "Ev Idx": 6775 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 1336753, "tid": 1336753, + "ts": 1708036801840.002, "dur": 18931.681, + "args": { + "External id": 4671457,"Record function id": 0, "Ev Idx": 6776 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 1336753, "tid": 1336753, + "ts": 1708036801848.629, "dur": 1041.291, + "args": { + "External id": 4671458,"Record function id": 0, "Ev Idx": 6777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036801931.143, "dur": 8.187, + "args": { + "External id": 4671459,"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": 1708036801952.517, "dur": 71.390, + "args": { + "External id": 4671460,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036801957.738, "dur": 2.148, + "args": { + "External id": 4671461,"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": 1708036801963.947, "dur": 0.832, + "args": { + "External id": 4671462,"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": 1708036801965.781, "dur": 0.415, + "args": { + "External id": 4671463,"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": 1708036801967.162, "dur": 0.500, + "args": { + "External id": 4671464,"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": 1708036801970.476, "dur": 0.376, + "args": { + "External id": 4671465,"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": 1708036801971.895, "dur": 0.717, + "args": { + "External id": 4671466,"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": 1708036801973.588, "dur": 3.441, + "args": { + "External id": 4671467,"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": 1708036801978.124, "dur": 0.586, + "args": { + "External id": 4671468,"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": 1708036801979.539, "dur": 0.513, + "args": { + "External id": 4671469,"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": 1708036802037.201, "dur": 45.648, + "args": { + "External id": 4671470,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036802117.901, "dur": 117.468, + "args": { + "External id": 4671471,"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": 1708036802134.002, "dur": 5.196, + "args": { + "External id": 4671472,"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": 1708036802144.446, "dur": 10.551, + "args": { + "External id": 4671473,"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": 1708036802148.838, "dur": 5.772, + "args": { + "External id": 4671474,"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": 1708036802152.422, "dur": 0.802, + "args": { + "External id": 4671475,"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": 1708036802162.085, "dur": 31.169, + "args": { + "External id": 4671476,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036802163.996, "dur": 2.253, + "args": { + "External id": 4671477,"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": 1708036802167.483, "dur": 0.766, + "args": { + "External id": 4671478,"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": 1708036802169.251, "dur": 0.476, + "args": { + "External id": 4671479,"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": 1708036802172.965, "dur": 2.479, + "args": { + "External id": 4671480,"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": 1708036802177.144, "dur": 0.432, + "args": { + "External id": 4671481,"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": 1708036802179.290, "dur": 0.326, + "args": { + "External id": 4671482,"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": 1708036802182.397, "dur": 0.403, + "args": { + "External id": 4671483,"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": 1708036802184.469, "dur": 0.540, + "args": { + "External id": 4671484,"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": 1708036802186.424, "dur": 1.708, + "args": { + "External id": 4671485,"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": 1708036802204.045, "dur": 23.561, + "args": { + "External id": 4671486,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036802290.470, "dur": 497.075, + "args": { + "External id": 4671487,"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": 1708036802321.128, "dur": 460.576, + "args": { + "External id": 4671488,"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": 1708036802419.834, "dur": 353.606, + "args": { + "External id": 4671489,"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": 1708036802812.937, "dur": 2.700, + "args": { + "External id": 4671490,"Record function id": 0, "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": 1708036802910.397, "dur": 17662.233, + "args": { + "External id": 4671491,"Record function id": 0, "Ev Idx": 6810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036803054.123, "dur": 7.483, + "args": { + "External id": 4671492,"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": 1708036803065.636, "dur": 1.124, + "args": { + "External id": 4671493,"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": 1708036803068.601, "dur": 3.343, + "args": { + "External id": 4671494,"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": 1708036803074.474, "dur": 0.842, + "args": { + "External id": 4671495,"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": 1708036803076.739, "dur": 0.852, + "args": { + "External id": 4671496,"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": 1708036803079.356, "dur": 0.915, + "args": { + "External id": 4671497,"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": 1708036803083.469, "dur": 0.984, + "args": { + "External id": 4671498,"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": 1708036803085.802, "dur": 5.388, + "args": { + "External id": 4671499,"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": 1708036803092.860, "dur": 0.755, + "args": { + "External id": 4671500,"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": 1708036803095.068, "dur": 0.792, + "args": { + "External id": 4671501,"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": 1708036803116.963, "dur": 17405.128, + "args": { + "External id": 4671502,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036803133.695, "dur": 17381.660, + "args": { + "External id": 4671503,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036803152.643, "dur": 14.241, + "args": { + "External id": 4671504,"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": 1708036803169.984, "dur": 17312.314, + "args": { + "External id": 4671505,"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": 1708036803172.511, "dur": 17309.206, + "args": { + "External id": 4671506,"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": 1708036803178.171, "dur": 6.152, + "args": { + "External id": 4671507,"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": 1708036803185.803, "dur": 17293.264, + "args": { + "External id": 4671508,"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": 1708036820711.597, "dur": 35.830, + "args": { + "External id": 4671509,"Sequence number": 46526453, "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": 1708036820711.597, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036820735.330, "dur": 7.492, + "args": { + "External id": 4671510,"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": 1708036820738.523, "dur": 4.011, + "args": { + "External id": 4671511,"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": 1708036820810.519, "dur": 78.190, + "args": { + "External id": 4671512,"Record function id": 0, "Ev Idx": 6831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036820890.192, "dur": 1044.792, + "args": { + "External id": 4671513,"Record function id": 0, "Ev Idx": 6832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036820931.906, "dur": 989.153, + "args": { + "External id": 4671514,"Sequence number": 46526454, "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": 1708036820931.906, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036821024.720, "dur": 43.480, + "args": { + "External id": 4671515,"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": 1708036821082.722, "dur": 103.294, + "args": { + "External id": 4671516,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036821196.158, "dur": 37.976, + "args": { + "External id": 4671517,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036821241.720, "dur": 30.741, + "args": { + "External id": 4671518,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036821297.808, "dur": 23.875, + "args": { + "External id": 4671519,"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": 1708036821338.501, "dur": 16.715, + "args": { + "External id": 4671520,"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": 1708036821375.302, "dur": 128.880, + "args": { + "External id": 4671521,"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": 1708036821425.974, "dur": 10.253, + "args": { + "External id": 4671522,"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": 1708036821430.898, "dur": 4.442, + "args": { + "External id": 4671523,"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": 1708036821439.325, "dur": 4.813, + "args": { + "External id": 4671524,"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": 1708036821445.551, "dur": 1.361, + "args": { + "External id": 4671525,"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": 1708036821449.478, "dur": 5.660, + "args": { + "External id": 4671526,"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": 1708036821513.841, "dur": 62.074, + "args": { + "External id": 4671527,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036821607.790, "dur": 28.430, + "args": { + "External id": 4671528,"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": 1708036821646.854, "dur": 44.378, + "args": { + "External id": 4671529,"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": 1708036821698.647, "dur": 35.809, + "args": { + "External id": 4671530,"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": 1708036821755.972, "dur": 24.502, + "args": { + "External id": 4671531,"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": 1708036821785.987, "dur": 33.499, + "args": { + "External id": 4671532,"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": 1708036821837.913, "dur": 17.190, + "args": { + "External id": 4671533,"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": 1708036822030.792, "dur": 77.304, + "args": { + "External id": 4671534,"Record function id": 0, "Ev Idx": 6853 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036822187.970, "dur": 48.899, + "args": { + "External id": 4671535,"Record function id": 0, "Ev Idx": 6854 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 1336753, "tid": 1336753, + "ts": 1708036822245.557, "dur": 18857.575, + "args": { + "External id": 4671536,"Record function id": 0, "Ev Idx": 6855 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 1336753, "tid": 1336753, + "ts": 1708036822253.723, "dur": 995.178, + "args": { + "External id": 4671537,"Record function id": 0, "Ev Idx": 6856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036822340.192, "dur": 8.166, + "args": { + "External id": 4671538,"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": 1708036822362.269, "dur": 39.523, + "args": { + "External id": 4671539,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036822367.694, "dur": 2.161, + "args": { + "External id": 4671540,"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": 1708036822374.288, "dur": 0.541, + "args": { + "External id": 4671541,"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": 1708036822376.145, "dur": 0.736, + "args": { + "External id": 4671542,"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": 1708036822378.376, "dur": 0.608, + "args": { + "External id": 4671543,"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": 1708036822382.015, "dur": 0.459, + "args": { + "External id": 4671544,"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": 1708036822384.015, "dur": 0.480, + "args": { + "External id": 4671545,"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": 1708036822386.008, "dur": 4.444, + "args": { + "External id": 4671546,"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": 1708036822391.691, "dur": 0.715, + "args": { + "External id": 4671547,"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": 1708036822393.773, "dur": 0.617, + "args": { + "External id": 4671548,"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": 1708036822415.558, "dur": 47.946, + "args": { + "External id": 4671549,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036822499.580, "dur": 145.111, + "args": { + "External id": 4671550,"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": 1708036822511.835, "dur": 4.389, + "args": { + "External id": 4671551,"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": 1708036822521.460, "dur": 32.203, + "args": { + "External id": 4671552,"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": 1708036822541.820, "dur": 11.444, + "args": { + "External id": 4671553,"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": 1708036822550.422, "dur": 0.910, + "args": { + "External id": 4671554,"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": 1708036822562.373, "dur": 28.893, + "args": { + "External id": 4671555,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036822564.618, "dur": 0.594, + "args": { + "External id": 4671556,"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": 1708036822566.751, "dur": 2.368, + "args": { + "External id": 4671557,"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": 1708036822570.468, "dur": 0.385, + "args": { + "External id": 4671558,"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": 1708036822571.979, "dur": 2.405, + "args": { + "External id": 4671559,"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": 1708036822577.411, "dur": 0.288, + "args": { + "External id": 4671560,"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": 1708036822578.999, "dur": 0.240, + "args": { + "External id": 4671561,"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": 1708036822580.355, "dur": 0.373, + "args": { + "External id": 4671562,"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": 1708036822583.797, "dur": 0.374, + "args": { + "External id": 4671563,"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": 1708036822585.292, "dur": 0.287, + "args": { + "External id": 4671564,"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": 1708036822604.443, "dur": 32.120, + "args": { + "External id": 4671565,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036822699.371, "dur": 443.525, + "args": { + "External id": 4671566,"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": 1708036822727.894, "dur": 409.274, + "args": { + "External id": 4671567,"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": 1708036822738.360, "dur": 389.441, + "args": { + "External id": 4671568,"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": 1708036823168.582, "dur": 2.473, + "args": { + "External id": 4671569,"Record function id": 0, "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": 1708036823269.821, "dur": 17577.293, + "args": { + "External id": 4671570,"Record function id": 0, "Ev Idx": 6889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036823369.638, "dur": 6.709, + "args": { + "External id": 4671571,"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": 1708036823379.841, "dur": 1.612, + "args": { + "External id": 4671572,"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": 1708036823383.028, "dur": 2.786, + "args": { + "External id": 4671573,"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": 1708036823387.608, "dur": 0.841, + "args": { + "External id": 4671574,"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": 1708036823389.936, "dur": 0.733, + "args": { + "External id": 4671575,"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": 1708036823392.164, "dur": 1.045, + "args": { + "External id": 4671576,"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": 1708036823397.035, "dur": 1.200, + "args": { + "External id": 4671577,"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": 1708036823399.587, "dur": 2.542, + "args": { + "External id": 4671578,"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": 1708036823403.869, "dur": 0.850, + "args": { + "External id": 4671579,"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": 1708036823406.605, "dur": 0.943, + "args": { + "External id": 4671580,"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": 1708036823427.079, "dur": 17380.622, + "args": { + "External id": 4671581,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036823446.178, "dur": 17355.023, + "args": { + "External id": 4671582,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036823467.885, "dur": 13.971, + "args": { + "External id": 4671583,"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": 1708036823484.644, "dur": 17284.584, + "args": { + "External id": 4671584,"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": 1708036823487.288, "dur": 17281.181, + "args": { + "External id": 4671585,"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": 1708036823496.421, "dur": 5.886, + "args": { + "External id": 4671586,"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": 1708036823503.968, "dur": 17261.704, + "args": { + "External id": 4671587,"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": 1708036841032.853, "dur": 42.090, + "args": { + "External id": 4671588,"Sequence number": 46526455, "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": 1708036841032.853, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036841062.260, "dur": 7.725, + "args": { + "External id": 4671589,"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": 1708036841065.295, "dur": 4.335, + "args": { + "External id": 4671590,"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": 1708036841143.749, "dur": 77.596, + "args": { + "External id": 4671591,"Record function id": 0, "Ev Idx": 6910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036841222.768, "dur": 1068.435, + "args": { + "External id": 4671592,"Record function id": 0, "Ev Idx": 6911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036841263.039, "dur": 1011.254, + "args": { + "External id": 4671593,"Sequence number": 46526456, "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": 1708036841263.039, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036841329.574, "dur": 44.062, + "args": { + "External id": 4671594,"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": 1708036841385.475, "dur": 111.515, + "args": { + "External id": 4671595,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036841505.530, "dur": 54.537, + "args": { + "External id": 4671596,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036841570.451, "dur": 34.532, + "args": { + "External id": 4671597,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036841631.068, "dur": 24.583, + "args": { + "External id": 4671598,"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": 1708036841673.408, "dur": 14.044, + "args": { + "External id": 4671599,"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": 1708036841705.826, "dur": 127.455, + "args": { + "External id": 4671600,"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": 1708036841753.914, "dur": 10.438, + "args": { + "External id": 4671601,"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": 1708036841758.788, "dur": 4.861, + "args": { + "External id": 4671602,"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": 1708036841767.036, "dur": 5.429, + "args": { + "External id": 4671603,"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": 1708036841773.802, "dur": 1.161, + "args": { + "External id": 4671604,"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": 1708036841777.247, "dur": 5.943, + "args": { + "External id": 4671605,"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": 1708036841843.596, "dur": 47.586, + "args": { + "External id": 4671606,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036841916.603, "dur": 27.557, + "args": { + "External id": 4671607,"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": 1708036841953.141, "dur": 76.128, + "args": { + "External id": 4671608,"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": 1708036842042.572, "dur": 38.767, + "args": { + "External id": 4671609,"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": 1708036842103.946, "dur": 28.061, + "args": { + "External id": 4671610,"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": 1708036842137.947, "dur": 33.809, + "args": { + "External id": 4671611,"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": 1708036842191.049, "dur": 16.924, + "args": { + "External id": 4671612,"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": 1708036842356.754, "dur": 77.329, + "args": { + "External id": 4671613,"Record function id": 0, "Ev Idx": 6932 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036842512.227, "dur": 66.600, + "args": { + "External id": 4671614,"Record function id": 0, "Ev Idx": 6933 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 1336753, "tid": 1336753, + "ts": 1708036842590.655, "dur": 18988.679, + "args": { + "External id": 4671615,"Record function id": 0, "Ev Idx": 6934 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 1336753, "tid": 1336753, + "ts": 1708036842598.771, "dur": 901.343, + "args": { + "External id": 4671616,"Record function id": 0, "Ev Idx": 6935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036842686.760, "dur": 8.707, + "args": { + "External id": 4671617,"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": 1708036842711.433, "dur": 39.533, + "args": { + "External id": 4671618,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036842717.128, "dur": 2.342, + "args": { + "External id": 4671619,"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": 1708036842726.283, "dur": 0.622, + "args": { + "External id": 4671620,"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": 1708036842728.181, "dur": 0.695, + "args": { + "External id": 4671621,"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": 1708036842730.351, "dur": 2.228, + "args": { + "External id": 4671622,"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": 1708036842733.758, "dur": 0.339, + "args": { + "External id": 4671623,"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": 1708036842735.762, "dur": 0.352, + "args": { + "External id": 4671624,"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": 1708036842738.937, "dur": 1.762, + "args": { + "External id": 4671625,"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": 1708036842742.136, "dur": 0.401, + "args": { + "External id": 4671626,"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": 1708036842743.563, "dur": 0.445, + "args": { + "External id": 4671627,"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": 1708036842761.701, "dur": 44.288, + "args": { + "External id": 4671628,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036842837.992, "dur": 108.318, + "args": { + "External id": 4671629,"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": 1708036842850.124, "dur": 3.905, + "args": { + "External id": 4671630,"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": 1708036842859.416, "dur": 11.909, + "args": { + "External id": 4671631,"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": 1708036842863.649, "dur": 7.259, + "args": { + "External id": 4671632,"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": 1708036842867.530, "dur": 2.213, + "args": { + "External id": 4671633,"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": 1708036842878.325, "dur": 27.669, + "args": { + "External id": 4671634,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036842880.175, "dur": 0.474, + "args": { + "External id": 4671635,"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": 1708036842882.244, "dur": 0.722, + "args": { + "External id": 4671636,"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": 1708036842884.039, "dur": 0.570, + "args": { + "External id": 4671637,"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": 1708036842887.341, "dur": 2.032, + "args": { + "External id": 4671638,"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": 1708036842890.786, "dur": 0.249, + "args": { + "External id": 4671639,"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": 1708036842892.739, "dur": 2.114, + "args": { + "External id": 4671640,"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": 1708036842895.974, "dur": 0.275, + "args": { + "External id": 4671641,"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": 1708036842897.604, "dur": 0.296, + "args": { + "External id": 4671642,"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": 1708036842900.770, "dur": 0.306, + "args": { + "External id": 4671643,"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": 1708036842916.532, "dur": 22.205, + "args": { + "External id": 4671644,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036843036.492, "dur": 367.564, + "args": { + "External id": 4671645,"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": 1708036843066.145, "dur": 333.320, + "args": { + "External id": 4671646,"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": 1708036843078.173, "dur": 315.368, + "args": { + "External id": 4671647,"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": 1708036843429.786, "dur": 2.259, + "args": { + "External id": 4671648,"Record function id": 0, "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": 1708036843520.735, "dur": 17845.089, + "args": { + "External id": 4671649,"Record function id": 0, "Ev Idx": 6968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036843647.971, "dur": 6.859, + "args": { + "External id": 4671650,"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": 1708036843658.114, "dur": 1.470, + "args": { + "External id": 4671651,"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": 1708036843661.487, "dur": 3.264, + "args": { + "External id": 4671652,"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": 1708036843666.439, "dur": 1.042, + "args": { + "External id": 4671653,"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": 1708036843668.972, "dur": 0.734, + "args": { + "External id": 4671654,"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": 1708036843670.929, "dur": 0.832, + "args": { + "External id": 4671655,"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": 1708036843675.274, "dur": 0.916, + "args": { + "External id": 4671656,"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": 1708036843677.615, "dur": 2.365, + "args": { + "External id": 4671657,"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": 1708036843681.474, "dur": 1.126, + "args": { + "External id": 4671658,"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": 1708036843684.274, "dur": 1.025, + "args": { + "External id": 4671659,"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": 1708036843705.696, "dur": 17622.291, + "args": { + "External id": 4671660,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036843722.584, "dur": 17599.097, + "args": { + "External id": 4671661,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036843745.347, "dur": 13.640, + "args": { + "External id": 4671662,"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": 1708036843761.834, "dur": 17528.123, + "args": { + "External id": 4671663,"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": 1708036843764.340, "dur": 17525.117, + "args": { + "External id": 4671664,"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": 1708036843770.671, "dur": 6.663, + "args": { + "External id": 4671665,"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": 1708036843778.825, "dur": 17507.811, + "args": { + "External id": 4671666,"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": 1708036861503.626, "dur": 49.178, + "args": { + "External id": 4671667,"Sequence number": 46526457, "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": 1708036861503.626, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036861539.991, "dur": 7.827, + "args": { + "External id": 4671668,"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": 1708036861543.179, "dur": 4.357, + "args": { + "External id": 4671669,"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": 1708036861619.786, "dur": 79.187, + "args": { + "External id": 4671670,"Record function id": 0, "Ev Idx": 6989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036861700.625, "dur": 1084.372, + "args": { + "External id": 4671671,"Record function id": 0, "Ev Idx": 6990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036861744.625, "dur": 1027.152, + "args": { + "External id": 4671672,"Sequence number": 46526458, "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": 1708036861744.625, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036861808.609, "dur": 43.727, + "args": { + "External id": 4671673,"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": 1708036861865.769, "dur": 102.231, + "args": { + "External id": 4671674,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036861977.816, "dur": 80.047, + "args": { + "External id": 4671675,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036862069.054, "dur": 32.271, + "args": { + "External id": 4671676,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036862126.734, "dur": 24.735, + "args": { + "External id": 4671677,"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": 1708036862167.270, "dur": 14.499, + "args": { + "External id": 4671678,"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": 1708036862200.687, "dur": 126.037, + "args": { + "External id": 4671679,"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": 1708036862248.106, "dur": 11.265, + "args": { + "External id": 4671680,"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": 1708036862253.393, "dur": 5.280, + "args": { + "External id": 4671681,"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": 1708036862262.102, "dur": 5.647, + "args": { + "External id": 4671682,"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": 1708036862269.203, "dur": 1.110, + "args": { + "External id": 4671683,"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": 1708036862272.777, "dur": 5.817, + "args": { + "External id": 4671684,"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": 1708036862336.556, "dur": 42.534, + "args": { + "External id": 4671685,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036862407.352, "dur": 29.242, + "args": { + "External id": 4671686,"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": 1708036862446.523, "dur": 42.224, + "args": { + "External id": 4671687,"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": 1708036862495.364, "dur": 53.138, + "args": { + "External id": 4671688,"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": 1708036862589.173, "dur": 33.133, + "args": { + "External id": 4671689,"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": 1708036862630.593, "dur": 38.308, + "args": { + "External id": 4671690,"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": 1708036862685.843, "dur": 17.355, + "args": { + "External id": 4671691,"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": 1708036862851.031, "dur": 80.142, + "args": { + "External id": 4671692,"Record function id": 0, "Ev Idx": 7011 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036863046.360, "dur": 50.017, + "args": { + "External id": 4671693,"Record function id": 0, "Ev Idx": 7012 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 1336753, "tid": 1336753, + "ts": 1708036863107.158, "dur": 18992.395, + "args": { + "External id": 4671694,"Record function id": 0, "Ev Idx": 7013 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 1336753, "tid": 1336753, + "ts": 1708036863115.800, "dur": 851.799, + "args": { + "External id": 4671695,"Record function id": 0, "Ev Idx": 7014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036863196.046, "dur": 9.225, + "args": { + "External id": 4671696,"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": 1708036863219.077, "dur": 37.526, + "args": { + "External id": 4671697,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036863224.972, "dur": 2.353, + "args": { + "External id": 4671698,"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": 1708036863231.697, "dur": 0.678, + "args": { + "External id": 4671699,"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": 1708036863233.654, "dur": 0.555, + "args": { + "External id": 4671700,"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": 1708036863235.572, "dur": 0.516, + "args": { + "External id": 4671701,"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": 1708036863239.044, "dur": 0.807, + "args": { + "External id": 4671702,"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": 1708036863241.128, "dur": 0.285, + "args": { + "External id": 4671703,"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": 1708036863242.697, "dur": 3.621, + "args": { + "External id": 4671704,"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": 1708036863247.766, "dur": 0.512, + "args": { + "External id": 4671705,"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": 1708036863249.459, "dur": 0.252, + "args": { + "External id": 4671706,"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": 1708036863268.345, "dur": 39.827, + "args": { + "External id": 4671707,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036863340.802, "dur": 112.671, + "args": { + "External id": 4671708,"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": 1708036863352.240, "dur": 3.619, + "args": { + "External id": 4671709,"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": 1708036863361.085, "dur": 9.995, + "args": { + "External id": 4671710,"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": 1708036863365.482, "dur": 5.168, + "args": { + "External id": 4671711,"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": 1708036863368.871, "dur": 0.550, + "args": { + "External id": 4671712,"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": 1708036863378.463, "dur": 31.206, + "args": { + "External id": 4671713,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036863380.818, "dur": 1.966, + "args": { + "External id": 4671714,"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": 1708036863384.813, "dur": 0.550, + "args": { + "External id": 4671715,"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": 1708036863387.107, "dur": 0.408, + "args": { + "External id": 4671716,"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": 1708036863390.744, "dur": 2.443, + "args": { + "External id": 4671717,"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": 1708036863394.375, "dur": 0.854, + "args": { + "External id": 4671718,"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": 1708036863396.524, "dur": 0.319, + "args": { + "External id": 4671719,"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": 1708036863399.443, "dur": 0.419, + "args": { + "External id": 4671720,"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": 1708036863401.050, "dur": 0.265, + "args": { + "External id": 4671721,"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": 1708036863402.613, "dur": 2.174, + "args": { + "External id": 4671722,"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": 1708036863421.569, "dur": 23.778, + "args": { + "External id": 4671723,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036863507.273, "dur": 368.949, + "args": { + "External id": 4671724,"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": 1708036863556.997, "dur": 314.222, + "args": { + "External id": 4671725,"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": 1708036863569.287, "dur": 296.684, + "args": { + "External id": 4671726,"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": 1708036863899.276, "dur": 2.092, + "args": { + "External id": 4671727,"Record function id": 0, "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": 1708036864026.019, "dur": 17833.241, + "args": { + "External id": 4671728,"Record function id": 0, "Ev Idx": 7047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036864128.391, "dur": 6.773, + "args": { + "External id": 4671729,"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": 1708036864138.663, "dur": 1.095, + "args": { + "External id": 4671730,"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": 1708036864141.457, "dur": 3.143, + "args": { + "External id": 4671731,"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": 1708036864146.234, "dur": 1.070, + "args": { + "External id": 4671732,"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": 1708036864148.780, "dur": 0.745, + "args": { + "External id": 4671733,"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": 1708036864150.692, "dur": 1.198, + "args": { + "External id": 4671734,"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": 1708036864155.280, "dur": 0.944, + "args": { + "External id": 4671735,"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": 1708036864157.806, "dur": 2.030, + "args": { + "External id": 4671736,"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": 1708036864161.320, "dur": 0.692, + "args": { + "External id": 4671737,"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": 1708036864163.553, "dur": 0.802, + "args": { + "External id": 4671738,"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": 1708036864183.876, "dur": 17635.633, + "args": { + "External id": 4671739,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036864200.713, "dur": 17612.088, + "args": { + "External id": 4671740,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036864224.851, "dur": 15.153, + "args": { + "External id": 4671741,"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": 1708036864243.037, "dur": 17538.843, + "args": { + "External id": 4671742,"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": 1708036864245.615, "dur": 17535.633, + "args": { + "External id": 4671743,"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": 1708036864251.288, "dur": 4.519, + "args": { + "External id": 4671744,"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": 1708036864257.373, "dur": 17521.061, + "args": { + "External id": 4671745,"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": 1708036882032.721, "dur": 39.985, + "args": { + "External id": 4671746,"Sequence number": 46526459, "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": 1708036882032.721, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036882059.723, "dur": 8.148, + "args": { + "External id": 4671747,"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": 1708036882062.952, "dur": 4.595, + "args": { + "External id": 4671748,"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": 1708036882139.360, "dur": 76.612, + "args": { + "External id": 4671749,"Record function id": 0, "Ev Idx": 7068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036882217.391, "dur": 1069.280, + "args": { + "External id": 4671750,"Record function id": 0, "Ev Idx": 7069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036882256.942, "dur": 1016.790, + "args": { + "External id": 4671751,"Sequence number": 46526460, "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": 1708036882256.942, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036882321.648, "dur": 42.805, + "args": { + "External id": 4671752,"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": 1708036882376.028, "dur": 106.159, + "args": { + "External id": 4671753,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036882492.854, "dur": 56.196, + "args": { + "External id": 4671754,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036882559.613, "dur": 35.107, + "args": { + "External id": 4671755,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036882619.304, "dur": 29.995, + "args": { + "External id": 4671756,"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": 1708036882667.117, "dur": 16.823, + "args": { + "External id": 4671757,"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": 1708036882702.583, "dur": 125.188, + "args": { + "External id": 4671758,"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": 1708036882752.083, "dur": 10.204, + "args": { + "External id": 4671759,"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": 1708036882756.986, "dur": 4.547, + "args": { + "External id": 4671760,"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": 1708036882765.138, "dur": 5.147, + "args": { + "External id": 4671761,"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": 1708036882771.733, "dur": 1.049, + "args": { + "External id": 4671762,"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": 1708036882775.358, "dur": 4.505, + "args": { + "External id": 4671763,"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": 1708036882838.571, "dur": 44.409, + "args": { + "External id": 4671764,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036882910.573, "dur": 30.636, + "args": { + "External id": 4671765,"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": 1708036882949.658, "dur": 78.168, + "args": { + "External id": 4671766,"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": 1708036883039.604, "dur": 39.877, + "args": { + "External id": 4671767,"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": 1708036883102.825, "dur": 28.356, + "args": { + "External id": 4671768,"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": 1708036883137.049, "dur": 33.379, + "args": { + "External id": 4671769,"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": 1708036883188.640, "dur": 16.856, + "args": { + "External id": 4671770,"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": 1708036883347.359, "dur": 72.193, + "args": { + "External id": 4671771,"Record function id": 0, "Ev Idx": 7090 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036883491.192, "dur": 63.677, + "args": { + "External id": 4671772,"Record function id": 0, "Ev Idx": 7091 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 1336753, "tid": 1336753, + "ts": 1708036883566.005, "dur": 18983.084, + "args": { + "External id": 4671773,"Record function id": 0, "Ev Idx": 7092 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 1336753, "tid": 1336753, + "ts": 1708036883575.395, "dur": 925.034, + "args": { + "External id": 4671774,"Record function id": 0, "Ev Idx": 7093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036883655.501, "dur": 11.875, + "args": { + "External id": 4671775,"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": 1708036883681.792, "dur": 62.818, + "args": { + "External id": 4671776,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036883706.288, "dur": 2.467, + "args": { + "External id": 4671777,"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": 1708036883712.911, "dur": 0.369, + "args": { + "External id": 4671778,"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": 1708036883714.559, "dur": 0.364, + "args": { + "External id": 4671779,"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": 1708036883719.545, "dur": 2.469, + "args": { + "External id": 4671780,"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": 1708036883723.663, "dur": 0.322, + "args": { + "External id": 4671781,"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": 1708036883726.723, "dur": 0.623, + "args": { + "External id": 4671782,"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": 1708036883730.094, "dur": 1.914, + "args": { + "External id": 4671783,"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": 1708036883733.095, "dur": 0.388, + "args": { + "External id": 4671784,"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": 1708036883735.048, "dur": 1.023, + "args": { + "External id": 4671785,"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": 1708036883756.024, "dur": 45.812, + "args": { + "External id": 4671786,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036883837.720, "dur": 108.269, + "args": { + "External id": 4671787,"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": 1708036883849.854, "dur": 4.050, + "args": { + "External id": 4671788,"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": 1708036883859.186, "dur": 10.334, + "args": { + "External id": 4671789,"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": 1708036883863.696, "dur": 5.408, + "args": { + "External id": 4671790,"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": 1708036883867.355, "dur": 0.498, + "args": { + "External id": 4671791,"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": 1708036883876.422, "dur": 29.389, + "args": { + "External id": 4671792,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036883879.205, "dur": 0.479, + "args": { + "External id": 4671793,"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": 1708036883881.315, "dur": 0.524, + "args": { + "External id": 4671794,"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": 1708036883883.264, "dur": 2.201, + "args": { + "External id": 4671795,"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": 1708036883886.671, "dur": 2.459, + "args": { + "External id": 4671796,"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": 1708036883890.506, "dur": 0.641, + "args": { + "External id": 4671797,"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": 1708036883893.951, "dur": 0.377, + "args": { + "External id": 4671798,"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": 1708036883895.500, "dur": 0.304, + "args": { + "External id": 4671799,"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": 1708036883897.210, "dur": 0.550, + "args": { + "External id": 4671800,"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": 1708036883900.359, "dur": 0.313, + "args": { + "External id": 4671801,"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": 1708036883916.114, "dur": 22.068, + "args": { + "External id": 4671802,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036884034.876, "dur": 366.408, + "args": { + "External id": 4671803,"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": 1708036884066.558, "dur": 329.676, + "args": { + "External id": 4671804,"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": 1708036884077.139, "dur": 313.363, + "args": { + "External id": 4671805,"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": 1708036884424.911, "dur": 2.249, + "args": { + "External id": 4671806,"Record function id": 0, "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": 1708036884521.460, "dur": 17815.122, + "args": { + "External id": 4671807,"Record function id": 0, "Ev Idx": 7126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036884636.038, "dur": 6.746, + "args": { + "External id": 4671808,"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": 1708036884645.992, "dur": 1.011, + "args": { + "External id": 4671809,"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": 1708036884648.464, "dur": 3.006, + "args": { + "External id": 4671810,"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": 1708036884653.034, "dur": 1.088, + "args": { + "External id": 4671811,"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": 1708036884655.825, "dur": 0.865, + "args": { + "External id": 4671812,"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": 1708036884658.033, "dur": 1.092, + "args": { + "External id": 4671813,"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": 1708036884662.307, "dur": 0.807, + "args": { + "External id": 4671814,"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": 1708036884664.481, "dur": 2.042, + "args": { + "External id": 4671815,"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": 1708036884668.001, "dur": 0.813, + "args": { + "External id": 4671816,"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": 1708036884670.164, "dur": 0.739, + "args": { + "External id": 4671817,"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": 1708036884695.016, "dur": 17603.072, + "args": { + "External id": 4671818,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036884709.572, "dur": 17581.587, + "args": { + "External id": 4671819,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036884733.489, "dur": 17.354, + "args": { + "External id": 4671820,"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": 1708036884753.569, "dur": 17502.373, + "args": { + "External id": 4671821,"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": 1708036884756.125, "dur": 17499.089, + "args": { + "External id": 4671822,"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": 1708036884761.872, "dur": 6.510, + "args": { + "External id": 4671823,"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": 1708036884769.959, "dur": 17482.329, + "args": { + "External id": 4671824,"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": 1708036902474.610, "dur": 35.309, + "args": { + "External id": 4671825,"Sequence number": 46526461, "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": 1708036902474.610, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036902497.981, "dur": 7.386, + "args": { + "External id": 4671826,"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": 1708036902501.165, "dur": 3.997, + "args": { + "External id": 4671827,"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": 1708036902588.847, "dur": 75.752, + "args": { + "External id": 4671828,"Record function id": 0, "Ev Idx": 7147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036902666.042, "dur": 1097.883, + "args": { + "External id": 4671829,"Record function id": 0, "Ev Idx": 7148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036902710.726, "dur": 1039.661, + "args": { + "External id": 4671830,"Sequence number": 46526462, "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": 1708036902710.726, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036902777.609, "dur": 45.801, + "args": { + "External id": 4671831,"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": 1708036902836.316, "dur": 104.268, + "args": { + "External id": 4671832,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036902949.740, "dur": 73.050, + "args": { + "External id": 4671833,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036903035.025, "dur": 35.889, + "args": { + "External id": 4671834,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036903097.029, "dur": 26.556, + "args": { + "External id": 4671835,"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": 1708036903140.168, "dur": 16.929, + "args": { + "External id": 4671836,"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": 1708036903176.708, "dur": 149.439, + "args": { + "External id": 4671837,"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": 1708036903243.318, "dur": 10.862, + "args": { + "External id": 4671838,"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": 1708036903248.707, "dur": 4.818, + "args": { + "External id": 4671839,"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": 1708036903257.100, "dur": 7.431, + "args": { + "External id": 4671840,"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": 1708036903265.668, "dur": 0.815, + "args": { + "External id": 4671841,"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": 1708036903269.053, "dur": 4.435, + "args": { + "External id": 4671842,"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": 1708036903336.642, "dur": 49.291, + "args": { + "External id": 4671843,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036903415.878, "dur": 28.970, + "args": { + "External id": 4671844,"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": 1708036903454.319, "dur": 41.482, + "args": { + "External id": 4671845,"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": 1708036903503.768, "dur": 50.785, + "args": { + "External id": 4671846,"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": 1708036903578.956, "dur": 26.682, + "args": { + "External id": 4671847,"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": 1708036903612.029, "dur": 37.328, + "args": { + "External id": 4671848,"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": 1708036903669.698, "dur": 16.487, + "args": { + "External id": 4671849,"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": 1708036903827.460, "dur": 78.373, + "args": { + "External id": 4671850,"Record function id": 0, "Ev Idx": 7169 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036904019.257, "dur": 55.483, + "args": { + "External id": 4671851,"Record function id": 0, "Ev Idx": 7170 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 1336753, "tid": 1336753, + "ts": 1708036904085.669, "dur": 18881.747, + "args": { + "External id": 4671852,"Record function id": 0, "Ev Idx": 7171 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 1336753, "tid": 1336753, + "ts": 1708036904094.016, "dur": 878.598, + "args": { + "External id": 4671853,"Record function id": 0, "Ev Idx": 7172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036904172.778, "dur": 8.984, + "args": { + "External id": 4671854,"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": 1708036904195.791, "dur": 36.822, + "args": { + "External id": 4671855,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036904201.435, "dur": 2.145, + "args": { + "External id": 4671856,"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": 1708036904208.263, "dur": 0.453, + "args": { + "External id": 4671857,"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": 1708036904210.220, "dur": 0.363, + "args": { + "External id": 4671858,"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": 1708036904212.109, "dur": 0.603, + "args": { + "External id": 4671859,"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": 1708036904215.591, "dur": 0.495, + "args": { + "External id": 4671860,"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": 1708036904217.936, "dur": 0.404, + "args": { + "External id": 4671861,"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": 1708036904219.532, "dur": 2.331, + "args": { + "External id": 4671862,"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": 1708036904223.295, "dur": 0.391, + "args": { + "External id": 4671863,"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": 1708036904224.999, "dur": 0.481, + "args": { + "External id": 4671864,"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": 1708036904243.998, "dur": 39.288, + "args": { + "External id": 4671865,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036904316.088, "dur": 156.543, + "args": { + "External id": 4671866,"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": 1708036904326.675, "dur": 3.795, + "args": { + "External id": 4671867,"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": 1708036904335.670, "dur": 10.471, + "args": { + "External id": 4671868,"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": 1708036904340.369, "dur": 5.401, + "args": { + "External id": 4671869,"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": 1708036904343.990, "dur": 0.649, + "args": { + "External id": 4671870,"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": 1708036904353.119, "dur": 30.835, + "args": { + "External id": 4671871,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036904355.134, "dur": 2.396, + "args": { + "External id": 4671872,"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": 1708036904359.020, "dur": 0.550, + "args": { + "External id": 4671873,"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": 1708036904360.763, "dur": 0.607, + "args": { + "External id": 4671874,"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": 1708036904364.963, "dur": 2.251, + "args": { + "External id": 4671875,"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": 1708036904368.563, "dur": 0.501, + "args": { + "External id": 4671876,"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": 1708036904370.505, "dur": 0.487, + "args": { + "External id": 4671877,"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": 1708036904374.007, "dur": 0.549, + "args": { + "External id": 4671878,"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": 1708036904375.953, "dur": 0.343, + "args": { + "External id": 4671879,"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": 1708036904377.507, "dur": 1.740, + "args": { + "External id": 4671880,"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": 1708036904436.991, "dur": 24.090, + "args": { + "External id": 4671881,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036904543.280, "dur": 338.427, + "args": { + "External id": 4671882,"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": 1708036904574.962, "dur": 302.098, + "args": { + "External id": 4671883,"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": 1708036904586.915, "dur": 285.117, + "args": { + "External id": 4671884,"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": 1708036904903.752, "dur": 2.209, + "args": { + "External id": 4671885,"Record function id": 0, "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": 1708036905031.612, "dur": 17735.122, + "args": { + "External id": 4671886,"Record function id": 0, "Ev Idx": 7205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036905139.148, "dur": 6.938, + "args": { + "External id": 4671887,"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": 1708036905149.753, "dur": 1.399, + "args": { + "External id": 4671888,"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": 1708036905152.768, "dur": 3.310, + "args": { + "External id": 4671889,"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": 1708036905157.953, "dur": 1.039, + "args": { + "External id": 4671890,"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": 1708036905160.408, "dur": 1.077, + "args": { + "External id": 4671891,"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": 1708036905162.852, "dur": 1.034, + "args": { + "External id": 4671892,"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": 1708036905167.109, "dur": 1.082, + "args": { + "External id": 4671893,"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": 1708036905169.869, "dur": 2.100, + "args": { + "External id": 4671894,"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": 1708036905173.511, "dur": 1.173, + "args": { + "External id": 4671895,"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": 1708036905176.447, "dur": 0.957, + "args": { + "External id": 4671896,"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": 1708036905200.598, "dur": 17526.028, + "args": { + "External id": 4671897,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036905215.547, "dur": 17504.221, + "args": { + "External id": 4671898,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036905237.338, "dur": 17.833, + "args": { + "External id": 4671899,"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": 1708036905258.243, "dur": 17430.343, + "args": { + "External id": 4671900,"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": 1708036905261.195, "dur": 17426.853, + "args": { + "External id": 4671901,"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": 1708036905267.785, "dur": 5.380, + "args": { + "External id": 4671902,"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": 1708036905274.767, "dur": 17410.359, + "args": { + "External id": 4671903,"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": 1708036922905.540, "dur": 35.602, + "args": { + "External id": 4671904,"Sequence number": 46526463, "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": 1708036922905.540, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036922929.329, "dur": 7.546, + "args": { + "External id": 4671905,"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": 1708036922932.480, "dur": 4.160, + "args": { + "External id": 4671906,"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": 1708036923038.751, "dur": 80.289, + "args": { + "External id": 4671907,"Record function id": 0, "Ev Idx": 7226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036923121.130, "dur": 1079.536, + "args": { + "External id": 4671908,"Record function id": 0, "Ev Idx": 7227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036923165.735, "dur": 1020.441, + "args": { + "External id": 4671909,"Sequence number": 46526464, "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": 1708036923165.735, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036923232.143, "dur": 43.837, + "args": { + "External id": 4671910,"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": 1708036923287.917, "dur": 104.474, + "args": { + "External id": 4671911,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036923402.378, "dur": 38.774, + "args": { + "External id": 4671912,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036923449.572, "dur": 31.189, + "args": { + "External id": 4671913,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036923504.601, "dur": 44.197, + "args": { + "External id": 4671914,"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": 1708036923569.707, "dur": 15.538, + "args": { + "External id": 4671915,"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": 1708036923604.010, "dur": 126.953, + "args": { + "External id": 4671916,"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": 1708036923652.255, "dur": 11.964, + "args": { + "External id": 4671917,"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": 1708036923657.744, "dur": 5.824, + "args": { + "External id": 4671918,"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": 1708036923667.068, "dur": 6.283, + "args": { + "External id": 4671919,"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": 1708036923674.655, "dur": 1.373, + "args": { + "External id": 4671920,"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": 1708036923678.301, "dur": 4.367, + "args": { + "External id": 4671921,"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": 1708036923741.109, "dur": 46.910, + "args": { + "External id": 4671922,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036923817.178, "dur": 27.447, + "args": { + "External id": 4671923,"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": 1708036923853.358, "dur": 39.840, + "args": { + "External id": 4671924,"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": 1708036923901.374, "dur": 35.149, + "args": { + "External id": 4671925,"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": 1708036923959.077, "dur": 66.103, + "args": { + "External id": 4671926,"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": 1708036924032.857, "dur": 41.196, + "args": { + "External id": 4671927,"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": 1708036924094.447, "dur": 18.981, + "args": { + "External id": 4671928,"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": 1708036924268.301, "dur": 74.290, + "args": { + "External id": 4671929,"Record function id": 0, "Ev Idx": 7248 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036924417.435, "dur": 48.875, + "args": { + "External id": 4671930,"Record function id": 0, "Ev Idx": 7249 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 1336753, "tid": 1336753, + "ts": 1708036924476.589, "dur": 18831.813, + "args": { + "External id": 4671931,"Record function id": 0, "Ev Idx": 7250 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 1336753, "tid": 1336753, + "ts": 1708036924484.886, "dur": 971.044, + "args": { + "External id": 4671932,"Record function id": 0, "Ev Idx": 7251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036924583.264, "dur": 9.085, + "args": { + "External id": 4671933,"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": 1708036924607.259, "dur": 35.282, + "args": { + "External id": 4671934,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036924612.782, "dur": 2.260, + "args": { + "External id": 4671935,"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": 1708036924619.118, "dur": 0.355, + "args": { + "External id": 4671936,"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": 1708036924621.336, "dur": 0.338, + "args": { + "External id": 4671937,"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": 1708036924623.097, "dur": 0.396, + "args": { + "External id": 4671938,"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": 1708036924626.326, "dur": 0.491, + "args": { + "External id": 4671939,"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": 1708036924627.980, "dur": 0.544, + "args": { + "External id": 4671940,"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": 1708036924629.848, "dur": 2.185, + "args": { + "External id": 4671941,"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": 1708036924633.428, "dur": 0.637, + "args": { + "External id": 4671942,"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": 1708036924635.637, "dur": 0.148, + "args": { + "External id": 4671943,"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": 1708036924658.205, "dur": 43.161, + "args": { + "External id": 4671944,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036924734.498, "dur": 108.120, + "args": { + "External id": 4671945,"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": 1708036924748.062, "dur": 5.507, + "args": { + "External id": 4671946,"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": 1708036924758.652, "dur": 10.230, + "args": { + "External id": 4671947,"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": 1708036924763.019, "dur": 5.459, + "args": { + "External id": 4671948,"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": 1708036924766.561, "dur": 0.762, + "args": { + "External id": 4671949,"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": 1708036924775.976, "dur": 26.636, + "args": { + "External id": 4671950,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036924778.646, "dur": 0.259, + "args": { + "External id": 4671951,"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": 1708036924780.223, "dur": 1.990, + "args": { + "External id": 4671952,"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": 1708036924783.712, "dur": 0.357, + "args": { + "External id": 4671953,"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": 1708036924785.762, "dur": 1.723, + "args": { + "External id": 4671954,"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": 1708036924790.469, "dur": 0.314, + "args": { + "External id": 4671955,"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": 1708036924792.253, "dur": 0.289, + "args": { + "External id": 4671956,"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": 1708036924793.665, "dur": 0.352, + "args": { + "External id": 4671957,"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": 1708036924796.640, "dur": 0.259, + "args": { + "External id": 4671958,"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": 1708036924797.972, "dur": 0.150, + "args": { + "External id": 4671959,"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": 1708036924813.653, "dur": 21.705, + "args": { + "External id": 4671960,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036924893.143, "dur": 458.332, + "args": { + "External id": 4671961,"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": 1708036924924.262, "dur": 421.383, + "args": { + "External id": 4671962,"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": 1708036924933.804, "dur": 402.034, + "args": { + "External id": 4671963,"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": 1708036925378.104, "dur": 2.478, + "args": { + "External id": 4671964,"Record function id": 0, "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": 1708036925476.969, "dur": 17617.519, + "args": { + "External id": 4671965,"Record function id": 0, "Ev Idx": 7284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036925600.497, "dur": 7.020, + "args": { + "External id": 4671966,"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": 1708036925611.383, "dur": 1.131, + "args": { + "External id": 4671967,"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": 1708036925614.113, "dur": 2.351, + "args": { + "External id": 4671968,"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": 1708036925618.173, "dur": 0.809, + "args": { + "External id": 4671969,"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": 1708036925620.542, "dur": 0.944, + "args": { + "External id": 4671970,"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": 1708036925622.813, "dur": 1.060, + "args": { + "External id": 4671971,"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": 1708036925627.384, "dur": 0.965, + "args": { + "External id": 4671972,"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": 1708036925630.270, "dur": 1.996, + "args": { + "External id": 4671973,"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": 1708036925633.780, "dur": 0.999, + "args": { + "External id": 4671974,"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": 1708036925636.167, "dur": 0.660, + "args": { + "External id": 4671975,"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": 1708036925658.156, "dur": 17395.585, + "args": { + "External id": 4671976,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036925677.658, "dur": 17369.200, + "args": { + "External id": 4671977,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036925702.822, "dur": 14.081, + "args": { + "External id": 4671978,"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": 1708036925722.932, "dur": 17289.261, + "args": { + "External id": 4671979,"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": 1708036925725.554, "dur": 17286.130, + "args": { + "External id": 4671980,"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": 1708036925731.163, "dur": 5.715, + "args": { + "External id": 4671981,"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": 1708036925738.411, "dur": 17270.458, + "args": { + "External id": 4671982,"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": 1708036943244.768, "dur": 37.422, + "args": { + "External id": 4671983,"Sequence number": 46526465, "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": 1708036943244.768, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036943269.851, "dur": 7.662, + "args": { + "External id": 4671984,"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": 1708036943272.954, "dur": 4.338, + "args": { + "External id": 4671985,"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": 1708036943347.938, "dur": 77.669, + "args": { + "External id": 4671986,"Record function id": 0, "Ev Idx": 7305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036943427.107, "dur": 1217.996, + "args": { + "External id": 4671987,"Record function id": 0, "Ev Idx": 7306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036943470.434, "dur": 1160.424, + "args": { + "External id": 4671988,"Sequence number": 46526466, "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": 1708036943470.434, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036943549.138, "dur": 43.659, + "args": { + "External id": 4671989,"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": 1708036943607.389, "dur": 104.139, + "args": { + "External id": 4671990,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036943724.517, "dur": 40.772, + "args": { + "External id": 4671991,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036943773.139, "dur": 33.820, + "args": { + "External id": 4671992,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036943852.126, "dur": 28.554, + "args": { + "External id": 4671993,"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": 1708036943901.312, "dur": 14.540, + "args": { + "External id": 4671994,"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": 1708036943934.040, "dur": 169.403, + "args": { + "External id": 4671995,"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": 1708036944016.688, "dur": 13.582, + "args": { + "External id": 4671996,"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": 1708036944022.101, "dur": 7.282, + "args": { + "External id": 4671997,"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": 1708036944033.178, "dur": 5.766, + "args": { + "External id": 4671998,"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": 1708036944040.374, "dur": 1.109, + "args": { + "External id": 4671999,"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": 1708036944044.483, "dur": 6.058, + "args": { + "External id": 4672000,"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": 1708036944186.260, "dur": 57.169, + "args": { + "External id": 4672001,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036944283.439, "dur": 31.932, + "args": { + "External id": 4672002,"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": 1708036944325.124, "dur": 43.924, + "args": { + "External id": 4672003,"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": 1708036944377.670, "dur": 34.456, + "args": { + "External id": 4672004,"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": 1708036944433.407, "dur": 26.151, + "args": { + "External id": 4672005,"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": 1708036944464.427, "dur": 36.143, + "args": { + "External id": 4672006,"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": 1708036944537.586, "dur": 21.683, + "args": { + "External id": 4672007,"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": 1708036944708.092, "dur": 73.861, + "args": { + "External id": 4672008,"Record function id": 0, "Ev Idx": 7327 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036944855.513, "dur": 46.521, + "args": { + "External id": 4672009,"Record function id": 0, "Ev Idx": 7328 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 1336753, "tid": 1336753, + "ts": 1708036944913.024, "dur": 18666.932, + "args": { + "External id": 4672010,"Record function id": 0, "Ev Idx": 7329 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 1336753, "tid": 1336753, + "ts": 1708036944920.845, "dur": 931.487, + "args": { + "External id": 4672011,"Record function id": 0, "Ev Idx": 7330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036945046.256, "dur": 9.967, + "args": { + "External id": 4672012,"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": 1708036945071.050, "dur": 37.723, + "args": { + "External id": 4672013,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036945076.809, "dur": 2.256, + "args": { + "External id": 4672014,"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": 1708036945083.344, "dur": 0.468, + "args": { + "External id": 4672015,"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": 1708036945085.371, "dur": 0.376, + "args": { + "External id": 4672016,"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": 1708036945087.273, "dur": 0.323, + "args": { + "External id": 4672017,"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": 1708036945090.503, "dur": 0.595, + "args": { + "External id": 4672018,"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": 1708036945092.529, "dur": 0.409, + "args": { + "External id": 4672019,"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": 1708036945094.324, "dur": 3.453, + "args": { + "External id": 4672020,"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": 1708036945099.801, "dur": 0.387, + "args": { + "External id": 4672021,"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": 1708036945101.532, "dur": 0.453, + "args": { + "External id": 4672022,"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": 1708036945121.036, "dur": 41.024, + "args": { + "External id": 4672023,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036945195.489, "dur": 111.644, + "args": { + "External id": 4672024,"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": 1708036945206.430, "dur": 3.875, + "args": { + "External id": 4672025,"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": 1708036945215.313, "dur": 9.918, + "args": { + "External id": 4672026,"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": 1708036945219.438, "dur": 5.395, + "args": { + "External id": 4672027,"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": 1708036945223.174, "dur": 0.481, + "args": { + "External id": 4672028,"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": 1708036945232.904, "dur": 29.738, + "args": { + "External id": 4672029,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036945235.484, "dur": 2.131, + "args": { + "External id": 4672030,"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": 1708036945239.055, "dur": 0.392, + "args": { + "External id": 4672031,"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": 1708036945240.913, "dur": 0.435, + "args": { + "External id": 4672032,"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": 1708036945244.393, "dur": 1.644, + "args": { + "External id": 4672033,"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": 1708036945247.259, "dur": 0.404, + "args": { + "External id": 4672034,"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": 1708036945248.882, "dur": 0.394, + "args": { + "External id": 4672035,"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": 1708036945251.908, "dur": 0.418, + "args": { + "External id": 4672036,"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": 1708036945253.655, "dur": 0.391, + "args": { + "External id": 4672037,"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": 1708036945255.699, "dur": 2.269, + "args": { + "External id": 4672038,"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": 1708036945275.455, "dur": 22.881, + "args": { + "External id": 4672039,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036945362.341, "dur": 391.165, + "args": { + "External id": 4672040,"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": 1708036945392.636, "dur": 355.859, + "args": { + "External id": 4672041,"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": 1708036945402.675, "dur": 339.584, + "args": { + "External id": 4672042,"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": 1708036945778.977, "dur": 2.508, + "args": { + "External id": 4672043,"Record function id": 0, "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": 1708036945873.092, "dur": 17482.915, + "args": { + "External id": 4672044,"Record function id": 0, "Ev Idx": 7363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036945977.304, "dur": 6.399, + "args": { + "External id": 4672045,"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": 1708036946023.533, "dur": 2.102, + "args": { + "External id": 4672046,"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": 1708036946027.771, "dur": 2.685, + "args": { + "External id": 4672047,"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": 1708036946032.374, "dur": 0.903, + "args": { + "External id": 4672048,"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": 1708036946034.601, "dur": 0.971, + "args": { + "External id": 4672049,"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": 1708036946036.854, "dur": 0.890, + "args": { + "External id": 4672050,"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": 1708036946041.167, "dur": 0.987, + "args": { + "External id": 4672051,"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": 1708036946043.765, "dur": 2.764, + "args": { + "External id": 4672052,"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": 1708036946048.383, "dur": 0.826, + "args": { + "External id": 4672053,"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": 1708036946050.656, "dur": 0.944, + "args": { + "External id": 4672054,"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": 1708036946072.460, "dur": 17243.589, + "args": { + "External id": 4672055,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036946092.541, "dur": 17216.729, + "args": { + "External id": 4672056,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036946143.846, "dur": 14.732, + "args": { + "External id": 4672057,"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": 1708036946161.450, "dur": 17114.727, + "args": { + "External id": 4672058,"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": 1708036946163.925, "dur": 17111.665, + "args": { + "External id": 4672059,"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": 1708036946169.608, "dur": 6.215, + "args": { + "External id": 4672060,"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": 1708036946177.305, "dur": 17095.492, + "args": { + "External id": 4672061,"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": 1708036963500.330, "dur": 50.103, + "args": { + "External id": 4672062,"Sequence number": 46526467, "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": 1708036963500.330, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036963523.656, "dur": 21.503, + "args": { + "External id": 4672063,"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": 1708036963540.142, "dur": 4.684, + "args": { + "External id": 4672064,"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": 1708036963623.875, "dur": 79.559, + "args": { + "External id": 4672065,"Record function id": 0, "Ev Idx": 7384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036963705.068, "dur": 1068.806, + "args": { + "External id": 4672066,"Record function id": 0, "Ev Idx": 7385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036963746.734, "dur": 1014.158, + "args": { + "External id": 4672067,"Sequence number": 46526468, "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": 1708036963746.734, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036963812.375, "dur": 43.919, + "args": { + "External id": 4672068,"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": 1708036963868.616, "dur": 108.456, + "args": { + "External id": 4672069,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036964028.057, "dur": 47.478, + "args": { + "External id": 4672070,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036964084.588, "dur": 31.865, + "args": { + "External id": 4672071,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036964141.829, "dur": 25.028, + "args": { + "External id": 4672072,"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": 1708036964184.047, "dur": 14.100, + "args": { + "External id": 4672073,"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": 1708036964216.860, "dur": 123.290, + "args": { + "External id": 4672074,"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": 1708036964263.426, "dur": 11.151, + "args": { + "External id": 4672075,"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": 1708036964268.632, "dur": 5.239, + "args": { + "External id": 4672076,"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": 1708036964277.356, "dur": 5.643, + "args": { + "External id": 4672077,"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": 1708036964284.216, "dur": 1.333, + "args": { + "External id": 4672078,"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": 1708036964287.781, "dur": 4.639, + "args": { + "External id": 4672079,"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": 1708036964350.585, "dur": 44.950, + "args": { + "External id": 4672080,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036964427.636, "dur": 25.751, + "args": { + "External id": 4672081,"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": 1708036964463.042, "dur": 40.671, + "args": { + "External id": 4672082,"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": 1708036964510.514, "dur": 51.984, + "args": { + "External id": 4672083,"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": 1708036964587.380, "dur": 27.418, + "args": { + "External id": 4672084,"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": 1708036964620.825, "dur": 35.588, + "args": { + "External id": 4672085,"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": 1708036964674.922, "dur": 18.044, + "args": { + "External id": 4672086,"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": 1708036964841.147, "dur": 77.444, + "args": { + "External id": 4672087,"Record function id": 0, "Ev Idx": 7406 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036965034.588, "dur": 49.373, + "args": { + "External id": 4672088,"Record function id": 0, "Ev Idx": 7407 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 1336753, "tid": 1336753, + "ts": 1708036965094.839, "dur": 18763.575, + "args": { + "External id": 4672089,"Record function id": 0, "Ev Idx": 7408 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 1336753, "tid": 1336753, + "ts": 1708036965103.708, "dur": 868.896, + "args": { + "External id": 4672090,"Record function id": 0, "Ev Idx": 7409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036965190.049, "dur": 8.582, + "args": { + "External id": 4672091,"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": 1708036965213.200, "dur": 40.714, + "args": { + "External id": 4672092,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036965219.421, "dur": 5.264, + "args": { + "External id": 4672093,"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": 1708036965229.115, "dur": 0.515, + "args": { + "External id": 4672094,"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": 1708036965231.089, "dur": 0.582, + "args": { + "External id": 4672095,"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": 1708036965233.023, "dur": 0.509, + "args": { + "External id": 4672096,"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": 1708036965236.441, "dur": 0.331, + "args": { + "External id": 4672097,"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": 1708036965237.937, "dur": 0.583, + "args": { + "External id": 4672098,"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": 1708036965239.974, "dur": 3.395, + "args": { + "External id": 4672099,"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": 1708036965245.124, "dur": 0.371, + "args": { + "External id": 4672100,"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": 1708036965246.645, "dur": 0.484, + "args": { + "External id": 4672101,"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": 1708036965265.313, "dur": 38.909, + "args": { + "External id": 4672102,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036965337.219, "dur": 109.417, + "args": { + "External id": 4672103,"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": 1708036965350.980, "dur": 5.371, + "args": { + "External id": 4672104,"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": 1708036965361.631, "dur": 9.987, + "args": { + "External id": 4672105,"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": 1708036965365.774, "dur": 5.469, + "args": { + "External id": 4672106,"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": 1708036965369.369, "dur": 0.528, + "args": { + "External id": 4672107,"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": 1708036965378.727, "dur": 27.531, + "args": { + "External id": 4672108,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036965381.368, "dur": 0.466, + "args": { + "External id": 4672109,"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": 1708036965383.244, "dur": 2.220, + "args": { + "External id": 4672110,"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": 1708036965386.985, "dur": 0.318, + "args": { + "External id": 4672111,"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": 1708036965388.530, "dur": 1.748, + "args": { + "External id": 4672112,"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": 1708036965393.177, "dur": 0.346, + "args": { + "External id": 4672113,"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": 1708036965394.745, "dur": 0.171, + "args": { + "External id": 4672114,"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": 1708036965396.183, "dur": 0.260, + "args": { + "External id": 4672115,"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": 1708036965399.608, "dur": 0.244, + "args": { + "External id": 4672116,"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": 1708036965400.976, "dur": 0.409, + "args": { + "External id": 4672117,"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": 1708036965416.300, "dur": 22.943, + "args": { + "External id": 4672118,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036965497.673, "dur": 380.960, + "args": { + "External id": 4672119,"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": 1708036965545.680, "dur": 327.689, + "args": { + "External id": 4672120,"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": 1708036965557.069, "dur": 308.958, + "args": { + "External id": 4672121,"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": 1708036965901.746, "dur": 2.259, + "args": { + "External id": 4672122,"Record function id": 0, "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": 1708036966032.116, "dur": 17627.675, + "args": { + "External id": 4672123,"Record function id": 0, "Ev Idx": 7442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036966133.217, "dur": 6.550, + "args": { + "External id": 4672124,"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": 1708036966142.881, "dur": 1.403, + "args": { + "External id": 4672125,"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": 1708036966145.943, "dur": 3.147, + "args": { + "External id": 4672126,"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": 1708036966150.883, "dur": 0.892, + "args": { + "External id": 4672127,"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": 1708036966153.196, "dur": 1.000, + "args": { + "External id": 4672128,"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": 1708036966155.527, "dur": 0.768, + "args": { + "External id": 4672129,"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": 1708036966159.124, "dur": 0.978, + "args": { + "External id": 4672130,"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": 1708036966161.824, "dur": 2.705, + "args": { + "External id": 4672131,"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": 1708036966166.191, "dur": 0.841, + "args": { + "External id": 4672132,"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": 1708036966168.718, "dur": 0.954, + "args": { + "External id": 4672133,"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": 1708036966189.248, "dur": 17431.224, + "args": { + "External id": 4672134,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036966204.961, "dur": 17409.210, + "args": { + "External id": 4672135,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036966229.559, "dur": 13.569, + "args": { + "External id": 4672136,"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": 1708036966245.818, "dur": 17332.122, + "args": { + "External id": 4672137,"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": 1708036966248.286, "dur": 17329.067, + "args": { + "External id": 4672138,"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": 1708036966253.973, "dur": 5.322, + "args": { + "External id": 4672139,"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": 1708036966260.905, "dur": 17313.475, + "args": { + "External id": 4672140,"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": 1708036983797.525, "dur": 35.858, + "args": { + "External id": 4672141,"Sequence number": 46526469, "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": 1708036983797.525, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708036983820.945, "dur": 7.427, + "args": { + "External id": 4672142,"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": 1708036983824.076, "dur": 4.047, + "args": { + "External id": 4672143,"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": 1708036983901.431, "dur": 78.576, + "args": { + "External id": 4672144,"Record function id": 0, "Ev Idx": 7463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708036984012.015, "dur": 1095.155, + "args": { + "External id": 4672145,"Record function id": 0, "Ev Idx": 7464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708036984056.673, "dur": 1037.455, + "args": { + "External id": 4672146,"Sequence number": 46526470, "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": 1708036984056.673, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708036984141.767, "dur": 48.416, + "args": { + "External id": 4672147,"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": 1708036984204.345, "dur": 103.697, + "args": { + "External id": 4672148,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036984320.954, "dur": 36.979, + "args": { + "External id": 4672149,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036984363.821, "dur": 32.154, + "args": { + "External id": 4672150,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036984422.865, "dur": 23.816, + "args": { + "External id": 4672151,"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": 1708036984462.124, "dur": 16.659, + "args": { + "External id": 4672152,"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": 1708036984495.850, "dur": 152.916, + "args": { + "External id": 4672153,"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": 1708036984563.380, "dur": 12.407, + "args": { + "External id": 4672154,"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": 1708036984568.983, "dur": 5.864, + "args": { + "External id": 4672155,"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": 1708036984578.647, "dur": 5.993, + "args": { + "External id": 4672156,"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": 1708036984586.042, "dur": 3.006, + "args": { + "External id": 4672157,"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": 1708036984591.448, "dur": 4.614, + "args": { + "External id": 4672158,"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": 1708036984659.564, "dur": 51.844, + "args": { + "External id": 4672159,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708036984741.413, "dur": 27.910, + "args": { + "External id": 4672160,"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": 1708036984778.443, "dur": 40.717, + "args": { + "External id": 4672161,"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": 1708036984825.862, "dur": 34.203, + "args": { + "External id": 4672162,"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": 1708036984885.232, "dur": 25.399, + "args": { + "External id": 4672163,"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": 1708036984916.176, "dur": 32.844, + "args": { + "External id": 4672164,"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": 1708036984966.417, "dur": 54.615, + "args": { + "External id": 4672165,"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": 1708036985174.487, "dur": 74.053, + "args": { + "External id": 4672166,"Record function id": 0, "Ev Idx": 7485 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708036985322.224, "dur": 44.274, + "args": { + "External id": 4672167,"Record function id": 0, "Ev Idx": 7486 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 1336753, "tid": 1336753, + "ts": 1708036985376.085, "dur": 18808.404, + "args": { + "External id": 4672168,"Record function id": 0, "Ev Idx": 7487 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 1336753, "tid": 1336753, + "ts": 1708036985387.458, "dur": 921.761, + "args": { + "External id": 4672169,"Record function id": 0, "Ev Idx": 7488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708036985468.591, "dur": 8.648, + "args": { + "External id": 4672170,"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": 1708036985491.111, "dur": 51.540, + "args": { + "External id": 4672171,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036985496.406, "dur": 2.315, + "args": { + "External id": 4672172,"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": 1708036985502.886, "dur": 0.320, + "args": { + "External id": 4672173,"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": 1708036985504.659, "dur": 0.601, + "args": { + "External id": 4672174,"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": 1708036985506.704, "dur": 0.561, + "args": { + "External id": 4672175,"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": 1708036985509.887, "dur": 0.511, + "args": { + "External id": 4672176,"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": 1708036985511.781, "dur": 0.474, + "args": { + "External id": 4672177,"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": 1708036985513.647, "dur": 3.213, + "args": { + "External id": 4672178,"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": 1708036985517.989, "dur": 0.544, + "args": { + "External id": 4672179,"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": 1708036985519.938, "dur": 0.477, + "args": { + "External id": 4672180,"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": 1708036985556.330, "dur": 41.330, + "args": { + "External id": 4672181,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036985632.437, "dur": 111.259, + "args": { + "External id": 4672182,"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": 1708036985643.019, "dur": 4.588, + "args": { + "External id": 4672183,"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": 1708036985652.745, "dur": 10.327, + "args": { + "External id": 4672184,"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": 1708036985657.174, "dur": 5.513, + "args": { + "External id": 4672185,"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": 1708036985660.617, "dur": 0.705, + "args": { + "External id": 4672186,"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": 1708036985670.212, "dur": 30.333, + "args": { + "External id": 4672187,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708036985672.630, "dur": 2.072, + "args": { + "External id": 4672188,"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": 1708036985676.061, "dur": 0.535, + "args": { + "External id": 4672189,"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": 1708036985678.074, "dur": 0.455, + "args": { + "External id": 4672190,"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": 1708036985681.710, "dur": 1.695, + "args": { + "External id": 4672191,"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": 1708036985684.909, "dur": 0.445, + "args": { + "External id": 4672192,"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": 1708036985686.558, "dur": 0.158, + "args": { + "External id": 4672193,"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": 1708036985689.665, "dur": 0.337, + "args": { + "External id": 4672194,"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": 1708036985691.334, "dur": 0.444, + "args": { + "External id": 4672195,"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": 1708036985693.595, "dur": 1.888, + "args": { + "External id": 4672196,"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": 1708036985713.361, "dur": 22.973, + "args": { + "External id": 4672197,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708036985798.034, "dur": 411.119, + "args": { + "External id": 4672198,"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": 1708036985829.284, "dur": 374.563, + "args": { + "External id": 4672199,"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": 1708036985839.237, "dur": 358.246, + "args": { + "External id": 4672200,"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": 1708036986234.538, "dur": 2.489, + "args": { + "External id": 4672201,"Record function id": 0, "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": 1708036986330.908, "dur": 17613.836, + "args": { + "External id": 4672202,"Record function id": 0, "Ev Idx": 7521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708036986432.702, "dur": 6.452, + "args": { + "External id": 4672203,"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": 1708036986466.785, "dur": 1.613, + "args": { + "External id": 4672204,"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": 1708036986470.710, "dur": 2.053, + "args": { + "External id": 4672205,"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": 1708036986475.825, "dur": 1.194, + "args": { + "External id": 4672206,"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": 1708036986478.389, "dur": 0.646, + "args": { + "External id": 4672207,"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": 1708036986480.279, "dur": 0.720, + "args": { + "External id": 4672208,"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": 1708036986482.402, "dur": 0.838, + "args": { + "External id": 4672209,"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": 1708036986486.455, "dur": 2.008, + "args": { + "External id": 4672210,"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": 1708036986490.036, "dur": 0.615, + "args": { + "External id": 4672211,"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": 1708036986492.501, "dur": 0.739, + "args": { + "External id": 4672212,"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": 1708036986513.878, "dur": 17391.862, + "args": { + "External id": 4672213,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036986546.842, "dur": 17352.350, + "args": { + "External id": 4672214,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708036986567.637, "dur": 18.909, + "args": { + "External id": 4672215,"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": 1708036986591.400, "dur": 17272.269, + "args": { + "External id": 4672216,"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": 1708036986594.307, "dur": 17268.758, + "args": { + "External id": 4672217,"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": 1708036986599.967, "dur": 5.657, + "args": { + "External id": 4672218,"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": 1708036986607.308, "dur": 17253.132, + "args": { + "External id": 4672219,"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": 1708037004115.430, "dur": 41.696, + "args": { + "External id": 4672220,"Sequence number": 46526471, "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": 1708037004115.430, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708037004143.384, "dur": 8.742, + "args": { + "External id": 4672221,"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": 1708037004147.086, "dur": 4.667, + "args": { + "External id": 4672222,"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": 1708037004226.992, "dur": 78.754, + "args": { + "External id": 4672223,"Record function id": 0, "Ev Idx": 7542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708037004310.440, "dur": 1071.875, + "args": { + "External id": 4672224,"Record function id": 0, "Ev Idx": 7543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037004349.073, "dur": 1019.185, + "args": { + "External id": 4672225,"Sequence number": 46526472, "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": 1708037004349.073, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708037004417.563, "dur": 42.272, + "args": { + "External id": 4672226,"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": 1708037004471.746, "dur": 121.523, + "args": { + "External id": 4672227,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037004609.218, "dur": 39.521, + "args": { + "External id": 4672228,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037004656.792, "dur": 31.019, + "args": { + "External id": 4672229,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037004712.391, "dur": 26.517, + "args": { + "External id": 4672230,"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": 1708037004757.898, "dur": 14.636, + "args": { + "External id": 4672231,"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": 1708037004791.061, "dur": 128.884, + "args": { + "External id": 4672232,"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": 1708037004835.689, "dur": 15.160, + "args": { + "External id": 4672233,"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": 1708037004841.425, "dur": 8.648, + "args": { + "External id": 4672234,"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": 1708037004854.025, "dur": 5.700, + "args": { + "External id": 4672235,"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": 1708037004861.381, "dur": 1.062, + "args": { + "External id": 4672236,"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": 1708037004865.070, "dur": 4.945, + "args": { + "External id": 4672237,"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": 1708037004929.442, "dur": 44.420, + "args": { + "External id": 4672238,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037005043.111, "dur": 30.772, + "args": { + "External id": 4672239,"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": 1708037005084.330, "dur": 45.358, + "args": { + "External id": 4672240,"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": 1708037005137.359, "dur": 34.881, + "args": { + "External id": 4672241,"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": 1708037005192.713, "dur": 27.226, + "args": { + "External id": 4672242,"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": 1708037005225.610, "dur": 33.842, + "args": { + "External id": 4672243,"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": 1708037005279.620, "dur": 18.062, + "args": { + "External id": 4672244,"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": 1708037005448.712, "dur": 95.637, + "args": { + "External id": 4672245,"Record function id": 0, "Ev Idx": 7564 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708037005624.917, "dur": 53.928, + "args": { + "External id": 4672246,"Record function id": 0, "Ev Idx": 7565 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.20)", "pid": 1336753, "tid": 1336753, + "ts": 1708037005688.703, "dur": 18685.631, + "args": { + "External id": 4672247,"Record function id": 0, "Ev Idx": 7566 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 1336753, "tid": 1336753, + "ts": 1708037005701.519, "dur": 894.764, + "args": { + "External id": 4672248,"Record function id": 0, "Ev Idx": 7567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708037005783.146, "dur": 8.876, + "args": { + "External id": 4672249,"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": 1708037005805.950, "dur": 38.352, + "args": { + "External id": 4672250,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037005811.703, "dur": 2.448, + "args": { + "External id": 4672251,"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": 1708037005819.183, "dur": 0.478, + "args": { + "External id": 4672252,"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": 1708037005820.925, "dur": 0.431, + "args": { + "External id": 4672253,"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": 1708037005823.533, "dur": 0.212, + "args": { + "External id": 4672254,"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": 1708037005826.504, "dur": 0.334, + "args": { + "External id": 4672255,"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": 1708037005828.294, "dur": 0.400, + "args": { + "External id": 4672256,"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": 1708037005830.342, "dur": 2.988, + "args": { + "External id": 4672257,"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": 1708037005835.127, "dur": 0.285, + "args": { + "External id": 4672258,"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": 1708037005837.029, "dur": 0.257, + "args": { + "External id": 4672259,"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": 1708037005855.855, "dur": 41.183, + "args": { + "External id": 4672260,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037005928.766, "dur": 162.339, + "args": { + "External id": 4672261,"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": 1708037005939.266, "dur": 4.967, + "args": { + "External id": 4672262,"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": 1708037005949.029, "dur": 9.967, + "args": { + "External id": 4672263,"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": 1708037005953.416, "dur": 5.168, + "args": { + "External id": 4672264,"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": 1708037005956.996, "dur": 0.542, + "args": { + "External id": 4672265,"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": 1708037005966.961, "dur": 73.238, + "args": { + "External id": 4672266,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037005969.517, "dur": 2.001, + "args": { + "External id": 4672267,"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": 1708037005973.356, "dur": 0.481, + "args": { + "External id": 4672268,"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": 1708037005978.871, "dur": 0.228, + "args": { + "External id": 4672269,"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": 1708037006018.646, "dur": 1.962, + "args": { + "External id": 4672270,"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": 1708037006022.586, "dur": 0.402, + "args": { + "External id": 4672271,"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": 1708037006024.521, "dur": 2.220, + "args": { + "External id": 4672272,"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": 1708037006028.019, "dur": 0.230, + "args": { + "External id": 4672273,"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": 1708037006029.814, "dur": 0.411, + "args": { + "External id": 4672274,"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": 1708037006033.287, "dur": 0.178, + "args": { + "External id": 4672275,"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": 1708037006056.587, "dur": 26.642, + "args": { + "External id": 4672276,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037006147.595, "dur": 340.072, + "args": { + "External id": 4672277,"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": 1708037006178.488, "dur": 304.140, + "args": { + "External id": 4672278,"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": 1708037006188.398, "dur": 288.964, + "args": { + "External id": 4672279,"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": 1708037006509.120, "dur": 2.184, + "args": { + "External id": 4672280,"Record function id": 0, "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": 1708037006617.055, "dur": 17538.632, + "args": { + "External id": 4672281,"Record function id": 0, "Ev Idx": 7600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708037006714.308, "dur": 6.601, + "args": { + "External id": 4672282,"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": 1708037006724.438, "dur": 1.561, + "args": { + "External id": 4672283,"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": 1708037006727.841, "dur": 3.018, + "args": { + "External id": 4672284,"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": 1708037006732.647, "dur": 1.057, + "args": { + "External id": 4672285,"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": 1708037006735.425, "dur": 0.981, + "args": { + "External id": 4672286,"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": 1708037006737.806, "dur": 1.154, + "args": { + "External id": 4672287,"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": 1708037006742.667, "dur": 1.215, + "args": { + "External id": 4672288,"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": 1708037006745.391, "dur": 2.186, + "args": { + "External id": 4672289,"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": 1708037006748.967, "dur": 0.953, + "args": { + "External id": 4672290,"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": 1708037006751.465, "dur": 0.760, + "args": { + "External id": 4672291,"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": 1708037006774.981, "dur": 17344.088, + "args": { + "External id": 4672292,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037006791.480, "dur": 17321.056, + "args": { + "External id": 4672293,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037006814.515, "dur": 17.171, + "args": { + "External id": 4672294,"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": 1708037006834.469, "dur": 17241.833, + "args": { + "External id": 4672295,"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": 1708037006837.484, "dur": 17238.215, + "args": { + "External id": 4672296,"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": 1708037006843.144, "dur": 5.007, + "args": { + "External id": 4672297,"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": 1708037006849.853, "dur": 17223.121, + "args": { + "External id": 4672298,"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": 1708037024292.754, "dur": 53.499, + "args": { + "External id": 4672299,"Sequence number": 46526473, "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": 1708037024292.754, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708037024332.966, "dur": 8.056, + "args": { + "External id": 4672300,"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": 1708037024336.480, "dur": 4.294, + "args": { + "External id": 4672301,"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": 1708037024411.691, "dur": 80.256, + "args": { + "External id": 4672302,"Record function id": 0, "Ev Idx": 7621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708037024493.421, "dur": 1081.213, + "args": { + "External id": 4672303,"Record function id": 0, "Ev Idx": 7622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037024549.596, "dur": 1011.030, + "args": { + "External id": 4672304,"Sequence number": 46526474, "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": 1708037024549.596, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708037024614.704, "dur": 41.322, + "args": { + "External id": 4672305,"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": 1708037024668.123, "dur": 110.595, + "args": { + "External id": 4672306,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037024791.616, "dur": 38.731, + "args": { + "External id": 4672307,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037024836.814, "dur": 30.930, + "args": { + "External id": 4672308,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037024892.641, "dur": 23.760, + "args": { + "External id": 4672309,"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": 1708037024930.896, "dur": 15.249, + "args": { + "External id": 4672310,"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": 1708037024963.126, "dur": 178.191, + "args": { + "External id": 4672311,"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": 1708037025054.542, "dur": 12.344, + "args": { + "External id": 4672312,"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": 1708037025059.685, "dur": 6.354, + "args": { + "External id": 4672313,"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": 1708037025069.801, "dur": 5.539, + "args": { + "External id": 4672314,"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": 1708037025077.132, "dur": 1.112, + "args": { + "External id": 4672315,"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": 1708037025082.429, "dur": 4.345, + "args": { + "External id": 4672316,"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": 1708037025154.728, "dur": 50.782, + "args": { + "External id": 4672317,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037025236.977, "dur": 28.783, + "args": { + "External id": 4672318,"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": 1708037025275.774, "dur": 41.741, + "args": { + "External id": 4672319,"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": 1708037025324.494, "dur": 34.675, + "args": { + "External id": 4672320,"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": 1708037025380.997, "dur": 27.749, + "args": { + "External id": 4672321,"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": 1708037025413.915, "dur": 33.626, + "args": { + "External id": 4672322,"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": 1708037025463.750, "dur": 15.770, + "args": { + "External id": 4672323,"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": 1708037025641.713, "dur": 75.989, + "args": { + "External id": 4672324,"Record function id": 0, "Ev Idx": 7643 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708037025793.006, "dur": 49.261, + "args": { + "External id": 4672325,"Record function id": 0, "Ev Idx": 7644 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.21)", "pid": 1336753, "tid": 1336753, + "ts": 1708037025852.265, "dur": 18806.953, + "args": { + "External id": 4672326,"Record function id": 0, "Ev Idx": 7645 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 1336753, "tid": 1336753, + "ts": 1708037025863.416, "dur": 821.430, + "args": { + "External id": 4672327,"Record function id": 0, "Ev Idx": 7646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708037025943.663, "dur": 8.471, + "args": { + "External id": 4672328,"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": 1708037025965.828, "dur": 75.650, + "args": { + "External id": 4672329,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037025971.702, "dur": 2.177, + "args": { + "External id": 4672330,"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": 1708037025977.904, "dur": 0.205, + "args": { + "External id": 4672331,"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": 1708037025979.718, "dur": 0.275, + "args": { + "External id": 4672332,"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": 1708037026016.324, "dur": 0.943, + "args": { + "External id": 4672333,"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": 1708037026021.672, "dur": 0.398, + "args": { + "External id": 4672334,"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": 1708037026023.541, "dur": 0.500, + "args": { + "External id": 4672335,"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": 1708037026025.618, "dur": 3.434, + "args": { + "External id": 4672336,"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": 1708037026030.528, "dur": 0.262, + "args": { + "External id": 4672337,"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": 1708037026032.280, "dur": 0.354, + "args": { + "External id": 4672338,"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": 1708037026054.212, "dur": 41.261, + "args": { + "External id": 4672339,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037026132.166, "dur": 113.416, + "args": { + "External id": 4672340,"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": 1708037026143.136, "dur": 5.029, + "args": { + "External id": 4672341,"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": 1708037026153.189, "dur": 13.618, + "args": { + "External id": 4672342,"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": 1708037026161.047, "dur": 5.352, + "args": { + "External id": 4672343,"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": 1708037026164.513, "dur": 0.756, + "args": { + "External id": 4672344,"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": 1708037026174.026, "dur": 29.555, + "args": { + "External id": 4672345,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037026176.296, "dur": 2.085, + "args": { + "External id": 4672346,"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": 1708037026179.997, "dur": 0.402, + "args": { + "External id": 4672347,"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": 1708037026181.960, "dur": 0.366, + "args": { + "External id": 4672348,"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": 1708037026185.299, "dur": 1.424, + "args": { + "External id": 4672349,"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": 1708037026188.032, "dur": 0.401, + "args": { + "External id": 4672350,"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": 1708037026189.565, "dur": 0.458, + "args": { + "External id": 4672351,"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": 1708037026193.118, "dur": 0.674, + "args": { + "External id": 4672352,"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": 1708037026195.204, "dur": 0.145, + "args": { + "External id": 4672353,"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": 1708037026196.676, "dur": 1.897, + "args": { + "External id": 4672354,"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": 1708037026215.642, "dur": 22.349, + "args": { + "External id": 4672355,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037026340.052, "dur": 256.997, + "args": { + "External id": 4672356,"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": 1708037026375.287, "dur": 216.903, + "args": { + "External id": 4672357,"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": 1708037026385.957, "dur": 200.759, + "args": { + "External id": 4672358,"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": 1708037026618.275, "dur": 2.313, + "args": { + "External id": 4672359,"Record function id": 0, "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": 1708037026704.805, "dur": 17730.236, + "args": { + "External id": 4672360,"Record function id": 0, "Ev Idx": 7679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708037026799.715, "dur": 6.112, + "args": { + "External id": 4672361,"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": 1708037026808.934, "dur": 0.935, + "args": { + "External id": 4672362,"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": 1708037026811.486, "dur": 2.545, + "args": { + "External id": 4672363,"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": 1708037026815.603, "dur": 0.775, + "args": { + "External id": 4672364,"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": 1708037026817.686, "dur": 1.099, + "args": { + "External id": 4672365,"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": 1708037026820.275, "dur": 0.819, + "args": { + "External id": 4672366,"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": 1708037026824.912, "dur": 1.432, + "args": { + "External id": 4672367,"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": 1708037026828.199, "dur": 2.179, + "args": { + "External id": 4672368,"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": 1708037026831.859, "dur": 0.741, + "args": { + "External id": 4672369,"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": 1708037026834.019, "dur": 0.873, + "args": { + "External id": 4672370,"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": 1708037026854.952, "dur": 17542.771, + "args": { + "External id": 4672371,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037026870.502, "dur": 17520.561, + "args": { + "External id": 4672372,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037026890.701, "dur": 14.887, + "args": { + "External id": 4672373,"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": 1708037026908.598, "dur": 17449.899, + "args": { + "External id": 4672374,"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": 1708037026911.189, "dur": 17446.741, + "args": { + "External id": 4672375,"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": 1708037026916.593, "dur": 4.960, + "args": { + "External id": 4672376,"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": 1708037026923.215, "dur": 17431.989, + "args": { + "External id": 4672377,"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": 1708037044585.756, "dur": 43.832, + "args": { + "External id": 4672378,"Sequence number": 46526475, "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": 1708037044585.756, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708037044616.396, "dur": 8.109, + "args": { + "External id": 4672379,"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": 1708037044619.364, "dur": 4.817, + "args": { + "External id": 4672380,"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": 1708037044697.879, "dur": 81.902, + "args": { + "External id": 4672381,"Record function id": 0, "Ev Idx": 7700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708037044781.466, "dur": 1060.372, + "args": { + "External id": 4672382,"Record function id": 0, "Ev Idx": 7701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037044820.336, "dur": 1008.403, + "args": { + "External id": 4672383,"Sequence number": 46526476, "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": 1708037044820.336, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708037044898.572, "dur": 41.692, + "args": { + "External id": 4672384,"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": 1708037044956.202, "dur": 130.237, + "args": { + "External id": 4672385,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037045100.915, "dur": 40.724, + "args": { + "External id": 4672386,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037045149.235, "dur": 30.621, + "args": { + "External id": 4672387,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037045204.386, "dur": 25.871, + "args": { + "External id": 4672388,"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": 1708037045248.743, "dur": 14.779, + "args": { + "External id": 4672389,"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": 1708037045282.083, "dur": 126.801, + "args": { + "External id": 4672390,"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": 1708037045329.547, "dur": 11.359, + "args": { + "External id": 4672391,"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": 1708037045335.080, "dur": 5.145, + "args": { + "External id": 4672392,"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": 1708037045343.678, "dur": 5.281, + "args": { + "External id": 4672393,"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": 1708037045350.597, "dur": 1.015, + "args": { + "External id": 4672394,"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": 1708037045354.018, "dur": 3.968, + "args": { + "External id": 4672395,"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": 1708037045418.616, "dur": 45.876, + "args": { + "External id": 4672396,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037045491.004, "dur": 28.583, + "args": { + "External id": 4672397,"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": 1708037045545.385, "dur": 45.639, + "args": { + "External id": 4672398,"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": 1708037045599.741, "dur": 34.812, + "args": { + "External id": 4672399,"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": 1708037045657.767, "dur": 25.768, + "args": { + "External id": 4672400,"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": 1708037045688.685, "dur": 33.240, + "args": { + "External id": 4672401,"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": 1708037045740.570, "dur": 18.237, + "args": { + "External id": 4672402,"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": 1708037045903.195, "dur": 69.898, + "args": { + "External id": 4672403,"Record function id": 0, "Ev Idx": 7722 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708037046089.092, "dur": 47.622, + "args": { + "External id": 4672404,"Record function id": 0, "Ev Idx": 7723 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.22)", "pid": 1336753, "tid": 1336753, + "ts": 1708037046147.079, "dur": 18711.694, + "args": { + "External id": 4672405,"Record function id": 0, "Ev Idx": 7724 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 1336753, "tid": 1336753, + "ts": 1708037046156.230, "dur": 972.332, + "args": { + "External id": 4672406,"Record function id": 0, "Ev Idx": 7725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708037046236.529, "dur": 8.528, + "args": { + "External id": 4672407,"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": 1708037046258.649, "dur": 38.364, + "args": { + "External id": 4672408,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037046264.929, "dur": 2.072, + "args": { + "External id": 4672409,"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": 1708037046271.574, "dur": 0.287, + "args": { + "External id": 4672410,"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": 1708037046273.595, "dur": 0.494, + "args": { + "External id": 4672411,"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": 1708037046275.466, "dur": 0.487, + "args": { + "External id": 4672412,"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": 1708037046278.940, "dur": 0.491, + "args": { + "External id": 4672413,"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": 1708037046280.728, "dur": 0.219, + "args": { + "External id": 4672414,"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": 1708037046282.311, "dur": 4.085, + "args": { + "External id": 4672415,"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": 1708037046287.957, "dur": 0.482, + "args": { + "External id": 4672416,"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": 1708037046289.577, "dur": 0.152, + "args": { + "External id": 4672417,"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": 1708037046308.415, "dur": 39.238, + "args": { + "External id": 4672418,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037046380.730, "dur": 118.337, + "args": { + "External id": 4672419,"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": 1708037046391.389, "dur": 4.386, + "args": { + "External id": 4672420,"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": 1708037046400.813, "dur": 13.373, + "args": { + "External id": 4672421,"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": 1708037046405.249, "dur": 8.553, + "args": { + "External id": 4672422,"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": 1708037046412.187, "dur": 0.574, + "args": { + "External id": 4672423,"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": 1708037046421.382, "dur": 34.727, + "args": { + "External id": 4672424,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037046423.659, "dur": 2.193, + "args": { + "External id": 4672425,"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": 1708037046427.589, "dur": 0.565, + "args": { + "External id": 4672426,"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": 1708037046429.354, "dur": 0.230, + "args": { + "External id": 4672427,"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": 1708037046433.639, "dur": 1.863, + "args": { + "External id": 4672428,"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": 1708037046436.692, "dur": 0.574, + "args": { + "External id": 4672429,"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": 1708037046438.894, "dur": 0.494, + "args": { + "External id": 4672430,"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": 1708037046442.326, "dur": 0.457, + "args": { + "External id": 4672431,"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": 1708037046444.099, "dur": 0.287, + "args": { + "External id": 4672432,"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": 1708037046449.273, "dur": 1.712, + "args": { + "External id": 4672433,"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": 1708037046470.417, "dur": 21.201, + "args": { + "External id": 4672434,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037046568.708, "dur": 452.944, + "args": { + "External id": 4672435,"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": 1708037046603.466, "dur": 411.405, + "args": { + "External id": 4672436,"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": 1708037046613.450, "dur": 362.850, + "args": { + "External id": 4672437,"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": 1708037047048.660, "dur": 3.127, + "args": { + "External id": 4672438,"Record function id": 0, "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": 1708037047150.107, "dur": 17501.256, + "args": { + "External id": 4672439,"Record function id": 0, "Ev Idx": 7758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708037047262.413, "dur": 6.850, + "args": { + "External id": 4672440,"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": 1708037047272.823, "dur": 1.043, + "args": { + "External id": 4672441,"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": 1708037047275.853, "dur": 2.461, + "args": { + "External id": 4672442,"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": 1708037047280.155, "dur": 0.965, + "args": { + "External id": 4672443,"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": 1708037047282.609, "dur": 0.853, + "args": { + "External id": 4672444,"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": 1708037047284.681, "dur": 1.106, + "args": { + "External id": 4672445,"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": 1708037047288.874, "dur": 1.050, + "args": { + "External id": 4672446,"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": 1708037047291.633, "dur": 2.797, + "args": { + "External id": 4672447,"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": 1708037047296.167, "dur": 0.973, + "args": { + "External id": 4672448,"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": 1708037047298.812, "dur": 0.696, + "args": { + "External id": 4672449,"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": 1708037047324.437, "dur": 17287.636, + "args": { + "External id": 4672450,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037047357.417, "dur": 17247.995, + "args": { + "External id": 4672451,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037047376.219, "dur": 13.929, + "args": { + "External id": 4672452,"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": 1708037047392.905, "dur": 17180.055, + "args": { + "External id": 4672453,"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": 1708037047395.542, "dur": 17176.897, + "args": { + "External id": 4672454,"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": 1708037047401.188, "dur": 5.648, + "args": { + "External id": 4672455,"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": 1708037047408.867, "dur": 17160.827, + "args": { + "External id": 4672456,"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": 1708037064793.766, "dur": 40.004, + "args": { + "External id": 4672457,"Sequence number": 46526477, "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": 1708037064793.766, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708037064821.014, "dur": 7.750, + "args": { + "External id": 4672458,"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": 1708037064824.237, "dur": 4.302, + "args": { + "External id": 4672459,"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": 1708037064897.120, "dur": 78.111, + "args": { + "External id": 4672460,"Record function id": 0, "Ev Idx": 7779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708037064976.747, "dur": 1109.785, + "args": { + "External id": 4672461,"Record function id": 0, "Ev Idx": 7780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037065051.433, "dur": 1020.481, + "args": { + "External id": 4672462,"Sequence number": 46526478, "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": 1708037065051.433, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708037065120.411, "dur": 44.445, + "args": { + "External id": 4672463,"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": 1708037065177.220, "dur": 103.087, + "args": { + "External id": 4672464,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037065290.150, "dur": 39.279, + "args": { + "External id": 4672465,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037065337.765, "dur": 30.910, + "args": { + "External id": 4672466,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037065396.264, "dur": 24.743, + "args": { + "External id": 4672467,"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": 1708037065438.584, "dur": 15.128, + "args": { + "External id": 4672468,"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": 1708037065471.376, "dur": 155.802, + "args": { + "External id": 4672469,"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": 1708037065522.982, "dur": 28.857, + "args": { + "External id": 4672470,"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": 1708037065544.116, "dur": 6.752, + "args": { + "External id": 4672471,"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": 1708037065554.906, "dur": 5.875, + "args": { + "External id": 4672472,"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": 1708037065562.005, "dur": 1.092, + "args": { + "External id": 4672473,"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": 1708037065569.205, "dur": 3.672, + "args": { + "External id": 4672474,"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": 1708037065638.324, "dur": 49.917, + "args": { + "External id": 4672475,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037065717.606, "dur": 29.969, + "args": { + "External id": 4672476,"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": 1708037065756.068, "dur": 41.320, + "args": { + "External id": 4672477,"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": 1708037065805.121, "dur": 34.206, + "args": { + "External id": 4672478,"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": 1708037065862.110, "dur": 28.373, + "args": { + "External id": 4672479,"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": 1708037065896.063, "dur": 34.555, + "args": { + "External id": 4672480,"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": 1708037065950.004, "dur": 17.394, + "args": { + "External id": 4672481,"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": 1708037066151.086, "dur": 75.506, + "args": { + "External id": 4672482,"Record function id": 0, "Ev Idx": 7801 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708037066301.396, "dur": 47.203, + "args": { + "External id": 4672483,"Record function id": 0, "Ev Idx": 7802 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.23)", "pid": 1336753, "tid": 1336753, + "ts": 1708037066358.076, "dur": 18747.361, + "args": { + "External id": 4672484,"Record function id": 0, "Ev Idx": 7803 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 1336753, "tid": 1336753, + "ts": 1708037066367.071, "dur": 974.504, + "args": { + "External id": 4672485,"Record function id": 0, "Ev Idx": 7804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708037066444.445, "dur": 8.939, + "args": { + "External id": 4672486,"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": 1708037066467.298, "dur": 38.873, + "args": { + "External id": 4672487,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037066473.128, "dur": 2.213, + "args": { + "External id": 4672488,"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": 1708037066479.695, "dur": 0.450, + "args": { + "External id": 4672489,"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": 1708037066481.652, "dur": 0.602, + "args": { + "External id": 4672490,"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": 1708037066483.529, "dur": 0.655, + "args": { + "External id": 4672491,"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": 1708037066487.277, "dur": 0.545, + "args": { + "External id": 4672492,"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": 1708037066489.567, "dur": 0.578, + "args": { + "External id": 4672493,"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": 1708037066492.124, "dur": 3.227, + "args": { + "External id": 4672494,"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": 1708037066496.931, "dur": 0.459, + "args": { + "External id": 4672495,"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": 1708037066498.964, "dur": 0.407, + "args": { + "External id": 4672496,"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": 1708037066517.818, "dur": 60.353, + "args": { + "External id": 4672497,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037066613.821, "dur": 182.282, + "args": { + "External id": 4672498,"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": 1708037066628.382, "dur": 5.308, + "args": { + "External id": 4672499,"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": 1708037066638.836, "dur": 11.069, + "args": { + "External id": 4672500,"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": 1708037066643.617, "dur": 5.874, + "args": { + "External id": 4672501,"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": 1708037066647.108, "dur": 0.718, + "args": { + "External id": 4672502,"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": 1708037066657.631, "dur": 30.633, + "args": { + "External id": 4672503,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037066660.244, "dur": 2.502, + "args": { + "External id": 4672504,"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": 1708037066664.360, "dur": 0.277, + "args": { + "External id": 4672505,"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": 1708037066666.156, "dur": 0.417, + "args": { + "External id": 4672506,"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": 1708037066669.402, "dur": 1.545, + "args": { + "External id": 4672507,"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": 1708037066672.511, "dur": 0.442, + "args": { + "External id": 4672508,"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": 1708037066674.495, "dur": 0.398, + "args": { + "External id": 4672509,"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": 1708037066677.793, "dur": 0.615, + "args": { + "External id": 4672510,"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": 1708037066679.839, "dur": 0.458, + "args": { + "External id": 4672511,"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": 1708037066681.964, "dur": 1.974, + "args": { + "External id": 4672512,"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": 1708037066757.281, "dur": 29.871, + "args": { + "External id": 4672513,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037066851.826, "dur": 386.030, + "args": { + "External id": 4672514,"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": 1708037066883.536, "dur": 349.130, + "args": { + "External id": 4672515,"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": 1708037066894.498, "dur": 332.197, + "args": { + "External id": 4672516,"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": 1708037067266.353, "dur": 2.397, + "args": { + "External id": 4672517,"Record function id": 0, "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": 1708037067361.809, "dur": 17505.272, + "args": { + "External id": 4672518,"Record function id": 0, "Ev Idx": 7837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708037067460.326, "dur": 6.290, + "args": { + "External id": 4672519,"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": 1708037067469.682, "dur": 1.153, + "args": { + "External id": 4672520,"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": 1708037067472.533, "dur": 2.606, + "args": { + "External id": 4672521,"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": 1708037067476.683, "dur": 1.107, + "args": { + "External id": 4672522,"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": 1708037067479.012, "dur": 1.096, + "args": { + "External id": 4672523,"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": 1708037067481.213, "dur": 1.219, + "args": { + "External id": 4672524,"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": 1708037067485.261, "dur": 1.135, + "args": { + "External id": 4672525,"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": 1708037067488.136, "dur": 5.332, + "args": { + "External id": 4672526,"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": 1708037067494.727, "dur": 0.644, + "args": { + "External id": 4672527,"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": 1708037067496.760, "dur": 1.040, + "args": { + "External id": 4672528,"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": 1708037067517.207, "dur": 17309.568, + "args": { + "External id": 4672529,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037067553.436, "dur": 17266.841, + "args": { + "External id": 4672530,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037067589.117, "dur": 15.128, + "args": { + "External id": 4672531,"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": 1708037067607.277, "dur": 17180.925, + "args": { + "External id": 4672532,"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": 1708037067609.854, "dur": 17177.823, + "args": { + "External id": 4672533,"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": 1708037067615.691, "dur": 5.493, + "args": { + "External id": 4672534,"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": 1708037067622.959, "dur": 17161.973, + "args": { + "External id": 4672535,"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": 1708037085035.984, "dur": 40.565, + "args": { + "External id": 4672536,"Sequence number": 46526479, "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": 1708037085035.984, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708037085062.765, "dur": 8.297, + "args": { + "External id": 4672537,"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": 1708037085065.807, "dur": 4.975, + "args": { + "External id": 4672538,"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": 1708037085146.331, "dur": 75.346, + "args": { + "External id": 4672539,"Record function id": 0, "Ev Idx": 7858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708037085223.206, "dur": 1082.629, + "args": { + "External id": 4672540,"Record function id": 0, "Ev Idx": 7859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037085265.690, "dur": 1026.569, + "args": { + "External id": 4672541,"Sequence number": 46526480, "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": 1708037085265.690, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708037085332.033, "dur": 42.793, + "args": { + "External id": 4672542,"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": 1708037085386.307, "dur": 104.292, + "args": { + "External id": 4672543,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037085500.533, "dur": 57.052, + "args": { + "External id": 4672544,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037085569.118, "dur": 34.863, + "args": { + "External id": 4672545,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037085629.440, "dur": 30.371, + "args": { + "External id": 4672546,"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": 1708037085676.964, "dur": 15.229, + "args": { + "External id": 4672547,"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": 1708037085710.609, "dur": 121.139, + "args": { + "External id": 4672548,"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": 1708037085755.932, "dur": 11.174, + "args": { + "External id": 4672549,"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": 1708037085760.882, "dur": 5.308, + "args": { + "External id": 4672550,"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": 1708037085769.619, "dur": 5.523, + "args": { + "External id": 4672551,"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": 1708037085776.305, "dur": 1.246, + "args": { + "External id": 4672552,"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": 1708037085780.015, "dur": 3.848, + "args": { + "External id": 4672553,"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": 1708037085842.750, "dur": 47.000, + "args": { + "External id": 4672554,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037085919.108, "dur": 30.477, + "args": { + "External id": 4672555,"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": 1708037085957.879, "dur": 82.140, + "args": { + "External id": 4672556,"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": 1708037086052.286, "dur": 41.754, + "args": { + "External id": 4672557,"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": 1708037086120.426, "dur": 27.679, + "args": { + "External id": 4672558,"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": 1708037086153.513, "dur": 34.561, + "args": { + "External id": 4672559,"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": 1708037086206.181, "dur": 17.796, + "args": { + "External id": 4672560,"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": 1708037086368.882, "dur": 74.250, + "args": { + "External id": 4672561,"Record function id": 0, "Ev Idx": 7880 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708037086516.175, "dur": 66.936, + "args": { + "External id": 4672562,"Record function id": 0, "Ev Idx": 7881 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.24)", "pid": 1336753, "tid": 1336753, + "ts": 1708037086593.627, "dur": 18747.995, + "args": { + "External id": 4672563,"Record function id": 0, "Ev Idx": 7882 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 1336753, "tid": 1336753, + "ts": 1708037086601.680, "dur": 891.757, + "args": { + "External id": 4672564,"Record function id": 0, "Ev Idx": 7883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708037086681.016, "dur": 8.859, + "args": { + "External id": 4672565,"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": 1708037086704.585, "dur": 33.705, + "args": { + "External id": 4672566,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037086710.274, "dur": 2.023, + "args": { + "External id": 4672567,"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": 1708037086716.061, "dur": 0.225, + "args": { + "External id": 4672568,"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": 1708037086717.574, "dur": 0.461, + "args": { + "External id": 4672569,"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": 1708037086719.177, "dur": 0.468, + "args": { + "External id": 4672570,"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": 1708037086722.418, "dur": 0.576, + "args": { + "External id": 4672571,"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": 1708037086724.040, "dur": 0.641, + "args": { + "External id": 4672572,"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": 1708037086725.870, "dur": 3.194, + "args": { + "External id": 4672573,"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": 1708037086730.009, "dur": 0.352, + "args": { + "External id": 4672574,"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": 1708037086731.475, "dur": 0.144, + "args": { + "External id": 4672575,"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": 1708037086749.430, "dur": 44.260, + "args": { + "External id": 4672576,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037086829.223, "dur": 110.682, + "args": { + "External id": 4672577,"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": 1708037086839.386, "dur": 4.152, + "args": { + "External id": 4672578,"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": 1708037086848.968, "dur": 9.777, + "args": { + "External id": 4672579,"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": 1708037086853.229, "dur": 5.118, + "args": { + "External id": 4672580,"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": 1708037086856.616, "dur": 0.516, + "args": { + "External id": 4672581,"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": 1708037086864.804, "dur": 31.850, + "args": { + "External id": 4672582,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037086866.719, "dur": 5.169, + "args": { + "External id": 4672583,"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": 1708037086873.212, "dur": 0.575, + "args": { + "External id": 4672584,"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": 1708037086874.987, "dur": 0.580, + "args": { + "External id": 4672585,"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": 1708037086878.399, "dur": 1.489, + "args": { + "External id": 4672586,"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": 1708037086880.737, "dur": 0.558, + "args": { + "External id": 4672587,"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": 1708037086882.455, "dur": 0.620, + "args": { + "External id": 4672588,"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": 1708037086886.356, "dur": 0.560, + "args": { + "External id": 4672589,"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": 1708037086887.734, "dur": 0.409, + "args": { + "External id": 4672590,"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": 1708037086889.717, "dur": 1.894, + "args": { + "External id": 4672591,"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": 1708037086906.677, "dur": 25.631, + "args": { + "External id": 4672592,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037087030.942, "dur": 369.036, + "args": { + "External id": 4672593,"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": 1708037087069.154, "dur": 326.171, + "args": { + "External id": 4672594,"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": 1708037087080.303, "dur": 309.228, + "args": { + "External id": 4672595,"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": 1708037087422.625, "dur": 2.369, + "args": { + "External id": 4672596,"Record function id": 0, "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": 1708037087513.885, "dur": 17615.970, + "args": { + "External id": 4672597,"Record function id": 0, "Ev Idx": 7916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708037087633.999, "dur": 6.833, + "args": { + "External id": 4672598,"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": 1708037087657.789, "dur": 1.654, + "args": { + "External id": 4672599,"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": 1708037087661.506, "dur": 3.343, + "args": { + "External id": 4672600,"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": 1708037087667.635, "dur": 1.114, + "args": { + "External id": 4672601,"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": 1708037087670.144, "dur": 0.924, + "args": { + "External id": 4672602,"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": 1708037087672.548, "dur": 0.965, + "args": { + "External id": 4672603,"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": 1708037087675.040, "dur": 1.351, + "args": { + "External id": 4672604,"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": 1708037087679.703, "dur": 2.280, + "args": { + "External id": 4672605,"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": 1708037087683.372, "dur": 0.910, + "args": { + "External id": 4672606,"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": 1708037087685.799, "dur": 0.633, + "args": { + "External id": 4672607,"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": 1708037087707.724, "dur": 17382.729, + "args": { + "External id": 4672608,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037087726.962, "dur": 17356.750, + "args": { + "External id": 4672609,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037087745.970, "dur": 13.022, + "args": { + "External id": 4672610,"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": 1708037087763.385, "dur": 17288.362, + "args": { + "External id": 4672611,"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": 1708037087766.073, "dur": 17285.141, + "args": { + "External id": 4672612,"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": 1708037087772.193, "dur": 9.765, + "args": { + "External id": 4672613,"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": 1708037087783.459, "dur": 17264.970, + "args": { + "External id": 4672614,"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": 1708037105277.457, "dur": 36.243, + "args": { + "External id": 4672615,"Sequence number": 46526481, "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": 1708037105277.457, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708037105301.122, "dur": 7.392, + "args": { + "External id": 4672616,"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": 1708037105304.207, "dur": 4.152, + "args": { + "External id": 4672617,"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": 1708037105379.274, "dur": 73.105, + "args": { + "External id": 4672618,"Record function id": 0, "Ev Idx": 7937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708037105453.906, "dur": 1100.005, + "args": { + "External id": 4672619,"Record function id": 0, "Ev Idx": 7938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037105491.815, "dur": 1047.097, + "args": { + "External id": 4672620,"Sequence number": 46526482, "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": 1708037105491.815, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708037105572.532, "dur": 43.297, + "args": { + "External id": 4672621,"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": 1708037105629.407, "dur": 101.404, + "args": { + "External id": 4672622,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037105739.790, "dur": 39.265, + "args": { + "External id": 4672623,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037105786.497, "dur": 33.800, + "args": { + "External id": 4672624,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037105841.670, "dur": 27.536, + "args": { + "External id": 4672625,"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": 1708037105887.553, "dur": 15.813, + "args": { + "External id": 4672626,"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": 1708037105921.867, "dur": 166.194, + "args": { + "External id": 4672627,"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": 1708037105969.963, "dur": 11.300, + "args": { + "External id": 4672628,"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": 1708037105975.262, "dur": 5.162, + "args": { + "External id": 4672629,"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": 1708037106019.879, "dur": 6.383, + "args": { + "External id": 4672630,"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": 1708037106027.894, "dur": 1.023, + "args": { + "External id": 4672631,"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": 1708037106031.491, "dur": 4.146, + "args": { + "External id": 4672632,"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": 1708037106098.862, "dur": 48.914, + "args": { + "External id": 4672633,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037106181.822, "dur": 27.054, + "args": { + "External id": 4672634,"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": 1708037106217.781, "dur": 44.325, + "args": { + "External id": 4672635,"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": 1708037106269.701, "dur": 35.873, + "args": { + "External id": 4672636,"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": 1708037106350.135, "dur": 27.418, + "args": { + "External id": 4672637,"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": 1708037106385.151, "dur": 35.673, + "args": { + "External id": 4672638,"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": 1708037106439.430, "dur": 18.119, + "args": { + "External id": 4672639,"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": 1708037106620.076, "dur": 71.976, + "args": { + "External id": 4672640,"Record function id": 0, "Ev Idx": 7959 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708037106766.611, "dur": 47.018, + "args": { + "External id": 4672641,"Record function id": 0, "Ev Idx": 7960 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.25)", "pid": 1336753, "tid": 1336753, + "ts": 1708037106823.283, "dur": 18716.578, + "args": { + "External id": 4672642,"Record function id": 0, "Ev Idx": 7961 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 1336753, "tid": 1336753, + "ts": 1708037106831.270, "dur": 887.045, + "args": { + "External id": 4672643,"Record function id": 0, "Ev Idx": 7962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708037106910.925, "dur": 8.790, + "args": { + "External id": 4672644,"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": 1708037106933.660, "dur": 33.955, + "args": { + "External id": 4672645,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037106939.280, "dur": 2.092, + "args": { + "External id": 4672646,"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": 1708037106945.642, "dur": 0.642, + "args": { + "External id": 4672647,"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": 1708037106947.720, "dur": 0.316, + "args": { + "External id": 4672648,"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": 1708037106949.102, "dur": 0.338, + "args": { + "External id": 4672649,"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": 1708037106952.154, "dur": 0.502, + "args": { + "External id": 4672650,"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": 1708037106953.687, "dur": 0.435, + "args": { + "External id": 4672651,"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": 1708037106955.568, "dur": 2.876, + "args": { + "External id": 4672652,"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": 1708037106959.567, "dur": 0.564, + "args": { + "External id": 4672653,"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": 1708037106961.016, "dur": 0.370, + "args": { + "External id": 4672654,"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": 1708037106979.243, "dur": 76.854, + "args": { + "External id": 4672655,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037107093.905, "dur": 116.302, + "args": { + "External id": 4672656,"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": 1708037107108.799, "dur": 5.424, + "args": { + "External id": 4672657,"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": 1708037107119.685, "dur": 10.718, + "args": { + "External id": 4672658,"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": 1708037107124.034, "dur": 5.921, + "args": { + "External id": 4672659,"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": 1708037107127.772, "dur": 0.560, + "args": { + "External id": 4672660,"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": 1708037107137.346, "dur": 29.189, + "args": { + "External id": 4672661,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037107139.595, "dur": 2.326, + "args": { + "External id": 4672662,"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": 1708037107143.191, "dur": 0.162, + "args": { + "External id": 4672663,"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": 1708037107144.331, "dur": 0.182, + "args": { + "External id": 4672664,"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": 1708037107147.571, "dur": 1.292, + "args": { + "External id": 4672665,"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": 1708037107150.192, "dur": 0.260, + "args": { + "External id": 4672666,"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": 1708037107151.392, "dur": 0.281, + "args": { + "External id": 4672667,"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": 1708037107157.392, "dur": 0.406, + "args": { + "External id": 4672668,"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": 1708037107158.425, "dur": 0.265, + "args": { + "External id": 4672669,"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": 1708037107159.672, "dur": 1.992, + "args": { + "External id": 4672670,"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": 1708037107179.632, "dur": 23.352, + "args": { + "External id": 4672671,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037107267.393, "dur": 359.508, + "args": { + "External id": 4672672,"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": 1708037107296.858, "dur": 325.040, + "args": { + "External id": 4672673,"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": 1708037107306.560, "dur": 309.316, + "args": { + "External id": 4672674,"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": 1708037107649.178, "dur": 2.358, + "args": { + "External id": 4672675,"Record function id": 0, "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": 1708037107738.463, "dur": 17573.589, + "args": { + "External id": 4672676,"Record function id": 0, "Ev Idx": 7995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708037107833.588, "dur": 6.271, + "args": { + "External id": 4672677,"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": 1708037107843.070, "dur": 1.271, + "args": { + "External id": 4672678,"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": 1708037107846.214, "dur": 2.097, + "args": { + "External id": 4672679,"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": 1708037107850.058, "dur": 0.860, + "args": { + "External id": 4672680,"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": 1708037107852.416, "dur": 0.933, + "args": { + "External id": 4672681,"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": 1708037107854.668, "dur": 1.032, + "args": { + "External id": 4672682,"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": 1708037107858.801, "dur": 1.240, + "args": { + "External id": 4672683,"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": 1708037107861.281, "dur": 2.368, + "args": { + "External id": 4672684,"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": 1708037107865.040, "dur": 0.881, + "args": { + "External id": 4672685,"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": 1708037107867.096, "dur": 0.871, + "args": { + "External id": 4672686,"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": 1708037107887.682, "dur": 17374.814, + "args": { + "External id": 4672687,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037107903.730, "dur": 17350.017, + "args": { + "External id": 4672688,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037107931.130, "dur": 13.617, + "args": { + "External id": 4672689,"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": 1708037107947.669, "dur": 17270.730, + "args": { + "External id": 4672690,"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": 1708037107950.443, "dur": 17267.007, + "args": { + "External id": 4672691,"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": 1708037107956.533, "dur": 5.326, + "args": { + "External id": 4672692,"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": 1708037107963.662, "dur": 17249.963, + "args": { + "External id": 4672693,"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": 1708037125457.122, "dur": 41.656, + "args": { + "External id": 4672694,"Sequence number": 46526483, "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": 1708037125457.122, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708037125484.740, "dur": 9.088, + "args": { + "External id": 4672695,"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": 1708037125488.168, "dur": 5.456, + "args": { + "External id": 4672696,"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": 1708037125581.641, "dur": 81.852, + "args": { + "External id": 4672697,"Record function id": 0, "Ev Idx": 8016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708037125665.414, "dur": 1070.537, + "args": { + "External id": 4672698,"Record function id": 0, "Ev Idx": 8017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037125708.144, "dur": 1013.760, + "args": { + "External id": 4672699,"Sequence number": 46526484, "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": 1708037125708.144, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708037125773.807, "dur": 42.785, + "args": { + "External id": 4672700,"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": 1708037125829.079, "dur": 106.053, + "args": { + "External id": 4672701,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037125946.865, "dur": 76.196, + "args": { + "External id": 4672702,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037126034.662, "dur": 35.246, + "args": { + "External id": 4672703,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037126096.004, "dur": 25.948, + "args": { + "External id": 4672704,"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": 1708037126139.340, "dur": 13.196, + "args": { + "External id": 4672705,"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": 1708037126171.083, "dur": 121.377, + "args": { + "External id": 4672706,"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": 1708037126218.095, "dur": 11.097, + "args": { + "External id": 4672707,"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": 1708037126223.459, "dur": 5.013, + "args": { + "External id": 4672708,"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": 1708037126232.164, "dur": 4.209, + "args": { + "External id": 4672709,"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": 1708037126237.822, "dur": 1.296, + "args": { + "External id": 4672710,"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": 1708037126241.462, "dur": 3.572, + "args": { + "External id": 4672711,"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": 1708037126303.132, "dur": 51.872, + "args": { + "External id": 4672712,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037126384.340, "dur": 29.947, + "args": { + "External id": 4672713,"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": 1708037126421.798, "dur": 42.014, + "args": { + "External id": 4672714,"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": 1708037126471.889, "dur": 34.959, + "args": { + "External id": 4672715,"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": 1708037126544.148, "dur": 26.737, + "args": { + "External id": 4672716,"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": 1708037126577.727, "dur": 37.529, + "args": { + "External id": 4672717,"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": 1708037126635.218, "dur": 17.702, + "args": { + "External id": 4672718,"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": 1708037126806.609, "dur": 76.145, + "args": { + "External id": 4672719,"Record function id": 0, "Ev Idx": 8038 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708037126959.813, "dur": 86.169, + "args": { + "External id": 4672720,"Record function id": 0, "Ev Idx": 8039 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.26)", "pid": 1336753, "tid": 1336753, + "ts": 1708037127057.673, "dur": 18878.950, + "args": { + "External id": 4672721,"Record function id": 0, "Ev Idx": 8040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.26)", "pid": 1336753, "tid": 1336753, + "ts": 1708037127066.665, "dur": 889.969, + "args": { + "External id": 4672722,"Record function id": 0, "Ev Idx": 8041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708037127151.654, "dur": 9.383, + "args": { + "External id": 4672723,"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": 1708037127175.531, "dur": 36.241, + "args": { + "External id": 4672724,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037127180.855, "dur": 2.186, + "args": { + "External id": 4672725,"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": 1708037127187.156, "dur": 0.638, + "args": { + "External id": 4672726,"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": 1708037127189.290, "dur": 0.502, + "args": { + "External id": 4672727,"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": 1708037127191.227, "dur": 0.478, + "args": { + "External id": 4672728,"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": 1708037127194.481, "dur": 0.633, + "args": { + "External id": 4672729,"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": 1708037127196.412, "dur": 0.886, + "args": { + "External id": 4672730,"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": 1708037127199.110, "dur": 1.749, + "args": { + "External id": 4672731,"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": 1708037127202.290, "dur": 0.587, + "args": { + "External id": 4672732,"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": 1708037127203.680, "dur": 1.100, + "args": { + "External id": 4672733,"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": 1708037127223.493, "dur": 44.710, + "args": { + "External id": 4672734,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037127304.292, "dur": 131.189, + "args": { + "External id": 4672735,"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": 1708037127314.754, "dur": 4.642, + "args": { + "External id": 4672736,"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": 1708037127324.893, "dur": 10.064, + "args": { + "External id": 4672737,"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": 1708037127329.012, "dur": 5.558, + "args": { + "External id": 4672738,"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": 1708037127332.446, "dur": 0.863, + "args": { + "External id": 4672739,"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": 1708037127341.479, "dur": 47.242, + "args": { + "External id": 4672740,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037127343.637, "dur": 2.438, + "args": { + "External id": 4672741,"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": 1708037127347.097, "dur": 0.665, + "args": { + "External id": 4672742,"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": 1708037127367.529, "dur": 0.728, + "args": { + "External id": 4672743,"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": 1708037127371.222, "dur": 0.462, + "args": { + "External id": 4672744,"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": 1708037127372.862, "dur": 0.800, + "args": { + "External id": 4672745,"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": 1708037127374.575, "dur": 2.233, + "args": { + "External id": 4672746,"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": 1708037127377.820, "dur": 0.632, + "args": { + "External id": 4672747,"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": 1708037127379.448, "dur": 0.592, + "args": { + "External id": 4672748,"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": 1708037127382.819, "dur": 0.486, + "args": { + "External id": 4672749,"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": 1708037127400.068, "dur": 26.919, + "args": { + "External id": 4672750,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037127489.975, "dur": 374.134, + "args": { + "External id": 4672751,"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": 1708037127519.166, "dur": 339.862, + "args": { + "External id": 4672752,"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": 1708037127549.440, "dur": 301.688, + "args": { + "External id": 4672753,"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": 1708037127886.960, "dur": 2.015, + "args": { + "External id": 4672754,"Record function id": 0, "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": 1708037127976.764, "dur": 17749.318, + "args": { + "External id": 4672755,"Record function id": 0, "Ev Idx": 8074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708037128113.763, "dur": 6.847, + "args": { + "External id": 4672756,"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": 1708037128124.221, "dur": 1.454, + "args": { + "External id": 4672757,"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": 1708037128133.562, "dur": 1.083, + "args": { + "External id": 4672758,"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": 1708037128137.821, "dur": 0.793, + "args": { + "External id": 4672759,"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": 1708037128140.007, "dur": 0.930, + "args": { + "External id": 4672760,"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": 1708037128142.350, "dur": 1.014, + "args": { + "External id": 4672761,"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": 1708037128145.199, "dur": 1.242, + "args": { + "External id": 4672762,"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": 1708037128149.422, "dur": 2.309, + "args": { + "External id": 4672763,"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": 1708037128156.434, "dur": 1.297, + "args": { + "External id": 4672764,"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": 1708037128159.499, "dur": 0.764, + "args": { + "External id": 4672765,"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": 1708037128180.424, "dur": 17504.016, + "args": { + "External id": 4672766,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037128195.894, "dur": 17481.646, + "args": { + "External id": 4672767,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037128216.943, "dur": 13.891, + "args": { + "External id": 4672768,"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": 1708037128235.535, "dur": 17405.057, + "args": { + "External id": 4672769,"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": 1708037128238.329, "dur": 17401.721, + "args": { + "External id": 4672770,"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": 1708037128243.560, "dur": 5.577, + "args": { + "External id": 4672771,"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": 1708037128250.905, "dur": 17386.171, + "args": { + "External id": 4672772,"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": 1708037145869.422, "dur": 42.312, + "args": { + "External id": 4672773,"Sequence number": 46526485, "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": 1708037145869.422, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708037145899.335, "dur": 7.540, + "args": { + "External id": 4672774,"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": 1708037145902.643, "dur": 4.040, + "args": { + "External id": 4672775,"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": 1708037145979.423, "dur": 106.986, + "args": { + "External id": 4672776,"Record function id": 0, "Ev Idx": 8095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708037146089.658, "dur": 1075.771, + "args": { + "External id": 4672777,"Record function id": 0, "Ev Idx": 8096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037146129.693, "dur": 1022.215, + "args": { + "External id": 4672778,"Sequence number": 46526486, "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": 1708037146129.693, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708037146197.746, "dur": 46.328, + "args": { + "External id": 4672779,"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": 1708037146257.320, "dur": 105.312, + "args": { + "External id": 4672780,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037146372.709, "dur": 38.753, + "args": { + "External id": 4672781,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037146420.034, "dur": 31.257, + "args": { + "External id": 4672782,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037146476.178, "dur": 26.037, + "args": { + "External id": 4672783,"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": 1708037146520.485, "dur": 32.979, + "args": { + "External id": 4672784,"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": 1708037146572.541, "dur": 133.695, + "args": { + "External id": 4672785,"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": 1708037146625.414, "dur": 12.844, + "args": { + "External id": 4672786,"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": 1708037146630.654, "dur": 6.655, + "args": { + "External id": 4672787,"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": 1708037146640.935, "dur": 4.924, + "args": { + "External id": 4672788,"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": 1708037146647.481, "dur": 1.901, + "args": { + "External id": 4672789,"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": 1708037146651.656, "dur": 3.853, + "args": { + "External id": 4672790,"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": 1708037146717.126, "dur": 49.351, + "args": { + "External id": 4672791,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037146798.504, "dur": 26.850, + "args": { + "External id": 4672792,"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": 1708037146834.072, "dur": 40.691, + "args": { + "External id": 4672793,"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": 1708037146882.724, "dur": 34.752, + "args": { + "External id": 4672794,"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": 1708037146938.960, "dur": 25.662, + "args": { + "External id": 4672795,"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": 1708037146970.291, "dur": 71.471, + "args": { + "External id": 4672796,"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": 1708037147064.844, "dur": 18.811, + "args": { + "External id": 4672797,"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": 1708037147227.452, "dur": 79.811, + "args": { + "External id": 4672798,"Record function id": 0, "Ev Idx": 8117 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336753, "tid": 1336753, + "ts": 1708037147381.549, "dur": 48.342, + "args": { + "External id": 4672799,"Record function id": 0, "Ev Idx": 8118 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.27)", "pid": 1336753, "tid": 1336753, + "ts": 1708037147439.361, "dur": 18730.409, + "args": { + "External id": 4672800,"Record function id": 0, "Ev Idx": 8119 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.27)", "pid": 1336753, "tid": 1336753, + "ts": 1708037147447.277, "dur": 970.380, + "args": { + "External id": 4672801,"Record function id": 0, "Ev Idx": 8120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708037147545.620, "dur": 9.490, + "args": { + "External id": 4672802,"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": 1708037147574.452, "dur": 33.193, + "args": { + "External id": 4672803,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037147579.920, "dur": 2.407, + "args": { + "External id": 4672804,"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": 1708037147586.072, "dur": 0.756, + "args": { + "External id": 4672805,"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": 1708037147587.974, "dur": 0.891, + "args": { + "External id": 4672806,"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": 1708037147589.805, "dur": 0.360, + "args": { + "External id": 4672807,"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": 1708037147592.571, "dur": 0.797, + "args": { + "External id": 4672808,"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": 1708037147594.443, "dur": 0.627, + "args": { + "External id": 4672809,"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": 1708037147596.187, "dur": 2.046, + "args": { + "External id": 4672810,"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": 1708037147599.188, "dur": 0.642, + "args": { + "External id": 4672811,"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": 1708037147600.767, "dur": 0.607, + "args": { + "External id": 4672812,"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": 1708037147621.531, "dur": 38.889, + "args": { + "External id": 4672813,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037147696.175, "dur": 117.348, + "args": { + "External id": 4672814,"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": 1708037147706.515, "dur": 4.340, + "args": { + "External id": 4672815,"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": 1708037147716.329, "dur": 10.052, + "args": { + "External id": 4672816,"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": 1708037147720.695, "dur": 5.282, + "args": { + "External id": 4672817,"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": 1708037147723.962, "dur": 0.901, + "args": { + "External id": 4672818,"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": 1708037147733.080, "dur": 28.990, + "args": { + "External id": 4672819,"Record function id": 0, "Concrete Inputs": ["", "[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": 1708037147734.790, "dur": 5.623, + "args": { + "External id": 4672820,"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": 1708037147741.354, "dur": 0.564, + "args": { + "External id": 4672821,"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": 1708037147742.884, "dur": 0.379, + "args": { + "External id": 4672822,"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": 1708037147746.122, "dur": 0.703, + "args": { + "External id": 4672823,"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": 1708037147747.852, "dur": 0.455, + "args": { + "External id": 4672824,"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": 1708037147749.545, "dur": 0.525, + "args": { + "External id": 4672825,"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": 1708037147752.529, "dur": 0.622, + "args": { + "External id": 4672826,"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": 1708037147754.226, "dur": 0.520, + "args": { + "External id": 4672827,"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": 1708037147755.936, "dur": 2.003, + "args": { + "External id": 4672828,"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": 1708037147774.056, "dur": 31.334, + "args": { + "External id": 4672829,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [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": 1708037147866.649, "dur": 444.598, + "args": { + "External id": 4672830,"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": 1708037147896.728, "dur": 409.080, + "args": { + "External id": 4672831,"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": 1708037147906.575, "dur": 392.798, + "args": { + "External id": 4672832,"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": 1708037148336.541, "dur": 2.448, + "args": { + "External id": 4672833,"Record function id": 0, "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": 1708037148438.626, "dur": 17503.882, + "args": { + "External id": 4672834,"Record function id": 0, "Ev Idx": 8153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708037148598.731, "dur": 8.108, + "args": { + "External id": 4672835,"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": 1708037148610.947, "dur": 1.053, + "args": { + "External id": 4672836,"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": 1708037148613.667, "dur": 1.529, + "args": { + "External id": 4672837,"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": 1708037148618.256, "dur": 1.251, + "args": { + "External id": 4672838,"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": 1708037148620.875, "dur": 1.014, + "args": { + "External id": 4672839,"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": 1708037148623.229, "dur": 0.901, + "args": { + "External id": 4672840,"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": 1708037148625.992, "dur": 0.885, + "args": { + "External id": 4672841,"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": 1708037148629.693, "dur": 1.883, + "args": { + "External id": 4672842,"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": 1708037148633.096, "dur": 1.294, + "args": { + "External id": 4672843,"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": 1708037148635.509, "dur": 0.956, + "args": { + "External id": 4672844,"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": 1708037148656.806, "dur": 17246.536, + "args": { + "External id": 4672845,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037148672.751, "dur": 17223.705, + "args": { + "External id": 4672846,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "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": 1708037148690.880, "dur": 13.684, + "args": { + "External id": 4672847,"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": 1708037148709.257, "dur": 17155.317, + "args": { + "External id": 4672848,"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": 1708037148711.907, "dur": 17152.115, + "args": { + "External id": 4672849,"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": 1708037148717.533, "dur": 5.116, + "args": { + "External id": 4672850,"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": 1708037148724.299, "dur": 17137.011, + "args": { + "External id": 4672851,"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": 1708037166104.740, "dur": 40.057, + "args": { + "External id": 4672852,"Sequence number": 46526487, "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": 1708037166104.740, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336753, "tid": 1336753, + "ts": 1708037166130.905, "dur": 8.795, + "args": { + "External id": 4672853,"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": 1708037166134.620, "dur": 4.713, + "args": { + "External id": 4672854,"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": 1708037166207.390, "dur": 74.582, + "args": { + "External id": 4672855,"Record function id": 0, "Ev Idx": 8174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336753, "tid": 1336753, + "ts": 1708037166283.490, "dur": 1061.802, + "args": { + "External id": 4672856,"Record function id": 0, "Ev Idx": 8175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037166323.647, "dur": 1007.495, + "args": { + "External id": 4672857,"Sequence number": 46526488, "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": 1708037166323.647, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708037166389.627, "dur": 44.208, + "args": { + "External id": 4672858,"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": 1708037166445.887, "dur": 104.515, + "args": { + "External id": 4672859,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037166562.208, "dur": 43.844, + "args": { + "External id": 4672860,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037166614.723, "dur": 31.144, + "args": { + "External id": 4672861,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037166670.489, "dur": 24.672, + "args": { + "External id": 4672862,"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": 1708037166713.148, "dur": 14.174, + "args": { + "External id": 4672863,"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": 1708037166744.331, "dur": 126.394, + "args": { + "External id": 4672864,"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": 1708037166794.872, "dur": 11.423, + "args": { + "External id": 4672865,"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": 1708037166800.323, "dur": 5.212, + "args": { + "External id": 4672866,"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": 1708037166809.153, "dur": 4.182, + "args": { + "External id": 4672867,"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": 1708037166814.815, "dur": 1.657, + "args": { + "External id": 4672868,"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": 1708037166818.841, "dur": 3.200, + "args": { + "External id": 4672869,"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": 1708037166881.819, "dur": 43.269, + "args": { + "External id": 4672870,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["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": 1708037166954.997, "dur": 76.038, + "args": { + "External id": 4672871,"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": 1708037167043.343, "dur": 45.209, + "args": { + "External id": 4672872,"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": 1708037167098.003, "dur": 35.073, + "args": { + "External id": 4672873,"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": 1708037167154.623, "dur": 29.445, + "args": { + "External id": 4672874,"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": 1708037167190.214, "dur": 33.293, + "args": { + "External id": 4672875,"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": 1708037167243.271, "dur": 17.559, + "args": { + "External id": 4672876,"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": 1708037167408.208, "dur": 34.336, + "args": { + "External id": 4672877,"Record function id": 0, "Ev Idx": 8196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037167602.185, "dur": 314.380, + "args": { + "External id": 4672878,"Sequence number": 46526489, "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": 1708037167602.185, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037167634.720, "dur": 8.940, + "args": { + "External id": 4672879,"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": 1708037167636.909, "dur": 6.415, + "args": { + "External id": 4672880,"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": 1708037167654.718, "dur": 12.710, + "args": { + "External id": 4672881,"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": 1708037167658.343, "dur": 8.366, + "args": { + "External id": 4672882,"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": 1708037167676.817, "dur": 5.229, + "args": { + "External id": 4672883,"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": 1708037167894.856, "dur": 7.187, + "args": { + "External id": 4672884,"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": 1708037167898.534, "dur": 3.262, + "args": { + "External id": 4672885,"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": 1708037167946.920, "dur": 169.977, + "args": { + "External id": 4672886,"Sequence number": 46526490, "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": 1708037167950.667, "dur": 14.052, + "args": { + "External id": 4672887,"Sequence number": 46526490, "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": 1708037167950.667, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037167955.900, "dur": 7.174, + "args": { + "External id": 4672888,"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": 1708037167960.559, "dur": 2.168, + "args": { + "External id": 4672889,"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": 1708037167967.699, "dur": 148.884, + "args": { + "External id": 4672890,"Sequence number": 46526491, "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": 1708037167970.948, "dur": 4.591, + "args": { + "External id": 4672891,"Sequence number": 46526491, "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": 1708037167971.788, "dur": 3.604, + "args": { + "External id": 4672892,"Sequence number": 46526491, "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": 1708037167971.788, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037167979.582, "dur": 125.975, + "args": { + "External id": 4672893,"Sequence number": 46526492, "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": 1708037167979.582, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037168110.292, "dur": 5.030, + "args": { + "External id": 4672894,"Sequence number": 46526493, "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": 1708037168110.292, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037168128.824, "dur": 67.202, + "args": { + "External id": 4672895,"Sequence number": 46526494, "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": 1708037168129.974, "dur": 9.572, + "args": { + "External id": 4672896,"Sequence number": 46526494, "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": 1708037168129.974, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037168133.017, "dur": 5.267, + "args": { + "External id": 4672897,"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": 1708037168136.673, "dur": 1.425, + "args": { + "External id": 4672898,"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": 1708037168140.263, "dur": 55.530, + "args": { + "External id": 4672899,"Sequence number": 46526495, "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": 1708037168141.137, "dur": 5.869, + "args": { + "External id": 4672900,"Sequence number": 46526495, "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": 1708037168142.376, "dur": 4.460, + "args": { + "External id": 4672901,"Sequence number": 46526495, "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": 1708037168142.376, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037168147.712, "dur": 41.300, + "args": { + "External id": 4672902,"Sequence number": 46526496, "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": 1708037168147.712, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037168190.623, "dur": 4.703, + "args": { + "External id": 4672903,"Sequence number": 46526497, "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": 1708037168190.623, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037168203.758, "dur": 62.489, + "args": { + "External id": 4672904,"Sequence number": 46526498, "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": 1708037168204.447, "dur": 5.607, + "args": { + "External id": 4672905,"Sequence number": 46526498, "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": 1708037168204.447, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037168206.084, "dur": 2.815, + "args": { + "External id": 4672906,"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": 1708037168207.689, "dur": 1.067, + "args": { + "External id": 4672907,"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": 1708037168212.499, "dur": 53.497, + "args": { + "External id": 4672908,"Sequence number": 46526499, "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": 1708037168213.615, "dur": 5.087, + "args": { + "External id": 4672909,"Sequence number": 46526499, "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": 1708037168214.500, "dur": 4.058, + "args": { + "External id": 4672910,"Sequence number": 46526499, "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": 1708037168214.500, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037168219.210, "dur": 38.890, + "args": { + "External id": 4672911,"Sequence number": 46526500, "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": 1708037168219.210, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037168259.668, "dur": 5.937, + "args": { + "External id": 4672912,"Sequence number": 46526501, "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": 1708037168259.668, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037168288.318, "dur": 4.272, + "args": { + "External id": 4672913,"Sequence number": 46526502, "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": 1708037168289.614, "dur": 2.824, + "args": { + "External id": 4672914,"Sequence number": 46526502, "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": 1708037168289.614, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037168300.221, "dur": 3.360, + "args": { + "External id": 4672915,"Sequence number": 46526503, "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": 1708037168301.256, "dur": 2.180, + "args": { + "External id": 4672916,"Sequence number": 46526503, "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": 1708037168301.256, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037168309.544, "dur": 4.935, + "args": { + "External id": 4672917,"Sequence number": 46526504, "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": 1708037168310.728, "dur": 3.612, + "args": { + "External id": 4672918,"Sequence number": 46526504, "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": 1708037168310.728, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037168350.247, "dur": 199.794, + "args": { + "External id": 4672919,"Sequence number": 46526505, "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": 1708037168350.247, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1708037168373.306, "dur": 8.571, + "args": { + "External id": 4672920,"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": 1708037168376.657, "dur": 4.783, + "args": { + "External id": 4672921,"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": 1708037168566.324, "dur": 120.257, + "args": { + "External id": 4672922,"Sequence number": 46526506, "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": 1708037168566.324, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1708037168583.030, "dur": 9.408, + "args": { + "External id": 4672923,"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": 1708037168586.159, "dur": 5.840, + "args": { + "External id": 4672924,"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": 1708037168716.837, "dur": 197.121, + "args": { + "External id": 4672925,"Sequence number": 46526507, "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": 1708037168716.837, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1708037168746.694, "dur": 134.692, + "args": { + "External id": 4672926,"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": 1708037168796.236, "dur": 7.865, + "args": { + "External id": 4672927,"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": 1708037168798.580, "dur": 4.890, + "args": { + "External id": 4672928,"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": 1708037168806.977, "dur": 4.428, + "args": { + "External id": 4672929,"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": 1708037168812.907, "dur": 1.451, + "args": { + "External id": 4672930,"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": 1708037168818.283, "dur": 3.711, + "args": { + "External id": 4672931,"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": 1708037168897.834, "dur": 6.233, + "args": { + "External id": 4672932,"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": 1708037168920.017, "dur": 5.946, + "args": { + "External id": 4672933,"Sequence number": 46526508, "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": 1708037168921.347, "dur": 4.426, + "args": { + "External id": 4672934,"Sequence number": 46526508, "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": 1708037168921.347, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037168942.337, "dur": 174.040, + "args": { + "External id": 4672935,"Sequence number": 46526509, "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": 1708037168945.760, "dur": 9.655, + "args": { + "External id": 4672936,"Sequence number": 46526509, "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": 1708037168945.760, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037168949.242, "dur": 5.148, + "args": { + "External id": 4672937,"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": 1708037168951.726, "dur": 2.360, + "args": { + "External id": 4672938,"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": 1708037168956.945, "dur": 159.048, + "args": { + "External id": 4672939,"Sequence number": 46526510, "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": 1708037168958.972, "dur": 8.623, + "args": { + "External id": 4672940,"Sequence number": 46526510, "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": 1708037168961.722, "dur": 5.653, + "args": { + "External id": 4672941,"Sequence number": 46526510, "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": 1708037168961.722, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037168968.706, "dur": 136.586, + "args": { + "External id": 4672942,"Sequence number": 46526511, "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": 1708037168968.706, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037169109.689, "dur": 5.360, + "args": { + "External id": 4672943,"Sequence number": 46526512, "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": 1708037169109.689, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037169156.513, "dur": 233.022, + "args": { + "External id": 4672944,"Sequence number": 46526513, "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": 1708037169156.513, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037169177.848, "dur": 3.947, + "args": { + "External id": 4672945,"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": 1708037169179.334, "dur": 2.287, + "args": { + "External id": 4672946,"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": 1708037169187.489, "dur": 4.536, + "args": { + "External id": 4672947,"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": 1708037169188.812, "dur": 3.110, + "args": { + "External id": 4672948,"Record 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": 1708037169189.970, "dur": 1.844, + "args": { + "External id": 4672949,"Record 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": 1708037169200.460, "dur": 9.365, + "args": { + "External id": 4672950,"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": 1708037169204.600, "dur": 4.904, + "args": { + "External id": 4672951,"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": 1708037169216.940, "dur": 4.357, + "args": { + "External id": 4672952,"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": 1708037169224.852, "dur": 3.165, + "args": { + "External id": 4672953,"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": 1708037169364.526, "dur": 3.851, + "args": { + "External id": 4672954,"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": 1708037169365.891, "dur": 2.293, + "args": { + "External id": 4672955,"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": 1708037169370.959, "dur": 2.625, + "args": { + "External id": 4672956,"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": 1708037169372.250, "dur": 1.216, + "args": { + "External id": 4672957,"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": 1708037169410.163, "dur": 94.444, + "args": { + "External id": 4672958,"Sequence number": 46526514, "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": 1708037169411.702, "dur": 8.116, + "args": { + "External id": 4672959,"Sequence number": 46526514, "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": 1708037169411.702, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037169414.168, "dur": 4.465, + "args": { + "External id": 4672960,"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": 1708037169416.521, "dur": 1.787, + "args": { + "External id": 4672961,"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": 1708037169420.898, "dur": 83.331, + "args": { + "External id": 4672962,"Sequence number": 46526515, "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": 1708037169423.911, "dur": 3.853, + "args": { + "External id": 4672963,"Sequence number": 46526515, "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": 1708037169424.654, "dur": 2.907, + "args": { + "External id": 4672964,"Sequence number": 46526515, "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": 1708037169424.654, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037169428.721, "dur": 70.069, + "args": { + "External id": 4672965,"Sequence number": 46526516, "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": 1708037169428.721, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037169500.648, "dur": 2.989, + "args": { + "External id": 4672966,"Sequence number": 46526517, "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": 1708037169500.648, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037169513.793, "dur": 95.429, + "args": { + "External id": 4672967,"Sequence number": 46526518, "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": 1708037169516.254, "dur": 6.449, + "args": { + "External id": 4672968,"Sequence number": 46526518, "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": 1708037169516.254, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037169518.449, "dur": 3.102, + "args": { + "External id": 4672969,"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": 1708037169520.066, "dur": 1.341, + "args": { + "External id": 4672970,"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": 1708037169523.486, "dur": 85.456, + "args": { + "External id": 4672971,"Sequence number": 46526519, "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": 1708037169541.461, "dur": 9.224, + "args": { + "External id": 4672972,"Sequence number": 46526519, "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": 1708037169544.098, "dur": 6.336, + "args": { + "External id": 4672973,"Sequence number": 46526519, "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": 1708037169544.098, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037169551.559, "dur": 50.957, + "args": { + "External id": 4672974,"Sequence number": 46526520, "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": 1708037169551.559, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037169604.057, "dur": 4.319, + "args": { + "External id": 4672975,"Sequence number": 46526521, "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": 1708037169604.057, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037169632.633, "dur": 156.820, + "args": { + "External id": 4672976,"Sequence number": 46526522, "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": 1708037169632.633, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708037169676.077, "dur": 4.918, + "args": { + "External id": 4672977,"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": 1708037169716.804, "dur": 58.445, + "args": { + "External id": 4672978,"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": 1708037169717.690, "dur": 6.111, + "args": { + "External id": 4672979,"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": 1708037169718.978, "dur": 3.828, + "args": { + "External id": 4672980,"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": 1708037169720.783, "dur": 1.860, + "args": { + "External id": 4672981,"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": 1708037169724.501, "dur": 50.442, + "args": { + "External id": 4672982,"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": 1708037169727.745, "dur": 2.244, + "args": { + "External id": 4672983,"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": 1708037169728.453, "dur": 1.426, + "args": { + "External id": 4672984,"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": 1708037169730.418, "dur": 40.893, + "args": { + "External id": 4672985,"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": 1708037169773.033, "dur": 1.186, + "args": { + "External id": 4672986,"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": 1708037169799.852, "dur": 26.326, + "args": { + "External id": 4672987,"Sequence number": 46526523, "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": 1708037169799.852, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037169861.444, "dur": 234.826, + "args": { + "External id": 4672988,"Sequence number": 46526524, "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": 1708037169861.444, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037169880.013, "dur": 4.693, + "args": { + "External id": 4672989,"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": 1708037169882.599, "dur": 2.011, + "args": { + "External id": 4672990,"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": 1708037169892.403, "dur": 7.121, + "args": { + "External id": 4672991,"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": 1708037169894.926, "dur": 4.210, + "args": { + "External id": 4672992,"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": 1708037169905.449, "dur": 3.917, + "args": { + "External id": 4672993,"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": 1708037170078.203, "dur": 4.616, + "args": { + "External id": 4672994,"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": 1708037170079.413, "dur": 3.035, + "args": { + "External id": 4672995,"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": 1708037170117.812, "dur": 90.468, + "args": { + "External id": 4672996,"Sequence number": 46526525, "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": 1708037170119.030, "dur": 9.716, + "args": { + "External id": 4672997,"Sequence number": 46526525, "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": 1708037170119.030, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037170123.512, "dur": 3.801, + "args": { + "External id": 4672998,"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": 1708037170125.465, "dur": 1.452, + "args": { + "External id": 4672999,"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": 1708037170129.762, "dur": 78.241, + "args": { + "External id": 4673000,"Sequence number": 46526526, "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": 1708037170131.337, "dur": 5.803, + "args": { + "External id": 4673001,"Sequence number": 46526526, "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": 1708037170133.673, "dur": 3.341, + "args": { + "External id": 4673002,"Sequence number": 46526526, "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": 1708037170133.673, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037170138.046, "dur": 64.227, + "args": { + "External id": 4673003,"Sequence number": 46526527, "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": 1708037170138.046, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037170204.493, "dur": 2.839, + "args": { + "External id": 4673004,"Sequence number": 46526528, "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": 1708037170204.493, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037170216.955, "dur": 66.937, + "args": { + "External id": 4673005,"Sequence number": 46526529, "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": 1708037170217.585, "dur": 10.147, + "args": { + "External id": 4673006,"Sequence number": 46526529, "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": 1708037170217.585, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037170224.027, "dur": 2.699, + "args": { + "External id": 4673007,"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": 1708037170225.077, "dur": 1.492, + "args": { + "External id": 4673008,"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": 1708037170228.342, "dur": 55.253, + "args": { + "External id": 4673009,"Sequence number": 46526530, "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": 1708037170229.656, "dur": 4.962, + "args": { + "External id": 4673010,"Sequence number": 46526530, "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": 1708037170230.218, "dur": 4.271, + "args": { + "External id": 4673011,"Sequence number": 46526530, "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": 1708037170230.218, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037170235.256, "dur": 44.490, + "args": { + "External id": 4673012,"Sequence number": 46526531, "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": 1708037170235.256, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037170281.222, "dur": 2.051, + "args": { + "External id": 4673013,"Sequence number": 46526532, "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": 1708037170281.222, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037170290.850, "dur": 58.729, + "args": { + "External id": 4673014,"Sequence number": 46526533, "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": 1708037170291.532, "dur": 8.518, + "args": { + "External id": 4673015,"Sequence number": 46526533, "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": 1708037170291.532, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037170293.630, "dur": 5.380, + "args": { + "External id": 4673016,"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": 1708037170296.448, "dur": 2.264, + "args": { + "External id": 4673017,"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": 1708037170300.581, "dur": 48.757, + "args": { + "External id": 4673018,"Sequence number": 46526534, "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": 1708037170301.443, "dur": 4.984, + "args": { + "External id": 4673019,"Sequence number": 46526534, "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": 1708037170302.506, "dur": 3.648, + "args": { + "External id": 4673020,"Sequence number": 46526534, "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": 1708037170302.506, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037170308.398, "dur": 35.613, + "args": { + "External id": 4673021,"Sequence number": 46526535, "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": 1708037170308.398, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037170345.421, "dur": 3.565, + "args": { + "External id": 4673022,"Sequence number": 46526536, "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": 1708037170345.421, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037170364.132, "dur": 4.532, + "args": { + "External id": 4673023,"Sequence number": 46526537, "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": 1708037170364.779, "dur": 3.731, + "args": { + "External id": 4673024,"Sequence number": 46526537, "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": 1708037170364.779, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037170457.166, "dur": 7.669, + "args": { + "External id": 4673025,"Sequence number": 46526538, "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": 1708037170460.603, "dur": 4.103, + "args": { + "External id": 4673026,"Sequence number": 46526538, "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": 1708037170460.603, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037170469.700, "dur": 4.690, + "args": { + "External id": 4673027,"Sequence number": 46526539, "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": 1708037170470.556, "dur": 3.676, + "args": { + "External id": 4673028,"Sequence number": 46526539, "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": 1708037170470.556, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037170503.484, "dur": 181.103, + "args": { + "External id": 4673029,"Sequence number": 46526540, "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": 1708037170503.484, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1708037170522.762, "dur": 25.856, + "args": { + "External id": 4673030,"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": 1708037170541.932, "dur": 6.014, + "args": { + "External id": 4673031,"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": 1708037170699.626, "dur": 96.896, + "args": { + "External id": 4673032,"Sequence number": 46526541, "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": 1708037170699.626, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1708037170713.613, "dur": 6.372, + "args": { + "External id": 4673033,"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": 1708037170715.734, "dur": 3.764, + "args": { + "External id": 4673034,"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": 1708037170823.472, "dur": 213.865, + "args": { + "External id": 4673035,"Sequence number": 46526542, "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": 1708037170823.472, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1708037170853.715, "dur": 118.144, + "args": { + "External id": 4673036,"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": 1708037170900.647, "dur": 6.905, + "args": { + "External id": 4673037,"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": 1708037170903.115, "dur": 4.048, + "args": { + "External id": 4673038,"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": 1708037170909.961, "dur": 3.852, + "args": { + "External id": 4673039,"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": 1708037170914.981, "dur": 2.674, + "args": { + "External id": 4673040,"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": 1708037170920.144, "dur": 3.347, + "args": { + "External id": 4673041,"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": 1708037170983.815, "dur": 40.634, + "args": { + "External id": 4673042,"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": 1708037171044.410, "dur": 7.603, + "args": { + "External id": 4673043,"Sequence number": 46526543, "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": 1708037171045.990, "dur": 5.864, + "args": { + "External id": 4673044,"Sequence number": 46526543, "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": 1708037171045.990, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037171068.330, "dur": 111.988, + "args": { + "External id": 4673045,"Sequence number": 46526544, "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": 1708037171069.667, "dur": 8.859, + "args": { + "External id": 4673046,"Sequence number": 46526544, "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": 1708037171069.667, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037171072.673, "dur": 4.560, + "args": { + "External id": 4673047,"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": 1708037171074.950, "dur": 1.947, + "args": { + "External id": 4673048,"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": 1708037171080.045, "dur": 99.916, + "args": { + "External id": 4673049,"Sequence number": 46526545, "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": 1708037171083.305, "dur": 4.356, + "args": { + "External id": 4673050,"Sequence number": 46526545, "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": 1708037171083.916, "dur": 3.576, + "args": { + "External id": 4673051,"Sequence number": 46526545, "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": 1708037171083.916, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037171088.611, "dur": 83.046, + "args": { + "External id": 4673052,"Sequence number": 46526546, "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": 1708037171088.611, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037171173.962, "dur": 5.233, + "args": { + "External id": 4673053,"Sequence number": 46526547, "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": 1708037171173.962, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037171216.426, "dur": 217.377, + "args": { + "External id": 4673054,"Sequence number": 46526548, "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": 1708037171216.426, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037171238.192, "dur": 2.541, + "args": { + "External id": 4673055,"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": 1708037171238.938, "dur": 1.659, + "args": { + "External id": 4673056,"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": 1708037171245.130, "dur": 5.448, + "args": { + "External id": 4673057,"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": 1708037171246.010, "dur": 4.458, + "args": { + "External id": 4673058,"Record 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": 1708037171249.080, "dur": 1.293, + "args": { + "External id": 4673059,"Record 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": 1708037171258.678, "dur": 8.124, + "args": { + "External id": 4673060,"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": 1708037171261.275, "dur": 5.087, + "args": { + "External id": 4673061,"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": 1708037171272.926, "dur": 4.029, + "args": { + "External id": 4673062,"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": 1708037171280.675, "dur": 3.701, + "args": { + "External id": 4673063,"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": 1708037171411.706, "dur": 3.182, + "args": { + "External id": 4673064,"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": 1708037171412.729, "dur": 1.865, + "args": { + "External id": 4673065,"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": 1708037171418.818, "dur": 2.636, + "args": { + "External id": 4673066,"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": 1708037171420.165, "dur": 1.167, + "args": { + "External id": 4673067,"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": 1708037171453.444, "dur": 108.833, + "args": { + "External id": 4673068,"Sequence number": 46526549, "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": 1708037171454.418, "dur": 6.795, + "args": { + "External id": 4673069,"Sequence number": 46526549, "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": 1708037171454.418, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037171456.904, "dur": 3.035, + "args": { + "External id": 4673070,"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": 1708037171458.526, "dur": 1.169, + "args": { + "External id": 4673071,"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": 1708037171463.703, "dur": 98.266, + "args": { + "External id": 4673072,"Sequence number": 46526550, "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": 1708037171464.949, "dur": 3.685, + "args": { + "External id": 4673073,"Sequence number": 46526550, "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": 1708037171466.070, "dur": 2.419, + "args": { + "External id": 4673074,"Sequence number": 46526550, "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": 1708037171466.070, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037171469.323, "dur": 83.404, + "args": { + "External id": 4673075,"Sequence number": 46526551, "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": 1708037171469.323, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037171556.077, "dur": 5.036, + "args": { + "External id": 4673076,"Sequence number": 46526552, "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": 1708037171556.077, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037171571.566, "dur": 71.795, + "args": { + "External id": 4673077,"Sequence number": 46526553, "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": 1708037171572.155, "dur": 6.750, + "args": { + "External id": 4673078,"Sequence number": 46526553, "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": 1708037171572.155, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037171574.655, "dur": 2.940, + "args": { + "External id": 4673079,"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": 1708037171576.291, "dur": 1.147, + "args": { + "External id": 4673080,"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": 1708037171579.613, "dur": 63.477, + "args": { + "External id": 4673081,"Sequence number": 46526554, "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": 1708037171582.131, "dur": 5.655, + "args": { + "External id": 4673082,"Sequence number": 46526554, "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": 1708037171582.946, "dur": 4.685, + "args": { + "External id": 4673083,"Sequence number": 46526554, "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": 1708037171582.946, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037171588.294, "dur": 48.892, + "args": { + "External id": 4673084,"Sequence number": 46526555, "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": 1708037171588.294, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037171638.829, "dur": 3.860, + "args": { + "External id": 4673085,"Sequence number": 46526556, "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": 1708037171638.829, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037171665.708, "dur": 141.792, + "args": { + "External id": 4673086,"Sequence number": 46526557, "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": 1708037171665.708, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708037171702.947, "dur": 4.537, + "args": { + "External id": 4673087,"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": 1708037171737.271, "dur": 57.594, + "args": { + "External id": 4673088,"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": 1708037171738.012, "dur": 4.905, + "args": { + "External id": 4673089,"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": 1708037171739.183, "dur": 2.944, + "args": { + "External id": 4673090,"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": 1708037171740.640, "dur": 1.275, + "args": { + "External id": 4673091,"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": 1708037171745.510, "dur": 49.045, + "args": { + "External id": 4673092,"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": 1708037171746.914, "dur": 2.522, + "args": { + "External id": 4673093,"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": 1708037171747.900, "dur": 1.388, + "args": { + "External id": 4673094,"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": 1708037171750.155, "dur": 40.823, + "args": { + "External id": 4673095,"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": 1708037171792.742, "dur": 1.227, + "args": { + "External id": 4673096,"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": 1708037171815.741, "dur": 23.733, + "args": { + "External id": 4673097,"Sequence number": 46526558, "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": 1708037171815.741, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037171872.551, "dur": 219.787, + "args": { + "External id": 4673098,"Sequence number": 46526559, "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": 1708037171872.551, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037171891.238, "dur": 2.875, + "args": { + "External id": 4673099,"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": 1708037171892.089, "dur": 1.906, + "args": { + "External id": 4673100,"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": 1708037171901.284, "dur": 6.131, + "args": { + "External id": 4673101,"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": 1708037171903.348, "dur": 3.662, + "args": { + "External id": 4673102,"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": 1708037171913.056, "dur": 3.377, + "args": { + "External id": 4673103,"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": 1708037172073.439, "dur": 4.296, + "args": { + "External id": 4673104,"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": 1708037172074.503, "dur": 2.985, + "args": { + "External id": 4673105,"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": 1708037172112.193, "dur": 85.871, + "args": { + "External id": 4673106,"Sequence number": 46526560, "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": 1708037172113.106, "dur": 6.999, + "args": { + "External id": 4673107,"Sequence number": 46526560, "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": 1708037172113.106, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037172115.498, "dur": 3.147, + "args": { + "External id": 4673108,"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": 1708037172117.378, "dur": 1.053, + "args": { + "External id": 4673109,"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": 1708037172121.043, "dur": 76.635, + "args": { + "External id": 4673110,"Sequence number": 46526561, "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": 1708037172124.255, "dur": 3.591, + "args": { + "External id": 4673111,"Sequence number": 46526561, "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": 1708037172124.920, "dur": 2.772, + "args": { + "External id": 4673112,"Sequence number": 46526561, "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": 1708037172124.920, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037172128.707, "dur": 61.853, + "args": { + "External id": 4673113,"Sequence number": 46526562, "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": 1708037172128.707, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037172192.518, "dur": 4.476, + "args": { + "External id": 4673114,"Sequence number": 46526563, "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": 1708037172192.518, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037172206.145, "dur": 60.174, + "args": { + "External id": 4673115,"Sequence number": 46526564, "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": 1708037172208.811, "dur": 6.311, + "args": { + "External id": 4673116,"Sequence number": 46526564, "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": 1708037172208.811, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037172211.355, "dur": 2.373, + "args": { + "External id": 4673117,"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": 1708037172212.965, "dur": 0.629, + "args": { + "External id": 4673118,"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": 1708037172215.608, "dur": 50.494, + "args": { + "External id": 4673119,"Sequence number": 46526565, "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": 1708037172216.505, "dur": 4.382, + "args": { + "External id": 4673120,"Sequence number": 46526565, "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": 1708037172218.802, "dur": 1.949, + "args": { + "External id": 4673121,"Sequence number": 46526565, "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": 1708037172218.802, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037172221.489, "dur": 40.054, + "args": { + "External id": 4673122,"Sequence number": 46526566, "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": 1708037172221.489, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037172263.183, "dur": 2.571, + "args": { + "External id": 4673123,"Sequence number": 46526567, "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": 1708037172263.183, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037172272.402, "dur": 59.981, + "args": { + "External id": 4673124,"Sequence number": 46526568, "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": 1708037172273.330, "dur": 8.299, + "args": { + "External id": 4673125,"Sequence number": 46526568, "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": 1708037172273.330, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037172276.463, "dur": 3.887, + "args": { + "External id": 4673126,"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": 1708037172277.735, "dur": 2.306, + "args": { + "External id": 4673127,"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": 1708037172282.159, "dur": 49.940, + "args": { + "External id": 4673128,"Sequence number": 46526569, "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": 1708037172283.176, "dur": 5.263, + "args": { + "External id": 4673129,"Sequence number": 46526569, "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": 1708037172285.364, "dur": 2.945, + "args": { + "External id": 4673130,"Sequence number": 46526569, "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": 1708037172285.364, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037172288.899, "dur": 37.732, + "args": { + "External id": 4673131,"Sequence number": 46526570, "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": 1708037172288.899, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037172328.142, "dur": 3.597, + "args": { + "External id": 4673132,"Sequence number": 46526571, "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": 1708037172328.142, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037172346.945, "dur": 6.271, + "args": { + "External id": 4673133,"Sequence number": 46526572, "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": 1708037172349.002, "dur": 3.973, + "args": { + "External id": 4673134,"Sequence number": 46526572, "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": 1708037172349.002, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037172359.604, "dur": 2.749, + "args": { + "External id": 4673135,"Sequence number": 46526573, "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": 1708037172360.558, "dur": 1.670, + "args": { + "External id": 4673136,"Sequence number": 46526573, "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": 1708037172360.558, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037172366.587, "dur": 3.574, + "args": { + "External id": 4673137,"Sequence number": 46526574, "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": 1708037172367.584, "dur": 2.458, + "args": { + "External id": 4673138,"Sequence number": 46526574, "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": 1708037172367.584, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037172397.805, "dur": 171.007, + "args": { + "External id": 4673139,"Sequence number": 46526575, "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": 1708037172397.805, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1708037172417.938, "dur": 9.429, + "args": { + "External id": 4673140,"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": 1708037172420.441, "dur": 6.410, + "args": { + "External id": 4673141,"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": 1708037172583.401, "dur": 111.678, + "args": { + "External id": 4673142,"Sequence number": 46526576, "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": 1708037172583.401, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1708037172597.530, "dur": 8.001, + "args": { + "External id": 4673143,"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": 1708037172600.019, "dur": 5.115, + "args": { + "External id": 4673144,"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": 1708037172723.136, "dur": 170.293, + "args": { + "External id": 4673145,"Sequence number": 46526577, "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": 1708037172723.136, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1708037172749.002, "dur": 120.599, + "args": { + "External id": 4673146,"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": 1708037172796.565, "dur": 6.802, + "args": { + "External id": 4673147,"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": 1708037172798.945, "dur": 4.023, + "args": { + "External id": 4673148,"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": 1708037172805.936, "dur": 3.905, + "args": { + "External id": 4673149,"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": 1708037172811.000, "dur": 1.821, + "args": { + "External id": 4673150,"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": 1708037172815.532, "dur": 3.099, + "args": { + "External id": 4673151,"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": 1708037172880.823, "dur": 4.350, + "args": { + "External id": 4673152,"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": 1708037172898.739, "dur": 5.589, + "args": { + "External id": 4673153,"Sequence number": 46526578, "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": 1708037172900.040, "dur": 4.154, + "args": { + "External id": 4673154,"Sequence number": 46526578, "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": 1708037172900.040, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037172914.415, "dur": 145.455, + "args": { + "External id": 4673155,"Sequence number": 46526579, "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": 1708037172915.798, "dur": 11.118, + "args": { + "External id": 4673156,"Sequence number": 46526579, "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": 1708037172915.798, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037172920.742, "dur": 4.965, + "args": { + "External id": 4673157,"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": 1708037172924.033, "dur": 1.433, + "args": { + "External id": 4673158,"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": 1708037172928.182, "dur": 131.243, + "args": { + "External id": 4673159,"Sequence number": 46526580, "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": 1708037172929.854, "dur": 3.725, + "args": { + "External id": 4673160,"Sequence number": 46526580, "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": 1708037172930.841, "dur": 2.625, + "args": { + "External id": 4673161,"Sequence number": 46526580, "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": 1708037172930.841, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037172934.603, "dur": 114.397, + "args": { + "External id": 4673162,"Sequence number": 46526581, "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": 1708037172934.603, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037173053.051, "dur": 5.500, + "args": { + "External id": 4673163,"Sequence number": 46526582, "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": 1708037173053.051, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037173095.680, "dur": 199.609, + "args": { + "External id": 4673164,"Sequence number": 46526583, "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": 1708037173095.680, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037173113.460, "dur": 3.244, + "args": { + "External id": 4673165,"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": 1708037173114.624, "dur": 1.955, + "args": { + "External id": 4673166,"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": 1708037173120.460, "dur": 5.204, + "args": { + "External id": 4673167,"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": 1708037173123.448, "dur": 2.108, + "args": { + "External id": 4673168,"Record 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": 1708037173124.168, "dur": 1.288, + "args": { + "External id": 4673169,"Record 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": 1708037173132.844, "dur": 7.898, + "args": { + "External id": 4673170,"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": 1708037173134.763, "dur": 5.657, + "args": { + "External id": 4673171,"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": 1708037173146.744, "dur": 3.511, + "args": { + "External id": 4673172,"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": 1708037173153.588, "dur": 3.451, + "args": { + "External id": 4673173,"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": 1708037173274.250, "dur": 3.138, + "args": { + "External id": 4673174,"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": 1708037173275.129, "dur": 1.988, + "args": { + "External id": 4673175,"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": 1708037173280.154, "dur": 2.441, + "args": { + "External id": 4673176,"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": 1708037173281.120, "dur": 1.364, + "args": { + "External id": 4673177,"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": 1708037173313.272, "dur": 101.510, + "args": { + "External id": 4673178,"Sequence number": 46526584, "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": 1708037173321.881, "dur": 8.618, + "args": { + "External id": 4673179,"Sequence number": 46526584, "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": 1708037173321.881, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037173325.849, "dur": 3.395, + "args": { + "External id": 4673180,"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": 1708037173327.678, "dur": 1.276, + "args": { + "External id": 4673181,"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": 1708037173331.452, "dur": 83.082, + "args": { + "External id": 4673182,"Sequence number": 46526585, "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": 1708037173333.047, "dur": 6.029, + "args": { + "External id": 4673183,"Sequence number": 46526585, "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": 1708037173333.670, "dur": 5.221, + "args": { + "External id": 4673184,"Sequence number": 46526585, "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": 1708037173333.670, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037173340.053, "dur": 67.151, + "args": { + "External id": 4673185,"Sequence number": 46526586, "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": 1708037173340.053, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037173409.119, "dur": 4.836, + "args": { + "External id": 4673186,"Sequence number": 46526587, "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": 1708037173409.119, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037173422.023, "dur": 87.412, + "args": { + "External id": 4673187,"Sequence number": 46526588, "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": 1708037173422.707, "dur": 7.499, + "args": { + "External id": 4673188,"Sequence number": 46526588, "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": 1708037173422.707, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037173424.136, "dur": 4.857, + "args": { + "External id": 4673189,"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": 1708037173427.793, "dur": 1.055, + "args": { + "External id": 4673190,"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": 1708037173430.860, "dur": 78.389, + "args": { + "External id": 4673191,"Sequence number": 46526589, "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": 1708037173431.774, "dur": 5.179, + "args": { + "External id": 4673192,"Sequence number": 46526589, "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": 1708037173432.913, "dur": 3.878, + "args": { + "External id": 4673193,"Sequence number": 46526589, "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": 1708037173432.913, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037173439.509, "dur": 65.436, + "args": { + "External id": 4673194,"Sequence number": 46526590, "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": 1708037173439.509, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037173506.649, "dur": 2.195, + "args": { + "External id": 4673195,"Sequence number": 46526591, "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": 1708037173506.649, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037173544.644, "dur": 160.256, + "args": { + "External id": 4673196,"Sequence number": 46526592, "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": 1708037173544.644, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708037173582.421, "dur": 4.773, + "args": { + "External id": 4673197,"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": 1708037173621.576, "dur": 70.417, + "args": { + "External id": 4673198,"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": 1708037173622.480, "dur": 5.290, + "args": { + "External id": 4673199,"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": 1708037173623.863, "dur": 2.867, + "args": { + "External id": 4673200,"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": 1708037173625.689, "dur": 0.767, + "args": { + "External id": 4673201,"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": 1708037173628.512, "dur": 63.115, + "args": { + "External id": 4673202,"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": 1708037173629.823, "dur": 2.258, + "args": { + "External id": 4673203,"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": 1708037173630.578, "dur": 1.392, + "args": { + "External id": 4673204,"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": 1708037173635.228, "dur": 52.405, + "args": { + "External id": 4673205,"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": 1708037173689.514, "dur": 1.286, + "args": { + "External id": 4673206,"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": 1708037173713.707, "dur": 26.229, + "args": { + "External id": 4673207,"Sequence number": 46526593, "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": 1708037173713.707, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037173774.536, "dur": 207.795, + "args": { + "External id": 4673208,"Sequence number": 46526594, "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": 1708037173774.536, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037173792.417, "dur": 2.818, + "args": { + "External id": 4673209,"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": 1708037173793.535, "dur": 1.548, + "args": { + "External id": 4673210,"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": 1708037173818.728, "dur": 9.943, + "args": { + "External id": 4673211,"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": 1708037173823.317, "dur": 4.905, + "args": { + "External id": 4673212,"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": 1708037173845.622, "dur": 5.802, + "args": { + "External id": 4673213,"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": 1708037173969.300, "dur": 3.652, + "args": { + "External id": 4673214,"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": 1708037173970.716, "dur": 1.989, + "args": { + "External id": 4673215,"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": 1708037174038.438, "dur": 95.018, + "args": { + "External id": 4673216,"Sequence number": 46526595, "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": 1708037174039.514, "dur": 9.814, + "args": { + "External id": 4673217,"Sequence number": 46526595, "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": 1708037174039.514, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037174042.022, "dur": 5.406, + "args": { + "External id": 4673218,"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": 1708037174045.332, "dur": 1.775, + "args": { + "External id": 4673219,"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": 1708037174050.291, "dur": 82.893, + "args": { + "External id": 4673220,"Sequence number": 46526596, "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": 1708037174051.406, "dur": 4.160, + "args": { + "External id": 4673221,"Sequence number": 46526596, "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": 1708037174052.060, "dur": 3.361, + "args": { + "External id": 4673222,"Sequence number": 46526596, "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": 1708037174052.060, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037174058.572, "dur": 67.964, + "args": { + "External id": 4673223,"Sequence number": 46526597, "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": 1708037174058.572, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037174128.606, "dur": 3.769, + "args": { + "External id": 4673224,"Sequence number": 46526598, "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": 1708037174128.606, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037174140.703, "dur": 64.302, + "args": { + "External id": 4673225,"Sequence number": 46526599, "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": 1708037174141.460, "dur": 8.854, + "args": { + "External id": 4673226,"Sequence number": 46526599, "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": 1708037174141.460, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037174142.629, "dur": 6.318, + "args": { + "External id": 4673227,"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": 1708037174145.727, "dur": 2.980, + "args": { + "External id": 4673228,"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": 1708037174150.915, "dur": 53.802, + "args": { + "External id": 4673229,"Sequence number": 46526600, "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": 1708037174151.890, "dur": 3.827, + "args": { + "External id": 4673230,"Sequence number": 46526600, "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": 1708037174152.681, "dur": 2.898, + "args": { + "External id": 4673231,"Sequence number": 46526600, "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": 1708037174152.681, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037174156.298, "dur": 42.550, + "args": { + "External id": 4673232,"Sequence number": 46526601, "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": 1708037174156.298, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037174200.092, "dur": 4.260, + "args": { + "External id": 4673233,"Sequence number": 46526602, "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": 1708037174200.092, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037174211.305, "dur": 58.396, + "args": { + "External id": 4673234,"Sequence number": 46526603, "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": 1708037174212.072, "dur": 5.157, + "args": { + "External id": 4673235,"Sequence number": 46526603, "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": 1708037174212.072, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037174213.730, "dur": 2.204, + "args": { + "External id": 4673236,"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": 1708037174215.197, "dur": 0.614, + "args": { + "External id": 4673237,"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": 1708037174219.247, "dur": 50.272, + "args": { + "External id": 4673238,"Sequence number": 46526604, "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": 1708037174220.380, "dur": 4.959, + "args": { + "External id": 4673239,"Sequence number": 46526604, "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": 1708037174221.204, "dur": 3.993, + "args": { + "External id": 4673240,"Sequence number": 46526604, "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": 1708037174221.204, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037174225.969, "dur": 38.333, + "args": { + "External id": 4673241,"Sequence number": 46526605, "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": 1708037174225.969, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037174265.663, "dur": 3.558, + "args": { + "External id": 4673242,"Sequence number": 46526606, "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": 1708037174265.663, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037174284.713, "dur": 4.537, + "args": { + "External id": 4673243,"Sequence number": 46526607, "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": 1708037174286.089, "dur": 3.026, + "args": { + "External id": 4673244,"Sequence number": 46526607, "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": 1708037174286.089, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037174295.876, "dur": 3.772, + "args": { + "External id": 4673245,"Sequence number": 46526608, "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": 1708037174296.817, "dur": 2.660, + "args": { + "External id": 4673246,"Sequence number": 46526608, "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": 1708037174296.817, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037174305.201, "dur": 4.894, + "args": { + "External id": 4673247,"Sequence number": 46526609, "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": 1708037174306.183, "dur": 3.756, + "args": { + "External id": 4673248,"Sequence number": 46526609, "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": 1708037174306.183, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037174335.753, "dur": 147.620, + "args": { + "External id": 4673249,"Sequence number": 46526610, "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": 1708037174335.753, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1708037174354.324, "dur": 8.742, + "args": { + "External id": 4673250,"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": 1708037174357.635, "dur": 4.928, + "args": { + "External id": 4673251,"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": 1708037174494.539, "dur": 120.891, + "args": { + "External id": 4673252,"Sequence number": 46526611, "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": 1708037174494.539, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336753, "tid": 1336753, + "ts": 1708037174507.321, "dur": 5.938, + "args": { + "External id": 4673253,"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": 1708037174509.442, "dur": 3.444, + "args": { + "External id": 4673254,"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": 1708037174643.421, "dur": 173.338, + "args": { + "External id": 4673255,"Sequence number": 46526612, "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": 1708037174643.421, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336753, "tid": 1336753, + "ts": 1708037174670.537, "dur": 122.191, + "args": { + "External id": 4673256,"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": 1708037174718.198, "dur": 8.512, + "args": { + "External id": 4673257,"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": 1708037174720.664, "dur": 5.511, + "args": { + "External id": 4673258,"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": 1708037174729.263, "dur": 3.886, + "args": { + "External id": 4673259,"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": 1708037174734.242, "dur": 2.958, + "args": { + "External id": 4673260,"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": 1708037174739.661, "dur": 3.468, + "args": { + "External id": 4673261,"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": 1708037174804.197, "dur": 4.182, + "args": { + "External id": 4673262,"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": 1708037174822.318, "dur": 5.434, + "args": { + "External id": 4673263,"Sequence number": 46526613, "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": 1708037174823.502, "dur": 4.103, + "args": { + "External id": 4673264,"Sequence number": 46526613, "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": 1708037174823.502, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037174838.762, "dur": 92.996, + "args": { + "External id": 4673265,"Sequence number": 46526614, "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": 1708037174841.597, "dur": 6.988, + "args": { + "External id": 4673266,"Sequence number": 46526614, "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": 1708037174841.597, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037174844.056, "dur": 3.491, + "args": { + "External id": 4673267,"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": 1708037174845.957, "dur": 1.357, + "args": { + "External id": 4673268,"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": 1708037174849.769, "dur": 81.736, + "args": { + "External id": 4673269,"Sequence number": 46526615, "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": 1708037174851.550, "dur": 5.058, + "args": { + "External id": 4673270,"Sequence number": 46526615, "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": 1708037174854.023, "dur": 2.454, + "args": { + "External id": 4673271,"Sequence number": 46526615, "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": 1708037174854.023, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037174857.430, "dur": 67.761, + "args": { + "External id": 4673272,"Sequence number": 46526616, "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": 1708037174857.430, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037174927.180, "dur": 3.710, + "args": { + "External id": 4673273,"Sequence number": 46526617, "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": 1708037174927.180, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037174960.977, "dur": 244.324, + "args": { + "External id": 4673274,"Sequence number": 46526618, "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": 1708037174960.977, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336753, "tid": 1336753, + "ts": 1708037174978.404, "dur": 3.086, + "args": { + "External id": 4673275,"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": 1708037174979.575, "dur": 1.768, + "args": { + "External id": 4673276,"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": 1708037175021.189, "dur": 5.206, + "args": { + "External id": 4673277,"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": 1708037175022.602, "dur": 3.680, + "args": { + "External id": 4673278,"Record 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": 1708037175023.690, "dur": 2.324, + "args": { + "External id": 4673279,"Record 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": 1708037175034.753, "dur": 9.746, + "args": { + "External id": 4673280,"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": 1708037175038.337, "dur": 5.780, + "args": { + "External id": 4673281,"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": 1708037175051.089, "dur": 3.438, + "args": { + "External id": 4673282,"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": 1708037175058.402, "dur": 4.426, + "args": { + "External id": 4673283,"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": 1708037175182.752, "dur": 3.467, + "args": { + "External id": 4673284,"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": 1708037175183.804, "dur": 2.215, + "args": { + "External id": 4673285,"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": 1708037175188.879, "dur": 2.578, + "args": { + "External id": 4673286,"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": 1708037175189.873, "dur": 1.469, + "args": { + "External id": 4673287,"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": 1708037175222.836, "dur": 94.157, + "args": { + "External id": 4673288,"Sequence number": 46526619, "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": 1708037175223.937, "dur": 9.353, + "args": { + "External id": 4673289,"Sequence number": 46526619, "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": 1708037175223.937, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037175226.498, "dur": 5.623, + "args": { + "External id": 4673290,"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": 1708037175228.514, "dur": 3.263, + "args": { + "External id": 4673291,"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": 1708037175234.530, "dur": 82.144, + "args": { + "External id": 4673292,"Sequence number": 46526620, "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": 1708037175236.729, "dur": 5.529, + "args": { + "External id": 4673293,"Sequence number": 46526620, "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": 1708037175238.952, "dur": 3.111, + "args": { + "External id": 4673294,"Sequence number": 46526620, "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": 1708037175238.952, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037175243.141, "dur": 66.463, + "args": { + "External id": 4673295,"Sequence number": 46526621, "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": 1708037175243.141, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037175311.363, "dur": 4.747, + "args": { + "External id": 4673296,"Sequence number": 46526622, "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": 1708037175311.363, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336753, "tid": 1336753, + "ts": 1708037175325.140, "dur": 72.366, + "args": { + "External id": 4673297,"Sequence number": 46526623, "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": 1708037175325.649, "dur": 9.416, + "args": { + "External id": 4673298,"Sequence number": 46526623, "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": 1708037175325.649, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336753, "tid": 1336753, + "ts": 1708037175331.098, "dur": 2.799, + "args": { + "External id": 4673299,"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": 1708037175332.438, "dur": 1.308, + "args": { + "External id": 4673300,"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": 1708037175335.821, "dur": 61.428, + "args": { + "External id": 4673301,"Sequence number": 46526624, "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": 1708037175336.946, "dur": 8.216, + "args": { + "External id": 4673302,"Sequence number": 46526624, "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": 1708037175340.226, "dur": 4.791, + "args": { + "External id": 4673303,"Sequence number": 46526624, "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": 1708037175340.226, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336753, "tid": 1336753, + "ts": 1708037175345.656, "dur": 47.064, + "args": { + "External id": 4673304,"Sequence number": 46526625, "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": 1708037175345.656, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336753, "tid": 1336753, + "ts": 1708037175394.077, "dur": 2.798, + "args": { + "External id": 4673305,"Sequence number": 46526626, "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": 1708037175394.077, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037175415.299, "dur": 156.860, + "args": { + "External id": 4673306,"Sequence number": 46526627, "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": 1708037175415.299, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336753, "tid": 1336753, + "ts": 1708037175451.152, "dur": 4.273, + "args": { + "External id": 4673307,"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": 1708037175484.238, "dur": 75.921, + "args": { + "External id": 4673308,"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": 1708037175485.403, "dur": 6.013, + "args": { + "External id": 4673309,"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": 1708037175486.385, "dur": 4.384, + "args": { + "External id": 4673310,"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": 1708037175488.343, "dur": 2.200, + "args": { + "External id": 4673311,"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": 1708037175492.100, "dur": 67.745, + "args": { + "External id": 4673312,"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": 1708037175493.373, "dur": 3.948, + "args": { + "External id": 4673313,"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": 1708037175495.639, "dur": 1.464, + "args": { + "External id": 4673314,"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": 1708037175497.860, "dur": 56.652, + "args": { + "External id": 4673315,"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": 1708037175557.647, "dur": 1.389, + "args": { + "External id": 4673316,"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": 1708037175581.605, "dur": 25.333, + "args": { + "External id": 4673317,"Sequence number": 46526628, "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": 1708037175581.605, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 1336753, "tid": 1336753, + "ts": 1708037175625.827, "dur": 42.595, + "args": { + "External id": 4673318,"Sequence number": 46526629, "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": 1708037175625.827, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 1336753, "tid": 1336753, + "ts": 1708037175636.104, "dur": 27.173, + "args": { + "External id": 4673319,"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": 1708037175664.806, "dur": 2.147, + "args": { + "External id": 4673320,"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": 1708037175705.256, "dur": 40.592, + "args": { + "External id": 4673321,"Record function id": 0, "Ev Idx": 8640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 1336753, "tid": 1336753, + "ts": 1708037175747.071, "dur": 189.994, + "args": { + "External id": 4673322,"Record function id": 0, "Ev Idx": 8641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336753, "tid": 1336753, + "ts": 1708037175782.599, "dur": 145.314, + "args": { + "External id": 4673323,"Sequence number": 46526630, "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": 1708037175782.599, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336753, "tid": 1336753, + "ts": 1708037175848.006, "dur": 43.588, + "args": { + "External id": 4673324,"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": 1708037176064.784, "dur": 44.648, + "args": { + "External id": 4673325,"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": 1708037176068.444, "dur": 6.537, + "args": { + "External id": 4673326,"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": 1708037176078.301, "dur": 30.828, + "args": { + "External id": 4673327,"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": 1708037176081.871, "dur": 26.561, + "args": { + "External id": 4673328,"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": 1708037176114.283, "dur": 17.797, + "args": { + "External id": 4673329,"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": 1708037176115.415, "dur": 2.869, + "args": { + "External id": 4673330,"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": 1708037176120.790, "dur": 11.037, + "args": { + "External id": 4673331,"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": 1708037176121.816, "dur": 9.614, + "args": { + "External id": 4673332,"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": 1708037176134.823, "dur": 15.393, + "args": { + "External id": 4673333,"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": 1708037176135.772, "dur": 2.662, + "args": { + "External id": 4673334,"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": 1708037176139.257, "dur": 10.690, + "args": { + "External id": 4673335,"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": 1708037176140.019, "dur": 9.408, + "args": { + "External id": 4673336,"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": 1708037176161.707, "dur": 0.905, + "args": { + "External id": 4673337,"Sequence number": 46526631, "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": 1708037176170.248, "dur": 11.234, + "args": { + "External id": 4673338,"Sequence number": 46526631, "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": 1708037176177.598, "dur": 2.106, + "args": { + "External id": 4673339,"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": 1708037176187.520, "dur": 7.130, + "args": { + "External id": 4673340,"Sequence number": 46526631, "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": 1708037176191.851, "dur": 1.154, + "args": { + "External id": 4673341,"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": 1708037176195.870, "dur": 3.795, + "args": { + "External id": 4673342,"Sequence number": 46526631, "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": 1708037176197.964, "dur": 0.987, + "args": { + "External id": 4673343,"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": 1708037176200.890, "dur": 3.190, + "args": { + "External id": 4673344,"Sequence number": 46526631, "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": 1708037176202.743, "dur": 0.792, + "args": { + "External id": 4673345,"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": 1708037176207.231, "dur": 2.945, + "args": { + "External id": 4673346,"Sequence number": 46526631, "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": 1708037176208.794, "dur": 0.833, + "args": { + "External id": 4673347,"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": 1708037176211.413, "dur": 3.431, + "args": { + "External id": 4673348,"Sequence number": 46526631, "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": 1708037176213.658, "dur": 0.457, + "args": { + "External id": 4673349,"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": 1708037176215.894, "dur": 2.696, + "args": { + "External id": 4673350,"Sequence number": 46526631, "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": 1708037176217.472, "dur": 0.635, + "args": { + "External id": 4673351,"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": 1708037176223.269, "dur": 4.730, + "args": { + "External id": 4673352,"Sequence number": 46526631, "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": 1708037176226.455, "dur": 0.692, + "args": { + "External id": 4673353,"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": 1708037176232.020, "dur": 3.253, + "args": { + "External id": 4673354,"Sequence number": 46526631, "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": 1708037176234.102, "dur": 0.647, + "args": { + "External id": 4673355,"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": 1708037176240.312, "dur": 6.561, + "args": { + "External id": 4673356,"Sequence number": 46526631, "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": 1708037176244.929, "dur": 0.802, + "args": { + "External id": 4673357,"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": 1708037176247.975, "dur": 2.678, + "args": { + "External id": 4673358,"Sequence number": 46526631, "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": 1708037176249.328, "dur": 0.774, + "args": { + "External id": 4673359,"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": 1708037176253.595, "dur": 8.245, + "args": { + "External id": 4673360,"Sequence number": 46526631, "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": 1708037176253.595, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037176259.144, "dur": 0.941, + "args": { + "External id": 4673361,"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": 1708037176263.071, "dur": 4.930, + "args": { + "External id": 4673362,"Sequence number": 46526632, "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": 1708037176263.071, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037176266.730, "dur": 0.553, + "args": { + "External id": 4673363,"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": 1708037176269.249, "dur": 6.833, + "args": { + "External id": 4673364,"Sequence number": 46526633, "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": 1708037176269.249, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037176274.554, "dur": 0.695, + "args": { + "External id": 4673365,"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": 1708037176277.284, "dur": 6.750, + "args": { + "External id": 4673366,"Sequence number": 46526634, "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": 1708037176277.284, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037176280.669, "dur": 2.608, + "args": { + "External id": 4673367,"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": 1708037176289.415, "dur": 38.894, + "args": { + "External id": 4673368,"Sequence number": 46526635, "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": 1708037176291.851, "dur": 36.258, + "args": { + "External id": 4673369,"Sequence number": 46526635, "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": 1708037176294.602, "dur": 5.791, + "args": { + "External id": 4673370,"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": 1708037176296.525, "dur": 3.293, + "args": { + "External id": 4673371,"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": 1708037176302.093, "dur": 25.658, + "args": { + "External id": 4673372,"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": 1708037176352.821, "dur": 4.834, + "args": { + "External id": 4673373,"Sequence number": 46526635, "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": 1708037176352.821, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708037176359.753, "dur": 1.477, + "args": { + "External id": 4673374,"Sequence number": 46526636, "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": 1708037176389.583, "dur": 72043.799, + "args": { + "External id": 4673375,"Sequence number": 46526636, "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": 1708037176389.583, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1708037176403.231, "dur": 28.995, + "args": { + "External id": 4673376,"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": 1708037176404.098, "dur": 27.915, + "args": { + "External id": 4673377,"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": 1708037176405.394, "dur": 6.901, + "args": { + "External id": 4673378,"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": 1708037176407.203, "dur": 4.664, + "args": { + "External id": 4673379,"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": 1708037176413.246, "dur": 18.293, + "args": { + "External id": 4673380,"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": 1708037176448.887, "dur": 23.744, + "args": { + "External id": 4673381,"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": 1708037176449.937, "dur": 6.688, + "args": { + "External id": 4673382,"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": 1708037176452.807, "dur": 3.488, + "args": { + "External id": 4673383,"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": 1708037176457.488, "dur": 14.922, + "args": { + "External id": 4673384,"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": 1708037176458.657, "dur": 13.324, + "args": { + "External id": 4673385,"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": 1708037176476.025, "dur": 28.688, + "args": { + "External id": 4673386,"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": 1708037176477.030, "dur": 7.324, + "args": { + "External id": 4673387,"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": 1708037176480.603, "dur": 3.528, + "args": { + "External id": 4673388,"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": 1708037176493.257, "dur": 11.261, + "args": { + "External id": 4673389,"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": 1708037176493.891, "dur": 10.169, + "args": { + "External id": 4673390,"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": 1708037176508.856, "dur": 33.949, + "args": { + "External id": 4673391,"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": 1708037176510.314, "dur": 4.640, + "args": { + "External id": 4673392,"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": 1708037176515.795, "dur": 26.728, + "args": { + "External id": 4673393,"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": 1708037176516.388, "dur": 25.394, + "args": { + "External id": 4673394,"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": 1708037176553.046, "dur": 29.994, + "args": { + "External id": 4673395,"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": 1708037176588.628, "dur": 59.647, + "args": { + "External id": 4673396,"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": 1708037176592.257, "dur": 55.610, + "args": { + "External id": 4673397,"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": 1708037176598.294, "dur": 1.536, + "args": { + "External id": 4673398,"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": 1708037176601.359, "dur": 26.617, + "args": { + "External id": 4673399,"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": 1708037176603.636, "dur": 24.040, + "args": { + "External id": 4673400,"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": 1708037176608.257, "dur": 3.016, + "args": { + "External id": 4673401,"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": 1708037176612.223, "dur": 15.100, + "args": { + "External id": 4673402,"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": 1708037176653.159, "dur": 65792.433, + "args": { + "External id": 4673403,"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": 1708037176655.033, "dur": 65788.963, + "args": { + "External id": 4673404,"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": 1708037242461.240, "dur": 12.339, + "args": { + "External id": 4673405,"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": 1708037242469.055, "dur": 1.636, + "args": { + "External id": 4673406,"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": 1708037242479.559, "dur": 137.964, + "args": { + "External id": 4673407,"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": 1708037242481.449, "dur": 11.658, + "args": { + "External id": 4673408,"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": 1708037242485.048, "dur": 6.996, + "args": { + "External id": 4673409,"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": 1708037242490.904, "dur": 0.868, + "args": { + "External id": 4673410,"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": 1708037242494.843, "dur": 121.801, + "args": { + "External id": 4673411,"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": 1708037242499.202, "dur": 115.879, + "args": { + "External id": 4673412,"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": 1708037242622.894, "dur": 5.973, + "args": { + "External id": 4673413,"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": 1708037242625.666, "dur": 1.275, + "args": { + "External id": 4673414,"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": 1708037242639.734, "dur": 4.384, + "args": { + "External id": 4673415,"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": 1708037242657.172, "dur": 8.757, + "args": { + "External id": 4673416,"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": 1708037242660.498, "dur": 5.121, + "args": { + "External id": 4673417,"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": 1708037242818.406, "dur": 300.215, + "args": { + "External id": 4673418,"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": 1708037242823.911, "dur": 2.317, + "args": { + "External id": 4673419,"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": 1708037242829.478, "dur": 288.524, + "args": { + "External id": 4673420,"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": 1708037242833.213, "dur": 0.647, + "args": { + "External id": 4673421,"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": 1708037242836.768, "dur": 32.757, + "args": { + "External id": 4673422,"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": 1708037242872.871, "dur": 5.600, + "args": { + "External id": 4673423,"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": 1708037242877.124, "dur": 0.821, + "args": { + "External id": 4673424,"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": 1708037242881.664, "dur": 30.632, + "args": { + "External id": 4673425,"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": 1708037242883.114, "dur": 1.883, + "args": { + "External id": 4673426,"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": 1708037242889.159, "dur": 22.858, + "args": { + "External id": 4673427,"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": 1708037242893.797, "dur": 3.287, + "args": { + "External id": 4673428,"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": 1708037242914.968, "dur": 24.048, + "args": { + "External id": 4673429,"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": 1708037242942.374, "dur": 20.620, + "args": { + "External id": 4673430,"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": 1708037242967.288, "dur": 62.917, + "args": { + "External id": 4673431,"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": 1708037243034.282, "dur": 18.746, + "args": { + "External id": 4673432,"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": 1708037243056.128, "dur": 27.558, + "args": { + "External id": 4673433,"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": 1708037243058.961, "dur": 2.559, + "args": { + "External id": 4673434,"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": 1708037243065.340, "dur": 1.173, + "args": { + "External id": 4673435,"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": 1708037243087.231, "dur": 14.609, + "args": { + "External id": 4673436,"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": 1708037243105.126, "dur": 11.551, + "args": { + "External id": 4673437,"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": 1708037243127.584, "dur": 2.916, + "args": { + "External id": 4673438,"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": 1708037243138.586, "dur": 4.984, + "args": { + "External id": 4673439,"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": 1708037243141.134, "dur": 1.005, + "args": { + "External id": 4673440,"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": 1708037243230.976, "dur": 76.252, + "args": { + "External id": 4673441,"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": 1708037243313.006, "dur": 6.510, + "args": { + "External id": 4673442,"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": 1708037243317.421, "dur": 0.780, + "args": { + "External id": 4673443,"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": 1708037243321.485, "dur": 33.656, + "args": { + "External id": 4673444,"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": 1708037243361.086, "dur": 6.364, + "args": { + "External id": 4673445,"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": 1708037243363.026, "dur": 3.756, + "args": { + "External id": 4673446,"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": 1708037243365.314, "dur": 1.193, + "args": { + "External id": 4673447,"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": 1708037243372.095, "dur": 49.953, + "args": { + "External id": 4673448,"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": 1708037243375.286, "dur": 46.110, + "args": { + "External id": 4673449,"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": 1708037243427.997, "dur": 17.056, + "args": { + "External id": 4673450,"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": 1708037243450.988, "dur": 4.190, + "args": { + "External id": 4673451,"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": 1708037243453.244, "dur": 0.834, + "args": { + "External id": 4673452,"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": 1708037243459.752, "dur": 51.553, + "args": { + "External id": 4673453,"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": 1708037243460.837, "dur": 6.016, + "args": { + "External id": 4673454,"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": 1708037243461.851, "dur": 4.415, + "args": { + "External id": 4673455,"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": 1708037243465.279, "dur": 0.821, + "args": { + "External id": 4673456,"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": 1708037243467.979, "dur": 42.942, + "args": { + "External id": 4673457,"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": 1708037243468.508, "dur": 41.722, + "args": { + "External id": 4673458,"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": 1708037243515.086, "dur": 4.324, + "args": { + "External id": 4673459,"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": 1708037243517.221, "dur": 0.971, + "args": { + "External id": 4673460,"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": 1708037243541.154, "dur": 2.502, + "args": { + "External id": 4673461,"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": 1708037243554.472, "dur": 8.412, + "args": { + "External id": 4673462,"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": 1708037243556.436, "dur": 6.092, + "args": { + "External id": 4673463,"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": 1708037243660.791, "dur": 187.130, + "args": { + "External id": 4673464,"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": 1708037243663.034, "dur": 3.020, + "args": { + "External id": 4673465,"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": 1708037243668.027, "dur": 179.319, + "args": { + "External id": 4673466,"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": 1708037243669.837, "dur": 0.305, + "args": { + "External id": 4673467,"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": 1708037243672.793, "dur": 24.445, + "args": { + "External id": 4673468,"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": 1708037243699.036, "dur": 3.939, + "args": { + "External id": 4673469,"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": 1708037243701.044, "dur": 1.615, + "args": { + "External id": 4673470,"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": 1708037243704.053, "dur": 24.280, + "args": { + "External id": 4673471,"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": 1708037243705.377, "dur": 1.849, + "args": { + "External id": 4673472,"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": 1708037243708.605, "dur": 19.407, + "args": { + "External id": 4673473,"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": 1708037243713.806, "dur": 2.636, + "args": { + "External id": 4673474,"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": 1708037243730.139, "dur": 20.730, + "args": { + "External id": 4673475,"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": 1708037243752.584, "dur": 13.848, + "args": { + "External id": 4673476,"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": 1708037243769.437, "dur": 13.199, + "args": { + "External id": 4673477,"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": 1708037243786.095, "dur": 12.528, + "args": { + "External id": 4673478,"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": 1708037243800.864, "dur": 20.563, + "args": { + "External id": 4673479,"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": 1708037243803.117, "dur": 1.414, + "args": { + "External id": 4673480,"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": 1708037243806.808, "dur": 0.797, + "args": { + "External id": 4673481,"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": 1708037243823.047, "dur": 11.194, + "args": { + "External id": 4673482,"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": 1708037243835.723, "dur": 10.513, + "args": { + "External id": 4673483,"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": 1708037243854.832, "dur": 1.668, + "args": { + "External id": 4673484,"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": 1708037243866.970, "dur": 3.608, + "args": { + "External id": 4673485,"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": 1708037243869.335, "dur": 0.545, + "args": { + "External id": 4673486,"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": 1708037243939.449, "dur": 117.779, + "args": { + "External id": 4673487,"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": 1708037244065.789, "dur": 7.041, + "args": { + "External id": 4673488,"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": 1708037244069.265, "dur": 1.974, + "args": { + "External id": 4673489,"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": 1708037244074.464, "dur": 28.302, + "args": { + "External id": 4673490,"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": 1708037244108.484, "dur": 7.455, + "args": { + "External id": 4673491,"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": 1708037244110.352, "dur": 4.938, + "args": { + "External id": 4673492,"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": 1708037244114.137, "dur": 0.899, + "args": { + "External id": 4673493,"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": 1708037244119.559, "dur": 51.600, + "args": { + "External id": 4673494,"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": 1708037244121.228, "dur": 49.147, + "args": { + "External id": 4673495,"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": 1708037244175.658, "dur": 15.184, + "args": { + "External id": 4673496,"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": 1708037244196.642, "dur": 4.517, + "args": { + "External id": 4673497,"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": 1708037244199.229, "dur": 1.031, + "args": { + "External id": 4673498,"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": 1708037244207.264, "dur": 52.259, + "args": { + "External id": 4673499,"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": 1708037244208.671, "dur": 5.271, + "args": { + "External id": 4673500,"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": 1708037244209.594, "dur": 3.700, + "args": { + "External id": 4673501,"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": 1708037244210.585, "dur": 2.514, + "args": { + "External id": 4673502,"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": 1708037244214.680, "dur": 44.406, + "args": { + "External id": 4673503,"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": 1708037244215.195, "dur": 43.296, + "args": { + "External id": 4673504,"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": 1708037244263.144, "dur": 4.461, + "args": { + "External id": 4673505,"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": 1708037244265.458, "dur": 0.796, + "args": { + "External id": 4673506,"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": 1708037244276.147, "dur": 1.798, + "args": { + "External id": 4673507,"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": 1708037244286.165, "dur": 6.508, + "args": { + "External id": 4673508,"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": 1708037244288.323, "dur": 4.092, + "args": { + "External id": 4673509,"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": 1708037244386.615, "dur": 302.363, + "args": { + "External id": 4673510,"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": 1708037244389.050, "dur": 2.716, + "args": { + "External id": 4673511,"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": 1708037244393.122, "dur": 295.337, + "args": { + "External id": 4673512,"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": 1708037244396.326, "dur": 0.272, + "args": { + "External id": 4673513,"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": 1708037244399.416, "dur": 22.730, + "args": { + "External id": 4673514,"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": 1708037244424.061, "dur": 3.463, + "args": { + "External id": 4673515,"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": 1708037244426.296, "dur": 0.890, + "args": { + "External id": 4673516,"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": 1708037244428.872, "dur": 25.434, + "args": { + "External id": 4673517,"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": 1708037244430.030, "dur": 2.796, + "args": { + "External id": 4673518,"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": 1708037244434.541, "dur": 19.433, + "args": { + "External id": 4673519,"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": 1708037244437.226, "dur": 2.645, + "args": { + "External id": 4673520,"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": 1708037244455.646, "dur": 44.607, + "args": { + "External id": 4673521,"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": 1708037244502.202, "dur": 39.707, + "args": { + "External id": 4673522,"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": 1708037244546.299, "dur": 38.941, + "args": { + "External id": 4673523,"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": 1708037244588.513, "dur": 29.818, + "args": { + "External id": 4673524,"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": 1708037244620.547, "dur": 28.070, + "args": { + "External id": 4673525,"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": 1708037244622.876, "dur": 1.977, + "args": { + "External id": 4673526,"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": 1708037244627.077, "dur": 1.023, + "args": { + "External id": 4673527,"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": 1708037244649.811, "dur": 20.957, + "args": { + "External id": 4673528,"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": 1708037244671.970, "dur": 13.412, + "args": { + "External id": 4673529,"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": 1708037244696.786, "dur": 2.469, + "args": { + "External id": 4673530,"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": 1708037244709.133, "dur": 3.646, + "args": { + "External id": 4673531,"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": 1708037244711.551, "dur": 0.442, + "args": { + "External id": 4673532,"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": 1708037244786.341, "dur": 56.312, + "args": { + "External id": 4673533,"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": 1708037244847.444, "dur": 5.222, + "args": { + "External id": 4673534,"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": 1708037244850.292, "dur": 1.443, + "args": { + "External id": 4673535,"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": 1708037244854.065, "dur": 24.008, + "args": { + "External id": 4673536,"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": 1708037244969.318, "dur": 10.500, + "args": { + "External id": 4673537,"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": 1708037244973.531, "dur": 5.367, + "args": { + "External id": 4673538,"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": 1708037244975.954, "dur": 2.638, + "args": { + "External id": 4673539,"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": 1708037245017.783, "dur": 54.718, + "args": { + "External id": 4673540,"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": 1708037245019.250, "dur": 52.305, + "args": { + "External id": 4673541,"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": 1708037245077.643, "dur": 17.225, + "args": { + "External id": 4673542,"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": 1708037245102.072, "dur": 6.522, + "args": { + "External id": 4673543,"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": 1708037245106.298, "dur": 1.167, + "args": { + "External id": 4673544,"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": 1708037245113.294, "dur": 48.537, + "args": { + "External id": 4673545,"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": 1708037245114.281, "dur": 3.586, + "args": { + "External id": 4673546,"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": 1708037245115.104, "dur": 2.168, + "args": { + "External id": 4673547,"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": 1708037245116.239, "dur": 0.888, + "args": { + "External id": 4673548,"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": 1708037245118.425, "dur": 42.948, + "args": { + "External id": 4673549,"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": 1708037245118.899, "dur": 41.825, + "args": { + "External id": 4673550,"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": 1708037245167.414, "dur": 4.209, + "args": { + "External id": 4673551,"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": 1708037245169.431, "dur": 0.661, + "args": { + "External id": 4673552,"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": 1708037245178.708, "dur": 1.723, + "args": { + "External id": 4673553,"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": 1708037245189.398, "dur": 6.631, + "args": { + "External id": 4673554,"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": 1708037245191.395, "dur": 4.324, + "args": { + "External id": 4673555,"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": 1708037245295.604, "dur": 177.770, + "args": { + "External id": 4673556,"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": 1708037245297.748, "dur": 2.192, + "args": { + "External id": 4673557,"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": 1708037245303.269, "dur": 169.569, + "args": { + "External id": 4673558,"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": 1708037245304.368, "dur": 0.393, + "args": { + "External id": 4673559,"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": 1708037245305.857, "dur": 21.447, + "args": { + "External id": 4673560,"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": 1708037245329.318, "dur": 5.479, + "args": { + "External id": 4673561,"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": 1708037245331.312, "dur": 3.126, + "args": { + "External id": 4673562,"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": 1708037245335.904, "dur": 22.413, + "args": { + "External id": 4673563,"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": 1708037245337.046, "dur": 1.358, + "args": { + "External id": 4673564,"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": 1708037245341.309, "dur": 16.650, + "args": { + "External id": 4673565,"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": 1708037245343.914, "dur": 2.178, + "args": { + "External id": 4673566,"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": 1708037245359.681, "dur": 20.152, + "args": { + "External id": 4673567,"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": 1708037245381.532, "dur": 13.464, + "args": { + "External id": 4673568,"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": 1708037245397.819, "dur": 13.331, + "args": { + "External id": 4673569,"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": 1708037245412.676, "dur": 11.447, + "args": { + "External id": 4673570,"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": 1708037245425.704, "dur": 20.196, + "args": { + "External id": 4673571,"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": 1708037245427.841, "dur": 1.160, + "args": { + "External id": 4673572,"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": 1708037245430.874, "dur": 2.125, + "args": { + "External id": 4673573,"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": 1708037245448.959, "dur": 11.036, + "args": { + "External id": 4673574,"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": 1708037245461.040, "dur": 10.819, + "args": { + "External id": 4673575,"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": 1708037245479.895, "dur": 1.839, + "args": { + "External id": 4673576,"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": 1708037245489.794, "dur": 3.490, + "args": { + "External id": 4673577,"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": 1708037245491.831, "dur": 0.565, + "args": { + "External id": 4673578,"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": 1708037245578.535, "dur": 54.622, + "args": { + "External id": 4673579,"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": 1708037245638.025, "dur": 7.424, + "args": { + "External id": 4673580,"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": 1708037245642.526, "dur": 1.409, + "args": { + "External id": 4673581,"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": 1708037245646.643, "dur": 26.779, + "args": { + "External id": 4673582,"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": 1708037245678.308, "dur": 5.325, + "args": { + "External id": 4673583,"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": 1708037245679.772, "dur": 3.262, + "args": { + "External id": 4673584,"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": 1708037245681.646, "dur": 1.144, + "args": { + "External id": 4673585,"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": 1708037245686.183, "dur": 39.482, + "args": { + "External id": 4673586,"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": 1708037245687.594, "dur": 37.550, + "args": { + "External id": 4673587,"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": 1708037245731.328, "dur": 14.449, + "args": { + "External id": 4673588,"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": 1708037245751.205, "dur": 3.840, + "args": { + "External id": 4673589,"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": 1708037245753.303, "dur": 0.797, + "args": { + "External id": 4673590,"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": 1708037245758.870, "dur": 47.987, + "args": { + "External id": 4673591,"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": 1708037245759.890, "dur": 4.826, + "args": { + "External id": 4673592,"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": 1708037245760.596, "dur": 3.574, + "args": { + "External id": 4673593,"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": 1708037245763.170, "dur": 0.849, + "args": { + "External id": 4673594,"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": 1708037245765.417, "dur": 41.045, + "args": { + "External id": 4673595,"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": 1708037245766.016, "dur": 39.933, + "args": { + "External id": 4673596,"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": 1708037245810.767, "dur": 3.645, + "args": { + "External id": 4673597,"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": 1708037245812.680, "dur": 0.550, + "args": { + "External id": 4673598,"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": 1708037245820.399, "dur": 1.470, + "args": { + "External id": 4673599,"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": 1708037245829.914, "dur": 7.993, + "args": { + "External id": 4673600,"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": 1708037245833.398, "dur": 4.222, + "args": { + "External id": 4673601,"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": 1708037245917.148, "dur": 245.363, + "args": { + "External id": 4673602,"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": 1708037245921.215, "dur": 2.020, + "args": { + "External id": 4673603,"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": 1708037245924.861, "dur": 237.049, + "args": { + "External id": 4673604,"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": 1708037245926.462, "dur": 0.257, + "args": { + "External id": 4673605,"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": 1708037245927.633, "dur": 20.050, + "args": { + "External id": 4673606,"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": 1708037245949.442, "dur": 4.635, + "args": { + "External id": 4673607,"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": 1708037245952.634, "dur": 1.175, + "args": { + "External id": 4673608,"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": 1708037245955.245, "dur": 21.954, + "args": { + "External id": 4673609,"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": 1708037245958.707, "dur": 1.602, + "args": { + "External id": 4673610,"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": 1708037245961.368, "dur": 15.478, + "args": { + "External id": 4673611,"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": 1708037245963.712, "dur": 2.633, + "args": { + "External id": 4673612,"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": 1708037245978.310, "dur": 78.866, + "args": { + "External id": 4673613,"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": 1708037246059.836, "dur": 12.269, + "args": { + "External id": 4673614,"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": 1708037246074.994, "dur": 18.462, + "args": { + "External id": 4673615,"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": 1708037246095.123, "dur": 13.529, + "args": { + "External id": 4673616,"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": 1708037246110.734, "dur": 25.282, + "args": { + "External id": 4673617,"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": 1708037246115.170, "dur": 1.565, + "args": { + "External id": 4673618,"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": 1708037246120.714, "dur": 0.930, + "args": { + "External id": 4673619,"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": 1708037246137.410, "dur": 11.017, + "args": { + "External id": 4673620,"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": 1708037246149.542, "dur": 11.307, + "args": { + "External id": 4673621,"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": 1708037246170.394, "dur": 2.123, + "args": { + "External id": 4673622,"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": 1708037246181.958, "dur": 3.904, + "args": { + "External id": 4673623,"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": 1708037246184.438, "dur": 0.518, + "args": { + "External id": 4673624,"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": 1708037246252.562, "dur": 53.358, + "args": { + "External id": 4673625,"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": 1708037246310.732, "dur": 6.178, + "args": { + "External id": 4673626,"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": 1708037246314.520, "dur": 1.197, + "args": { + "External id": 4673627,"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": 1708037246318.489, "dur": 24.556, + "args": { + "External id": 4673628,"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": 1708037246347.624, "dur": 5.680, + "args": { + "External id": 4673629,"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": 1708037246349.118, "dur": 3.448, + "args": { + "External id": 4673630,"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": 1708037246350.928, "dur": 1.367, + "args": { + "External id": 4673631,"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": 1708037246356.077, "dur": 41.363, + "args": { + "External id": 4673632,"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": 1708037246359.405, "dur": 37.233, + "args": { + "External id": 4673633,"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": 1708037246401.037, "dur": 13.651, + "args": { + "External id": 4673634,"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": 1708037246420.039, "dur": 3.950, + "args": { + "External id": 4673635,"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": 1708037246422.054, "dur": 1.103, + "args": { + "External id": 4673636,"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": 1708037246427.903, "dur": 48.253, + "args": { + "External id": 4673637,"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": 1708037246428.962, "dur": 5.676, + "args": { + "External id": 4673638,"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": 1708037246430.159, "dur": 3.925, + "args": { + "External id": 4673639,"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": 1708037246433.066, "dur": 0.905, + "args": { + "External id": 4673640,"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": 1708037246435.425, "dur": 40.398, + "args": { + "External id": 4673641,"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": 1708037246436.189, "dur": 38.947, + "args": { + "External id": 4673642,"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": 1708037246479.429, "dur": 3.797, + "args": { + "External id": 4673643,"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": 1708037246481.182, "dur": 0.950, + "args": { + "External id": 4673644,"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": 1708037246495.834, "dur": 1.508, + "args": { + "External id": 4673645,"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": 1708037246506.134, "dur": 7.449, + "args": { + "External id": 4673646,"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": 1708037246508.391, "dur": 4.894, + "args": { + "External id": 4673647,"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": 1708037246611.331, "dur": 218.440, + "args": { + "External id": 4673648,"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": 1708037246613.815, "dur": 2.811, + "args": { + "External id": 4673649,"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": 1708037246618.126, "dur": 211.162, + "args": { + "External id": 4673650,"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": 1708037246658.259, "dur": 0.592, + "args": { + "External id": 4673651,"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": 1708037246664.413, "dur": 23.046, + "args": { + "External id": 4673652,"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": 1708037246688.947, "dur": 5.555, + "args": { + "External id": 4673653,"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": 1708037246691.753, "dur": 2.440, + "args": { + "External id": 4673654,"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": 1708037246695.637, "dur": 21.373, + "args": { + "External id": 4673655,"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": 1708037246696.651, "dur": 1.760, + "args": { + "External id": 4673656,"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": 1708037246699.579, "dur": 17.032, + "args": { + "External id": 4673657,"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": 1708037246702.567, "dur": 2.545, + "args": { + "External id": 4673658,"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": 1708037246718.392, "dur": 18.583, + "args": { + "External id": 4673659,"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": 1708037246738.343, "dur": 12.918, + "args": { + "External id": 4673660,"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": 1708037246753.786, "dur": 12.737, + "args": { + "External id": 4673661,"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": 1708037246767.788, "dur": 12.032, + "args": { + "External id": 4673662,"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": 1708037246783.269, "dur": 20.509, + "args": { + "External id": 4673663,"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": 1708037246784.648, "dur": 1.785, + "args": { + "External id": 4673664,"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": 1708037246788.458, "dur": 2.371, + "args": { + "External id": 4673665,"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": 1708037246805.144, "dur": 11.266, + "args": { + "External id": 4673666,"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": 1708037246817.358, "dur": 10.880, + "args": { + "External id": 4673667,"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": 1708037246838.099, "dur": 2.206, + "args": { + "External id": 4673668,"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": 1708037246849.511, "dur": 4.193, + "args": { + "External id": 4673669,"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": 1708037246852.345, "dur": 0.578, + "args": { + "External id": 4673670,"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": 1708037246915.186, "dur": 53.677, + "args": { + "External id": 4673671,"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": 1708037246973.377, "dur": 4.614, + "args": { + "External id": 4673672,"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": 1708037246975.632, "dur": 1.344, + "args": { + "External id": 4673673,"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": 1708037246979.432, "dur": 58.940, + "args": { + "External id": 4673674,"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": 1708037247044.578, "dur": 8.469, + "args": { + "External id": 4673675,"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": 1708037247046.634, "dur": 5.553, + "args": { + "External id": 4673676,"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": 1708037247050.049, "dur": 1.908, + "args": { + "External id": 4673677,"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": 1708037247055.872, "dur": 44.385, + "args": { + "External id": 4673678,"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": 1708037247057.149, "dur": 42.478, + "args": { + "External id": 4673679,"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": 1708037247104.129, "dur": 14.875, + "args": { + "External id": 4673680,"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": 1708037247124.690, "dur": 3.888, + "args": { + "External id": 4673681,"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": 1708037247126.889, "dur": 0.700, + "args": { + "External id": 4673682,"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": 1708037247134.229, "dur": 47.855, + "args": { + "External id": 4673683,"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": 1708037247135.414, "dur": 3.752, + "args": { + "External id": 4673684,"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": 1708037247136.214, "dur": 2.416, + "args": { + "External id": 4673685,"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": 1708037247137.504, "dur": 1.000, + "args": { + "External id": 4673686,"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": 1708037247139.834, "dur": 41.820, + "args": { + "External id": 4673687,"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": 1708037247140.629, "dur": 40.449, + "args": { + "External id": 4673688,"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": 1708037247185.627, "dur": 3.624, + "args": { + "External id": 4673689,"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": 1708037247187.320, "dur": 0.867, + "args": { + "External id": 4673690,"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": 1708037247197.060, "dur": 1.350, + "args": { + "External id": 4673691,"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": 1708037247206.065, "dur": 6.503, + "args": { + "External id": 4673692,"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": 1708037247208.473, "dur": 3.847, + "args": { + "External id": 4673693,"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": 1708037247291.371, "dur": 172.061, + "args": { + "External id": 4673694,"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": 1708037247296.470, "dur": 1.959, + "args": { + "External id": 4673695,"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": 1708037247299.690, "dur": 163.078, + "args": { + "External id": 4673696,"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": 1708037247303.091, "dur": 0.370, + "args": { + "External id": 4673697,"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": 1708037247305.105, "dur": 19.052, + "args": { + "External id": 4673698,"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": 1708037247325.519, "dur": 4.902, + "args": { + "External id": 4673699,"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": 1708037247329.260, "dur": 0.903, + "args": { + "External id": 4673700,"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": 1708037247331.424, "dur": 19.909, + "args": { + "External id": 4673701,"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": 1708037247332.372, "dur": 1.644, + "args": { + "External id": 4673702,"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": 1708037247335.130, "dur": 15.867, + "args": { + "External id": 4673703,"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": 1708037247337.858, "dur": 2.540, + "args": { + "External id": 4673704,"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": 1708037247352.652, "dur": 19.554, + "args": { + "External id": 4673705,"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": 1708037247373.494, "dur": 13.906, + "args": { + "External id": 4673706,"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": 1708037247391.341, "dur": 13.485, + "args": { + "External id": 4673707,"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": 1708037247406.297, "dur": 11.056, + "args": { + "External id": 4673708,"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": 1708037247419.234, "dur": 17.653, + "args": { + "External id": 4673709,"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": 1708037247420.580, "dur": 1.098, + "args": { + "External id": 4673710,"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": 1708037247423.834, "dur": 0.653, + "args": { + "External id": 4673711,"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": 1708037247438.061, "dur": 10.945, + "args": { + "External id": 4673712,"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": 1708037247450.156, "dur": 11.487, + "args": { + "External id": 4673713,"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": 1708037247470.742, "dur": 1.386, + "args": { + "External id": 4673714,"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": 1708037247478.903, "dur": 3.068, + "args": { + "External id": 4673715,"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": 1708037247480.920, "dur": 0.311, + "args": { + "External id": 4673716,"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": 1708037247554.860, "dur": 49.888, + "args": { + "External id": 4673717,"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": 1708037247609.728, "dur": 5.164, + "args": { + "External id": 4673718,"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": 1708037247612.724, "dur": 0.995, + "args": { + "External id": 4673719,"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": 1708037247616.190, "dur": 25.717, + "args": { + "External id": 4673720,"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": 1708037247646.504, "dur": 7.551, + "args": { + "External id": 4673721,"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": 1708037247649.768, "dur": 3.701, + "args": { + "External id": 4673722,"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": 1708037247651.887, "dur": 1.422, + "args": { + "External id": 4673723,"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": 1708037247656.776, "dur": 39.340, + "args": { + "External id": 4673724,"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": 1708037247658.263, "dur": 37.143, + "args": { + "External id": 4673725,"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": 1708037247699.539, "dur": 13.916, + "args": { + "External id": 4673726,"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": 1708037247718.858, "dur": 4.859, + "args": { + "External id": 4673727,"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": 1708037247722.183, "dur": 0.704, + "args": { + "External id": 4673728,"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": 1708037247727.426, "dur": 46.870, + "args": { + "External id": 4673729,"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": 1708037247728.502, "dur": 4.168, + "args": { + "External id": 4673730,"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": 1708037247729.432, "dur": 2.717, + "args": { + "External id": 4673731,"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": 1708037247730.965, "dur": 0.948, + "args": { + "External id": 4673732,"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": 1708037247733.147, "dur": 40.790, + "args": { + "External id": 4673733,"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": 1708037247733.823, "dur": 39.338, + "args": { + "External id": 4673734,"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": 1708037247778.982, "dur": 3.756, + "args": { + "External id": 4673735,"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": 1708037247780.676, "dur": 1.070, + "args": { + "External id": 4673736,"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": 1708037247788.754, "dur": 1.389, + "args": { + "External id": 4673737,"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": 1708037247797.135, "dur": 7.261, + "args": { + "External id": 4673738,"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": 1708037247798.931, "dur": 5.212, + "args": { + "External id": 4673739,"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": 1708037247879.624, "dur": 208.725, + "args": { + "External id": 4673740,"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": 1708037247881.746, "dur": 1.715, + "args": { + "External id": 4673741,"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": 1708037247884.878, "dur": 202.859, + "args": { + "External id": 4673742,"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": 1708037247886.289, "dur": 0.274, + "args": { + "External id": 4673743,"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": 1708037247887.975, "dur": 22.364, + "args": { + "External id": 4673744,"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": 1708037247912.225, "dur": 2.806, + "args": { + "External id": 4673745,"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": 1708037247914.191, "dur": 0.577, + "args": { + "External id": 4673746,"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": 1708037247915.990, "dur": 22.860, + "args": { + "External id": 4673747,"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": 1708037247917.287, "dur": 1.475, + "args": { + "External id": 4673748,"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": 1708037247921.348, "dur": 17.200, + "args": { + "External id": 4673749,"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": 1708037247925.774, "dur": 2.206, + "args": { + "External id": 4673750,"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": 1708037247940.413, "dur": 18.326, + "args": { + "External id": 4673751,"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": 1708037247959.761, "dur": 12.207, + "args": { + "External id": 4673752,"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": 1708037247974.192, "dur": 48.703, + "args": { + "External id": 4673753,"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": 1708037248025.194, "dur": 13.264, + "args": { + "External id": 4673754,"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": 1708037248040.557, "dur": 19.628, + "args": { + "External id": 4673755,"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": 1708037248042.385, "dur": 1.665, + "args": { + "External id": 4673756,"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": 1708037248046.177, "dur": 0.711, + "args": { + "External id": 4673757,"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": 1708037248063.044, "dur": 11.576, + "args": { + "External id": 4673758,"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": 1708037248075.905, "dur": 10.824, + "args": { + "External id": 4673759,"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": 1708037248095.476, "dur": 2.070, + "args": { + "External id": 4673760,"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": 1708037248105.692, "dur": 3.441, + "args": { + "External id": 4673761,"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": 1708037248108.016, "dur": 0.330, + "args": { + "External id": 4673762,"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": 1708037248172.181, "dur": 49.750, + "args": { + "External id": 4673763,"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": 1708037248226.172, "dur": 5.734, + "args": { + "External id": 4673764,"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": 1708037248229.760, "dur": 1.193, + "args": { + "External id": 4673765,"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": 1708037248233.447, "dur": 21.415, + "args": { + "External id": 4673766,"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": 1708037248258.748, "dur": 5.553, + "args": { + "External id": 4673767,"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": 1708037248260.324, "dur": 3.376, + "args": { + "External id": 4673768,"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": 1708037248262.345, "dur": 1.085, + "args": { + "External id": 4673769,"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": 1708037248266.789, "dur": 38.210, + "args": { + "External id": 4673770,"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": 1708037248268.113, "dur": 36.199, + "args": { + "External id": 4673771,"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": 1708037248310.658, "dur": 13.736, + "args": { + "External id": 4673772,"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": 1708037248328.807, "dur": 25.949, + "args": { + "External id": 4673773,"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": 1708037248331.463, "dur": 22.905, + "args": { + "External id": 4673774,"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": 1708037248338.284, "dur": 0.640, + "args": { + "External id": 4673775,"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": 1708037248360.379, "dur": 25.017, + "args": { + "External id": 4673776,"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": 1708037248362.110, "dur": 23.075, + "args": { + "External id": 4673777,"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": 1708037248366.450, "dur": 3.665, + "args": { + "External id": 4673778,"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": 1708037248371.129, "dur": 13.650, + "args": { + "External id": 4673779,"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": 1708037248400.186, "dur": 6.810, + "args": { + "External id": 4673780,"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": 1708037248404.115, "dur": 2.587, + "args": { + "External id": 4673781,"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": 1708037248408.347, "dur": 0.955, + "args": { + "External id": 4673782,"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": 1708037248408.799, "dur": 0.420, + "args": { + "External id": 4673783,"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": 1708037248449.625, "dur": 20.528, + "args": { + "External id": 4673784,"Sequence number": 46526637, "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": 1708037248449.625, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1708037248475.738, "dur": 5.116, + "args": { + "External id": 4673785,"Sequence number": 46526638, "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": 1708037248478.784, "dur": 0.842, + "args": { + "External id": 4673786,"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": 1708037248483.255, "dur": 7.788, + "args": { + "External id": 4673787,"Sequence number": 46526638, "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": 1708037248488.923, "dur": 0.942, + "args": { + "External id": 4673788,"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": 1708037248492.303, "dur": 3.001, + "args": { + "External id": 4673789,"Sequence number": 46526638, "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": 1708037248493.789, "dur": 0.963, + "args": { + "External id": 4673790,"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": 1708037248499.668, "dur": 5.874, + "args": { + "External id": 4673791,"Sequence number": 46526638, "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": 1708037248499.668, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037248503.070, "dur": 1.070, + "args": { + "External id": 4673792,"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": 1708037248508.159, "dur": 5.248, + "args": { + "External id": 4673793,"Sequence number": 46526639, "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": 1708037248508.159, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037248511.271, "dur": 1.371, + "args": { + "External id": 4673794,"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": 1708037248514.527, "dur": 5.028, + "args": { + "External id": 4673795,"Sequence number": 46526640, "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": 1708037248514.527, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037248517.855, "dur": 0.889, + "args": { + "External id": 4673796,"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": 1708037248520.647, "dur": 22.432, + "args": { + "External id": 4673797,"Sequence number": 46526641, "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": 1708037248520.647, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037248523.173, "dur": 17.748, + "args": { + "External id": 4673798,"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": 1708037248548.433, "dur": 34.524, + "args": { + "External id": 4673799,"Sequence number": 46526642, "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": 1708037248551.720, "dur": 31.038, + "args": { + "External id": 4673800,"Sequence number": 46526642, "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": 1708037248554.454, "dur": 7.205, + "args": { + "External id": 4673801,"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": 1708037248557.052, "dur": 4.102, + "args": { + "External id": 4673802,"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": 1708037248562.740, "dur": 19.450, + "args": { + "External id": 4673803,"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": 1708037248608.937, "dur": 3.824, + "args": { + "External id": 4673804,"Sequence number": 46526642, "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": 1708037248608.937, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708037248615.227, "dur": 1.231, + "args": { + "External id": 4673805,"Sequence number": 46526643, "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": 1708037248649.017, "dur": 42714.196, + "args": { + "External id": 4673806,"Sequence number": 46526643, "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": 1708037248649.017, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1708037248663.191, "dur": 26.653, + "args": { + "External id": 4673807,"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": 1708037248664.054, "dur": 25.570, + "args": { + "External id": 4673808,"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": 1708037248665.825, "dur": 7.607, + "args": { + "External id": 4673809,"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": 1708037248669.294, "dur": 3.771, + "args": { + "External id": 4673810,"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": 1708037248674.309, "dur": 14.918, + "args": { + "External id": 4673811,"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": 1708037248704.961, "dur": 22.592, + "args": { + "External id": 4673812,"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": 1708037248706.080, "dur": 5.672, + "args": { + "External id": 4673813,"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": 1708037248708.191, "dur": 3.242, + "args": { + "External id": 4673814,"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": 1708037248713.126, "dur": 14.225, + "args": { + "External id": 4673815,"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": 1708037248714.853, "dur": 12.145, + "args": { + "External id": 4673816,"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": 1708037248731.131, "dur": 20.637, + "args": { + "External id": 4673817,"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": 1708037248732.060, "dur": 6.090, + "args": { + "External id": 4673818,"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": 1708037248735.173, "dur": 2.757, + "args": { + "External id": 4673819,"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": 1708037248739.051, "dur": 12.527, + "args": { + "External id": 4673820,"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": 1708037248739.831, "dur": 11.318, + "args": { + "External id": 4673821,"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": 1708037248757.167, "dur": 16.093, + "args": { + "External id": 4673822,"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": 1708037248759.076, "dur": 2.822, + "args": { + "External id": 4673823,"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": 1708037248762.762, "dur": 10.221, + "args": { + "External id": 4673824,"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": 1708037248763.760, "dur": 8.958, + "args": { + "External id": 4673825,"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": 1708037248777.717, "dur": 21.486, + "args": { + "External id": 4673826,"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": 1708037248803.428, "dur": 80.140, + "args": { + "External id": 4673827,"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": 1708037248833.985, "dur": 49.118, + "args": { + "External id": 4673828,"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": 1708037248841.691, "dur": 0.986, + "args": { + "External id": 4673829,"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": 1708037248844.081, "dur": 23.654, + "args": { + "External id": 4673830,"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": 1708037248845.868, "dur": 21.539, + "args": { + "External id": 4673831,"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": 1708037248848.344, "dur": 2.534, + "args": { + "External id": 4673832,"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": 1708037248851.911, "dur": 14.996, + "args": { + "External id": 4673833,"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": 1708037248887.927, "dur": 36825.464, + "args": { + "External id": 4673834,"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": 1708037248889.472, "dur": 36822.823, + "args": { + "External id": 4673835,"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": 1708037285723.415, "dur": 8.504, + "args": { + "External id": 4673836,"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": 1708037285729.178, "dur": 1.009, + "args": { + "External id": 4673837,"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": 1708037285737.092, "dur": 97.841, + "args": { + "External id": 4673838,"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": 1708037285738.441, "dur": 6.392, + "args": { + "External id": 4673839,"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": 1708037285740.829, "dur": 3.120, + "args": { + "External id": 4673840,"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": 1708037285742.636, "dur": 1.066, + "args": { + "External id": 4673841,"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": 1708037285746.399, "dur": 87.846, + "args": { + "External id": 4673842,"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": 1708037285747.939, "dur": 85.393, + "args": { + "External id": 4673843,"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": 1708037285840.132, "dur": 4.583, + "args": { + "External id": 4673844,"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": 1708037285842.293, "dur": 1.289, + "args": { + "External id": 4673845,"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": 1708037285852.537, "dur": 2.522, + "args": { + "External id": 4673846,"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": 1708037285864.021, "dur": 6.326, + "args": { + "External id": 4673847,"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": 1708037285866.294, "dur": 3.779, + "args": { + "External id": 4673848,"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": 1708037286030.384, "dur": 199.130, + "args": { + "External id": 4673849,"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": 1708037286033.677, "dur": 3.441, + "args": { + "External id": 4673850,"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": 1708037286038.999, "dur": 189.925, + "args": { + "External id": 4673851,"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": 1708037286041.217, "dur": 0.412, + "args": { + "External id": 4673852,"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": 1708037286043.121, "dur": 27.591, + "args": { + "External id": 4673853,"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": 1708037286072.756, "dur": 3.612, + "args": { + "External id": 4673854,"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": 1708037286075.074, "dur": 0.978, + "args": { + "External id": 4673855,"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": 1708037286077.566, "dur": 27.963, + "args": { + "External id": 4673856,"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": 1708037286079.146, "dur": 1.482, + "args": { + "External id": 4673857,"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": 1708037286082.591, "dur": 22.645, + "args": { + "External id": 4673858,"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": 1708037286089.927, "dur": 3.577, + "args": { + "External id": 4673859,"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": 1708037286107.788, "dur": 22.370, + "args": { + "External id": 4673860,"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": 1708037286132.002, "dur": 13.780, + "args": { + "External id": 4673861,"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": 1708037286149.343, "dur": 14.827, + "args": { + "External id": 4673862,"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": 1708037286165.864, "dur": 12.193, + "args": { + "External id": 4673863,"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": 1708037286179.837, "dur": 20.457, + "args": { + "External id": 4673864,"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": 1708037286181.930, "dur": 1.957, + "args": { + "External id": 4673865,"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": 1708037286186.481, "dur": 0.781, + "args": { + "External id": 4673866,"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": 1708037286203.983, "dur": 11.196, + "args": { + "External id": 4673867,"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": 1708037286216.529, "dur": 11.138, + "args": { + "External id": 4673868,"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": 1708037286237.027, "dur": 2.276, + "args": { + "External id": 4673869,"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": 1708037286246.199, "dur": 4.681, + "args": { + "External id": 4673870,"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": 1708037286248.581, "dur": 1.385, + "args": { + "External id": 4673871,"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": 1708037286327.374, "dur": 62.689, + "args": { + "External id": 4673872,"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": 1708037286395.222, "dur": 7.651, + "args": { + "External id": 4673873,"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": 1708037286399.327, "dur": 1.129, + "args": { + "External id": 4673874,"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": 1708037286404.468, "dur": 31.344, + "args": { + "External id": 4673875,"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": 1708037286441.251, "dur": 6.288, + "args": { + "External id": 4673876,"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": 1708037286443.291, "dur": 3.377, + "args": { + "External id": 4673877,"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": 1708037286445.172, "dur": 1.187, + "args": { + "External id": 4673878,"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": 1708037286450.054, "dur": 40.959, + "args": { + "External id": 4673879,"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": 1708037286451.406, "dur": 39.080, + "args": { + "External id": 4673880,"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": 1708037286496.446, "dur": 14.699, + "args": { + "External id": 4673881,"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": 1708037286517.177, "dur": 4.196, + "args": { + "External id": 4673882,"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": 1708037286519.512, "dur": 0.948, + "args": { + "External id": 4673883,"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": 1708037286540.017, "dur": 64.861, + "args": { + "External id": 4673884,"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": 1708037286541.313, "dur": 8.983, + "args": { + "External id": 4673885,"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": 1708037286542.634, "dur": 6.848, + "args": { + "External id": 4673886,"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": 1708037286546.128, "dur": 2.945, + "args": { + "External id": 4673887,"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": 1708037286551.248, "dur": 53.060, + "args": { + "External id": 4673888,"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": 1708037286557.651, "dur": 46.057, + "args": { + "External id": 4673889,"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": 1708037286609.171, "dur": 4.235, + "args": { + "External id": 4673890,"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": 1708037286611.347, "dur": 0.787, + "args": { + "External id": 4673891,"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": 1708037286620.249, "dur": 1.646, + "args": { + "External id": 4673892,"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": 1708037286632.471, "dur": 7.060, + "args": { + "External id": 4673893,"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": 1708037286634.674, "dur": 4.598, + "args": { + "External id": 4673894,"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": 1708037286730.356, "dur": 193.040, + "args": { + "External id": 4673895,"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": 1708037286734.224, "dur": 2.087, + "args": { + "External id": 4673896,"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": 1708037286737.941, "dur": 184.978, + "args": { + "External id": 4673897,"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": 1708037286739.474, "dur": 0.488, + "args": { + "External id": 4673898,"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": 1708037286740.867, "dur": 20.664, + "args": { + "External id": 4673899,"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": 1708037286778.105, "dur": 4.621, + "args": { + "External id": 4673900,"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": 1708037286781.499, "dur": 0.890, + "args": { + "External id": 4673901,"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": 1708037286783.765, "dur": 21.505, + "args": { + "External id": 4673902,"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": 1708037286784.990, "dur": 1.379, + "args": { + "External id": 4673903,"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": 1708037286787.631, "dur": 17.245, + "args": { + "External id": 4673904,"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": 1708037286790.509, "dur": 3.093, + "args": { + "External id": 4673905,"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": 1708037286806.954, "dur": 21.378, + "args": { + "External id": 4673906,"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": 1708037286829.889, "dur": 13.036, + "args": { + "External id": 4673907,"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": 1708037286846.099, "dur": 13.742, + "args": { + "External id": 4673908,"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": 1708037286861.188, "dur": 11.711, + "args": { + "External id": 4673909,"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": 1708037286876.482, "dur": 21.136, + "args": { + "External id": 4673910,"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": 1708037286880.212, "dur": 1.064, + "args": { + "External id": 4673911,"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": 1708037286883.546, "dur": 0.915, + "args": { + "External id": 4673912,"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": 1708037286898.960, "dur": 11.136, + "args": { + "External id": 4673913,"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": 1708037286911.402, "dur": 10.585, + "args": { + "External id": 4673914,"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": 1708037286930.743, "dur": 1.887, + "args": { + "External id": 4673915,"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": 1708037286940.432, "dur": 3.498, + "args": { + "External id": 4673916,"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": 1708037286942.649, "dur": 0.546, + "args": { + "External id": 4673917,"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": 1708037287064.548, "dur": 57.040, + "args": { + "External id": 4673918,"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": 1708037287126.760, "dur": 5.119, + "args": { + "External id": 4673919,"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": 1708037287129.408, "dur": 1.174, + "args": { + "External id": 4673920,"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": 1708037287133.394, "dur": 23.828, + "args": { + "External id": 4673921,"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": 1708037287162.124, "dur": 8.499, + "args": { + "External id": 4673922,"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": 1708037287164.093, "dur": 5.895, + "args": { + "External id": 4673923,"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": 1708037287167.935, "dur": 1.803, + "args": { + "External id": 4673924,"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": 1708037287173.533, "dur": 40.584, + "args": { + "External id": 4673925,"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": 1708037287174.897, "dur": 38.531, + "args": { + "External id": 4673926,"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": 1708037287217.995, "dur": 14.125, + "args": { + "External id": 4673927,"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": 1708037287237.942, "dur": 3.411, + "args": { + "External id": 4673928,"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": 1708037287239.581, "dur": 0.932, + "args": { + "External id": 4673929,"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": 1708037287245.533, "dur": 49.550, + "args": { + "External id": 4673930,"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": 1708037287248.218, "dur": 4.152, + "args": { + "External id": 4673931,"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": 1708037287248.945, "dur": 2.829, + "args": { + "External id": 4673932,"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": 1708037287250.418, "dur": 1.236, + "args": { + "External id": 4673933,"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": 1708037287253.384, "dur": 41.282, + "args": { + "External id": 4673934,"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": 1708037287253.966, "dur": 40.058, + "args": { + "External id": 4673935,"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": 1708037287299.189, "dur": 4.243, + "args": { + "External id": 4673936,"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": 1708037287301.003, "dur": 1.398, + "args": { + "External id": 4673937,"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": 1708037287309.668, "dur": 1.569, + "args": { + "External id": 4673938,"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": 1708037287320.072, "dur": 6.470, + "args": { + "External id": 4673939,"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": 1708037287322.255, "dur": 4.084, + "args": { + "External id": 4673940,"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": 1708037287410.812, "dur": 199.573, + "args": { + "External id": 4673941,"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": 1708037287415.517, "dur": 2.080, + "args": { + "External id": 4673942,"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": 1708037287418.936, "dur": 190.864, + "args": { + "External id": 4673943,"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": 1708037287420.485, "dur": 0.425, + "args": { + "External id": 4673944,"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": 1708037287423.791, "dur": 18.778, + "args": { + "External id": 4673945,"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": 1708037287444.723, "dur": 5.086, + "args": { + "External id": 4673946,"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": 1708037287448.133, "dur": 1.419, + "args": { + "External id": 4673947,"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": 1708037287450.877, "dur": 22.179, + "args": { + "External id": 4673948,"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": 1708037287452.013, "dur": 1.442, + "args": { + "External id": 4673949,"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": 1708037287454.636, "dur": 18.111, + "args": { + "External id": 4673950,"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": 1708037287457.310, "dur": 2.281, + "args": { + "External id": 4673951,"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": 1708037287474.547, "dur": 19.784, + "args": { + "External id": 4673952,"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": 1708037287495.805, "dur": 14.709, + "args": { + "External id": 4673953,"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": 1708037287513.445, "dur": 30.195, + "args": { + "External id": 4673954,"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": 1708037287545.933, "dur": 12.984, + "args": { + "External id": 4673955,"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": 1708037287563.109, "dur": 21.274, + "args": { + "External id": 4673956,"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": 1708037287565.378, "dur": 2.228, + "args": { + "External id": 4673957,"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": 1708037287569.920, "dur": 1.262, + "args": { + "External id": 4673958,"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": 1708037287585.733, "dur": 11.034, + "args": { + "External id": 4673959,"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": 1708037287598.175, "dur": 10.418, + "args": { + "External id": 4673960,"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": 1708037287619.769, "dur": 2.177, + "args": { + "External id": 4673961,"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": 1708037287631.048, "dur": 3.211, + "args": { + "External id": 4673962,"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": 1708037287633.106, "dur": 0.373, + "args": { + "External id": 4673963,"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": 1708037287698.992, "dur": 59.685, + "args": { + "External id": 4673964,"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": 1708037287762.938, "dur": 4.594, + "args": { + "External id": 4673965,"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": 1708037287765.267, "dur": 1.243, + "args": { + "External id": 4673966,"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": 1708037287769.368, "dur": 33.868, + "args": { + "External id": 4673967,"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": 1708037287808.184, "dur": 7.737, + "args": { + "External id": 4673968,"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": 1708037287809.969, "dur": 5.395, + "args": { + "External id": 4673969,"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": 1708037287813.204, "dur": 1.978, + "args": { + "External id": 4673970,"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": 1708037287818.456, "dur": 71.874, + "args": { + "External id": 4673971,"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": 1708037287819.616, "dur": 70.045, + "args": { + "External id": 4673972,"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": 1708037287893.744, "dur": 37.701, + "args": { + "External id": 4673973,"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": 1708037287936.519, "dur": 3.835, + "args": { + "External id": 4673974,"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": 1708037287938.729, "dur": 0.787, + "args": { + "External id": 4673975,"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": 1708037287945.874, "dur": 96.426, + "args": { + "External id": 4673976,"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": 1708037287946.720, "dur": 4.030, + "args": { + "External id": 4673977,"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": 1708037287947.687, "dur": 2.550, + "args": { + "External id": 4673978,"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": 1708037287948.902, "dur": 1.195, + "args": { + "External id": 4673979,"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": 1708037287951.695, "dur": 89.995, + "args": { + "External id": 4673980,"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": 1708037287952.425, "dur": 88.018, + "args": { + "External id": 4673981,"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": 1708037288049.819, "dur": 5.078, + "args": { + "External id": 4673982,"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": 1708037288052.523, "dur": 1.047, + "args": { + "External id": 4673983,"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": 1708037288061.423, "dur": 1.740, + "args": { + "External id": 4673984,"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": 1708037288070.961, "dur": 7.941, + "args": { + "External id": 4673985,"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": 1708037288072.714, "dur": 5.908, + "args": { + "External id": 4673986,"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": 1708037288165.387, "dur": 175.226, + "args": { + "External id": 4673987,"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": 1708037288167.871, "dur": 2.399, + "args": { + "External id": 4673988,"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": 1708037288171.790, "dur": 168.360, + "args": { + "External id": 4673989,"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": 1708037288173.311, "dur": 0.290, + "args": { + "External id": 4673990,"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": 1708037288174.486, "dur": 22.743, + "args": { + "External id": 4673991,"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": 1708037288198.975, "dur": 3.618, + "args": { + "External id": 4673992,"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": 1708037288201.293, "dur": 0.997, + "args": { + "External id": 4673993,"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": 1708037288203.554, "dur": 24.120, + "args": { + "External id": 4673994,"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": 1708037288204.987, "dur": 1.554, + "args": { + "External id": 4673995,"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": 1708037288207.777, "dur": 19.560, + "args": { + "External id": 4673996,"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": 1708037288213.450, "dur": 2.587, + "args": { + "External id": 4673997,"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": 1708037288229.384, "dur": 20.087, + "args": { + "External id": 4673998,"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": 1708037288251.106, "dur": 13.151, + "args": { + "External id": 4673999,"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": 1708037288267.065, "dur": 13.421, + "args": { + "External id": 4674000,"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": 1708037288281.731, "dur": 11.820, + "args": { + "External id": 4674001,"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": 1708037288295.171, "dur": 18.310, + "args": { + "External id": 4674002,"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": 1708037288296.997, "dur": 1.180, + "args": { + "External id": 4674003,"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": 1708037288300.179, "dur": 0.997, + "args": { + "External id": 4674004,"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": 1708037288316.387, "dur": 11.034, + "args": { + "External id": 4674005,"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": 1708037288328.675, "dur": 10.656, + "args": { + "External id": 4674006,"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": 1708037288346.999, "dur": 1.595, + "args": { + "External id": 4674007,"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": 1708037288356.327, "dur": 3.236, + "args": { + "External id": 4674008,"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": 1708037288358.240, "dur": 0.622, + "args": { + "External id": 4674009,"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": 1708037288423.700, "dur": 55.146, + "args": { + "External id": 4674010,"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": 1708037288483.120, "dur": 5.271, + "args": { + "External id": 4674011,"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": 1708037288485.549, "dur": 1.808, + "args": { + "External id": 4674012,"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": 1708037288491.596, "dur": 23.983, + "args": { + "External id": 4674013,"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": 1708037288519.906, "dur": 22.965, + "args": { + "External id": 4674014,"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": 1708037288521.485, "dur": 20.398, + "args": { + "External id": 4674015,"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": 1708037288523.351, "dur": 17.902, + "args": { + "External id": 4674016,"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": 1708037288546.938, "dur": 46.167, + "args": { + "External id": 4674017,"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": 1708037288548.402, "dur": 44.057, + "args": { + "External id": 4674018,"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": 1708037288597.349, "dur": 15.504, + "args": { + "External id": 4674019,"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": 1708037288620.513, "dur": 4.149, + "args": { + "External id": 4674020,"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": 1708037288622.822, "dur": 0.870, + "args": { + "External id": 4674021,"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": 1708037288628.532, "dur": 51.504, + "args": { + "External id": 4674022,"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": 1708037288629.626, "dur": 5.873, + "args": { + "External id": 4674023,"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": 1708037288631.025, "dur": 3.920, + "args": { + "External id": 4674024,"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": 1708037288632.409, "dur": 2.359, + "args": { + "External id": 4674025,"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": 1708037288638.398, "dur": 40.971, + "args": { + "External id": 4674026,"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": 1708037288639.401, "dur": 39.362, + "args": { + "External id": 4674027,"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": 1708037288684.123, "dur": 3.953, + "args": { + "External id": 4674028,"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": 1708037288686.208, "dur": 0.879, + "args": { + "External id": 4674029,"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": 1708037288694.062, "dur": 1.702, + "args": { + "External id": 4674030,"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": 1708037288703.181, "dur": 5.807, + "args": { + "External id": 4674031,"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": 1708037288704.905, "dur": 3.836, + "args": { + "External id": 4674032,"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": 1708037288793.648, "dur": 311.607, + "args": { + "External id": 4674033,"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": 1708037288795.811, "dur": 2.037, + "args": { + "External id": 4674034,"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": 1708037288799.602, "dur": 305.062, + "args": { + "External id": 4674035,"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": 1708037288800.997, "dur": 0.501, + "args": { + "External id": 4674036,"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": 1708037288804.088, "dur": 18.961, + "args": { + "External id": 4674037,"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": 1708037288824.650, "dur": 3.265, + "args": { + "External id": 4674038,"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": 1708037288826.773, "dur": 0.874, + "args": { + "External id": 4674039,"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": 1708037288828.822, "dur": 23.503, + "args": { + "External id": 4674040,"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": 1708037288830.077, "dur": 3.310, + "args": { + "External id": 4674041,"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": 1708037288836.299, "dur": 15.735, + "args": { + "External id": 4674042,"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": 1708037288839.097, "dur": 2.497, + "args": { + "External id": 4674043,"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": 1708037288853.814, "dur": 20.220, + "args": { + "External id": 4674044,"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": 1708037288875.378, "dur": 11.693, + "args": { + "External id": 4674045,"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": 1708037288889.956, "dur": 12.651, + "args": { + "External id": 4674046,"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": 1708037288903.869, "dur": 11.498, + "args": { + "External id": 4674047,"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": 1708037288916.996, "dur": 158.498, + "args": { + "External id": 4674048,"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": 1708037289048.661, "dur": 3.548, + "args": { + "External id": 4674049,"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": 1708037289056.338, "dur": 1.005, + "args": { + "External id": 4674050,"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": 1708037289079.312, "dur": 11.990, + "args": { + "External id": 4674051,"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": 1708037289092.391, "dur": 11.056, + "args": { + "External id": 4674052,"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": 1708037289114.771, "dur": 2.535, + "args": { + "External id": 4674053,"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": 1708037289127.549, "dur": 3.818, + "args": { + "External id": 4674054,"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": 1708037289129.960, "dur": 0.419, + "args": { + "External id": 4674055,"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": 1708037289205.606, "dur": 60.484, + "args": { + "External id": 4674056,"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": 1708037289270.535, "dur": 5.951, + "args": { + "External id": 4674057,"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": 1708037289274.217, "dur": 1.277, + "args": { + "External id": 4674058,"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": 1708037289277.706, "dur": 24.805, + "args": { + "External id": 4674059,"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": 1708037289306.602, "dur": 7.677, + "args": { + "External id": 4674060,"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": 1708037289308.361, "dur": 5.199, + "args": { + "External id": 4674061,"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": 1708037289310.208, "dur": 3.106, + "args": { + "External id": 4674062,"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": 1708037289317.002, "dur": 39.891, + "args": { + "External id": 4674063,"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": 1708037289318.370, "dur": 37.870, + "args": { + "External id": 4674064,"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": 1708037289362.180, "dur": 13.223, + "args": { + "External id": 4674065,"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": 1708037289381.153, "dur": 3.426, + "args": { + "External id": 4674066,"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": 1708037289382.965, "dur": 0.766, + "args": { + "External id": 4674067,"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": 1708037289388.635, "dur": 48.202, + "args": { + "External id": 4674068,"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": 1708037289389.507, "dur": 5.927, + "args": { + "External id": 4674069,"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": 1708037289390.089, "dur": 4.751, + "args": { + "External id": 4674070,"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": 1708037289393.591, "dur": 1.098, + "args": { + "External id": 4674071,"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": 1708037289396.051, "dur": 40.382, + "args": { + "External id": 4674072,"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": 1708037289396.681, "dur": 39.041, + "args": { + "External id": 4674073,"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": 1708037289440.339, "dur": 3.775, + "args": { + "External id": 4674074,"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": 1708037289442.080, "dur": 0.915, + "args": { + "External id": 4674075,"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": 1708037289449.805, "dur": 1.248, + "args": { + "External id": 4674076,"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": 1708037289460.257, "dur": 6.153, + "args": { + "External id": 4674077,"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": 1708037289462.051, "dur": 4.139, + "args": { + "External id": 4674078,"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": 1708037289567.205, "dur": 177.694, + "args": { + "External id": 4674079,"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": 1708037289569.856, "dur": 2.754, + "args": { + "External id": 4674080,"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": 1708037289576.195, "dur": 168.213, + "args": { + "External id": 4674081,"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": 1708037289577.675, "dur": 0.311, + "args": { + "External id": 4674082,"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": 1708037289579.192, "dur": 20.780, + "args": { + "External id": 4674083,"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": 1708037289601.704, "dur": 4.974, + "args": { + "External id": 4674084,"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": 1708037289603.626, "dur": 2.639, + "args": { + "External id": 4674085,"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": 1708037289609.519, "dur": 21.302, + "args": { + "External id": 4674086,"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": 1708037289610.332, "dur": 1.806, + "args": { + "External id": 4674087,"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": 1708037289613.306, "dur": 17.170, + "args": { + "External id": 4674088,"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": 1708037289616.118, "dur": 2.173, + "args": { + "External id": 4674089,"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": 1708037289632.145, "dur": 19.942, + "args": { + "External id": 4674090,"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": 1708037289653.479, "dur": 13.750, + "args": { + "External id": 4674091,"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": 1708037289669.863, "dur": 12.659, + "args": { + "External id": 4674092,"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": 1708037289683.993, "dur": 11.681, + "args": { + "External id": 4674093,"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": 1708037289697.642, "dur": 21.245, + "args": { + "External id": 4674094,"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": 1708037289700.971, "dur": 1.379, + "args": { + "External id": 4674095,"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": 1708037289704.272, "dur": 2.458, + "args": { + "External id": 4674096,"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": 1708037289720.062, "dur": 11.259, + "args": { + "External id": 4674097,"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": 1708037289732.524, "dur": 11.027, + "args": { + "External id": 4674098,"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": 1708037289751.185, "dur": 1.847, + "args": { + "External id": 4674099,"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": 1708037289761.018, "dur": 3.240, + "args": { + "External id": 4674100,"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": 1708037289762.995, "dur": 0.462, + "args": { + "External id": 4674101,"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": 1708037289828.690, "dur": 49.887, + "args": { + "External id": 4674102,"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": 1708037289883.185, "dur": 4.316, + "args": { + "External id": 4674103,"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": 1708037289885.431, "dur": 0.980, + "args": { + "External id": 4674104,"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": 1708037289888.989, "dur": 22.719, + "args": { + "External id": 4674105,"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": 1708037289916.070, "dur": 7.465, + "args": { + "External id": 4674106,"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": 1708037289917.462, "dur": 5.401, + "args": { + "External id": 4674107,"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": 1708037289921.063, "dur": 1.636, + "args": { + "External id": 4674108,"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": 1708037289926.029, "dur": 38.514, + "args": { + "External id": 4674109,"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": 1708037289926.978, "dur": 36.914, + "args": { + "External id": 4674110,"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": 1708037289968.154, "dur": 12.872, + "args": { + "External id": 4674111,"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": 1708037290021.783, "dur": 5.119, + "args": { + "External id": 4674112,"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": 1708037290024.318, "dur": 1.298, + "args": { + "External id": 4674113,"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": 1708037290031.978, "dur": 53.763, + "args": { + "External id": 4674114,"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": 1708037290034.491, "dur": 4.151, + "args": { + "External id": 4674115,"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": 1708037290035.591, "dur": 2.528, + "args": { + "External id": 4674116,"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": 1708037290036.876, "dur": 1.080, + "args": { + "External id": 4674117,"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": 1708037290039.260, "dur": 46.123, + "args": { + "External id": 4674118,"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": 1708037290040.022, "dur": 44.735, + "args": { + "External id": 4674119,"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": 1708037290090.051, "dur": 4.037, + "args": { + "External id": 4674120,"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": 1708037290091.887, "dur": 1.180, + "args": { + "External id": 4674121,"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": 1708037290100.487, "dur": 1.384, + "args": { + "External id": 4674122,"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": 1708037290110.642, "dur": 5.937, + "args": { + "External id": 4674123,"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": 1708037290112.455, "dur": 3.915, + "args": { + "External id": 4674124,"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": 1708037290193.708, "dur": 179.818, + "args": { + "External id": 4674125,"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": 1708037290197.757, "dur": 2.091, + "args": { + "External id": 4674126,"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": 1708037290200.863, "dur": 172.129, + "args": { + "External id": 4674127,"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": 1708037290202.428, "dur": 0.424, + "args": { + "External id": 4674128,"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": 1708037290205.793, "dur": 20.433, + "args": { + "External id": 4674129,"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": 1708037290227.858, "dur": 5.049, + "args": { + "External id": 4674130,"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": 1708037290231.903, "dur": 0.677, + "args": { + "External id": 4674131,"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": 1708037290240.790, "dur": 20.050, + "args": { + "External id": 4674132,"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": 1708037290241.539, "dur": 1.791, + "args": { + "External id": 4674133,"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": 1708037290244.566, "dur": 15.885, + "args": { + "External id": 4674134,"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": 1708037290247.319, "dur": 2.493, + "args": { + "External id": 4674135,"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": 1708037290262.291, "dur": 20.512, + "args": { + "External id": 4674136,"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": 1708037290284.064, "dur": 13.976, + "args": { + "External id": 4674137,"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": 1708037290302.022, "dur": 13.665, + "args": { + "External id": 4674138,"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": 1708037290317.045, "dur": 11.469, + "args": { + "External id": 4674139,"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": 1708037290330.301, "dur": 17.735, + "args": { + "External id": 4674140,"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": 1708037290332.370, "dur": 1.077, + "args": { + "External id": 4674141,"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": 1708037290335.257, "dur": 0.698, + "args": { + "External id": 4674142,"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": 1708037290349.001, "dur": 10.862, + "args": { + "External id": 4674143,"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": 1708037290360.920, "dur": 11.309, + "args": { + "External id": 4674144,"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": 1708037290381.398, "dur": 1.480, + "args": { + "External id": 4674145,"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": 1708037290390.079, "dur": 3.519, + "args": { + "External id": 4674146,"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": 1708037290392.451, "dur": 0.465, + "args": { + "External id": 4674147,"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": 1708037290450.246, "dur": 45.869, + "args": { + "External id": 4674148,"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": 1708037290500.689, "dur": 4.225, + "args": { + "External id": 4674149,"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": 1708037290502.845, "dur": 1.116, + "args": { + "External id": 4674150,"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": 1708037290519.102, "dur": 40.467, + "args": { + "External id": 4674151,"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": 1708037290567.721, "dur": 7.286, + "args": { + "External id": 4674152,"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": 1708037290569.093, "dur": 4.951, + "args": { + "External id": 4674153,"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": 1708037290571.088, "dur": 2.785, + "args": { + "External id": 4674154,"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": 1708037290577.865, "dur": 44.309, + "args": { + "External id": 4674155,"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": 1708037290579.131, "dur": 42.321, + "args": { + "External id": 4674156,"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": 1708037290626.031, "dur": 15.019, + "args": { + "External id": 4674157,"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": 1708037290646.988, "dur": 5.428, + "args": { + "External id": 4674158,"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": 1708037290650.724, "dur": 0.946, + "args": { + "External id": 4674159,"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": 1708037290655.720, "dur": 48.450, + "args": { + "External id": 4674160,"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": 1708037290656.691, "dur": 4.012, + "args": { + "External id": 4674161,"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": 1708037290657.647, "dur": 2.558, + "args": { + "External id": 4674162,"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": 1708037290659.063, "dur": 1.028, + "args": { + "External id": 4674163,"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": 1708037290661.191, "dur": 42.603, + "args": { + "External id": 4674164,"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": 1708037290663.923, "dur": 39.323, + "args": { + "External id": 4674165,"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": 1708037290707.698, "dur": 4.001, + "args": { + "External id": 4674166,"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": 1708037290709.622, "dur": 1.153, + "args": { + "External id": 4674167,"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": 1708037290717.778, "dur": 1.740, + "args": { + "External id": 4674168,"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": 1708037290726.760, "dur": 7.506, + "args": { + "External id": 4674169,"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": 1708037290729.954, "dur": 4.098, + "args": { + "External id": 4674170,"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": 1708037290811.306, "dur": 168.867, + "args": { + "External id": 4674171,"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": 1708037290813.615, "dur": 2.581, + "args": { + "External id": 4674172,"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": 1708037290818.863, "dur": 160.786, + "args": { + "External id": 4674173,"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": 1708037290820.008, "dur": 0.486, + "args": { + "External id": 4674174,"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": 1708037290821.579, "dur": 19.847, + "args": { + "External id": 4674175,"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": 1708037290842.748, "dur": 5.225, + "args": { + "External id": 4674176,"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": 1708037290845.126, "dur": 2.528, + "args": { + "External id": 4674177,"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": 1708037290849.159, "dur": 21.022, + "args": { + "External id": 4674178,"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": 1708037290852.033, "dur": 1.780, + "args": { + "External id": 4674179,"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": 1708037290854.796, "dur": 15.077, + "args": { + "External id": 4674180,"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": 1708037290857.077, "dur": 2.109, + "args": { + "External id": 4674181,"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": 1708037290871.296, "dur": 18.691, + "args": { + "External id": 4674182,"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": 1708037290891.095, "dur": 12.571, + "args": { + "External id": 4674183,"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": 1708037290906.470, "dur": 11.693, + "args": { + "External id": 4674184,"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": 1708037290919.539, "dur": 11.428, + "args": { + "External id": 4674185,"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": 1708037290932.881, "dur": 21.094, + "args": { + "External id": 4674186,"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": 1708037290934.262, "dur": 1.118, + "args": { + "External id": 4674187,"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": 1708037290939.038, "dur": 2.843, + "args": { + "External id": 4674188,"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": 1708037290955.328, "dur": 11.740, + "args": { + "External id": 4674189,"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": 1708037290967.990, "dur": 10.905, + "args": { + "External id": 4674190,"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": 1708037291020.861, "dur": 2.187, + "args": { + "External id": 4674191,"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": 1708037291032.685, "dur": 3.974, + "args": { + "External id": 4674192,"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": 1708037291035.361, "dur": 0.516, + "args": { + "External id": 4674193,"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": 1708037291102.653, "dur": 53.439, + "args": { + "External id": 4674194,"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": 1708037291160.639, "dur": 6.230, + "args": { + "External id": 4674195,"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": 1708037291164.461, "dur": 1.135, + "args": { + "External id": 4674196,"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": 1708037291168.034, "dur": 23.575, + "args": { + "External id": 4674197,"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": 1708037291195.695, "dur": 5.564, + "args": { + "External id": 4674198,"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": 1708037291197.049, "dur": 3.329, + "args": { + "External id": 4674199,"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": 1708037291198.815, "dur": 1.366, + "args": { + "External id": 4674200,"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": 1708037291203.706, "dur": 41.170, + "args": { + "External id": 4674201,"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": 1708037291206.494, "dur": 37.712, + "args": { + "External id": 4674202,"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": 1708037291248.041, "dur": 14.046, + "args": { + "External id": 4674203,"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": 1708037291266.380, "dur": 22.691, + "args": { + "External id": 4674204,"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": 1708037291268.647, "dur": 20.065, + "args": { + "External id": 4674205,"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": 1708037291273.658, "dur": 1.252, + "args": { + "External id": 4674206,"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": 1708037291293.754, "dur": 24.677, + "args": { + "External id": 4674207,"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": 1708037291295.483, "dur": 22.756, + "args": { + "External id": 4674208,"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": 1708037291299.592, "dur": 4.211, + "args": { + "External id": 4674209,"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": 1708037291305.042, "dur": 12.811, + "args": { + "External id": 4674210,"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": 1708037291331.183, "dur": 6.264, + "args": { + "External id": 4674211,"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": 1708037291334.539, "dur": 2.541, + "args": { + "External id": 4674212,"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": 1708037291338.626, "dur": 1.199, + "args": { + "External id": 4674213,"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": 1708037291339.108, "dur": 0.632, + "args": { + "External id": 4674214,"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": 1708037291377.801, "dur": 19.636, + "args": { + "External id": 4674215,"Sequence number": 46526644, "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": 1708037291399.372, "dur": 14.638, + "args": { + "External id": 4674216,"Sequence number": 46526645, "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": 1708037291399.372, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1708037291419.847, "dur": 5.416, + "args": { + "External id": 4674217,"Sequence number": 46526646, "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": 1708037291422.849, "dur": 1.188, + "args": { + "External id": 4674218,"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": 1708037291429.087, "dur": 6.108, + "args": { + "External id": 4674219,"Sequence number": 46526646, "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": 1708037291432.898, "dur": 0.998, + "args": { + "External id": 4674220,"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": 1708037291436.511, "dur": 3.257, + "args": { + "External id": 4674221,"Sequence number": 46526646, "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": 1708037291437.960, "dur": 1.188, + "args": { + "External id": 4674222,"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": 1708037291444.108, "dur": 7.567, + "args": { + "External id": 4674223,"Sequence number": 46526646, "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": 1708037291444.108, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037291449.381, "dur": 1.016, + "args": { + "External id": 4674224,"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": 1708037291452.797, "dur": 5.571, + "args": { + "External id": 4674225,"Sequence number": 46526647, "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": 1708037291452.797, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037291456.767, "dur": 0.877, + "args": { + "External id": 4674226,"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": 1708037291459.218, "dur": 7.026, + "args": { + "External id": 4674227,"Sequence number": 46526648, "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": 1708037291459.218, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037291464.368, "dur": 0.984, + "args": { + "External id": 4674228,"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": 1708037291467.555, "dur": 4.334, + "args": { + "External id": 4674229,"Sequence number": 46526649, "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": 1708037291467.555, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037291470.254, "dur": 0.780, + "args": { + "External id": 4674230,"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": 1708037291475.798, "dur": 28.894, + "args": { + "External id": 4674231,"Sequence number": 46526650, "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": 1708037291477.422, "dur": 27.069, + "args": { + "External id": 4674232,"Sequence number": 46526650, "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": 1708037291480.313, "dur": 6.305, + "args": { + "External id": 4674233,"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": 1708037291482.481, "dur": 3.600, + "args": { + "External id": 4674234,"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": 1708037291487.464, "dur": 16.566, + "args": { + "External id": 4674235,"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": 1708037291548.042, "dur": 7.001, + "args": { + "External id": 4674236,"Sequence number": 46526650, "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": 1708037291548.042, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708037291557.781, "dur": 1.424, + "args": { + "External id": 4674237,"Sequence number": 46526651, "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": 1708037291593.290, "dur": 44837.460, + "args": { + "External id": 4674238,"Sequence number": 46526651, "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": 1708037291593.290, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1708037291608.348, "dur": 28.448, + "args": { + "External id": 4674239,"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": 1708037291609.034, "dur": 27.577, + "args": { + "External id": 4674240,"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": 1708037291610.461, "dur": 6.707, + "args": { + "External id": 4674241,"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": 1708037291612.175, "dur": 4.592, + "args": { + "External id": 4674242,"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": 1708037291617.999, "dur": 18.217, + "args": { + "External id": 4674243,"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": 1708037291651.503, "dur": 24.792, + "args": { + "External id": 4674244,"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": 1708037291652.692, "dur": 5.948, + "args": { + "External id": 4674245,"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": 1708037291654.870, "dur": 3.395, + "args": { + "External id": 4674246,"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": 1708037291660.031, "dur": 16.059, + "args": { + "External id": 4674247,"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": 1708037291661.852, "dur": 13.852, + "args": { + "External id": 4674248,"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": 1708037291679.504, "dur": 19.543, + "args": { + "External id": 4674249,"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": 1708037291680.176, "dur": 5.570, + "args": { + "External id": 4674250,"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": 1708037291682.966, "dur": 2.574, + "args": { + "External id": 4674251,"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": 1708037291686.410, "dur": 12.433, + "args": { + "External id": 4674252,"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": 1708037291687.107, "dur": 11.348, + "args": { + "External id": 4674253,"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": 1708037291704.509, "dur": 17.426, + "args": { + "External id": 4674254,"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": 1708037291708.108, "dur": 2.619, + "args": { + "External id": 4674255,"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": 1708037291711.240, "dur": 10.431, + "args": { + "External id": 4674256,"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": 1708037291711.854, "dur": 9.531, + "args": { + "External id": 4674257,"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": 1708037291728.211, "dur": 21.390, + "args": { + "External id": 4674258,"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": 1708037291752.108, "dur": 47.266, + "args": { + "External id": 4674259,"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": 1708037291753.891, "dur": 45.000, + "args": { + "External id": 4674260,"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": 1708037291758.816, "dur": 1.352, + "args": { + "External id": 4674261,"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": 1708037291761.648, "dur": 22.798, + "args": { + "External id": 4674262,"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": 1708037291763.251, "dur": 20.965, + "args": { + "External id": 4674263,"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": 1708037291767.279, "dur": 3.276, + "args": { + "External id": 4674264,"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": 1708037291771.266, "dur": 12.640, + "args": { + "External id": 4674265,"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": 1708037291803.320, "dur": 38863.550, + "args": { + "External id": 4674266,"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": 1708037291804.775, "dur": 38860.095, + "args": { + "External id": 4674267,"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": 1708037330681.878, "dur": 11.088, + "args": { + "External id": 4674268,"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": 1708037330689.280, "dur": 1.310, + "args": { + "External id": 4674269,"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": 1708037330698.505, "dur": 114.099, + "args": { + "External id": 4674270,"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": 1708037330700.564, "dur": 7.094, + "args": { + "External id": 4674271,"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": 1708037330703.084, "dur": 3.703, + "args": { + "External id": 4674272,"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": 1708037330705.049, "dur": 1.459, + "args": { + "External id": 4674273,"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": 1708037330709.179, "dur": 102.739, + "args": { + "External id": 4674274,"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": 1708037330713.397, "dur": 97.444, + "args": { + "External id": 4674275,"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": 1708037330816.044, "dur": 4.678, + "args": { + "External id": 4674276,"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": 1708037330818.041, "dur": 1.267, + "args": { + "External id": 4674277,"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": 1708037330830.170, "dur": 2.693, + "args": { + "External id": 4674278,"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": 1708037330843.295, "dur": 7.214, + "args": { + "External id": 4674279,"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": 1708037330845.809, "dur": 4.394, + "args": { + "External id": 4674280,"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": 1708037331014.742, "dur": 203.064, + "args": { + "External id": 4674281,"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": 1708037331018.221, "dur": 3.286, + "args": { + "External id": 4674282,"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": 1708037331024.960, "dur": 192.279, + "args": { + "External id": 4674283,"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": 1708037331026.413, "dur": 0.547, + "args": { + "External id": 4674284,"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": 1708037331028.360, "dur": 28.252, + "args": { + "External id": 4674285,"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": 1708037331058.407, "dur": 6.419, + "args": { + "External id": 4674286,"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": 1708037331060.782, "dur": 3.611, + "args": { + "External id": 4674287,"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": 1708037331066.160, "dur": 25.815, + "args": { + "External id": 4674288,"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": 1708037331067.532, "dur": 1.766, + "args": { + "External id": 4674289,"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": 1708037331072.343, "dur": 19.278, + "args": { + "External id": 4674290,"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": 1708037331076.520, "dur": 3.344, + "args": { + "External id": 4674291,"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": 1708037331093.904, "dur": 22.260, + "args": { + "External id": 4674292,"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": 1708037331117.868, "dur": 14.500, + "args": { + "External id": 4674293,"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": 1708037331135.693, "dur": 14.082, + "args": { + "External id": 4674294,"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": 1708037331151.369, "dur": 13.082, + "args": { + "External id": 4674295,"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": 1708037331166.411, "dur": 23.726, + "args": { + "External id": 4674296,"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": 1708037331168.412, "dur": 1.592, + "args": { + "External id": 4674297,"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": 1708037331174.394, "dur": 2.444, + "args": { + "External id": 4674298,"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": 1708037331191.691, "dur": 11.958, + "args": { + "External id": 4674299,"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": 1708037331205.378, "dur": 10.691, + "args": { + "External id": 4674300,"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": 1708037331225.431, "dur": 2.537, + "args": { + "External id": 4674301,"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": 1708037331235.388, "dur": 4.346, + "args": { + "External id": 4674302,"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": 1708037331237.817, "dur": 0.891, + "args": { + "External id": 4674303,"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": 1708037331318.603, "dur": 68.062, + "args": { + "External id": 4674304,"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": 1708037331392.011, "dur": 7.622, + "args": { + "External id": 4674305,"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": 1708037331396.213, "dur": 1.025, + "args": { + "External id": 4674306,"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": 1708037331401.061, "dur": 25.850, + "args": { + "External id": 4674307,"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": 1708037331432.113, "dur": 6.378, + "args": { + "External id": 4674308,"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": 1708037331433.849, "dur": 3.834, + "args": { + "External id": 4674309,"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": 1708037331435.899, "dur": 1.535, + "args": { + "External id": 4674310,"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": 1708037331441.222, "dur": 44.727, + "args": { + "External id": 4674311,"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": 1708037331444.077, "dur": 41.162, + "args": { + "External id": 4674312,"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": 1708037331490.283, "dur": 14.712, + "args": { + "External id": 4674313,"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": 1708037331510.960, "dur": 3.634, + "args": { + "External id": 4674314,"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": 1708037331513.000, "dur": 0.632, + "args": { + "External id": 4674315,"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": 1708037331518.590, "dur": 70.791, + "args": { + "External id": 4674316,"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": 1708037331519.534, "dur": 21.014, + "args": { + "External id": 4674317,"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": 1708037331520.706, "dur": 18.971, + "args": { + "External id": 4674318,"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": 1708037331538.493, "dur": 0.781, + "args": { + "External id": 4674319,"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": 1708037331541.314, "dur": 47.600, + "args": { + "External id": 4674320,"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": 1708037331542.196, "dur": 46.174, + "args": { + "External id": 4674321,"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": 1708037331594.099, "dur": 3.983, + "args": { + "External id": 4674322,"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": 1708037331596.029, "dur": 0.827, + "args": { + "External id": 4674323,"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": 1708037331604.338, "dur": 1.813, + "args": { + "External id": 4674324,"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": 1708037331615.690, "dur": 7.138, + "args": { + "External id": 4674325,"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": 1708037331618.101, "dur": 4.470, + "args": { + "External id": 4674326,"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": 1708037331716.938, "dur": 177.743, + "args": { + "External id": 4674327,"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": 1708037331720.696, "dur": 2.214, + "args": { + "External id": 4674328,"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": 1708037331724.093, "dur": 170.008, + "args": { + "External id": 4674329,"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": 1708037331725.614, "dur": 0.262, + "args": { + "External id": 4674330,"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": 1708037331728.853, "dur": 20.799, + "args": { + "External id": 4674331,"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": 1708037331751.569, "dur": 5.122, + "args": { + "External id": 4674332,"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": 1708037331755.307, "dur": 1.075, + "args": { + "External id": 4674333,"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": 1708037331757.733, "dur": 21.579, + "args": { + "External id": 4674334,"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": 1708037331758.892, "dur": 1.663, + "args": { + "External id": 4674335,"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": 1708037331761.757, "dur": 17.209, + "args": { + "External id": 4674336,"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": 1708037331764.808, "dur": 2.861, + "args": { + "External id": 4674337,"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": 1708037331780.964, "dur": 20.108, + "args": { + "External id": 4674338,"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": 1708037331802.490, "dur": 12.631, + "args": { + "External id": 4674339,"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": 1708037331817.708, "dur": 13.775, + "args": { + "External id": 4674340,"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": 1708037331834.936, "dur": 11.120, + "args": { + "External id": 4674341,"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": 1708037331847.756, "dur": 20.541, + "args": { + "External id": 4674342,"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": 1708037331851.603, "dur": 1.234, + "args": { + "External id": 4674343,"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": 1708037331854.760, "dur": 1.034, + "args": { + "External id": 4674344,"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": 1708037331869.691, "dur": 11.471, + "args": { + "External id": 4674345,"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": 1708037331882.191, "dur": 10.903, + "args": { + "External id": 4674346,"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": 1708037331900.863, "dur": 1.673, + "args": { + "External id": 4674347,"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": 1708037331912.610, "dur": 2.851, + "args": { + "External id": 4674348,"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": 1708037331914.331, "dur": 0.408, + "args": { + "External id": 4674349,"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": 1708037332028.051, "dur": 59.798, + "args": { + "External id": 4674350,"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": 1708037332094.069, "dur": 6.113, + "args": { + "External id": 4674351,"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": 1708037332096.976, "dur": 1.492, + "args": { + "External id": 4674352,"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": 1708037332101.465, "dur": 26.015, + "args": { + "External id": 4674353,"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": 1708037332132.588, "dur": 7.440, + "args": { + "External id": 4674354,"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": 1708037332134.058, "dur": 5.360, + "args": { + "External id": 4674355,"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": 1708037332137.674, "dur": 1.503, + "args": { + "External id": 4674356,"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": 1708037332143.165, "dur": 40.702, + "args": { + "External id": 4674357,"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": 1708037332144.673, "dur": 38.605, + "args": { + "External id": 4674358,"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": 1708037332187.724, "dur": 14.599, + "args": { + "External id": 4674359,"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": 1708037332207.996, "dur": 3.511, + "args": { + "External id": 4674360,"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": 1708037332210.085, "dur": 0.633, + "args": { + "External id": 4674361,"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": 1708037332217.540, "dur": 46.060, + "args": { + "External id": 4674362,"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": 1708037332218.568, "dur": 3.196, + "args": { + "External id": 4674363,"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": 1708037332219.192, "dur": 2.021, + "args": { + "External id": 4674364,"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": 1708037332220.342, "dur": 0.746, + "args": { + "External id": 4674365,"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": 1708037332222.468, "dur": 40.800, + "args": { + "External id": 4674366,"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": 1708037332222.998, "dur": 39.756, + "args": { + "External id": 4674367,"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": 1708037332282.336, "dur": 3.723, + "args": { + "External id": 4674368,"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": 1708037332284.143, "dur": 0.723, + "args": { + "External id": 4674369,"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": 1708037332293.747, "dur": 2.042, + "args": { + "External id": 4674370,"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": 1708037332303.585, "dur": 7.997, + "args": { + "External id": 4674371,"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": 1708037332305.287, "dur": 5.972, + "args": { + "External id": 4674372,"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": 1708037332400.706, "dur": 195.793, + "args": { + "External id": 4674373,"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": 1708037332402.806, "dur": 1.976, + "args": { + "External id": 4674374,"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": 1708037332406.593, "dur": 189.336, + "args": { + "External id": 4674375,"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": 1708037332409.718, "dur": 0.262, + "args": { + "External id": 4674376,"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": 1708037332411.192, "dur": 21.291, + "args": { + "External id": 4674377,"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": 1708037332434.312, "dur": 3.003, + "args": { + "External id": 4674378,"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": 1708037332436.512, "dur": 0.519, + "args": { + "External id": 4674379,"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": 1708037332438.315, "dur": 24.667, + "args": { + "External id": 4674380,"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": 1708037332439.352, "dur": 1.851, + "args": { + "External id": 4674381,"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": 1708037332442.328, "dur": 20.367, + "args": { + "External id": 4674382,"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": 1708037332446.341, "dur": 2.869, + "args": { + "External id": 4674383,"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": 1708037332464.698, "dur": 19.325, + "args": { + "External id": 4674384,"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": 1708037332485.431, "dur": 12.344, + "args": { + "External id": 4674385,"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": 1708037332499.996, "dur": 12.871, + "args": { + "External id": 4674386,"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": 1708037332515.886, "dur": 27.922, + "args": { + "External id": 4674387,"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": 1708037332546.823, "dur": 21.331, + "args": { + "External id": 4674388,"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": 1708037332548.465, "dur": 2.202, + "args": { + "External id": 4674389,"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": 1708037332552.983, "dur": 0.975, + "args": { + "External id": 4674390,"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": 1708037332569.596, "dur": 11.260, + "args": { + "External id": 4674391,"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": 1708037332581.764, "dur": 10.989, + "args": { + "External id": 4674392,"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": 1708037332603.983, "dur": 2.126, + "args": { + "External id": 4674393,"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": 1708037332615.559, "dur": 3.492, + "args": { + "External id": 4674394,"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": 1708037332617.788, "dur": 0.475, + "args": { + "External id": 4674395,"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": 1708037332686.256, "dur": 85.147, + "args": { + "External id": 4674396,"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": 1708037332775.851, "dur": 4.148, + "args": { + "External id": 4674397,"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": 1708037332777.967, "dur": 0.914, + "args": { + "External id": 4674398,"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": 1708037332781.381, "dur": 37.158, + "args": { + "External id": 4674399,"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": 1708037332822.900, "dur": 7.550, + "args": { + "External id": 4674400,"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": 1708037332826.198, "dur": 3.612, + "args": { + "External id": 4674401,"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": 1708037332828.461, "dur": 1.158, + "args": { + "External id": 4674402,"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": 1708037332849.080, "dur": 69.454, + "args": { + "External id": 4674403,"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": 1708037332850.329, "dur": 67.551, + "args": { + "External id": 4674404,"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": 1708037332922.466, "dur": 23.917, + "args": { + "External id": 4674405,"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": 1708037332951.869, "dur": 5.174, + "args": { + "External id": 4674406,"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": 1708037332955.460, "dur": 0.826, + "args": { + "External id": 4674407,"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": 1708037332960.738, "dur": 96.429, + "args": { + "External id": 4674408,"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": 1708037332961.681, "dur": 3.510, + "args": { + "External id": 4674409,"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": 1708037332962.436, "dur": 2.245, + "args": { + "External id": 4674410,"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": 1708037332963.752, "dur": 0.806, + "args": { + "External id": 4674411,"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": 1708037332965.714, "dur": 90.852, + "args": { + "External id": 4674412,"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": 1708037332966.366, "dur": 89.058, + "args": { + "External id": 4674413,"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": 1708037333064.801, "dur": 6.340, + "args": { + "External id": 4674414,"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": 1708037333067.296, "dur": 2.541, + "args": { + "External id": 4674415,"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": 1708037333078.296, "dur": 1.839, + "args": { + "External id": 4674416,"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": 1708037333088.433, "dur": 6.667, + "args": { + "External id": 4674417,"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": 1708037333090.409, "dur": 4.462, + "args": { + "External id": 4674418,"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": 1708037333183.883, "dur": 172.363, + "args": { + "External id": 4674419,"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": 1708037333186.387, "dur": 2.051, + "args": { + "External id": 4674420,"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": 1708037333189.458, "dur": 166.277, + "args": { + "External id": 4674421,"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": 1708037333190.612, "dur": 0.278, + "args": { + "External id": 4674422,"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": 1708037333192.063, "dur": 22.351, + "args": { + "External id": 4674423,"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": 1708037333215.883, "dur": 3.632, + "args": { + "External id": 4674424,"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": 1708037333218.012, "dur": 1.212, + "args": { + "External id": 4674425,"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": 1708037333220.416, "dur": 23.672, + "args": { + "External id": 4674426,"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": 1708037333221.253, "dur": 1.823, + "args": { + "External id": 4674427,"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": 1708037333226.295, "dur": 17.446, + "args": { + "External id": 4674428,"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": 1708037333230.485, "dur": 2.361, + "args": { + "External id": 4674429,"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": 1708037333245.473, "dur": 20.020, + "args": { + "External id": 4674430,"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": 1708037333266.880, "dur": 12.466, + "args": { + "External id": 4674431,"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": 1708037333282.246, "dur": 13.812, + "args": { + "External id": 4674432,"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": 1708037333297.499, "dur": 11.310, + "args": { + "External id": 4674433,"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": 1708037333310.536, "dur": 17.724, + "args": { + "External id": 4674434,"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": 1708037333312.527, "dur": 1.130, + "args": { + "External id": 4674435,"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": 1708037333315.666, "dur": 0.580, + "args": { + "External id": 4674436,"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": 1708037333331.497, "dur": 11.199, + "args": { + "External id": 4674437,"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": 1708037333343.764, "dur": 11.111, + "args": { + "External id": 4674438,"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": 1708037333362.837, "dur": 1.414, + "args": { + "External id": 4674439,"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": 1708037333371.668, "dur": 3.087, + "args": { + "External id": 4674440,"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": 1708037333373.501, "dur": 0.491, + "args": { + "External id": 4674441,"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": 1708037333435.705, "dur": 51.303, + "args": { + "External id": 4674442,"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": 1708037333491.426, "dur": 6.206, + "args": { + "External id": 4674443,"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": 1708037333495.599, "dur": 0.791, + "args": { + "External id": 4674444,"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": 1708037333498.921, "dur": 23.214, + "args": { + "External id": 4674445,"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": 1708037333544.265, "dur": 6.047, + "args": { + "External id": 4674446,"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": 1708037333545.827, "dur": 3.604, + "args": { + "External id": 4674447,"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": 1708037333547.738, "dur": 1.378, + "args": { + "External id": 4674448,"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": 1708037333553.098, "dur": 45.086, + "args": { + "External id": 4674449,"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": 1708037333554.307, "dur": 43.268, + "args": { + "External id": 4674450,"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": 1708037333603.805, "dur": 15.254, + "args": { + "External id": 4674451,"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": 1708037333624.711, "dur": 3.712, + "args": { + "External id": 4674452,"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": 1708037333626.707, "dur": 0.879, + "args": { + "External id": 4674453,"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": 1708037333632.109, "dur": 48.937, + "args": { + "External id": 4674454,"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": 1708037333632.968, "dur": 6.912, + "args": { + "External id": 4674455,"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": 1708037333634.169, "dur": 5.155, + "args": { + "External id": 4674456,"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": 1708037333636.972, "dur": 2.168, + "args": { + "External id": 4674457,"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": 1708037333640.429, "dur": 40.219, + "args": { + "External id": 4674458,"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": 1708037333641.073, "dur": 39.085, + "args": { + "External id": 4674459,"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": 1708037333706.241, "dur": 9.234, + "args": { + "External id": 4674460,"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": 1708037333713.284, "dur": 1.036, + "args": { + "External id": 4674461,"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": 1708037333722.067, "dur": 1.663, + "args": { + "External id": 4674462,"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": 1708037333731.461, "dur": 7.266, + "args": { + "External id": 4674463,"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": 1708037333734.669, "dur": 3.794, + "args": { + "External id": 4674464,"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": 1708037333830.265, "dur": 213.433, + "args": { + "External id": 4674465,"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": 1708037333833.831, "dur": 2.192, + "args": { + "External id": 4674466,"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": 1708037333837.511, "dur": 205.559, + "args": { + "External id": 4674467,"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": 1708037333838.628, "dur": 0.304, + "args": { + "External id": 4674468,"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": 1708037333840.049, "dur": 20.894, + "args": { + "External id": 4674469,"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": 1708037333862.423, "dur": 4.602, + "args": { + "External id": 4674470,"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": 1708037333866.039, "dur": 0.694, + "args": { + "External id": 4674471,"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": 1708037333868.078, "dur": 22.347, + "args": { + "External id": 4674472,"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": 1708037333870.825, "dur": 1.467, + "args": { + "External id": 4674473,"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": 1708037333873.372, "dur": 16.730, + "args": { + "External id": 4674474,"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": 1708037333875.940, "dur": 2.488, + "args": { + "External id": 4674475,"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": 1708037333891.863, "dur": 19.455, + "args": { + "External id": 4674476,"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": 1708037333912.657, "dur": 12.925, + "args": { + "External id": 4674477,"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": 1708037333928.233, "dur": 12.720, + "args": { + "External id": 4674478,"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": 1708037333942.363, "dur": 11.752, + "args": { + "External id": 4674479,"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": 1708037333956.137, "dur": 21.987, + "args": { + "External id": 4674480,"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": 1708037333959.443, "dur": 1.301, + "args": { + "External id": 4674481,"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": 1708037333964.349, "dur": 1.377, + "args": { + "External id": 4674482,"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": 1708037333979.231, "dur": 49.381, + "args": { + "External id": 4674483,"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": 1708037334030.910, "dur": 10.471, + "args": { + "External id": 4674484,"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": 1708037334051.864, "dur": 2.271, + "args": { + "External id": 4674485,"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": 1708037334063.208, "dur": 3.595, + "args": { + "External id": 4674486,"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": 1708037334065.435, "dur": 0.512, + "args": { + "External id": 4674487,"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": 1708037334137.040, "dur": 56.643, + "args": { + "External id": 4674488,"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": 1708037334198.294, "dur": 6.661, + "args": { + "External id": 4674489,"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": 1708037334202.428, "dur": 1.324, + "args": { + "External id": 4674490,"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": 1708037334206.251, "dur": 22.745, + "args": { + "External id": 4674491,"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": 1708037334233.498, "dur": 6.162, + "args": { + "External id": 4674492,"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": 1708037334235.033, "dur": 3.741, + "args": { + "External id": 4674493,"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": 1708037334236.853, "dur": 1.705, + "args": { + "External id": 4674494,"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": 1708037334242.314, "dur": 43.102, + "args": { + "External id": 4674495,"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": 1708037334245.281, "dur": 39.412, + "args": { + "External id": 4674496,"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": 1708037334289.150, "dur": 14.064, + "args": { + "External id": 4674497,"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": 1708037334308.544, "dur": 3.871, + "args": { + "External id": 4674498,"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": 1708037334310.586, "dur": 1.098, + "args": { + "External id": 4674499,"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": 1708037334316.380, "dur": 86.736, + "args": { + "External id": 4674500,"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": 1708037334352.721, "dur": 7.048, + "args": { + "External id": 4674501,"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": 1708037334356.072, "dur": 3.129, + "args": { + "External id": 4674502,"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": 1708037334358.275, "dur": 0.771, + "args": { + "External id": 4674503,"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": 1708037334360.339, "dur": 42.380, + "args": { + "External id": 4674504,"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": 1708037334360.949, "dur": 41.282, + "args": { + "External id": 4674505,"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": 1708037334407.141, "dur": 3.752, + "args": { + "External id": 4674506,"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": 1708037334409.089, "dur": 0.729, + "args": { + "External id": 4674507,"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": 1708037334418.148, "dur": 1.760, + "args": { + "External id": 4674508,"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": 1708037334427.034, "dur": 8.098, + "args": { + "External id": 4674509,"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": 1708037334428.937, "dur": 5.889, + "args": { + "External id": 4674510,"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": 1708037334517.998, "dur": 197.089, + "args": { + "External id": 4674511,"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": 1708037334519.826, "dur": 2.232, + "args": { + "External id": 4674512,"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": 1708037334523.133, "dur": 191.163, + "args": { + "External id": 4674513,"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": 1708037334541.730, "dur": 0.408, + "args": { + "External id": 4674514,"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": 1708037334543.656, "dur": 25.693, + "args": { + "External id": 4674515,"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": 1708037334570.949, "dur": 3.521, + "args": { + "External id": 4674516,"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": 1708037334573.211, "dur": 0.909, + "args": { + "External id": 4674517,"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": 1708037334575.546, "dur": 22.796, + "args": { + "External id": 4674518,"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": 1708037334576.662, "dur": 2.030, + "args": { + "External id": 4674519,"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": 1708037334579.812, "dur": 18.237, + "args": { + "External id": 4674520,"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": 1708037334584.365, "dur": 2.770, + "args": { + "External id": 4674521,"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": 1708037334599.628, "dur": 20.735, + "args": { + "External id": 4674522,"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": 1708037334621.669, "dur": 12.465, + "args": { + "External id": 4674523,"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": 1708037334637.055, "dur": 13.111, + "args": { + "External id": 4674524,"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": 1708037334653.191, "dur": 11.823, + "args": { + "External id": 4674525,"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": 1708037334666.845, "dur": 18.919, + "args": { + "External id": 4674526,"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": 1708037334668.677, "dur": 1.574, + "args": { + "External id": 4674527,"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": 1708037334672.439, "dur": 0.802, + "args": { + "External id": 4674528,"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": 1708037334687.043, "dur": 12.116, + "args": { + "External id": 4674529,"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": 1708037334700.183, "dur": 11.403, + "args": { + "External id": 4674530,"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": 1708037334722.108, "dur": 2.284, + "args": { + "External id": 4674531,"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": 1708037334733.068, "dur": 3.866, + "args": { + "External id": 4674532,"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": 1708037334735.490, "dur": 0.558, + "args": { + "External id": 4674533,"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": 1708037334802.578, "dur": 50.625, + "args": { + "External id": 4674534,"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": 1708037334857.874, "dur": 4.515, + "args": { + "External id": 4674535,"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": 1708037334860.188, "dur": 1.115, + "args": { + "External id": 4674536,"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": 1708037334863.775, "dur": 28.162, + "args": { + "External id": 4674537,"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": 1708037334896.158, "dur": 6.706, + "args": { + "External id": 4674538,"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": 1708037334899.606, "dur": 2.618, + "args": { + "External id": 4674539,"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": 1708037334901.245, "dur": 0.821, + "args": { + "External id": 4674540,"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": 1708037334905.391, "dur": 39.083, + "args": { + "External id": 4674541,"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": 1708037334906.283, "dur": 37.524, + "args": { + "External id": 4674542,"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": 1708037334948.084, "dur": 13.245, + "args": { + "External id": 4674543,"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": 1708037334966.644, "dur": 4.487, + "args": { + "External id": 4674544,"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": 1708037334969.608, "dur": 0.797, + "args": { + "External id": 4674545,"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": 1708037334974.547, "dur": 89.734, + "args": { + "External id": 4674546,"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": 1708037334975.488, "dur": 38.707, + "args": { + "External id": 4674547,"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": 1708037334976.146, "dur": 3.630, + "args": { + "External id": 4674548,"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": 1708037334977.304, "dur": 2.277, + "args": { + "External id": 4674549,"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": 1708037335016.239, "dur": 47.504, + "args": { + "External id": 4674550,"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": 1708037335017.021, "dur": 46.117, + "args": { + "External id": 4674551,"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": 1708037335069.399, "dur": 4.175, + "args": { + "External id": 4674552,"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": 1708037335071.701, "dur": 0.753, + "args": { + "External id": 4674553,"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": 1708037335081.876, "dur": 1.558, + "args": { + "External id": 4674554,"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": 1708037335090.809, "dur": 6.452, + "args": { + "External id": 4674555,"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": 1708037335092.840, "dur": 4.191, + "args": { + "External id": 4674556,"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": 1708037335176.664, "dur": 251.294, + "args": { + "External id": 4674557,"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": 1708037335178.895, "dur": 2.061, + "args": { + "External id": 4674558,"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": 1708037335183.849, "dur": 243.510, + "args": { + "External id": 4674559,"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": 1708037335185.184, "dur": 0.494, + "args": { + "External id": 4674560,"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": 1708037335265.086, "dur": 23.277, + "args": { + "External id": 4674561,"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": 1708037335290.171, "dur": 3.010, + "args": { + "External id": 4674562,"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": 1708037335292.223, "dur": 0.700, + "args": { + "External id": 4674563,"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": 1708037335294.259, "dur": 22.109, + "args": { + "External id": 4674564,"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": 1708037335294.982, "dur": 2.936, + "args": { + "External id": 4674565,"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": 1708037335299.008, "dur": 16.869, + "args": { + "External id": 4674566,"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": 1708037335301.852, "dur": 2.273, + "args": { + "External id": 4674567,"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": 1708037335319.396, "dur": 19.499, + "args": { + "External id": 4674568,"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": 1708037335340.147, "dur": 13.220, + "args": { + "External id": 4674569,"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": 1708037335355.866, "dur": 12.768, + "args": { + "External id": 4674570,"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": 1708037335369.977, "dur": 11.549, + "args": { + "External id": 4674571,"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": 1708037335383.286, "dur": 18.014, + "args": { + "External id": 4674572,"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": 1708037335384.836, "dur": 1.190, + "args": { + "External id": 4674573,"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": 1708037335388.213, "dur": 0.727, + "args": { + "External id": 4674574,"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": 1708037335402.480, "dur": 11.207, + "args": { + "External id": 4674575,"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": 1708037335416.700, "dur": 9.797, + "args": { + "External id": 4674576,"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": 1708037335433.922, "dur": 1.895, + "args": { + "External id": 4674577,"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": 1708037335443.540, "dur": 3.208, + "args": { + "External id": 4674578,"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": 1708037335445.546, "dur": 0.377, + "args": { + "External id": 4674579,"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": 1708037335508.585, "dur": 69.007, + "args": { + "External id": 4674580,"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": 1708037335584.144, "dur": 5.789, + "args": { + "External id": 4674581,"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": 1708037335586.989, "dur": 1.447, + "args": { + "External id": 4674582,"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": 1708037335591.412, "dur": 23.798, + "args": { + "External id": 4674583,"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": 1708037335621.629, "dur": 7.303, + "args": { + "External id": 4674584,"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": 1708037335623.361, "dur": 4.850, + "args": { + "External id": 4674585,"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": 1708037335624.889, "dur": 3.072, + "args": { + "External id": 4674586,"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": 1708037335631.867, "dur": 41.148, + "args": { + "External id": 4674587,"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": 1708037335633.120, "dur": 39.247, + "args": { + "External id": 4674588,"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": 1708037335676.489, "dur": 14.067, + "args": { + "External id": 4674589,"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": 1708037335695.952, "dur": 5.377, + "args": { + "External id": 4674590,"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": 1708037335699.639, "dur": 0.900, + "args": { + "External id": 4674591,"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": 1708037335705.592, "dur": 48.251, + "args": { + "External id": 4674592,"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": 1708037335706.603, "dur": 3.909, + "args": { + "External id": 4674593,"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": 1708037335707.859, "dur": 2.142, + "args": { + "External id": 4674594,"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": 1708037335709.162, "dur": 0.694, + "args": { + "External id": 4674595,"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": 1708037335711.208, "dur": 42.194, + "args": { + "External id": 4674596,"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": 1708037335713.362, "dur": 39.221, + "args": { + "External id": 4674597,"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": 1708037335757.420, "dur": 3.538, + "args": { + "External id": 4674598,"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": 1708037335758.854, "dur": 1.179, + "args": { + "External id": 4674599,"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": 1708037335766.696, "dur": 1.657, + "args": { + "External id": 4674600,"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": 1708037335775.683, "dur": 8.542, + "args": { + "External id": 4674601,"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": 1708037335779.503, "dur": 4.482, + "args": { + "External id": 4674602,"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": 1708037335861.473, "dur": 216.863, + "args": { + "External id": 4674603,"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": 1708037335863.960, "dur": 2.124, + "args": { + "External id": 4674604,"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": 1708037335869.294, "dur": 208.568, + "args": { + "External id": 4674605,"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": 1708037335870.633, "dur": 0.551, + "args": { + "External id": 4674606,"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": 1708037335872.248, "dur": 19.488, + "args": { + "External id": 4674607,"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": 1708037335893.273, "dur": 4.813, + "args": { + "External id": 4674608,"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": 1708037335895.072, "dur": 2.640, + "args": { + "External id": 4674609,"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": 1708037335899.522, "dur": 25.562, + "args": { + "External id": 4674610,"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": 1708037335905.636, "dur": 2.004, + "args": { + "External id": 4674611,"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": 1708037335908.864, "dur": 15.949, + "args": { + "External id": 4674612,"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": 1708037335911.399, "dur": 2.213, + "args": { + "External id": 4674613,"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": 1708037335926.916, "dur": 19.061, + "args": { + "External id": 4674614,"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": 1708037335947.267, "dur": 14.054, + "args": { + "External id": 4674615,"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": 1708037335964.002, "dur": 13.031, + "args": { + "External id": 4674616,"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": 1708037335978.257, "dur": 46.158, + "args": { + "External id": 4674617,"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": 1708037336027.225, "dur": 23.357, + "args": { + "External id": 4674618,"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": 1708037336029.181, "dur": 2.016, + "args": { + "External id": 4674619,"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": 1708037336034.632, "dur": 1.484, + "args": { + "External id": 4674620,"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": 1708037336052.310, "dur": 11.185, + "args": { + "External id": 4674621,"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": 1708037336064.771, "dur": 12.050, + "args": { + "External id": 4674622,"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": 1708037336085.652, "dur": 2.942, + "args": { + "External id": 4674623,"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": 1708037336097.201, "dur": 3.803, + "args": { + "External id": 4674624,"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": 1708037336099.725, "dur": 0.533, + "args": { + "External id": 4674625,"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": 1708037336165.040, "dur": 52.293, + "args": { + "External id": 4674626,"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": 1708037336221.489, "dur": 5.786, + "args": { + "External id": 4674627,"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": 1708037336225.521, "dur": 0.791, + "args": { + "External id": 4674628,"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": 1708037336228.656, "dur": 23.577, + "args": { + "External id": 4674629,"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": 1708037336256.484, "dur": 5.882, + "args": { + "External id": 4674630,"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": 1708037336257.874, "dur": 3.796, + "args": { + "External id": 4674631,"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": 1708037336260.013, "dur": 1.442, + "args": { + "External id": 4674632,"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": 1708037336265.015, "dur": 42.049, + "args": { + "External id": 4674633,"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": 1708037336267.464, "dur": 38.874, + "args": { + "External id": 4674634,"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": 1708037336310.483, "dur": 13.378, + "args": { + "External id": 4674635,"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": 1708037336328.200, "dur": 25.304, + "args": { + "External id": 4674636,"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": 1708037336330.688, "dur": 22.437, + "args": { + "External id": 4674637,"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": 1708037336335.648, "dur": 2.197, + "args": { + "External id": 4674638,"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": 1708037336358.587, "dur": 27.105, + "args": { + "External id": 4674639,"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": 1708037336360.591, "dur": 24.852, + "args": { + "External id": 4674640,"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": 1708037336365.074, "dur": 4.153, + "args": { + "External id": 4674641,"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": 1708037336372.167, "dur": 12.892, + "args": { + "External id": 4674642,"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": 1708037336398.548, "dur": 5.084, + "args": { + "External id": 4674643,"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": 1708037336400.644, "dur": 2.587, + "args": { + "External id": 4674644,"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": 1708037336404.520, "dur": 1.656, + "args": { + "External id": 4674645,"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": 1708037336405.394, "dur": 0.612, + "args": { + "External id": 4674646,"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": 1708037336447.776, "dur": 20.092, + "args": { + "External id": 4674647,"Sequence number": 46526652, "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": 1708037336469.768, "dur": 12.888, + "args": { + "External id": 4674648,"Sequence number": 46526653, "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": 1708037336469.768, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336753, "tid": 1336753, + "ts": 1708037336488.497, "dur": 5.561, + "args": { + "External id": 4674649,"Sequence number": 46526654, "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": 1708037336491.774, "dur": 1.159, + "args": { + "External id": 4674650,"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": 1708037336500.688, "dur": 7.889, + "args": { + "External id": 4674651,"Sequence number": 46526654, "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": 1708037336506.734, "dur": 0.663, + "args": { + "External id": 4674652,"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": 1708037336509.799, "dur": 3.040, + "args": { + "External id": 4674653,"Sequence number": 46526654, "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": 1708037336511.098, "dur": 1.161, + "args": { + "External id": 4674654,"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": 1708037336518.409, "dur": 23.604, + "args": { + "External id": 4674655,"Sequence number": 46526654, "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": 1708037336518.409, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037336522.248, "dur": 1.078, + "args": { + "External id": 4674656,"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": 1708037336544.384, "dur": 5.354, + "args": { + "External id": 4674657,"Sequence number": 46526655, "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": 1708037336544.384, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037336547.945, "dur": 0.914, + "args": { + "External id": 4674658,"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": 1708037336551.070, "dur": 6.913, + "args": { + "External id": 4674659,"Sequence number": 46526656, "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": 1708037336551.070, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037336556.423, "dur": 0.673, + "args": { + "External id": 4674660,"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": 1708037336559.255, "dur": 5.708, + "args": { + "External id": 4674661,"Sequence number": 46526657, "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": 1708037336559.255, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336753, "tid": 1336753, + "ts": 1708037336562.015, "dur": 2.134, + "args": { + "External id": 4674662,"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": 1708037336569.983, "dur": 32.410, + "args": { + "External id": 4674663,"Sequence number": 46526658, "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": 1708037336571.989, "dur": 30.167, + "args": { + "External id": 4674664,"Sequence number": 46526658, "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": 1708037336574.531, "dur": 6.618, + "args": { + "External id": 4674665,"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": 1708037336577.010, "dur": 3.639, + "args": { + "External id": 4674666,"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": 1708037336582.375, "dur": 19.313, + "args": { + "External id": 4674667,"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": 1708037336628.080, "dur": 5.051, + "args": { + "External id": 4674668,"Sequence number": 46526658, "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": 1708037336628.080, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336753, "tid": 1336753, + "ts": 1708037336635.308, "dur": 1.386, + "args": { + "External id": 4674669,"Sequence number": 46526659, "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": 1708037336667.795, "dur": 44150.899, + "args": { + "External id": 4674670,"Sequence number": 46526659, "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": 1708037336667.795, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336753, "tid": 1336753, + "ts": 1708037336682.332, "dur": 25.070, + "args": { + "External id": 4674671,"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": 1708037336683.450, "dur": 23.755, + "args": { + "External id": 4674672,"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": 1708037336684.635, "dur": 6.521, + "args": { + "External id": 4674673,"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": 1708037336685.854, "dur": 4.831, + "args": { + "External id": 4674674,"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": 1708037336691.988, "dur": 14.834, + "args": { + "External id": 4674675,"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": 1708037336722.231, "dur": 25.701, + "args": { + "External id": 4674676,"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": 1708037336723.504, "dur": 8.037, + "args": { + "External id": 4674677,"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": 1708037336726.985, "dur": 3.916, + "args": { + "External id": 4674678,"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": 1708037336732.935, "dur": 14.790, + "args": { + "External id": 4674679,"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": 1708037336734.947, "dur": 12.372, + "args": { + "External id": 4674680,"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": 1708037336751.305, "dur": 17.754, + "args": { + "External id": 4674681,"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": 1708037336752.193, "dur": 4.310, + "args": { + "External id": 4674682,"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": 1708037336753.534, "dur": 2.712, + "args": { + "External id": 4674683,"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": 1708037336757.416, "dur": 11.466, + "args": { + "External id": 4674684,"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": 1708037336757.780, "dur": 10.812, + "args": { + "External id": 4674685,"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": 1708037336774.369, "dur": 17.942, + "args": { + "External id": 4674686,"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": 1708037336777.749, "dur": 3.119, + "args": { + "External id": 4674687,"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": 1708037336781.598, "dur": 10.438, + "args": { + "External id": 4674688,"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": 1708037336782.260, "dur": 9.421, + "args": { + "External id": 4674689,"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": 1708037336796.842, "dur": 21.354, + "args": { + "External id": 4674690,"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": 1708037336820.356, "dur": 45.963, + "args": { + "External id": 4674691,"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": 1708037336822.200, "dur": 43.705, + "args": { + "External id": 4674692,"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": 1708037336828.211, "dur": 0.643, + "args": { + "External id": 4674693,"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": 1708037336830.882, "dur": 20.221, + "args": { + "External id": 4674694,"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": 1708037336832.504, "dur": 18.407, + "args": { + "External id": 4674695,"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": 1708037336835.188, "dur": 2.412, + "args": { + "External id": 4674696,"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": 1708037336838.604, "dur": 11.930, + "args": { + "External id": 4674697,"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": 1708037336871.767, "dur": 38420.454, + "args": { + "External id": 4674698,"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": 1708037336873.228, "dur": 38417.745, + "args": { + "External id": 4674699,"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": 1708037375304.211, "dur": 6.615, + "args": { + "External id": 4674700,"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": 1708037375307.993, "dur": 1.000, + "args": { + "External id": 4674701,"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": 1708037375316.072, "dur": 103.742, + "args": { + "External id": 4674702,"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": 1708037375317.524, "dur": 7.533, + "args": { + "External id": 4674703,"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": 1708037375319.590, "dur": 4.469, + "args": { + "External id": 4674704,"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": 1708037375322.800, "dur": 0.961, + "args": { + "External id": 4674705,"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": 1708037375326.526, "dur": 92.527, + "args": { + "External id": 4674706,"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": 1708037375328.419, "dur": 89.756, + "args": { + "External id": 4674707,"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": 1708037375422.832, "dur": 4.120, + "args": { + "External id": 4674708,"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": 1708037375424.819, "dur": 1.074, + "args": { + "External id": 4674709,"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": 1708037375434.041, "dur": 2.506, + "args": { + "External id": 4674710,"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": 1708037375446.564, "dur": 7.026, + "args": { + "External id": 4674711,"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": 1708037375448.770, "dur": 4.518, + "args": { + "External id": 4674712,"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": 1708037375597.791, "dur": 193.637, + "args": { + "External id": 4674713,"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": 1708037375601.914, "dur": 3.010, + "args": { + "External id": 4674714,"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": 1708037375606.653, "dur": 184.338, + "args": { + "External id": 4674715,"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": 1708037375608.431, "dur": 0.388, + "args": { + "External id": 4674716,"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": 1708037375609.964, "dur": 24.854, + "args": { + "External id": 4674717,"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": 1708037375638.627, "dur": 4.895, + "args": { + "External id": 4674718,"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": 1708037375642.185, "dur": 0.983, + "args": { + "External id": 4674719,"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": 1708037375644.562, "dur": 23.922, + "args": { + "External id": 4674720,"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": 1708037375645.770, "dur": 1.578, + "args": { + "External id": 4674721,"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": 1708037375648.921, "dur": 19.292, + "args": { + "External id": 4674722,"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": 1708037375652.823, "dur": 3.514, + "args": { + "External id": 4674723,"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": 1708037375670.266, "dur": 23.238, + "args": { + "External id": 4674724,"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": 1708037375695.351, "dur": 13.280, + "args": { + "External id": 4674725,"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": 1708037375711.625, "dur": 15.292, + "args": { + "External id": 4674726,"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": 1708037375728.428, "dur": 12.278, + "args": { + "External id": 4674727,"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": 1708037375744.269, "dur": 20.306, + "args": { + "External id": 4674728,"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": 1708037375746.276, "dur": 1.676, + "args": { + "External id": 4674729,"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": 1708037375750.172, "dur": 1.096, + "args": { + "External id": 4674730,"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": 1708037375765.913, "dur": 11.356, + "args": { + "External id": 4674731,"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": 1708037375778.539, "dur": 11.302, + "args": { + "External id": 4674732,"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": 1708037375798.464, "dur": 2.203, + "args": { + "External id": 4674733,"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": 1708037375808.830, "dur": 4.210, + "args": { + "External id": 4674734,"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": 1708037375811.215, "dur": 0.895, + "args": { + "External id": 4674735,"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": 1708037375886.700, "dur": 65.671, + "args": { + "External id": 4674736,"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": 1708037375957.685, "dur": 5.917, + "args": { + "External id": 4674737,"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": 1708037375960.088, "dur": 1.208, + "args": { + "External id": 4674738,"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": 1708037375965.105, "dur": 76.411, + "args": { + "External id": 4674739,"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": 1708037376049.232, "dur": 9.213, + "args": { + "External id": 4674740,"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": 1708037376051.061, "dur": 6.392, + "args": { + "External id": 4674741,"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": 1708037376055.123, "dur": 2.067, + "args": { + "External id": 4674742,"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": 1708037376061.825, "dur": 50.438, + "args": { + "External id": 4674743,"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": 1708037376063.403, "dur": 48.251, + "args": { + "External id": 4674744,"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": 1708037376116.646, "dur": 16.224, + "args": { + "External id": 4674745,"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": 1708037376139.430, "dur": 3.562, + "args": { + "External id": 4674746,"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": 1708037376141.385, "dur": 0.694, + "args": { + "External id": 4674747,"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": 1708037376149.234, "dur": 49.604, + "args": { + "External id": 4674748,"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": 1708037376150.357, "dur": 3.844, + "args": { + "External id": 4674749,"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": 1708037376151.160, "dur": 2.462, + "args": { + "External id": 4674750,"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": 1708037376152.534, "dur": 0.938, + "args": { + "External id": 4674751,"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": 1708037376155.094, "dur": 43.414, + "args": { + "External id": 4674752,"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": 1708037376155.874, "dur": 42.050, + "args": { + "External id": 4674753,"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": 1708037376204.072, "dur": 5.219, + "args": { + "External id": 4674754,"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": 1708037376206.065, "dur": 2.116, + "args": { + "External id": 4674755,"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": 1708037376215.637, "dur": 1.663, + "args": { + "External id": 4674756,"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": 1708037376225.811, "dur": 6.111, + "args": { + "External id": 4674757,"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": 1708037376227.937, "dur": 3.700, + "args": { + "External id": 4674758,"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": 1708037376330.043, "dur": 176.400, + "args": { + "External id": 4674759,"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": 1708037376332.275, "dur": 1.917, + "args": { + "External id": 4674760,"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": 1708037376335.664, "dur": 170.410, + "args": { + "External id": 4674761,"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": 1708037376336.983, "dur": 0.327, + "args": { + "External id": 4674762,"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": 1708037376338.513, "dur": 22.184, + "args": { + "External id": 4674763,"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": 1708037376362.290, "dur": 3.856, + "args": { + "External id": 4674764,"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": 1708037376364.815, "dur": 1.113, + "args": { + "External id": 4674765,"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": 1708037376367.224, "dur": 23.780, + "args": { + "External id": 4674766,"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": 1708037376368.155, "dur": 1.355, + "args": { + "External id": 4674767,"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": 1708037376370.779, "dur": 19.846, + "args": { + "External id": 4674768,"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": 1708037376377.110, "dur": 2.848, + "args": { + "External id": 4674769,"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": 1708037376392.640, "dur": 19.507, + "args": { + "External id": 4674770,"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": 1708037376413.648, "dur": 13.548, + "args": { + "External id": 4674771,"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": 1708037376430.306, "dur": 12.613, + "args": { + "External id": 4674772,"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": 1708037376444.818, "dur": 12.034, + "args": { + "External id": 4674773,"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": 1708037376458.754, "dur": 19.048, + "args": { + "External id": 4674774,"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": 1708037376460.748, "dur": 1.242, + "args": { + "External id": 4674775,"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": 1708037376464.309, "dur": 1.051, + "args": { + "External id": 4674776,"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": 1708037376481.060, "dur": 12.103, + "args": { + "External id": 4674777,"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": 1708037376494.412, "dur": 10.852, + "args": { + "External id": 4674778,"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": 1708037376512.845, "dur": 1.648, + "args": { + "External id": 4674779,"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": 1708037376521.984, "dur": 19.952, + "args": { + "External id": 4674780,"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": 1708037376539.648, "dur": 0.917, + "args": { + "External id": 4674781,"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": 1708037376614.566, "dur": 53.704, + "args": { + "External id": 4674782,"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": 1708037376672.919, "dur": 4.444, + "args": { + "External id": 4674783,"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": 1708037376675.239, "dur": 1.164, + "args": { + "External id": 4674784,"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": 1708037376680.303, "dur": 24.801, + "args": { + "External id": 4674785,"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": 1708037376709.998, "dur": 5.011, + "args": { + "External id": 4674786,"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": 1708037376711.270, "dur": 3.110, + "args": { + "External id": 4674787,"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": 1708037376713.065, "dur": 1.086, + "args": { + "External id": 4674788,"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": 1708037376717.821, "dur": 40.204, + "args": { + "External id": 4674789,"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": 1708037376719.077, "dur": 38.426, + "args": { + "External id": 4674790,"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": 1708037376761.821, "dur": 14.504, + "args": { + "External id": 4674791,"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": 1708037376783.616, "dur": 3.795, + "args": { + "External id": 4674792,"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": 1708037376785.549, "dur": 1.012, + "args": { + "External id": 4674793,"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": 1708037376790.819, "dur": 49.823, + "args": { + "External id": 4674794,"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": 1708037376791.758, "dur": 5.511, + "args": { + "External id": 4674795,"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": 1708037376792.492, "dur": 4.155, + "args": { + "External id": 4674796,"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": 1708037376795.793, "dur": 0.699, + "args": { + "External id": 4674797,"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": 1708037376799.337, "dur": 40.827, + "args": { + "External id": 4674798,"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": 1708037376799.960, "dur": 39.613, + "args": { + "External id": 4674799,"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": 1708037376844.537, "dur": 3.534, + "args": { + "External id": 4674800,"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": 1708037376846.186, "dur": 0.932, + "args": { + "External id": 4674801,"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": 1708037376853.524, "dur": 1.540, + "args": { + "External id": 4674802,"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": 1708037376862.293, "dur": 6.073, + "args": { + "External id": 4674803,"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": 1708037376864.367, "dur": 3.735, + "args": { + "External id": 4674804,"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": 1708037376947.361, "dur": 215.436, + "args": { + "External id": 4674805,"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": 1708037376949.937, "dur": 1.823, + "args": { + "External id": 4674806,"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": 1708037376953.181, "dur": 209.061, + "args": { + "External id": 4674807,"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": 1708037376956.052, "dur": 0.199, + "args": { + "External id": 4674808,"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": 1708037376957.430, "dur": 18.766, + "args": { + "External id": 4674809,"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": 1708037376977.596, "dur": 37.920, + "args": { + "External id": 4674810,"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": 1708037376980.015, "dur": 0.965, + "args": { + "External id": 4674811,"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": 1708037377017.426, "dur": 27.662, + "args": { + "External id": 4674812,"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": 1708037377020.696, "dur": 2.283, + "args": { + "External id": 4674813,"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": 1708037377024.411, "dur": 20.398, + "args": { + "External id": 4674814,"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": 1708037377029.061, "dur": 2.784, + "args": { + "External id": 4674815,"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": 1708037377046.620, "dur": 23.286, + "args": { + "External id": 4674816,"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": 1708037377071.397, "dur": 12.413, + "args": { + "External id": 4674817,"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": 1708037377086.692, "dur": 13.465, + "args": { + "External id": 4674818,"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": 1708037377101.477, "dur": 11.451, + "args": { + "External id": 4674819,"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": 1708037377114.758, "dur": 19.923, + "args": { + "External id": 4674820,"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": 1708037377116.887, "dur": 1.399, + "args": { + "External id": 4674821,"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": 1708037377120.800, "dur": 0.616, + "args": { + "External id": 4674822,"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": 1708037377137.512, "dur": 11.483, + "args": { + "External id": 4674823,"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": 1708037377150.543, "dur": 10.571, + "args": { + "External id": 4674824,"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": 1708037377170.352, "dur": 2.153, + "args": { + "External id": 4674825,"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": 1708037377181.647, "dur": 3.490, + "args": { + "External id": 4674826,"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": 1708037377183.764, "dur": 0.621, + "args": { + "External id": 4674827,"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": 1708037377250.842, "dur": 53.226, + "args": { + "External id": 4674828,"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": 1708037377308.813, "dur": 5.689, + "args": { + "External id": 4674829,"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": 1708037377312.650, "dur": 0.852, + "args": { + "External id": 4674830,"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": 1708037377315.804, "dur": 25.092, + "args": { + "External id": 4674831,"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": 1708037377345.223, "dur": 7.408, + "args": { + "External id": 4674832,"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": 1708037377346.750, "dur": 5.254, + "args": { + "External id": 4674833,"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": 1708037377348.509, "dur": 3.238, + "args": { + "External id": 4674834,"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": 1708037377355.427, "dur": 65.593, + "args": { + "External id": 4674835,"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": 1708037377356.778, "dur": 63.134, + "args": { + "External id": 4674836,"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": 1708037377426.503, "dur": 34.650, + "args": { + "External id": 4674837,"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": 1708037377466.546, "dur": 3.576, + "args": { + "External id": 4674838,"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": 1708037377468.607, "dur": 0.740, + "args": { + "External id": 4674839,"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": 1708037377473.437, "dur": 72.758, + "args": { + "External id": 4674840,"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": 1708037377474.384, "dur": 5.535, + "args": { + "External id": 4674841,"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": 1708037377475.465, "dur": 3.823, + "args": { + "External id": 4674842,"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": 1708037377478.297, "dur": 0.738, + "args": { + "External id": 4674843,"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": 1708037377480.651, "dur": 65.089, + "args": { + "External id": 4674844,"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": 1708037377481.090, "dur": 63.641, + "args": { + "External id": 4674845,"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": 1708037377552.027, "dur": 16.146, + "args": { + "External id": 4674846,"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": 1708037377565.926, "dur": 0.994, + "args": { + "External id": 4674847,"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": 1708037377574.739, "dur": 1.546, + "args": { + "External id": 4674848,"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": 1708037377585.894, "dur": 7.573, + "args": { + "External id": 4674849,"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": 1708037377587.905, "dur": 5.299, + "args": { + "External id": 4674850,"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": 1708037377679.293, "dur": 173.904, + "args": { + "External id": 4674851,"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": 1708037377681.499, "dur": 2.168, + "args": { + "External id": 4674852,"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": 1708037377684.953, "dur": 167.765, + "args": { + "External id": 4674853,"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": 1708037377686.261, "dur": 0.429, + "args": { + "External id": 4674854,"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": 1708037377687.666, "dur": 23.172, + "args": { + "External id": 4674855,"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": 1708037377714.374, "dur": 3.209, + "args": { + "External id": 4674856,"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": 1708037377716.405, "dur": 0.790, + "args": { + "External id": 4674857,"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": 1708037377718.432, "dur": 21.732, + "args": { + "External id": 4674858,"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": 1708037377719.667, "dur": 1.824, + "args": { + "External id": 4674859,"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": 1708037377722.586, "dur": 17.283, + "args": { + "External id": 4674860,"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": 1708037377727.115, "dur": 2.103, + "args": { + "External id": 4674861,"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": 1708037377741.785, "dur": 19.030, + "args": { + "External id": 4674862,"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": 1708037377762.244, "dur": 13.357, + "args": { + "External id": 4674863,"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": 1708037377778.148, "dur": 13.203, + "args": { + "External id": 4674864,"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": 1708037377792.969, "dur": 11.882, + "args": { + "External id": 4674865,"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": 1708037377808.193, "dur": 18.976, + "args": { + "External id": 4674866,"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": 1708037377809.626, "dur": 1.398, + "args": { + "External id": 4674867,"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": 1708037377813.298, "dur": 1.168, + "args": { + "External id": 4674868,"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": 1708037377828.235, "dur": 11.132, + "args": { + "External id": 4674869,"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": 1708037377840.783, "dur": 11.005, + "args": { + "External id": 4674870,"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": 1708037377859.270, "dur": 1.671, + "args": { + "External id": 4674871,"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": 1708037377868.516, "dur": 3.229, + "args": { + "External id": 4674872,"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": 1708037377870.490, "dur": 0.540, + "args": { + "External id": 4674873,"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": 1708037377937.554, "dur": 89.968, + "args": { + "External id": 4674874,"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": 1708037378034.626, "dur": 6.043, + "args": { + "External id": 4674875,"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": 1708037378037.675, "dur": 1.397, + "args": { + "External id": 4674876,"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": 1708037378042.001, "dur": 25.456, + "args": { + "External id": 4674877,"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": 1708037378072.758, "dur": 7.215, + "args": { + "External id": 4674878,"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": 1708037378074.347, "dur": 4.903, + "args": { + "External id": 4674879,"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": 1708037378077.673, "dur": 1.283, + "args": { + "External id": 4674880,"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": 1708037378083.233, "dur": 44.689, + "args": { + "External id": 4674881,"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": 1708037378084.780, "dur": 42.515, + "args": { + "External id": 4674882,"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": 1708037378132.093, "dur": 14.451, + "args": { + "External id": 4674883,"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": 1708037378152.064, "dur": 3.545, + "args": { + "External id": 4674884,"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": 1708037378154.068, "dur": 0.781, + "args": { + "External id": 4674885,"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": 1708037378159.329, "dur": 51.049, + "args": { + "External id": 4674886,"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": 1708037378161.801, "dur": 5.665, + "args": { + "External id": 4674887,"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": 1708037378162.547, "dur": 4.284, + "args": { + "External id": 4674888,"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": 1708037378164.195, "dur": 2.472, + "args": { + "External id": 4674889,"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": 1708037378168.006, "dur": 41.950, + "args": { + "External id": 4674890,"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": 1708037378168.595, "dur": 40.885, + "args": { + "External id": 4674891,"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": 1708037378214.081, "dur": 3.335, + "args": { + "External id": 4674892,"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": 1708037378215.882, "dur": 0.559, + "args": { + "External id": 4674893,"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": 1708037378223.884, "dur": 1.508, + "args": { + "External id": 4674894,"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": 1708037378234.718, "dur": 6.431, + "args": { + "External id": 4674895,"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": 1708037378236.787, "dur": 4.105, + "args": { + "External id": 4674896,"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": 1708037378326.872, "dur": 192.361, + "args": { + "External id": 4674897,"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": 1708037378329.504, "dur": 2.367, + "args": { + "External id": 4674898,"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": 1708037378333.230, "dur": 185.504, + "args": { + "External id": 4674899,"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": 1708037378334.615, "dur": 0.439, + "args": { + "External id": 4674900,"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": 1708037378339.508, "dur": 19.229, + "args": { + "External id": 4674901,"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": 1708037378380.426, "dur": 5.139, + "args": { + "External id": 4674902,"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": 1708037378384.185, "dur": 1.051, + "args": { + "External id": 4674903,"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": 1708037378386.783, "dur": 21.846, + "args": { + "External id": 4674904,"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": 1708037378387.795, "dur": 2.904, + "args": { + "External id": 4674905,"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": 1708037378391.985, "dur": 16.296, + "args": { + "External id": 4674906,"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": 1708037378394.598, "dur": 2.277, + "args": { + "External id": 4674907,"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": 1708037378410.331, "dur": 20.242, + "args": { + "External id": 4674908,"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": 1708037378432.125, "dur": 12.096, + "args": { + "External id": 4674909,"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": 1708037378448.442, "dur": 12.580, + "args": { + "External id": 4674910,"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": 1708037378462.511, "dur": 11.089, + "args": { + "External id": 4674911,"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": 1708037378475.330, "dur": 18.650, + "args": { + "External id": 4674912,"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": 1708037378476.976, "dur": 1.247, + "args": { + "External id": 4674913,"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": 1708037378480.077, "dur": 0.919, + "args": { + "External id": 4674914,"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": 1708037378495.353, "dur": 10.769, + "args": { + "External id": 4674915,"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": 1708037378507.288, "dur": 10.604, + "args": { + "External id": 4674916,"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": 1708037378545.306, "dur": 2.539, + "args": { + "External id": 4674917,"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": 1708037378557.501, "dur": 3.392, + "args": { + "External id": 4674918,"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": 1708037378559.734, "dur": 0.441, + "args": { + "External id": 4674919,"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": 1708037378629.323, "dur": 53.417, + "args": { + "External id": 4674920,"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": 1708037378687.142, "dur": 4.241, + "args": { + "External id": 4674921,"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": 1708037378689.734, "dur": 0.685, + "args": { + "External id": 4674922,"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": 1708037378692.775, "dur": 23.347, + "args": { + "External id": 4674923,"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": 1708037378720.444, "dur": 7.161, + "args": { + "External id": 4674924,"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": 1708037378723.870, "dur": 2.945, + "args": { + "External id": 4674925,"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": 1708037378725.551, "dur": 1.063, + "args": { + "External id": 4674926,"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": 1708037378730.442, "dur": 38.592, + "args": { + "External id": 4674927,"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": 1708037378731.798, "dur": 36.628, + "args": { + "External id": 4674928,"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": 1708037378772.524, "dur": 14.424, + "args": { + "External id": 4674929,"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": 1708037378792.196, "dur": 5.345, + "args": { + "External id": 4674930,"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": 1708037378795.800, "dur": 1.025, + "args": { + "External id": 4674931,"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": 1708037378801.195, "dur": 47.380, + "args": { + "External id": 4674932,"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": 1708037378802.172, "dur": 5.358, + "args": { + "External id": 4674933,"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": 1708037378803.118, "dur": 3.883, + "args": { + "External id": 4674934,"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": 1708037378806.324, "dur": 0.548, + "args": { + "External id": 4674935,"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": 1708037378808.288, "dur": 39.892, + "args": { + "External id": 4674936,"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": 1708037378809.148, "dur": 38.545, + "args": { + "External id": 4674937,"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": 1708037378853.875, "dur": 3.744, + "args": { + "External id": 4674938,"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": 1708037378855.930, "dur": 0.700, + "args": { + "External id": 4674939,"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": 1708037378862.558, "dur": 1.335, + "args": { + "External id": 4674940,"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": 1708037378871.146, "dur": 5.969, + "args": { + "External id": 4674941,"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": 1708037378873.189, "dur": 3.662, + "args": { + "External id": 4674942,"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": 1708037378954.285, "dur": 220.696, + "args": { + "External id": 4674943,"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": 1708037378956.602, "dur": 2.381, + "args": { + "External id": 4674944,"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": 1708037378960.803, "dur": 213.672, + "args": { + "External id": 4674945,"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": 1708037378963.736, "dur": 0.327, + "args": { + "External id": 4674946,"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": 1708037378965.217, "dur": 54.719, + "args": { + "External id": 4674947,"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": 1708037379022.796, "dur": 3.185, + "args": { + "External id": 4674948,"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": 1708037379024.799, "dur": 0.826, + "args": { + "External id": 4674949,"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": 1708037379027.000, "dur": 25.065, + "args": { + "External id": 4674950,"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": 1708037379029.786, "dur": 1.694, + "args": { + "External id": 4674951,"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": 1708037379032.746, "dur": 18.920, + "args": { + "External id": 4674952,"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": 1708037379037.458, "dur": 2.724, + "args": { + "External id": 4674953,"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": 1708037379053.429, "dur": 19.684, + "args": { + "External id": 4674954,"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": 1708037379074.771, "dur": 13.225, + "args": { + "External id": 4674955,"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": 1708037379090.780, "dur": 20.426, + "args": { + "External id": 4674956,"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": 1708037379112.529, "dur": 13.626, + "args": { + "External id": 4674957,"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": 1708037379127.753, "dur": 19.692, + "args": { + "External id": 4674958,"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": 1708037379129.368, "dur": 1.451, + "args": { + "External id": 4674959,"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": 1708037379132.644, "dur": 0.811, + "args": { + "External id": 4674960,"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": 1708037379150.520, "dur": 10.499, + "args": { + "External id": 4674961,"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": 1708037379162.153, "dur": 11.325, + "args": { + "External id": 4674962,"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": 1708037379182.119, "dur": 2.130, + "args": { + "External id": 4674963,"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": 1708037379192.626, "dur": 3.557, + "args": { + "External id": 4674964,"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": 1708037379195.064, "dur": 0.375, + "args": { + "External id": 4674965,"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": 1708037379259.986, "dur": 51.759, + "args": { + "External id": 4674966,"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": 1708037379316.481, "dur": 8.203, + "args": { + "External id": 4674967,"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": 1708037379320.913, "dur": 2.732, + "args": { + "External id": 4674968,"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": 1708037379326.159, "dur": 22.544, + "args": { + "External id": 4674969,"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": 1708037379352.846, "dur": 4.818, + "args": { + "External id": 4674970,"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": 1708037379354.173, "dur": 2.801, + "args": { + "External id": 4674971,"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": 1708037379355.733, "dur": 1.043, + "args": { + "External id": 4674972,"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": 1708037379360.549, "dur": 38.478, + "args": { + "External id": 4674973,"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": 1708037379361.901, "dur": 36.581, + "args": { + "External id": 4674974,"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": 1708037379404.249, "dur": 13.944, + "args": { + "External id": 4674975,"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": 1708037379423.295, "dur": 3.777, + "args": { + "External id": 4674976,"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": 1708037379425.353, "dur": 0.931, + "args": { + "External id": 4674977,"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": 1708037379430.555, "dur": 47.300, + "args": { + "External id": 4674978,"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": 1708037379431.394, "dur": 4.965, + "args": { + "External id": 4674979,"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": 1708037379432.283, "dur": 3.603, + "args": { + "External id": 4674980,"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": 1708037379435.043, "dur": 0.692, + "args": { + "External id": 4674981,"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": 1708037379437.172, "dur": 40.323, + "args": { + "External id": 4674982,"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": 1708037379437.794, "dur": 39.069, + "args": { + "External id": 4674983,"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": 1708037379481.195, "dur": 3.916, + "args": { + "External id": 4674984,"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": 1708037379483.196, "dur": 0.946, + "args": { + "External id": 4674985,"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": 1708037379489.832, "dur": 1.442, + "args": { + "External id": 4674986,"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": 1708037379498.418, "dur": 7.083, + "args": { + "External id": 4674987,"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": 1708037379501.909, "dur": 3.347, + "args": { + "External id": 4674988,"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": 1708037379603.918, "dur": 170.492, + "args": { + "External id": 4674989,"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": 1708037379606.001, "dur": 4.504, + "args": { + "External id": 4674990,"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": 1708037379612.200, "dur": 161.740, + "args": { + "External id": 4674991,"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": 1708037379613.265, "dur": 0.516, + "args": { + "External id": 4674992,"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": 1708037379615.192, "dur": 19.949, + "args": { + "External id": 4674993,"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": 1708037379636.588, "dur": 5.071, + "args": { + "External id": 4674994,"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": 1708037379640.447, "dur": 0.889, + "args": { + "External id": 4674995,"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": 1708037379642.866, "dur": 21.306, + "args": { + "External id": 4674996,"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": 1708037379645.885, "dur": 1.453, + "args": { + "External id": 4674997,"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": 1708037379648.461, "dur": 15.486, + "args": { + "External id": 4674998,"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": 1708037379651.012, "dur": 2.167, + "args": { + "External id": 4674999,"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": 1708037379665.267, "dur": 18.694, + "args": { + "External id": 4675000,"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": 1708037379685.313, "dur": 12.310, + "args": { + "External id": 4675001,"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": 1708037379699.905, "dur": 13.053, + "args": { + "External id": 4675002,"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": 1708037379714.288, "dur": 10.962, + "args": { + "External id": 4675003,"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": 1708037379727.222, "dur": 21.089, + "args": { + "External id": 4675004,"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": 1708037379730.907, "dur": 1.140, + "args": { + "External id": 4675005,"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": 1708037379735.483, "dur": 0.909, + "args": { + "External id": 4675006,"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": 1708037379749.487, "dur": 11.115, + "args": { + "External id": 4675007,"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": 1708037379761.796, "dur": 11.281, + "args": { + "External id": 4675008,"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": 1708037379780.501, "dur": 1.768, + "args": { + "External id": 4675009,"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": 1708037379790.231, "dur": 3.253, + "args": { + "External id": 4675010,"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": 1708037379792.145, "dur": 0.568, + "args": { + "External id": 4675011,"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": 1708037379849.292, "dur": 47.754, + "args": { + "External id": 4675012,"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": 1708037379901.596, "dur": 5.432, + "args": { + "External id": 4675013,"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": 1708037379905.063, "dur": 0.954, + "args": { + "External id": 4675014,"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": 1708037379908.453, "dur": 21.679, + "args": { + "External id": 4675015,"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": 1708037379934.198, "dur": 4.745, + "args": { + "External id": 4675016,"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": 1708037379935.344, "dur": 2.837, + "args": { + "External id": 4675017,"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": 1708037379936.885, "dur": 1.133, + "args": { + "External id": 4675018,"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": 1708037379941.417, "dur": 39.508, + "args": { + "External id": 4675019,"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": 1708037379944.036, "dur": 36.133, + "args": { + "External id": 4675020,"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": 1708037379984.303, "dur": 50.573, + "args": { + "External id": 4675021,"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": 1708037380042.767, "dur": 4.146, + "args": { + "External id": 4675022,"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": 1708037380045.058, "dur": 0.820, + "args": { + "External id": 4675023,"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": 1708037380050.775, "dur": 51.224, + "args": { + "External id": 4675024,"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": 1708037380051.613, "dur": 5.959, + "args": { + "External id": 4675025,"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": 1708037380052.789, "dur": 4.250, + "args": { + "External id": 4675026,"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": 1708037380056.084, "dur": 0.834, + "args": { + "External id": 4675027,"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": 1708037380058.253, "dur": 43.366, + "args": { + "External id": 4675028,"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": 1708037380058.998, "dur": 41.987, + "args": { + "External id": 4675029,"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": 1708037380105.423, "dur": 3.850, + "args": { + "External id": 4675030,"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": 1708037380107.429, "dur": 0.840, + "args": { + "External id": 4675031,"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": 1708037380114.860, "dur": 1.384, + "args": { + "External id": 4675032,"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": 1708037380124.819, "dur": 5.548, + "args": { + "External id": 4675033,"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": 1708037380126.276, "dur": 3.840, + "args": { + "External id": 4675034,"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": 1708037380206.971, "dur": 166.264, + "args": { + "External id": 4675035,"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": 1708037380210.536, "dur": 2.149, + "args": { + "External id": 4675036,"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": 1708037380213.805, "dur": 159.039, + "args": { + "External id": 4675037,"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": 1708037380215.046, "dur": 0.415, + "args": { + "External id": 4675038,"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": 1708037380218.691, "dur": 19.133, + "args": { + "External id": 4675039,"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": 1708037380239.252, "dur": 4.848, + "args": { + "External id": 4675040,"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": 1708037380242.829, "dur": 1.014, + "args": { + "External id": 4675041,"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": 1708037380244.917, "dur": 19.799, + "args": { + "External id": 4675042,"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": 1708037380246.407, "dur": 1.618, + "args": { + "External id": 4675043,"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": 1708037380249.238, "dur": 15.174, + "args": { + "External id": 4675044,"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": 1708037380251.555, "dur": 2.324, + "args": { + "External id": 4675045,"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": 1708037380266.219, "dur": 19.519, + "args": { + "External id": 4675046,"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": 1708037380287.243, "dur": 12.074, + "args": { + "External id": 4675047,"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": 1708037380301.579, "dur": 12.405, + "args": { + "External id": 4675048,"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": 1708037380317.478, "dur": 10.984, + "args": { + "External id": 4675049,"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": 1708037380329.871, "dur": 17.827, + "args": { + "External id": 4675050,"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": 1708037380331.267, "dur": 1.257, + "args": { + "External id": 4675051,"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": 1708037380334.161, "dur": 0.808, + "args": { + "External id": 4675052,"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": 1708037380348.727, "dur": 10.940, + "args": { + "External id": 4675053,"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": 1708037380360.410, "dur": 11.565, + "args": { + "External id": 4675054,"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": 1708037380378.781, "dur": 1.512, + "args": { + "External id": 4675055,"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": 1708037380389.093, "dur": 2.869, + "args": { + "External id": 4675056,"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": 1708037380390.954, "dur": 0.322, + "args": { + "External id": 4675057,"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": 1708037380447.412, "dur": 44.697, + "args": { + "External id": 4675058,"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": 1708037380496.361, "dur": 4.174, + "args": { + "External id": 4675059,"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": 1708037380498.502, "dur": 0.982, + "args": { + "External id": 4675060,"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": 1708037380501.615, "dur": 21.146, + "args": { + "External id": 4675061,"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": 1708037380544.659, "dur": 7.667, + "args": { + "External id": 4675062,"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": 1708037380546.141, "dur": 5.276, + "args": { + "External id": 4675063,"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": 1708037380549.701, "dur": 1.415, + "args": { + "External id": 4675064,"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": 1708037380555.160, "dur": 43.791, + "args": { + "External id": 4675065,"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": 1708037380556.508, "dur": 41.608, + "args": { + "External id": 4675066,"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": 1708037380602.317, "dur": 15.212, + "args": { + "External id": 4675067,"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": 1708037380621.984, "dur": 24.055, + "args": { + "External id": 4675068,"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": 1708037380624.389, "dur": 21.273, + "args": { + "External id": 4675069,"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": 1708037380631.059, "dur": 0.532, + "args": { + "External id": 4675070,"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": 1708037380651.040, "dur": 123.555, + "args": { + "External id": 4675071,"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": 1708037380653.307, "dur": 120.964, + "args": { + "External id": 4675072,"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": 1708037380750.026, "dur": 4.788, + "args": { + "External id": 4675073,"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": 1708037380756.163, "dur": 17.451, + "args": { + "External id": 4675074,"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": 1708037380788.389, "dur": 4.704, + "args": { + "External id": 4675075,"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": 1708037380790.039, "dur": 2.773, + "args": { + "External id": 4675076,"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": 1708037380794.063, "dur": 0.866, + "args": { + "External id": 4675077,"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": 1708037380794.410, "dur": 0.446, + "args": { + "External id": 4675078,"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": 1708037380835.803, "dur": 22.379, + "args": { + "External id": 4675079,"Sequence number": 46526660, "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": 1708037380860.181, "dur": 13.401, + "args": { + "External id": 4675080,"Sequence number": 46526661, "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": 1708037380860.181, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 1336753, "tid": 1336753, + "ts": 1708037380980.514, "dur": 78.983, + "args": { + "External id": 4675081,"Record function id": 0, "Ev Idx": 10400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336753, "tid": 1336753, + "ts": 1708037381186.675, "dur": 40.598, + "args": { + "External id": 4675082,"Sequence number": 46526662, "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": 1708037381186.675, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 1336753, "tid": 1336753, + "ts": 1708037381261.355, "dur": 26.642, + "args": { + "External id": 4675083,"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": 1708037381263.214, "dur": 8.283, + "args": { + "External id": 4675084,"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": 1708037381266.806, "dur": 4.101, + "args": { + "External id": 4675085,"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": 1708037381273.375, "dur": 14.292, + "args": { + "External id": 4675086,"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": 1708038702942.943, "dur": 101.776, + "args": { + "External id": 4675087,"Sequence number": 46526663, "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": 1708038703057.903, "dur": 25.032, + "args": { + "External id": 4675088,"Sequence number": 46526664, "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": 1708038703092.597, "dur": 23.187, + "args": { + "External id": 4675089,"Sequence number": 46526665, "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": 1708038703676.424, "dur": 28.577, + "args": { + "External id": 4675090,"Sequence number": 46526666, "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": 1708038704306.347, "dur": 34.454, + "args": { + "External id": 4675091,"Sequence number": 46526667, "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": 1708038706012.298, "dur": 3021.369, + "args": { + "External id": 4675092,"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": 1708038706645.913, "dur": 974.619, + "args": { + "External id": 4675093,"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": 1708038706665.985, "dur": 61.915, + "args": { + "External id": 4675094,"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": 1708038706669.503, "dur": 12.898, + "args": { + "External id": 4675095,"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": 1708038706684.962, "dur": 42.674, + "args": { + "External id": 4675096,"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": 1708038706687.130, "dur": 40.005, + "args": { + "External id": 4675097,"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": 1708038709083.476, "dur": 3.991, + "args": { + "External id": 4675098,"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": 1708038709089.960, "dur": 0.349, + "args": { + "External id": 4675099,"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": 1708038709091.647, "dur": 0.366, + "args": { + "External id": 4675100,"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": 1708038709093.151, "dur": 0.249, + "args": { + "External id": 4675101,"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": 1708038709094.324, "dur": 0.286, + "args": { + "External id": 4675102,"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": 1708038709095.925, "dur": 0.585, + "args": { + "External id": 4675103,"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": 1708038709097.660, "dur": 0.255, + "args": { + "External id": 4675104,"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": 1708038709100.504, "dur": 0.417, + "args": { + "External id": 4675105,"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": 1708038709101.923, "dur": 0.439, + "args": { + "External id": 4675106,"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": 1708038709103.266, "dur": 0.341, + "args": { + "External id": 4675107,"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": 1708038709104.726, "dur": 0.236, + "args": { + "External id": 4675108,"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": 1708038709105.857, "dur": 0.382, + "args": { + "External id": 4675109,"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": 1708038709106.971, "dur": 0.382, + "args": { + "External id": 4675110,"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": 1708038709108.384, "dur": 0.415, + "args": { + "External id": 4675111,"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": 1708038709109.650, "dur": 0.329, + "args": { + "External id": 4675112,"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": 1708038709112.284, "dur": 0.228, + "args": { + "External id": 4675113,"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": 1708038709113.466, "dur": 0.225, + "args": { + "External id": 4675114,"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": 1708038709114.631, "dur": 0.228, + "args": { + "External id": 4675115,"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": 1708038709115.646, "dur": 0.219, + "args": { + "External id": 4675116,"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": 1708038709116.645, "dur": 0.216, + "args": { + "External id": 4675117,"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": 1708038709117.702, "dur": 0.240, + "args": { + "External id": 4675118,"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": 1708038709118.726, "dur": 0.226, + "args": { + "External id": 4675119,"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": 1708038709119.702, "dur": 0.218, + "args": { + "External id": 4675120,"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": 1708038709122.197, "dur": 0.207, + "args": { + "External id": 4675121,"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": 1708038709123.191, "dur": 0.211, + "args": { + "External id": 4675122,"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": 1708038709124.500, "dur": 0.212, + "args": { + "External id": 4675123,"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": 1708038709125.542, "dur": 0.419, + "args": { + "External id": 4675124,"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": 1708038709127.039, "dur": 0.265, + "args": { + "External id": 4675125,"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": 1708038709128.408, "dur": 0.220, + "args": { + "External id": 4675126,"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": 1708038709129.474, "dur": 0.218, + "args": { + "External id": 4675127,"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": 1708038709130.571, "dur": 0.434, + "args": { + "External id": 4675128,"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": 1708038709133.388, "dur": 0.282, + "args": { + "External id": 4675129,"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": 1708038709134.574, "dur": 0.381, + "args": { + "External id": 4675130,"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": 1708038709135.894, "dur": 0.217, + "args": { + "External id": 4675131,"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": 1708038709137.066, "dur": 0.167, + "args": { + "External id": 4675132,"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": 1708038709137.979, "dur": 0.405, + "args": { + "External id": 4675133,"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": 1708038709139.124, "dur": 0.220, + "args": { + "External id": 4675134,"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": 1708038709140.141, "dur": 0.208, + "args": { + "External id": 4675135,"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": 1708038709141.190, "dur": 0.221, + "args": { + "External id": 4675136,"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": 1708038709143.611, "dur": 0.206, + "args": { + "External id": 4675137,"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": 1708038709144.751, "dur": 0.211, + "args": { + "External id": 4675138,"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": 1708038709145.943, "dur": 0.210, + "args": { + "External id": 4675139,"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": 1708038709147.064, "dur": 0.208, + "args": { + "External id": 4675140,"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": 1708038709148.045, "dur": 0.208, + "args": { + "External id": 4675141,"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": 1708038709149.035, "dur": 0.207, + "args": { + "External id": 4675142,"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": 1708038709155.597, "dur": 0.231, + "args": { + "External id": 4675143,"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": 1708038709156.645, "dur": 0.212, + "args": { + "External id": 4675144,"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": 1708038709159.150, "dur": 0.205, + "args": { + "External id": 4675145,"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": 1708038709160.263, "dur": 0.207, + "args": { + "External id": 4675146,"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": 1708038709161.235, "dur": 0.205, + "args": { + "External id": 4675147,"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": 1708038709162.179, "dur": 0.215, + "args": { + "External id": 4675148,"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": 1708038709163.148, "dur": 0.208, + "args": { + "External id": 4675149,"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": 1708038709164.206, "dur": 0.208, + "args": { + "External id": 4675150,"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": 1708038709165.402, "dur": 0.229, + "args": { + "External id": 4675151,"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": 1708038709166.376, "dur": 0.231, + "args": { + "External id": 4675152,"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": 1708038709169.070, "dur": 0.403, + "args": { + "External id": 4675153,"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": 1708038709170.223, "dur": 0.399, + "args": { + "External id": 4675154,"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": 1708038709171.371, "dur": 0.206, + "args": { + "External id": 4675155,"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": 1708038709172.333, "dur": 0.394, + "args": { + "External id": 4675156,"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": 1708038709173.582, "dur": 0.406, + "args": { + "External id": 4675157,"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": 1708038709174.834, "dur": 0.214, + "args": { + "External id": 4675158,"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": 1708038709175.829, "dur": 0.217, + "args": { + "External id": 4675159,"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": 1708038709176.824, "dur": 0.431, + "args": { + "External id": 4675160,"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": 1708038709179.492, "dur": 0.211, + "args": { + "External id": 4675161,"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": 1708038709180.452, "dur": 0.411, + "args": { + "External id": 4675162,"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": 1708038709181.902, "dur": 0.204, + "args": { + "External id": 4675163,"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": 1708038709182.988, "dur": 0.202, + "args": { + "External id": 4675164,"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": 1708038709183.933, "dur": 0.212, + "args": { + "External id": 4675165,"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": 1708038709184.913, "dur": 0.209, + "args": { + "External id": 4675166,"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": 1708038709185.961, "dur": 0.204, + "args": { + "External id": 4675167,"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": 1708038709187.064, "dur": 0.211, + "args": { + "External id": 4675168,"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": 1708038709189.738, "dur": 0.204, + "args": { + "External id": 4675169,"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": 1708038709190.794, "dur": 0.214, + "args": { + "External id": 4675170,"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": 1708038709191.727, "dur": 0.208, + "args": { + "External id": 4675171,"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": 1708038709192.730, "dur": 0.203, + "args": { + "External id": 4675172,"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": 1708038709193.776, "dur": 0.207, + "args": { + "External id": 4675173,"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": 1708038709194.755, "dur": 0.246, + "args": { + "External id": 4675174,"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": 1708038709196.467, "dur": 0.216, + "args": { + "External id": 4675175,"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": 1708038709197.463, "dur": 0.211, + "args": { + "External id": 4675176,"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": 1708038709200.727, "dur": 0.201, + "args": { + "External id": 4675177,"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": 1708038709201.709, "dur": 0.232, + "args": { + "External id": 4675178,"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": 1708038709202.664, "dur": 0.204, + "args": { + "External id": 4675179,"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": 1708038709203.603, "dur": 0.205, + "args": { + "External id": 4675180,"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": 1708038709204.720, "dur": 0.204, + "args": { + "External id": 4675181,"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": 1708038709205.724, "dur": 0.213, + "args": { + "External id": 4675182,"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": 1708038709206.687, "dur": 0.210, + "args": { + "External id": 4675183,"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": 1708038709207.927, "dur": 0.210, + "args": { + "External id": 4675184,"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": 1708038709210.317, "dur": 0.214, + "args": { + "External id": 4675185,"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": 1708038709211.315, "dur": 0.208, + "args": { + "External id": 4675186,"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": 1708038709212.218, "dur": 0.213, + "args": { + "External id": 4675187,"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": 1708038709213.137, "dur": 0.216, + "args": { + "External id": 4675188,"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": 1708038709214.165, "dur": 0.222, + "args": { + "External id": 4675189,"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": 1708038709215.199, "dur": 0.222, + "args": { + "External id": 4675190,"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": 1708038709217.454, "dur": 0.329, + "args": { + "External id": 4675191,"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": 1708038709218.552, "dur": 0.373, + "args": { + "External id": 4675192,"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": 1708038709221.126, "dur": 0.424, + "args": { + "External id": 4675193,"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": 1708038709222.293, "dur": 0.404, + "args": { + "External id": 4675194,"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": 1708038709223.439, "dur": 0.213, + "args": { + "External id": 4675195,"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": 1708038709224.385, "dur": 0.366, + "args": { + "External id": 4675196,"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": 1708038709225.623, "dur": 0.207, + "args": { + "External id": 4675197,"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": 1708038709226.577, "dur": 0.216, + "args": { + "External id": 4675198,"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": 1708038709227.588, "dur": 0.445, + "args": { + "External id": 4675199,"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": 1708038709228.817, "dur": 0.209, + "args": { + "External id": 4675200,"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": 1708038709231.256, "dur": 0.414, + "args": { + "External id": 4675201,"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": 1708038709232.554, "dur": 0.407, + "args": { + "External id": 4675202,"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": 1708038709233.708, "dur": 0.206, + "args": { + "External id": 4675203,"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": 1708038709234.804, "dur": 0.243, + "args": { + "External id": 4675204,"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": 1708038709235.767, "dur": 0.208, + "args": { + "External id": 4675205,"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": 1708038709236.773, "dur": 0.205, + "args": { + "External id": 4675206,"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": 1708038709238.307, "dur": 0.215, + "args": { + "External id": 4675207,"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": 1708038709239.281, "dur": 0.208, + "args": { + "External id": 4675208,"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": 1708038709241.510, "dur": 0.213, + "args": { + "External id": 4675209,"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": 1708038709242.468, "dur": 0.212, + "args": { + "External id": 4675210,"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": 1708038709243.419, "dur": 0.204, + "args": { + "External id": 4675211,"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": 1708038709244.516, "dur": 0.340, + "args": { + "External id": 4675212,"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": 1708038709245.580, "dur": 0.203, + "args": { + "External id": 4675213,"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": 1708038709246.567, "dur": 0.241, + "args": { + "External id": 4675214,"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": 1708038709247.523, "dur": 0.209, + "args": { + "External id": 4675215,"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": 1708038709248.874, "dur": 0.209, + "args": { + "External id": 4675216,"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": 1708038709251.238, "dur": 0.214, + "args": { + "External id": 4675217,"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": 1708038709252.178, "dur": 0.203, + "args": { + "External id": 4675218,"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": 1708038709253.085, "dur": 0.207, + "args": { + "External id": 4675219,"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": 1708038709254.153, "dur": 0.210, + "args": { + "External id": 4675220,"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": 1708038709255.147, "dur": 0.211, + "args": { + "External id": 4675221,"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": 1708038709256.163, "dur": 0.213, + "args": { + "External id": 4675222,"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": 1708038709257.297, "dur": 0.202, + "args": { + "External id": 4675223,"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": 1708038709258.433, "dur": 0.212, + "args": { + "External id": 4675224,"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": 1708038709260.851, "dur": 0.207, + "args": { + "External id": 4675225,"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": 1708038709262.130, "dur": 0.300, + "args": { + "External id": 4675226,"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": 1708038709263.681, "dur": 0.214, + "args": { + "External id": 4675227,"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": 1708038709264.785, "dur": 0.328, + "args": { + "External id": 4675228,"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": 1708038709265.941, "dur": 0.213, + "args": { + "External id": 4675229,"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": 1708038709266.975, "dur": 0.202, + "args": { + "External id": 4675230,"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": 1708038709267.927, "dur": 0.307, + "args": { + "External id": 4675231,"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": 1708038709269.051, "dur": 0.352, + "args": { + "External id": 4675232,"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": 1708038709271.760, "dur": 0.348, + "args": { + "External id": 4675233,"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": 1708038709272.901, "dur": 0.414, + "args": { + "External id": 4675234,"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": 1708038709274.057, "dur": 0.204, + "args": { + "External id": 4675235,"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": 1708038709274.972, "dur": 0.321, + "args": { + "External id": 4675236,"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": 1708038709275.999, "dur": 0.320, + "args": { + "External id": 4675237,"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": 1708038709277.140, "dur": 0.215, + "args": { + "External id": 4675238,"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": 1708038709278.108, "dur": 0.209, + "args": { + "External id": 4675239,"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": 1708038709279.223, "dur": 0.202, + "args": { + "External id": 4675240,"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": 1708038709281.940, "dur": 0.240, + "args": { + "External id": 4675241,"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": 1708038709283.059, "dur": 0.235, + "args": { + "External id": 4675242,"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": 1708038709284.083, "dur": 0.215, + "args": { + "External id": 4675243,"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": 1708038709285.071, "dur": 0.203, + "args": { + "External id": 4675244,"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": 1708038709285.986, "dur": 0.217, + "args": { + "External id": 4675245,"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": 1708038709286.996, "dur": 0.207, + "args": { + "External id": 4675246,"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": 1708038709288.600, "dur": 0.345, + "args": { + "External id": 4675247,"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": 1708038709289.752, "dur": 0.234, + "args": { + "External id": 4675248,"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": 1708038709292.191, "dur": 0.204, + "args": { + "External id": 4675249,"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": 1708038709293.124, "dur": 0.214, + "args": { + "External id": 4675250,"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": 1708038709294.078, "dur": 0.208, + "args": { + "External id": 4675251,"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": 1708038709295.057, "dur": 0.205, + "args": { + "External id": 4675252,"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": 1708038709295.981, "dur": 0.206, + "args": { + "External id": 4675253,"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": 1708038709297.083, "dur": 0.206, + "args": { + "External id": 4675254,"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": 1708038709298.036, "dur": 0.209, + "args": { + "External id": 4675255,"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": 1708038709298.969, "dur": 0.216, + "args": { + "External id": 4675256,"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": 1708038709302.462, "dur": 0.225, + "args": { + "External id": 4675257,"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": 1708038709303.592, "dur": 0.210, + "args": { + "External id": 4675258,"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": 1708038709304.582, "dur": 0.209, + "args": { + "External id": 4675259,"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": 1708038709305.575, "dur": 0.202, + "args": { + "External id": 4675260,"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": 1708038709306.573, "dur": 0.205, + "args": { + "External id": 4675261,"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": 1708038709307.501, "dur": 0.215, + "args": { + "External id": 4675262,"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": 1708038709308.475, "dur": 0.208, + "args": { + "External id": 4675263,"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": 1708038709309.416, "dur": 0.208, + "args": { + "External id": 4675264,"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": 1708038709311.677, "dur": 0.212, + "args": { + "External id": 4675265,"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": 1708038709312.750, "dur": 0.219, + "args": { + "External id": 4675266,"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": 1708038709313.683, "dur": 0.211, + "args": { + "External id": 4675267,"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": 1708038709314.815, "dur": 0.206, + "args": { + "External id": 4675268,"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": 1708038709315.722, "dur": 0.219, + "args": { + "External id": 4675269,"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": 1708038709316.721, "dur": 0.220, + "args": { + "External id": 4675270,"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": 1708038709317.981, "dur": 0.206, + "args": { + "External id": 4675271,"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": 1708038709318.931, "dur": 0.311, + "args": { + "External id": 4675272,"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": 1708038709321.701, "dur": 0.333, + "args": { + "External id": 4675273,"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": 1708038709322.776, "dur": 0.367, + "args": { + "External id": 4675274,"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": 1708038709323.962, "dur": 0.210, + "args": { + "External id": 4675275,"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": 1708038709324.949, "dur": 0.332, + "args": { + "External id": 4675276,"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": 1708038709326.034, "dur": 0.220, + "args": { + "External id": 4675277,"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": 1708038709326.956, "dur": 0.312, + "args": { + "External id": 4675278,"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": 1708038709327.992, "dur": 0.212, + "args": { + "External id": 4675279,"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": 1708038709328.955, "dur": 0.208, + "args": { + "External id": 4675280,"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": 1708038709331.391, "dur": 0.321, + "args": { + "External id": 4675281,"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": 1708038709332.425, "dur": 0.206, + "args": { + "External id": 4675282,"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": 1708038709333.407, "dur": 0.205, + "args": { + "External id": 4675283,"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": 1708038709334.334, "dur": 0.257, + "args": { + "External id": 4675284,"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": 1708038709335.340, "dur": 0.209, + "args": { + "External id": 4675285,"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": 1708038709336.292, "dur": 0.202, + "args": { + "External id": 4675286,"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": 1708038709337.198, "dur": 0.209, + "args": { + "External id": 4675287,"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": 1708038709338.171, "dur": 0.205, + "args": { + "External id": 4675288,"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": 1708038709340.312, "dur": 0.210, + "args": { + "External id": 4675289,"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": 1708038709341.256, "dur": 0.207, + "args": { + "External id": 4675290,"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": 1708038709342.247, "dur": 0.206, + "args": { + "External id": 4675291,"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": 1708038709343.216, "dur": 0.211, + "args": { + "External id": 4675292,"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": 1708038709344.150, "dur": 0.205, + "args": { + "External id": 4675293,"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": 1708038709345.053, "dur": 0.219, + "args": { + "External id": 4675294,"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": 1708038709346.032, "dur": 0.206, + "args": { + "External id": 4675295,"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": 1708038709347.265, "dur": 0.201, + "args": { + "External id": 4675296,"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": 1708038709349.764, "dur": 0.216, + "args": { + "External id": 4675297,"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": 1708038709350.899, "dur": 0.210, + "args": { + "External id": 4675298,"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": 1708038709352.354, "dur": 0.250, + "args": { + "External id": 4675299,"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": 1708038709353.626, "dur": 0.379, + "args": { + "External id": 4675300,"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": 1708038709354.884, "dur": 0.174, + "args": { + "External id": 4675301,"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": 1708038709355.928, "dur": 0.218, + "args": { + "External id": 4675302,"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": 1708038709356.869, "dur": 0.203, + "args": { + "External id": 4675303,"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": 1708038709357.938, "dur": 0.369, + "args": { + "External id": 4675304,"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": 1708038709360.616, "dur": 0.224, + "args": { + "External id": 4675305,"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": 1708038709361.552, "dur": 0.214, + "args": { + "External id": 4675306,"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": 1708038709362.483, "dur": 0.209, + "args": { + "External id": 4675307,"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": 1708038709363.404, "dur": 0.347, + "args": { + "External id": 4675308,"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": 1708038709364.557, "dur": 0.212, + "args": { + "External id": 4675309,"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": 1708038709365.487, "dur": 0.208, + "args": { + "External id": 4675310,"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": 1708038709366.399, "dur": 0.219, + "args": { + "External id": 4675311,"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": 1708038709367.518, "dur": 0.217, + "args": { + "External id": 4675312,"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": 1708038709370.005, "dur": 0.215, + "args": { + "External id": 4675313,"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": 1708038709371.152, "dur": 0.214, + "args": { + "External id": 4675314,"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": 1708038709372.102, "dur": 0.243, + "args": { + "External id": 4675315,"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": 1708038709373.048, "dur": 0.221, + "args": { + "External id": 4675316,"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": 1708038709374.158, "dur": 0.213, + "args": { + "External id": 4675317,"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": 1708038709375.077, "dur": 0.205, + "args": { + "External id": 4675318,"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": 1708038709376.018, "dur": 0.213, + "args": { + "External id": 4675319,"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": 1708038709376.941, "dur": 0.208, + "args": { + "External id": 4675320,"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": 1708038709379.336, "dur": 0.214, + "args": { + "External id": 4675321,"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": 1708038709380.265, "dur": 0.213, + "args": { + "External id": 4675322,"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": 1708038709381.272, "dur": 0.208, + "args": { + "External id": 4675323,"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": 1708038709382.216, "dur": 0.240, + "args": { + "External id": 4675324,"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": 1708038709383.176, "dur": 0.250, + "args": { + "External id": 4675325,"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": 1708038709384.181, "dur": 0.392, + "args": { + "External id": 4675326,"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": 1708038709385.413, "dur": 0.216, + "args": { + "External id": 4675327,"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": 1708038709386.373, "dur": 0.209, + "args": { + "External id": 4675328,"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": 1708038709388.713, "dur": 0.212, + "args": { + "External id": 4675329,"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": 1708038709389.716, "dur": 0.201, + "args": { + "External id": 4675330,"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": 1708038709391.144, "dur": 0.214, + "args": { + "External id": 4675331,"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": 1708038709392.100, "dur": 0.232, + "args": { + "External id": 4675332,"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": 1708038709393.031, "dur": 0.420, + "args": { + "External id": 4675333,"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": 1708038709394.200, "dur": 0.211, + "args": { + "External id": 4675334,"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": 1708038709395.149, "dur": 0.407, + "args": { + "External id": 4675335,"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": 1708038709396.273, "dur": 0.250, + "args": { + "External id": 4675336,"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": 1708038709398.876, "dur": 0.206, + "args": { + "External id": 4675337,"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": 1708038709399.804, "dur": 0.207, + "args": { + "External id": 4675338,"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": 1708038709400.737, "dur": 0.414, + "args": { + "External id": 4675339,"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": 1708038709401.853, "dur": 0.237, + "args": { + "External id": 4675340,"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": 1708038709402.790, "dur": 0.224, + "args": { + "External id": 4675341,"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": 1708038709403.946, "dur": 0.444, + "args": { + "External id": 4675342,"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": 1708038709405.350, "dur": 0.207, + "args": { + "External id": 4675343,"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": 1708038709406.476, "dur": 0.237, + "args": { + "External id": 4675344,"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": 1708038709408.989, "dur": 0.244, + "args": { + "External id": 4675345,"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": 1708038709410.020, "dur": 0.223, + "args": { + "External id": 4675346,"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": 1708038709411.113, "dur": 0.200, + "args": { + "External id": 4675347,"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": 1708038709412.229, "dur": 0.207, + "args": { + "External id": 4675348,"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": 1708038709413.353, "dur": 0.204, + "args": { + "External id": 4675349,"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": 1708038709414.307, "dur": 0.236, + "args": { + "External id": 4675350,"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": 1708038709415.255, "dur": 0.210, + "args": { + "External id": 4675351,"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": 1708038709416.246, "dur": 0.214, + "args": { + "External id": 4675352,"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": 1708038709418.578, "dur": 0.218, + "args": { + "External id": 4675353,"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": 1708038709433.038, "dur": 0.512, + "args": { + "External id": 4675354,"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": 1708038709435.224, "dur": 0.216, + "args": { + "External id": 4675355,"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": 1708038709436.302, "dur": 0.308, + "args": { + "External id": 4675356,"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": 1708038709437.438, "dur": 0.208, + "args": { + "External id": 4675357,"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": 1708038709438.385, "dur": 0.317, + "args": { + "External id": 4675358,"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": 1708038709439.513, "dur": 0.355, + "args": { + "External id": 4675359,"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": 1708038709440.595, "dur": 0.358, + "args": { + "External id": 4675360,"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": 1708038709443.226, "dur": 0.278, + "args": { + "External id": 4675361,"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": 1708038709444.340, "dur": 0.197, + "args": { + "External id": 4675362,"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": 1708038709445.238, "dur": 0.203, + "args": { + "External id": 4675363,"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": 1708038709446.354, "dur": 0.302, + "args": { + "External id": 4675364,"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": 1708038709447.584, "dur": 0.222, + "args": { + "External id": 4675365,"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": 1708038709448.579, "dur": 0.469, + "args": { + "External id": 4675366,"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": 1708038709453.324, "dur": 0.230, + "args": { + "External id": 4675367,"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": 1708038709454.353, "dur": 0.271, + "args": { + "External id": 4675368,"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": 1708038709456.646, "dur": 0.201, + "args": { + "External id": 4675369,"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": 1708038709457.800, "dur": 0.240, + "args": { + "External id": 4675370,"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": 1708038709459.947, "dur": 0.233, + "args": { + "External id": 4675371,"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": 1708038709461.077, "dur": 0.450, + "args": { + "External id": 4675372,"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": 1708038709462.236, "dur": 0.367, + "args": { + "External id": 4675373,"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": 1708038709463.312, "dur": 0.348, + "args": { + "External id": 4675374,"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": 1708038709464.420, "dur": 0.615, + "args": { + "External id": 4675375,"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": 1708038709466.046, "dur": 0.245, + "args": { + "External id": 4675376,"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": 1708038709468.628, "dur": 0.329, + "args": { + "External id": 4675377,"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": 1708038709469.706, "dur": 0.305, + "args": { + "External id": 4675378,"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": 1708038709470.798, "dur": 0.233, + "args": { + "External id": 4675379,"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": 1708038709471.976, "dur": 0.342, + "args": { + "External id": 4675380,"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": 1708038709473.368, "dur": 0.207, + "args": { + "External id": 4675381,"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": 1708038709474.526, "dur": 0.447, + "args": { + "External id": 4675382,"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": 1708038709475.686, "dur": 0.208, + "args": { + "External id": 4675383,"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": 1708038709476.776, "dur": 0.208, + "args": { + "External id": 4675384,"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": 1708038709479.568, "dur": 0.218, + "args": { + "External id": 4675385,"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": 1708038709480.589, "dur": 0.203, + "args": { + "External id": 4675386,"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": 1708038709481.524, "dur": 0.198, + "args": { + "External id": 4675387,"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": 1708038709482.484, "dur": 0.207, + "args": { + "External id": 4675388,"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": 1708038709551.087, "dur": 1582.221, + "args": { + "External id": 4675389,"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": 1708038710039.079, "dur": 1017.921, + "args": { + "External id": 4675390,"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": 1708038710049.439, "dur": 7.428, + "args": { + "External id": 4675391,"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": 1708038710053.295, "dur": 2.920, + "args": { + "External id": 4675392,"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": 1708038710057.555, "dur": 3.093, + "args": { + "External id": 4675393,"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": 1708038710058.397, "dur": 2.084, + "args": { + "External id": 4675394,"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": 1708038710061.264, "dur": 2.603, + "args": { + "External id": 4675395,"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": 1708038710063.273, "dur": 0.526, + "args": { + "External id": 4675396,"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": 1708038710064.304, "dur": 1.331, + "args": { + "External id": 4675397,"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": 1708038710064.923, "dur": 0.641, + "args": { + "External id": 4675398,"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": 1708038710067.407, "dur": 4.886, + "args": { + "External id": 4675399,"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": 1708038710071.773, "dur": 0.451, + "args": { + "External id": 4675400,"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": 1708038710072.593, "dur": 1.136, + "args": { + "External id": 4675401,"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": 1708038710073.193, "dur": 0.465, + "args": { + "External id": 4675402,"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": 1708038710074.194, "dur": 1.240, + "args": { + "External id": 4675403,"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": 1708038710074.811, "dur": 0.551, + "args": { + "External id": 4675404,"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": 1708038710075.701, "dur": 3.204, + "args": { + "External id": 4675405,"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": 1708038710078.239, "dur": 0.598, + "args": { + "External id": 4675406,"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": 1708038710079.225, "dur": 1.069, + "args": { + "External id": 4675407,"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": 1708038710079.813, "dur": 0.414, + "args": { + "External id": 4675408,"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": 1708038710080.528, "dur": 2.372, + "args": { + "External id": 4675409,"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": 1708038710080.937, "dur": 1.756, + "args": { + "External id": 4675410,"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": 1708038710083.141, "dur": 2.974, + "args": { + "External id": 4675411,"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": 1708038710085.221, "dur": 0.809, + "args": { + "External id": 4675412,"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": 1708038710086.347, "dur": 1.260, + "args": { + "External id": 4675413,"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": 1708038710086.716, "dur": 0.820, + "args": { + "External id": 4675414,"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": 1708038710089.341, "dur": 3.565, + "args": { + "External id": 4675415,"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": 1708038710092.071, "dur": 0.764, + "args": { + "External id": 4675416,"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": 1708038710093.440, "dur": 1.285, + "args": { + "External id": 4675417,"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": 1708038710094.080, "dur": 0.575, + "args": { + "External id": 4675418,"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": 1708038710095.035, "dur": 1.472, + "args": { + "External id": 4675419,"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": 1708038710095.631, "dur": 0.804, + "args": { + "External id": 4675420,"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": 1708038710096.746, "dur": 2.635, + "args": { + "External id": 4675421,"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": 1708038710098.911, "dur": 0.401, + "args": { + "External id": 4675422,"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": 1708038710099.611, "dur": 1.662, + "args": { + "External id": 4675423,"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": 1708038710100.511, "dur": 0.693, + "args": { + "External id": 4675424,"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": 1708038710101.719, "dur": 2.320, + "args": { + "External id": 4675425,"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": 1708038710102.095, "dur": 1.869, + "args": { + "External id": 4675426,"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": 1708038710104.304, "dur": 2.735, + "args": { + "External id": 4675427,"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": 1708038710106.238, "dur": 0.734, + "args": { + "External id": 4675428,"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": 1708038710107.265, "dur": 1.686, + "args": { + "External id": 4675429,"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": 1708038710107.969, "dur": 0.910, + "args": { + "External id": 4675430,"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": 1708038710110.524, "dur": 4.550, + "args": { + "External id": 4675431,"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": 1708038710114.159, "dur": 0.848, + "args": { + "External id": 4675432,"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": 1708038710115.325, "dur": 0.975, + "args": { + "External id": 4675433,"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": 1708038710115.691, "dur": 0.541, + "args": { + "External id": 4675434,"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": 1708038710116.552, "dur": 1.156, + "args": { + "External id": 4675435,"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": 1708038710117.106, "dur": 0.534, + "args": { + "External id": 4675436,"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": 1708038710117.934, "dur": 3.120, + "args": { + "External id": 4675437,"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": 1708038710120.511, "dur": 0.473, + "args": { + "External id": 4675438,"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": 1708038710121.278, "dur": 1.190, + "args": { + "External id": 4675439,"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": 1708038710121.779, "dur": 0.622, + "args": { + "External id": 4675440,"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": 1708038710122.892, "dur": 2.724, + "args": { + "External id": 4675441,"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": 1708038710123.265, "dur": 2.075, + "args": { + "External id": 4675442,"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": 1708038710125.859, "dur": 1.733, + "args": { + "External id": 4675443,"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": 1708038710127.111, "dur": 0.410, + "args": { + "External id": 4675444,"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": 1708038710127.852, "dur": 1.379, + "args": { + "External id": 4675445,"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": 1708038710128.250, "dur": 0.914, + "args": { + "External id": 4675446,"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": 1708038710131.038, "dur": 4.148, + "args": { + "External id": 4675447,"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": 1708038710134.365, "dur": 0.749, + "args": { + "External id": 4675448,"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": 1708038710135.542, "dur": 0.870, + "args": { + "External id": 4675449,"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": 1708038710135.931, "dur": 0.413, + "args": { + "External id": 4675450,"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": 1708038710136.632, "dur": 1.012, + "args": { + "External id": 4675451,"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": 1708038710137.015, "dur": 0.558, + "args": { + "External id": 4675452,"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": 1708038710137.871, "dur": 3.944, + "args": { + "External id": 4675453,"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": 1708038710140.927, "dur": 0.814, + "args": { + "External id": 4675454,"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": 1708038710142.062, "dur": 1.402, + "args": { + "External id": 4675455,"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": 1708038710142.630, "dur": 0.763, + "args": { + "External id": 4675456,"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": 1708038710143.772, "dur": 2.608, + "args": { + "External id": 4675457,"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": 1708038710144.270, "dur": 2.034, + "args": { + "External id": 4675458,"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": 1708038710146.619, "dur": 3.624, + "args": { + "External id": 4675459,"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": 1708038710149.448, "dur": 0.725, + "args": { + "External id": 4675460,"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": 1708038710150.703, "dur": 2.831, + "args": { + "External id": 4675461,"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": 1708038710151.326, "dur": 2.044, + "args": { + "External id": 4675462,"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": 1708038710155.210, "dur": 2.320, + "args": { + "External id": 4675463,"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": 1708038710156.887, "dur": 0.574, + "args": { + "External id": 4675464,"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": 1708038710157.752, "dur": 1.234, + "args": { + "External id": 4675465,"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": 1708038710158.264, "dur": 0.649, + "args": { + "External id": 4675466,"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": 1708038710159.329, "dur": 3.117, + "args": { + "External id": 4675467,"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": 1708038710161.989, "dur": 0.388, + "args": { + "External id": 4675468,"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": 1708038710162.690, "dur": 2.046, + "args": { + "External id": 4675469,"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": 1708038710164.138, "dur": 0.531, + "args": { + "External id": 4675470,"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": 1708038710165.063, "dur": 1.418, + "args": { + "External id": 4675471,"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": 1708038710165.652, "dur": 0.754, + "args": { + "External id": 4675472,"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": 1708038710166.704, "dur": 2.871, + "args": { + "External id": 4675473,"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": 1708038710168.890, "dur": 0.616, + "args": { + "External id": 4675474,"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": 1708038710169.819, "dur": 2.762, + "args": { + "External id": 4675475,"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": 1708038710171.781, "dur": 0.730, + "args": { + "External id": 4675476,"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": 1708038710172.807, "dur": 2.676, + "args": { + "External id": 4675477,"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": 1708038710173.177, "dur": 2.229, + "args": { + "External id": 4675478,"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": 1708038710177.421, "dur": 2.218, + "args": { + "External id": 4675479,"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": 1708038710178.795, "dur": 0.775, + "args": { + "External id": 4675480,"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": 1708038710179.866, "dur": 1.382, + "args": { + "External id": 4675481,"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": 1708038710180.352, "dur": 0.823, + "args": { + "External id": 4675482,"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": 1708038710181.475, "dur": 2.493, + "args": { + "External id": 4675483,"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": 1708038710183.559, "dur": 0.336, + "args": { + "External id": 4675484,"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": 1708038710184.231, "dur": 2.088, + "args": { + "External id": 4675485,"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": 1708038710185.829, "dur": 0.423, + "args": { + "External id": 4675486,"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": 1708038710186.593, "dur": 1.432, + "args": { + "External id": 4675487,"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": 1708038710187.183, "dur": 0.769, + "args": { + "External id": 4675488,"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": 1708038710188.290, "dur": 3.076, + "args": { + "External id": 4675489,"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": 1708038710190.601, "dur": 0.698, + "args": { + "External id": 4675490,"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": 1708038710191.848, "dur": 2.233, + "args": { + "External id": 4675491,"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": 1708038710193.301, "dur": 0.712, + "args": { + "External id": 4675492,"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": 1708038710194.359, "dur": 3.148, + "args": { + "External id": 4675493,"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": 1708038710195.266, "dur": 2.073, + "args": { + "External id": 4675494,"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": 1708038710199.443, "dur": 1.913, + "args": { + "External id": 4675495,"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": 1708038710200.774, "dur": 0.514, + "args": { + "External id": 4675496,"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": 1708038710201.730, "dur": 1.562, + "args": { + "External id": 4675497,"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": 1708038710202.514, "dur": 0.706, + "args": { + "External id": 4675498,"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": 1708038710203.535, "dur": 3.469, + "args": { + "External id": 4675499,"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": 1708038710206.496, "dur": 0.439, + "args": { + "External id": 4675500,"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": 1708038710207.280, "dur": 1.334, + "args": { + "External id": 4675501,"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": 1708038710208.106, "dur": 0.440, + "args": { + "External id": 4675502,"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": 1708038710208.859, "dur": 2.101, + "args": { + "External id": 4675503,"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": 1708038710210.067, "dur": 0.823, + "args": { + "External id": 4675504,"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": 1708038710211.217, "dur": 2.700, + "args": { + "External id": 4675505,"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": 1708038710213.159, "dur": 0.688, + "args": { + "External id": 4675506,"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": 1708038710214.202, "dur": 1.737, + "args": { + "External id": 4675507,"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": 1708038710215.238, "dur": 0.633, + "args": { + "External id": 4675508,"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": 1708038710216.196, "dur": 2.918, + "args": { + "External id": 4675509,"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": 1708038710217.170, "dur": 1.869, + "args": { + "External id": 4675510,"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": 1708038710220.882, "dur": 1.437, + "args": { + "External id": 4675511,"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": 1708038710221.798, "dur": 0.449, + "args": { + "External id": 4675512,"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": 1708038710222.682, "dur": 1.525, + "args": { + "External id": 4675513,"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": 1708038710223.499, "dur": 0.636, + "args": { + "External id": 4675514,"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": 1708038710224.440, "dur": 2.783, + "args": { + "External id": 4675515,"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": 1708038710226.674, "dur": 0.482, + "args": { + "External id": 4675516,"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": 1708038710227.506, "dur": 1.264, + "args": { + "External id": 4675517,"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": 1708038710228.264, "dur": 0.435, + "args": { + "External id": 4675518,"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": 1708038710229.034, "dur": 1.586, + "args": { + "External id": 4675519,"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": 1708038710229.902, "dur": 0.645, + "args": { + "External id": 4675520,"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": 1708038710230.879, "dur": 3.011, + "args": { + "External id": 4675521,"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": 1708038710233.301, "dur": 0.520, + "args": { + "External id": 4675522,"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": 1708038710234.125, "dur": 1.974, + "args": { + "External id": 4675523,"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": 1708038710235.273, "dur": 0.756, + "args": { + "External id": 4675524,"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": 1708038710236.356, "dur": 2.727, + "args": { + "External id": 4675525,"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": 1708038710237.179, "dur": 1.829, + "args": { + "External id": 4675526,"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": 1708038710240.610, "dur": 1.308, + "args": { + "External id": 4675527,"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": 1708038710241.385, "dur": 0.467, + "args": { + "External id": 4675528,"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": 1708038710242.290, "dur": 1.324, + "args": { + "External id": 4675529,"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": 1708038710242.991, "dur": 0.547, + "args": { + "External id": 4675530,"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": 1708038710244.023, "dur": 3.490, + "args": { + "External id": 4675531,"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": 1708038710246.856, "dur": 0.587, + "args": { + "External id": 4675532,"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": 1708038710247.876, "dur": 1.680, + "args": { + "External id": 4675533,"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": 1708038710248.947, "dur": 0.540, + "args": { + "External id": 4675534,"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": 1708038710249.825, "dur": 2.285, + "args": { + "External id": 4675535,"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": 1708038710250.844, "dur": 1.193, + "args": { + "External id": 4675536,"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": 1708038710252.364, "dur": 2.769, + "args": { + "External id": 4675537,"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": 1708038710254.606, "dur": 0.458, + "args": { + "External id": 4675538,"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": 1708038710255.364, "dur": 1.719, + "args": { + "External id": 4675539,"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": 1708038710256.557, "dur": 0.459, + "args": { + "External id": 4675540,"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": 1708038710257.377, "dur": 2.799, + "args": { + "External id": 4675541,"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": 1708038710258.047, "dur": 1.963, + "args": { + "External id": 4675542,"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": 1708038710262.081, "dur": 1.470, + "args": { + "External id": 4675543,"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": 1708038710262.852, "dur": 0.630, + "args": { + "External id": 4675544,"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": 1708038710263.819, "dur": 1.519, + "args": { + "External id": 4675545,"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": 1708038710264.652, "dur": 0.612, + "args": { + "External id": 4675546,"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": 1708038710265.574, "dur": 2.706, + "args": { + "External id": 4675547,"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": 1708038710267.825, "dur": 0.385, + "args": { + "External id": 4675548,"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": 1708038710268.557, "dur": 1.543, + "args": { + "External id": 4675549,"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": 1708038710269.521, "dur": 0.511, + "args": { + "External id": 4675550,"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": 1708038710270.422, "dur": 1.678, + "args": { + "External id": 4675551,"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": 1708038710271.398, "dur": 0.628, + "args": { + "External id": 4675552,"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": 1708038710272.527, "dur": 2.833, + "args": { + "External id": 4675553,"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": 1708038710274.676, "dur": 0.614, + "args": { + "External id": 4675554,"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": 1708038710275.591, "dur": 1.807, + "args": { + "External id": 4675555,"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": 1708038710276.723, "dur": 0.610, + "args": { + "External id": 4675556,"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": 1708038710277.656, "dur": 2.915, + "args": { + "External id": 4675557,"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": 1708038710278.518, "dur": 1.896, + "args": { + "External id": 4675558,"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": 1708038710282.517, "dur": 1.592, + "args": { + "External id": 4675559,"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": 1708038710283.543, "dur": 0.488, + "args": { + "External id": 4675560,"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": 1708038710284.571, "dur": 1.199, + "args": { + "External id": 4675561,"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": 1708038710285.165, "dur": 0.533, + "args": { + "External id": 4675562,"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": 1708038710286.031, "dur": 2.830, + "args": { + "External id": 4675563,"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": 1708038710288.398, "dur": 0.396, + "args": { + "External id": 4675564,"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": 1708038710289.163, "dur": 1.970, + "args": { + "External id": 4675565,"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": 1708038710290.352, "dur": 0.708, + "args": { + "External id": 4675566,"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": 1708038710291.387, "dur": 1.842, + "args": { + "External id": 4675567,"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": 1708038710292.505, "dur": 0.650, + "args": { + "External id": 4675568,"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": 1708038710293.630, "dur": 2.443, + "args": { + "External id": 4675569,"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": 1708038710295.574, "dur": 0.432, + "args": { + "External id": 4675570,"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": 1708038710296.302, "dur": 1.450, + "args": { + "External id": 4675571,"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": 1708038710297.177, "dur": 0.505, + "args": { + "External id": 4675572,"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": 1708038710298.126, "dur": 2.492, + "args": { + "External id": 4675573,"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": 1708038710298.873, "dur": 1.668, + "args": { + "External id": 4675574,"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": 1708038710302.194, "dur": 1.938, + "args": { + "External id": 4675575,"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": 1708038710303.506, "dur": 0.556, + "args": { + "External id": 4675576,"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": 1708038710304.602, "dur": 1.549, + "args": { + "External id": 4675577,"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": 1708038710305.380, "dur": 0.698, + "args": { + "External id": 4675578,"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": 1708038710306.382, "dur": 3.060, + "args": { + "External id": 4675579,"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": 1708038710308.944, "dur": 0.426, + "args": { + "External id": 4675580,"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": 1708038710309.741, "dur": 1.534, + "args": { + "External id": 4675581,"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": 1708038710310.619, "dur": 0.585, + "args": { + "External id": 4675582,"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": 1708038710311.589, "dur": 1.713, + "args": { + "External id": 4675583,"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": 1708038710312.599, "dur": 0.629, + "args": { + "External id": 4675584,"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": 1708038710369.866, "dur": 3.465, + "args": { + "External id": 4681729,"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": 1708038710372.625, "dur": 0.599, + "args": { + "External id": 4681730,"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": 1708038710373.749, "dur": 1.570, + "args": { + "External id": 4681731,"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": 1708038710374.785, "dur": 0.466, + "args": { + "External id": 4681732,"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": 1708038710375.602, "dur": 2.609, + "args": { + "External id": 4681733,"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": 1708038710376.413, "dur": 1.713, + "args": { + "External id": 4681734,"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": 1708038710379.691, "dur": 1.640, + "args": { + "External id": 4681735,"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": 1708038710380.696, "dur": 0.568, + "args": { + "External id": 4681736,"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": 1708038710381.702, "dur": 1.158, + "args": { + "External id": 4681737,"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": 1708038710382.322, "dur": 0.460, + "args": { + "External id": 4681738,"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": 1708038710383.115, "dur": 3.330, + "args": { + "External id": 4681739,"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": 1708038710385.981, "dur": 0.394, + "args": { + "External id": 4681740,"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": 1708038710386.769, "dur": 1.095, + "args": { + "External id": 4681741,"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": 1708038710387.383, "dur": 0.414, + "args": { + "External id": 4681742,"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": 1708038710388.157, "dur": 1.524, + "args": { + "External id": 4681743,"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": 1708038710388.960, "dur": 0.642, + "args": { + "External id": 4681744,"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": 1708038710389.982, "dur": 2.696, + "args": { + "External id": 4681745,"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": 1708038710392.187, "dur": 0.423, + "args": { + "External id": 4681746,"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": 1708038710392.927, "dur": 1.390, + "args": { + "External id": 4681747,"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": 1708038710393.767, "dur": 0.483, + "args": { + "External id": 4681748,"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": 1708038710394.577, "dur": 2.433, + "args": { + "External id": 4681749,"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": 1708038710395.265, "dur": 1.669, + "args": { + "External id": 4681750,"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": 1708038710398.919, "dur": 1.378, + "args": { + "External id": 4681751,"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": 1708038710399.726, "dur": 0.502, + "args": { + "External id": 4681752,"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": 1708038710400.660, "dur": 1.360, + "args": { + "External id": 4681753,"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": 1708038710401.227, "dur": 0.720, + "args": { + "External id": 4681754,"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": 1708038710402.330, "dur": 3.413, + "args": { + "External id": 4681755,"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": 1708038710405.150, "dur": 0.521, + "args": { + "External id": 4681756,"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": 1708038710406.030, "dur": 1.133, + "args": { + "External id": 4681757,"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": 1708038710406.622, "dur": 0.468, + "args": { + "External id": 4681758,"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": 1708038710407.503, "dur": 1.832, + "args": { + "External id": 4681759,"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": 1708038710408.626, "dur": 0.636, + "args": { + "External id": 4681760,"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": 1708038710409.624, "dur": 2.390, + "args": { + "External id": 4681761,"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": 1708038710411.444, "dur": 0.502, + "args": { + "External id": 4681762,"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": 1708038710412.258, "dur": 1.718, + "args": { + "External id": 4681763,"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": 1708038710413.354, "dur": 0.555, + "args": { + "External id": 4681764,"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": 1708038710414.333, "dur": 2.789, + "args": { + "External id": 4681765,"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": 1708038710415.070, "dur": 1.976, + "args": { + "External id": 4681766,"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": 1708038710418.656, "dur": 1.915, + "args": { + "External id": 4681767,"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": 1708038710419.722, "dur": 0.778, + "args": { + "External id": 4681768,"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": 1708038710420.837, "dur": 1.378, + "args": { + "External id": 4681769,"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": 1708038710421.588, "dur": 0.551, + "args": { + "External id": 4681770,"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": 1708038710422.565, "dur": 3.254, + "args": { + "External id": 4681771,"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": 1708038710425.173, "dur": 0.576, + "args": { + "External id": 4681772,"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": 1708038710426.100, "dur": 1.204, + "args": { + "External id": 4681773,"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": 1708038710426.725, "dur": 0.509, + "args": { + "External id": 4681774,"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": 1708038710427.614, "dur": 1.680, + "args": { + "External id": 4681775,"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": 1708038710428.629, "dur": 0.590, + "args": { + "External id": 4681776,"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": 1708038710429.571, "dur": 2.468, + "args": { + "External id": 4681777,"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": 1708038710431.489, "dur": 0.477, + "args": { + "External id": 4681778,"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": 1708038710432.315, "dur": 1.862, + "args": { + "External id": 4681779,"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": 1708038710433.481, "dur": 0.626, + "args": { + "External id": 4681780,"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": 1708038710434.461, "dur": 2.954, + "args": { + "External id": 4681781,"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": 1708038710435.222, "dur": 2.017, + "args": { + "External id": 4681782,"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": 1708038710438.934, "dur": 1.561, + "args": { + "External id": 4681783,"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": 1708038710439.941, "dur": 0.484, + "args": { + "External id": 4681784,"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": 1708038710440.879, "dur": 1.473, + "args": { + "External id": 4681785,"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": 1708038710441.451, "dur": 0.824, + "args": { + "External id": 4681786,"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": 1708038710442.628, "dur": 3.753, + "args": { + "External id": 4681787,"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": 1708038710445.259, "dur": 1.049, + "args": { + "External id": 4681788,"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": 1708038710446.659, "dur": 1.190, + "args": { + "External id": 4681789,"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": 1708038710447.348, "dur": 0.432, + "args": { + "External id": 4681790,"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": 1708038710448.143, "dur": 1.667, + "args": { + "External id": 4681791,"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": 1708038710449.106, "dur": 0.631, + "args": { + "External id": 4681792,"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": 1708038710450.189, "dur": 2.557, + "args": { + "External id": 4681793,"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": 1708038710452.280, "dur": 0.398, + "args": { + "External id": 4681794,"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": 1708038710452.980, "dur": 1.395, + "args": { + "External id": 4681795,"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": 1708038710453.844, "dur": 0.465, + "args": { + "External id": 4681796,"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": 1708038710454.659, "dur": 2.647, + "args": { + "External id": 4681797,"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": 1708038710455.356, "dur": 1.868, + "args": { + "External id": 4681798,"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": 1708038710458.847, "dur": 1.558, + "args": { + "External id": 4681799,"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": 1708038710459.906, "dur": 0.431, + "args": { + "External id": 4681800,"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": 1708038710460.688, "dur": 1.325, + "args": { + "External id": 4681801,"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": 1708038710461.404, "dur": 0.535, + "args": { + "External id": 4681802,"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": 1708038710462.407, "dur": 3.217, + "args": { + "External id": 4681803,"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": 1708038710465.073, "dur": 0.478, + "args": { + "External id": 4681804,"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": 1708038710465.924, "dur": 1.376, + "args": { + "External id": 4681805,"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": 1708038710466.638, "dur": 0.595, + "args": { + "External id": 4681806,"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": 1708038710467.537, "dur": 1.620, + "args": { + "External id": 4681807,"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": 1708038710468.390, "dur": 0.695, + "args": { + "External id": 4681808,"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": 1708038710469.426, "dur": 2.424, + "args": { + "External id": 4681809,"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": 1708038710471.399, "dur": 0.387, + "args": { + "External id": 4681810,"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": 1708038710472.217, "dur": 1.387, + "args": { + "External id": 4681811,"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": 1708038710473.008, "dur": 0.526, + "args": { + "External id": 4681812,"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": 1708038710473.866, "dur": 2.668, + "args": { + "External id": 4681813,"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": 1708038710474.658, "dur": 1.794, + "args": { + "External id": 4681814,"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": 1708038710478.004, "dur": 1.568, + "args": { + "External id": 4681815,"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": 1708038710479.001, "dur": 0.498, + "args": { + "External id": 4681816,"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": 1708038710480.032, "dur": 1.343, + "args": { + "External id": 4681817,"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": 1708038710480.674, "dur": 0.627, + "args": { + "External id": 4681818,"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": 1708038710481.608, "dur": 3.160, + "args": { + "External id": 4681819,"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": 1708038710484.208, "dur": 0.490, + "args": { + "External id": 4681820,"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": 1708038710485.045, "dur": 1.206, + "args": { + "External id": 4681821,"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": 1708038710485.689, "dur": 0.483, + "args": { + "External id": 4681822,"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": 1708038710486.571, "dur": 1.612, + "args": { + "External id": 4681823,"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": 1708038710487.371, "dur": 0.737, + "args": { + "External id": 4681824,"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": 1708038710488.441, "dur": 2.491, + "args": { + "External id": 4681825,"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": 1708038710490.378, "dur": 0.476, + "args": { + "External id": 4681826,"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": 1708038710491.165, "dur": 1.432, + "args": { + "External id": 4681827,"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": 1708038710491.898, "dur": 0.630, + "args": { + "External id": 4681828,"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": 1708038710492.852, "dur": 2.374, + "args": { + "External id": 4681829,"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": 1708038710493.454, "dur": 1.691, + "args": { + "External id": 4681830,"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": 1708038710496.976, "dur": 1.620, + "args": { + "External id": 4681831,"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": 1708038710497.943, "dur": 0.583, + "args": { + "External id": 4681832,"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": 1708038710498.861, "dur": 1.398, + "args": { + "External id": 4681833,"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": 1708038710499.530, "dur": 0.654, + "args": { + "External id": 4681834,"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": 1708038710500.491, "dur": 3.099, + "args": { + "External id": 4681835,"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": 1708038710503.045, "dur": 0.477, + "args": { + "External id": 4681836,"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": 1708038710503.874, "dur": 1.074, + "args": { + "External id": 4681837,"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": 1708038710504.463, "dur": 0.418, + "args": { + "External id": 4681838,"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": 1708038710505.268, "dur": 1.710, + "args": { + "External id": 4681839,"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": 1708038710506.156, "dur": 0.749, + "args": { + "External id": 4681840,"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": 1708038710507.238, "dur": 2.186, + "args": { + "External id": 4681841,"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": 1708038710508.947, "dur": 0.410, + "args": { + "External id": 4681842,"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": 1708038710509.656, "dur": 1.445, + "args": { + "External id": 4681843,"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": 1708038710510.438, "dur": 0.594, + "args": { + "External id": 4681844,"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": 1708038710511.365, "dur": 2.439, + "args": { + "External id": 4681845,"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": 1708038710511.974, "dur": 1.755, + "args": { + "External id": 4681846,"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": 1708038710515.348, "dur": 1.428, + "args": { + "External id": 4681847,"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": 1708038710516.263, "dur": 0.446, + "args": { + "External id": 4681848,"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": 1708038710517.048, "dur": 1.793, + "args": { + "External id": 4681849,"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": 1708038710517.793, "dur": 0.979, + "args": { + "External id": 4681850,"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": 1708038710519.179, "dur": 2.834, + "args": { + "External id": 4681851,"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": 1708038710521.376, "dur": 0.567, + "args": { + "External id": 4681852,"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": 1708038710522.321, "dur": 13.909, + "args": { + "External id": 4681853,"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": 1708038710534.907, "dur": 0.721, + "args": { + "External id": 4681854,"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": 1708038710537.165, "dur": 1.883, + "args": { + "External id": 4681855,"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": 1708038710538.361, "dur": 0.604, + "args": { + "External id": 4681856,"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": 1708038710539.359, "dur": 2.436, + "args": { + "External id": 4681857,"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": 1708038710541.221, "dur": 0.502, + "args": { + "External id": 4681858,"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": 1708038710542.056, "dur": 2.541, + "args": { + "External id": 4681859,"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": 1708038710544.070, "dur": 0.457, + "args": { + "External id": 4681860,"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": 1708038710544.905, "dur": 2.367, + "args": { + "External id": 4681861,"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": 1708038710545.610, "dur": 1.587, + "args": { + "External id": 4681862,"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": 1708038710548.775, "dur": 1.673, + "args": { + "External id": 4681863,"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": 1708038710549.541, "dur": 0.838, + "args": { + "External id": 4681864,"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": 1708038710550.710, "dur": 1.595, + "args": { + "External id": 4681865,"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": 1708038710551.494, "dur": 0.741, + "args": { + "External id": 4681866,"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": 1708038710552.634, "dur": 3.298, + "args": { + "External id": 4681867,"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": 1708038710555.246, "dur": 0.617, + "args": { + "External id": 4681868,"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": 1708038710556.218, "dur": 1.151, + "args": { + "External id": 4681869,"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": 1708038710556.896, "dur": 0.407, + "args": { + "External id": 4681870,"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": 1708038710557.608, "dur": 1.609, + "args": { + "External id": 4681871,"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": 1708038710558.595, "dur": 0.554, + "args": { + "External id": 4681872,"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": 1708038710559.492, "dur": 2.829, + "args": { + "External id": 4681873,"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": 1708038710561.572, "dur": 0.682, + "args": { + "External id": 4681874,"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": 1708038710562.575, "dur": 1.477, + "args": { + "External id": 4681875,"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": 1708038710563.461, "dur": 0.521, + "args": { + "External id": 4681876,"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": 1708038710564.314, "dur": 2.287, + "args": { + "External id": 4681877,"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": 1708038710564.960, "dur": 1.566, + "args": { + "External id": 4681878,"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": 1708038710568.491, "dur": 1.616, + "args": { + "External id": 4681879,"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": 1708038710569.481, "dur": 0.555, + "args": { + "External id": 4681880,"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": 1708038710570.518, "dur": 1.319, + "args": { + "External id": 4681881,"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": 1708038710571.154, "dur": 0.616, + "args": { + "External id": 4681882,"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": 1708038710572.075, "dur": 3.170, + "args": { + "External id": 4681883,"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": 1708038710574.655, "dur": 0.522, + "args": { + "External id": 4681884,"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": 1708038710575.554, "dur": 1.640, + "args": { + "External id": 4681885,"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": 1708038710576.502, "dur": 0.623, + "args": { + "External id": 4681886,"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": 1708038710577.430, "dur": 1.704, + "args": { + "External id": 4681887,"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": 1708038710578.365, "dur": 0.702, + "args": { + "External id": 4681888,"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": 1708038710579.392, "dur": 2.431, + "args": { + "External id": 4681889,"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": 1708038710581.215, "dur": 0.537, + "args": { + "External id": 4681890,"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": 1708038710582.067, "dur": 1.451, + "args": { + "External id": 4681891,"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": 1708038710582.994, "dur": 0.454, + "args": { + "External id": 4681892,"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": 1708038710583.884, "dur": 2.508, + "args": { + "External id": 4681893,"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": 1708038710584.558, "dur": 1.660, + "args": { + "External id": 4681894,"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": 1708038710588.339, "dur": 2.047, + "args": { + "External id": 4681895,"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": 1708038710589.327, "dur": 0.991, + "args": { + "External id": 4681896,"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": 1708038710590.648, "dur": 1.486, + "args": { + "External id": 4681897,"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": 1708038710591.417, "dur": 0.647, + "args": { + "External id": 4681898,"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": 1708038710592.372, "dur": 3.274, + "args": { + "External id": 4681899,"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": 1708038710595.017, "dur": 0.559, + "args": { + "External id": 4681900,"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": 1708038710595.926, "dur": 1.300, + "args": { + "External id": 4681901,"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": 1708038710596.752, "dur": 0.401, + "args": { + "External id": 4681902,"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": 1708038710597.463, "dur": 1.641, + "args": { + "External id": 4681903,"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": 1708038710598.376, "dur": 0.657, + "args": { + "External id": 4681904,"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": 1708038710599.362, "dur": 2.404, + "args": { + "External id": 4681905,"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": 1708038710601.183, "dur": 0.517, + "args": { + "External id": 4681906,"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": 1708038710602.003, "dur": 1.506, + "args": { + "External id": 4681907,"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": 1708038710602.945, "dur": 0.498, + "args": { + "External id": 4681908,"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": 1708038710603.764, "dur": 2.525, + "args": { + "External id": 4681909,"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": 1708038710604.558, "dur": 1.656, + "args": { + "External id": 4681910,"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": 1708038710608.444, "dur": 1.365, + "args": { + "External id": 4681911,"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": 1708038710609.216, "dur": 0.524, + "args": { + "External id": 4681912,"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": 1708038710610.066, "dur": 1.404, + "args": { + "External id": 4681913,"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": 1708038710610.725, "dur": 0.676, + "args": { + "External id": 4681914,"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": 1708038710611.798, "dur": 2.950, + "args": { + "External id": 4681915,"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": 1708038710614.116, "dur": 0.563, + "args": { + "External id": 4681916,"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": 1708038710615.035, "dur": 1.302, + "args": { + "External id": 4681917,"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": 1708038710615.833, "dur": 0.433, + "args": { + "External id": 4681918,"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": 1708038710616.568, "dur": 1.604, + "args": { + "External id": 4681919,"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": 1708038710617.464, "dur": 0.640, + "args": { + "External id": 4681920,"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": 1708038710618.541, "dur": 2.477, + "args": { + "External id": 4681921,"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": 1708038710620.403, "dur": 0.546, + "args": { + "External id": 4681922,"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": 1708038710621.276, "dur": 1.541, + "args": { + "External id": 4681923,"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": 1708038710622.303, "dur": 0.444, + "args": { + "External id": 4681924,"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": 1708038710623.097, "dur": 2.530, + "args": { + "External id": 4681925,"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": 1708038710623.756, "dur": 1.795, + "args": { + "External id": 4681926,"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": 1708038710627.316, "dur": 1.722, + "args": { + "External id": 4681927,"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": 1708038710628.462, "dur": 0.507, + "args": { + "External id": 4681928,"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": 1708038710629.395, "dur": 1.247, + "args": { + "External id": 4681929,"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": 1708038710630.169, "dur": 0.404, + "args": { + "External id": 4681930,"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": 1708038710630.987, "dur": 2.786, + "args": { + "External id": 4681931,"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": 1708038710633.276, "dur": 0.425, + "args": { + "External id": 4681932,"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": 1708038710634.056, "dur": 1.481, + "args": { + "External id": 4681933,"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": 1708038710634.754, "dur": 0.713, + "args": { + "External id": 4681934,"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": 1708038710635.771, "dur": 1.732, + "args": { + "External id": 4681935,"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": 1708038710636.779, "dur": 0.657, + "args": { + "External id": 4681936,"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": 1708038710637.793, "dur": 2.578, + "args": { + "External id": 4681937,"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": 1708038710639.800, "dur": 0.509, + "args": { + "External id": 4681938,"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": 1708038710640.607, "dur": 1.364, + "args": { + "External id": 4681939,"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": 1708038710641.297, "dur": 0.607, + "args": { + "External id": 4681940,"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": 1708038710642.248, "dur": 2.643, + "args": { + "External id": 4681941,"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": 1708038710643.031, "dur": 1.782, + "args": { + "External id": 4681942,"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": 1708038710646.408, "dur": 1.803, + "args": { + "External id": 4681943,"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": 1708038710647.530, "dur": 0.611, + "args": { + "External id": 4681944,"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": 1708038710648.468, "dur": 1.216, + "args": { + "External id": 4681945,"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": 1708038710649.047, "dur": 0.569, + "args": { + "External id": 4681946,"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": 1708038710649.923, "dur": 2.950, + "args": { + "External id": 4681947,"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": 1708038710652.374, "dur": 0.429, + "args": { + "External id": 4681948,"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": 1708038710653.153, "dur": 1.322, + "args": { + "External id": 4681949,"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": 1708038710653.990, "dur": 0.417, + "args": { + "External id": 4681950,"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": 1708038710654.799, "dur": 1.805, + "args": { + "External id": 4681951,"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": 1708038710656.022, "dur": 0.511, + "args": { + "External id": 4681952,"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": 1708038710656.993, "dur": 3.148, + "args": { + "External id": 4681953,"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": 1708038710659.596, "dur": 0.477, + "args": { + "External id": 4681954,"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": 1708038710660.411, "dur": 1.379, + "args": { + "External id": 4681955,"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": 1708038710661.274, "dur": 0.449, + "args": { + "External id": 4681956,"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": 1708038710662.047, "dur": 2.493, + "args": { + "External id": 4681957,"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": 1708038710662.747, "dur": 1.722, + "args": { + "External id": 4681958,"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": 1708038710666.104, "dur": 1.511, + "args": { + "External id": 4681959,"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": 1708038710667.096, "dur": 0.448, + "args": { + "External id": 4681960,"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": 1708038710667.889, "dur": 1.504, + "args": { + "External id": 4681961,"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": 1708038710668.707, "dur": 0.616, + "args": { + "External id": 4681962,"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": 1708038710669.627, "dur": 3.540, + "args": { + "External id": 4681963,"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": 1708038710672.545, "dur": 0.550, + "args": { + "External id": 4681964,"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": 1708038710673.449, "dur": 1.218, + "args": { + "External id": 4681965,"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": 1708038710674.093, "dur": 0.502, + "args": { + "External id": 4681966,"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": 1708038710674.936, "dur": 1.475, + "args": { + "External id": 4681967,"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": 1708038710675.804, "dur": 0.533, + "args": { + "External id": 4681968,"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": 1708038710676.673, "dur": 2.500, + "args": { + "External id": 4681969,"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": 1708038710678.454, "dur": 0.652, + "args": { + "External id": 4681970,"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": 1708038710679.408, "dur": 1.354, + "args": { + "External id": 4681971,"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": 1708038710680.131, "dur": 0.560, + "args": { + "External id": 4681972,"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": 1708038710681.020, "dur": 2.898, + "args": { + "External id": 4681973,"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": 1708038710681.580, "dur": 2.259, + "args": { + "External id": 4681974,"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": 1708038710685.497, "dur": 1.516, + "args": { + "External id": 4681975,"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": 1708038710686.407, "dur": 0.536, + "args": { + "External id": 4681976,"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": 1708038710687.280, "dur": 1.483, + "args": { + "External id": 4681977,"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": 1708038710688.057, "dur": 0.634, + "args": { + "External id": 4681978,"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": 1708038710689.188, "dur": 2.879, + "args": { + "External id": 4681979,"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": 1708038710691.574, "dur": 0.426, + "args": { + "External id": 4681980,"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": 1708038710692.362, "dur": 1.126, + "args": { + "External id": 4681981,"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": 1708038710692.958, "dur": 0.463, + "args": { + "External id": 4681982,"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": 1708038710693.728, "dur": 1.620, + "args": { + "External id": 4681983,"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": 1708038710694.664, "dur": 0.613, + "args": { + "External id": 4681984,"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": 1708038710695.624, "dur": 2.920, + "args": { + "External id": 4681985,"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": 1708038710698.072, "dur": 0.403, + "args": { + "External id": 4681986,"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": 1708038710698.779, "dur": 1.549, + "args": { + "External id": 4681987,"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": 1708038710699.718, "dur": 0.537, + "args": { + "External id": 4681988,"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": 1708038710700.774, "dur": 2.188, + "args": { + "External id": 4681989,"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": 1708038710701.429, "dur": 1.369, + "args": { + "External id": 4681990,"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": 1708038710705.105, "dur": 1.525, + "args": { + "External id": 4681991,"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": 1708038710706.028, "dur": 0.534, + "args": { + "External id": 4681992,"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": 1708038710706.913, "dur": 1.320, + "args": { + "External id": 4681993,"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": 1708038710707.541, "dur": 0.622, + "args": { + "External id": 4681994,"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": 1708038710708.469, "dur": 3.042, + "args": { + "External id": 4681995,"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": 1708038710710.916, "dur": 0.524, + "args": { + "External id": 4681996,"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": 1708038710711.793, "dur": 1.364, + "args": { + "External id": 4681997,"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": 1708038710712.560, "dur": 0.530, + "args": { + "External id": 4681998,"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": 1708038710713.393, "dur": 1.655, + "args": { + "External id": 4681999,"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": 1708038710714.337, "dur": 0.641, + "args": { + "External id": 4682000,"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": 1708038710715.377, "dur": 2.380, + "args": { + "External id": 4682001,"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": 1708038710717.246, "dur": 0.439, + "args": { + "External id": 4682002,"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": 1708038710718.010, "dur": 1.780, + "args": { + "External id": 4682003,"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": 1708038710718.948, "dur": 0.771, + "args": { + "External id": 4682004,"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": 1708038710720.053, "dur": 2.724, + "args": { + "External id": 4682005,"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": 1708038710720.900, "dur": 1.803, + "args": { + "External id": 4682006,"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": 1708038710724.180, "dur": 1.402, + "args": { + "External id": 4682007,"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": 1708038710725.062, "dur": 0.449, + "args": { + "External id": 4682008,"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": 1708038710725.839, "dur": 1.160, + "args": { + "External id": 4682009,"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": 1708038710726.469, "dur": 0.463, + "args": { + "External id": 4682010,"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": 1708038710727.311, "dur": 3.501, + "args": { + "External id": 4682011,"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": 1708038710730.261, "dur": 0.478, + "args": { + "External id": 4682012,"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": 1708038710731.102, "dur": 1.390, + "args": { + "External id": 4682013,"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": 1708038710731.989, "dur": 0.435, + "args": { + "External id": 4682014,"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": 1708038710732.771, "dur": 1.512, + "args": { + "External id": 4682015,"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": 1708038710733.661, "dur": 0.552, + "args": { + "External id": 4682016,"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": 1708038710734.574, "dur": 2.775, + "args": { + "External id": 4682017,"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": 1708038710736.864, "dur": 0.414, + "args": { + "External id": 4682018,"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": 1708038710737.661, "dur": 1.414, + "args": { + "External id": 4682019,"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": 1708038710738.541, "dur": 0.468, + "args": { + "External id": 4682020,"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": 1708038710739.333, "dur": 2.645, + "args": { + "External id": 4682021,"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": 1708038710740.012, "dur": 1.692, + "args": { + "External id": 4682022,"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": 1708038710743.719, "dur": 1.641, + "args": { + "External id": 4682023,"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": 1708038710744.758, "dur": 0.535, + "args": { + "External id": 4682024,"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": 1708038710745.727, "dur": 1.471, + "args": { + "External id": 4682025,"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": 1708038710746.523, "dur": 0.605, + "args": { + "External id": 4682026,"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": 1708038710747.446, "dur": 2.731, + "args": { + "External id": 4682027,"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": 1708038710749.636, "dur": 0.472, + "args": { + "External id": 4682028,"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": 1708038710750.458, "dur": 1.306, + "args": { + "External id": 4682029,"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": 1708038710751.179, "dur": 0.516, + "args": { + "External id": 4682030,"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": 1708038710751.998, "dur": 1.704, + "args": { + "External id": 4682031,"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": 1708038710752.946, "dur": 0.687, + "args": { + "External id": 4682032,"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": 1708038710753.964, "dur": 2.380, + "args": { + "External id": 4682033,"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": 1708038710755.765, "dur": 0.510, + "args": { + "External id": 4682034,"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": 1708038710756.603, "dur": 1.850, + "args": { + "External id": 4682035,"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": 1708038710757.881, "dur": 0.503, + "args": { + "External id": 4682036,"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": 1708038710758.744, "dur": 2.900, + "args": { + "External id": 4682037,"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": 1708038710759.566, "dur": 1.923, + "args": { + "External id": 4682038,"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": 1708038710763.143, "dur": 1.614, + "args": { + "External id": 4682039,"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": 1708038710764.177, "dur": 0.510, + "args": { + "External id": 4682040,"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": 1708038710765.157, "dur": 1.528, + "args": { + "External id": 4682041,"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": 1708038710765.909, "dur": 0.708, + "args": { + "External id": 4682042,"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": 1708038710766.919, "dur": 3.204, + "args": { + "External id": 4682043,"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": 1708038710769.253, "dur": 0.800, + "args": { + "External id": 4682044,"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": 1708038710770.410, "dur": 1.440, + "args": { + "External id": 4682045,"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": 1708038710771.172, "dur": 0.611, + "args": { + "External id": 4682046,"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": 1708038710772.089, "dur": 1.828, + "args": { + "External id": 4682047,"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": 1708038710773.116, "dur": 0.737, + "args": { + "External id": 4682048,"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": 1708038710774.197, "dur": 2.770, + "args": { + "External id": 4682049,"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": 1708038710776.261, "dur": 0.638, + "args": { + "External id": 4682050,"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": 1708038710777.286, "dur": 1.561, + "args": { + "External id": 4682051,"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": 1708038710778.067, "dur": 0.715, + "args": { + "External id": 4682052,"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": 1708038710779.104, "dur": 2.251, + "args": { + "External id": 4682053,"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": 1708038710779.848, "dur": 1.432, + "args": { + "External id": 4682054,"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": 1708038710782.974, "dur": 1.682, + "args": { + "External id": 4682055,"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": 1708038710784.006, "dur": 0.574, + "args": { + "External id": 4682056,"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": 1708038710785.029, "dur": 1.314, + "args": { + "External id": 4682057,"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": 1708038710785.809, "dur": 0.465, + "args": { + "External id": 4682058,"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": 1708038710786.575, "dur": 2.894, + "args": { + "External id": 4682059,"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": 1708038710788.981, "dur": 0.421, + "args": { + "External id": 4682060,"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": 1708038710789.749, "dur": 1.421, + "args": { + "External id": 4682061,"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": 1708038710790.576, "dur": 0.526, + "args": { + "External id": 4682062,"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": 1708038710791.402, "dur": 1.680, + "args": { + "External id": 4682063,"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": 1708038710792.229, "dur": 0.787, + "args": { + "External id": 4682064,"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": 1708038710793.375, "dur": 2.445, + "args": { + "External id": 4682065,"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": 1708038710795.194, "dur": 0.557, + "args": { + "External id": 4682066,"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": 1708038710796.134, "dur": 1.771, + "args": { + "External id": 4682067,"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": 1708038710797.320, "dur": 0.515, + "args": { + "External id": 4682068,"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": 1708038710798.171, "dur": 2.731, + "args": { + "External id": 4682069,"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": 1708038710798.939, "dur": 1.896, + "args": { + "External id": 4682070,"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": 1708038710802.731, "dur": 1.537, + "args": { + "External id": 4682071,"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": 1708038710803.610, "dur": 0.592, + "args": { + "External id": 4682072,"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": 1708038710804.570, "dur": 1.305, + "args": { + "External id": 4682073,"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": 1708038710805.195, "dur": 0.612, + "args": { + "External id": 4682074,"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": 1708038710806.112, "dur": 3.225, + "args": { + "External id": 4682075,"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": 1708038710808.746, "dur": 0.522, + "args": { + "External id": 4682076,"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": 1708038710809.615, "dur": 1.221, + "args": { + "External id": 4682077,"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": 1708038710810.266, "dur": 0.502, + "args": { + "External id": 4682078,"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": 1708038710811.406, "dur": 1.582, + "args": { + "External id": 4682079,"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": 1708038710812.386, "dur": 0.533, + "args": { + "External id": 4682080,"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": 1708038710813.328, "dur": 2.422, + "args": { + "External id": 4682081,"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": 1708038710815.148, "dur": 0.417, + "args": { + "External id": 4682082,"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": 1708038710815.993, "dur": 1.740, + "args": { + "External id": 4682083,"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": 1708038710817.054, "dur": 0.608, + "args": { + "External id": 4682084,"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": 1708038710817.997, "dur": 2.312, + "args": { + "External id": 4682085,"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": 1708038710818.602, "dur": 1.544, + "args": { + "External id": 4682086,"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": 1708038710821.952, "dur": 1.460, + "args": { + "External id": 4682087,"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": 1708038710822.714, "dur": 0.627, + "args": { + "External id": 4682088,"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": 1708038710823.785, "dur": 1.296, + "args": { + "External id": 4682089,"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": 1708038710824.543, "dur": 0.473, + "args": { + "External id": 4682090,"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": 1708038710825.409, "dur": 2.982, + "args": { + "External id": 4682091,"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": 1708038710827.947, "dur": 0.375, + "args": { + "External id": 4682092,"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": 1708038710828.672, "dur": 1.228, + "args": { + "External id": 4682093,"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": 1708038710829.228, "dur": 0.605, + "args": { + "External id": 4682094,"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": 1708038710830.134, "dur": 1.829, + "args": { + "External id": 4682095,"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": 1708038710831.010, "dur": 0.885, + "args": { + "External id": 4682096,"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": 1708038710832.233, "dur": 2.834, + "args": { + "External id": 4682097,"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": 1708038710834.147, "dur": 0.852, + "args": { + "External id": 4682098,"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": 1708038710835.313, "dur": 1.836, + "args": { + "External id": 4682099,"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": 1708038710836.263, "dur": 0.818, + "args": { + "External id": 4682100,"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": 1708038710837.466, "dur": 2.916, + "args": { + "External id": 4682101,"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": 1708038710838.179, "dur": 2.134, + "args": { + "External id": 4682102,"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": 1708038710842.583, "dur": 1.430, + "args": { + "External id": 4682103,"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": 1708038710843.450, "dur": 0.490, + "args": { + "External id": 4682104,"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": 1708038710844.305, "dur": 1.479, + "args": { + "External id": 4682105,"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": 1708038710845.067, "dur": 0.649, + "args": { + "External id": 4682106,"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": 1708038710846.114, "dur": 2.899, + "args": { + "External id": 4682107,"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": 1708038710848.410, "dur": 0.533, + "args": { + "External id": 4682108,"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": 1708038710849.349, "dur": 1.349, + "args": { + "External id": 4682109,"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": 1708038710850.141, "dur": 0.490, + "args": { + "External id": 4682110,"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": 1708038710850.939, "dur": 1.353, + "args": { + "External id": 4682111,"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": 1708038710851.701, "dur": 0.525, + "args": { + "External id": 4682112,"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": 1708038710852.612, "dur": 2.389, + "args": { + "External id": 4682113,"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": 1708038710854.479, "dur": 0.453, + "args": { + "External id": 4682114,"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": 1708038710855.232, "dur": 2.829, + "args": { + "External id": 4682115,"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": 1708038710857.561, "dur": 0.433, + "args": { + "External id": 4682116,"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": 1708038710879.686, "dur": 163.916, + "args": { + "External id": 4682117,"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": 1708038711147.732, "dur": 129.639, + "args": { + "External id": 4682118,"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": 1708038711211.740, "dur": 46.294, + "args": { + "External id": 4682119,"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": 1708038711226.573, "dur": 1.577, + "args": { + "External id": 4682120,"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": 1708038711676.354, "dur": 973.756, + "args": { + "External id": 4682121,"Sequence number": 46526668, "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": 1708038711728.846, "dur": 121.839, + "args": { + "External id": 4682122,"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": 1708038711734.204, "dur": 1.594, + "args": { + "External id": 4682123,"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": 1708038711802.555, "dur": 0.823, + "args": { + "External id": 4682124,"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": 1708038711876.884, "dur": 457.456, + "args": { + "External id": 4682125,"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": 1708038711882.008, "dur": 45.532, + "args": { + "External id": 4682126,"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": 1708038711885.634, "dur": 8.820, + "args": { + "External id": 4682127,"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": 1708038711889.779, "dur": 3.965, + "args": { + "External id": 4682128,"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": 1708038711896.329, "dur": 30.676, + "args": { + "External id": 4682129,"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": 1708038711935.731, "dur": 395.497, + "args": { + "External id": 4682130,"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": 1708038711966.953, "dur": 357.607, + "args": { + "External id": 4682131,"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": 1708038712016.507, "dur": 296.899, + "args": { + "External id": 4682132,"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": 1708038712394.887, "dur": 218.051, + "args": { + "External id": 4682133,"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": 1708038712480.613, "dur": 30.938, + "args": { + "External id": 4682134,"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": 1708038712499.295, "dur": 4.027, + "args": { + "External id": 4682135,"Record function id": 0, "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": 1708038712563.215, "dur": 42.950, + "args": { + "External id": 4682136,"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": 1708038712565.738, "dur": 1.376, + "args": { + "External id": 4682137,"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": 1708038712568.480, "dur": 0.720, + "args": { + "External id": 4682138,"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": 1708038712667.139, "dur": 20.756, + "args": { + "External id": 4682139,"Sequence number": 46526669, "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": 1708038712676.652, "dur": 8.272, + "args": { + "External id": 4682140,"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": 1708038712679.141, "dur": 5.598, + "args": { + "External id": 4682141,"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": 1708038713118.228, "dur": 39.926, + "args": { + "External id": 4682142,"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": 1708038713169.185, "dur": 19.966, + "args": { + "External id": 4682143,"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": 1708038713195.829, "dur": 21.362, + "args": { + "External id": 4682144,"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": 1708038713230.072, "dur": 23.745, + "args": { + "External id": 4682145,"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": 1708038713233.034, "dur": 0.643, + "args": { + "External id": 4682146,"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": 1708038713272.951, "dur": 0.700, + "args": { + "External id": 4682147,"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": 1708038713401.111, "dur": 744.963, + "args": { + "External id": 4682148,"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": 1708038713919.555, "dur": 192.760, + "args": { + "External id": 4682149,"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": 1708038714195.810, "dur": 30.465, + "args": { + "External id": 4682150,"Sequence number": 46526670, "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": 1708038714200.051, "dur": 25.767, + "args": { + "External id": 4682151,"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": 1708038714230.602, "dur": 787.328, + "args": { + "External id": 4682152,"Sequence number": 46526670, "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": 1708038714232.672, "dur": 785.044, + "args": { + "External id": 4682153,"Sequence number": 46526670, "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": 1708038714234.335, "dur": 782.783, + "args": { + "External id": 4682154,"Sequence number": 46526670, "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": 1708038715024.959, "dur": 63.547, + "args": { + "External id": 4682155,"Sequence number": 46526670, "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": 1708038715028.938, "dur": 35.074, + "args": { + "External id": 4682156,"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": 1708038715035.816, "dur": 3.128, + "args": { + "External id": 4682157,"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": 1708038715040.809, "dur": 22.897, + "args": { + "External id": 4682158,"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": 1708038715046.263, "dur": 2.826, + "args": { + "External id": 4682159,"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": 1708038715066.060, "dur": 21.592, + "args": { + "External id": 4682160,"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": 1708038715091.087, "dur": 38.426, + "args": { + "External id": 4682161,"Sequence number": 46526670, "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": 1708038715094.423, "dur": 34.902, + "args": { + "External id": 4682162,"Sequence number": 46526670, "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": 1708038715095.507, "dur": 33.417, + "args": { + "External id": 4682163,"Sequence number": 46526670, "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": 1708038715165.568, "dur": 5804.951, + "args": { + "External id": 4682164,"Record function id": 0, "Ev Idx": 11339 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#AdamW.step", "pid": 1336753, "tid": 1336753, + "ts": 1708038715195.487, "dur": 5754.541, + "args": { + "External id": 4682165,"Record function id": 0, "Ev Idx": 11340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_add_", "pid": 1336753, "tid": 1336753, + "ts": 1708038716405.748, "dur": 363.248, + "args": { + "External id": 4682166,"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": 1708038716426.067, "dur": 1.103, + "args": { + "External id": 4682167,"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": 1708038716428.239, "dur": 0.129, + "args": { + "External id": 4682168,"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": 1708038716429.100, "dur": 0.057, + "args": { + "External id": 4682169,"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": 1708038716429.647, "dur": 0.048, + "args": { + "External id": 4682170,"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": 1708038716430.358, "dur": 0.095, + "args": { + "External id": 4682171,"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": 1708038716430.893, "dur": 0.302, + "args": { + "External id": 4682172,"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": 1708038716431.708, "dur": 0.066, + "args": { + "External id": 4682173,"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": 1708038716432.157, "dur": 0.074, + "args": { + "External id": 4682174,"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": 1708038716432.669, "dur": 0.082, + "args": { + "External id": 4682175,"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": 1708038716433.207, "dur": 0.066, + "args": { + "External id": 4682176,"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": 1708038716433.669, "dur": 0.090, + "args": { + "External id": 4682177,"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": 1708038716434.193, "dur": 0.286, + "args": { + "External id": 4682178,"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": 1708038716434.885, "dur": 0.043, + "args": { + "External id": 4682179,"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": 1708038716435.371, "dur": 0.067, + "args": { + "External id": 4682180,"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": 1708038716435.794, "dur": 0.066, + "args": { + "External id": 4682181,"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": 1708038716436.435, "dur": 0.068, + "args": { + "External id": 4682182,"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": 1708038716436.906, "dur": 0.059, + "args": { + "External id": 4682183,"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": 1708038716437.352, "dur": 0.059, + "args": { + "External id": 4682184,"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": 1708038716437.888, "dur": 0.058, + "args": { + "External id": 4682185,"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": 1708038716438.415, "dur": 0.051, + "args": { + "External id": 4682186,"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": 1708038716439.002, "dur": 0.060, + "args": { + "External id": 4682187,"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": 1708038716439.609, "dur": 0.071, + "args": { + "External id": 4682188,"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": 1708038716440.086, "dur": 0.067, + "args": { + "External id": 4682189,"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": 1708038716440.577, "dur": 0.062, + "args": { + "External id": 4682190,"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": 1708038716440.983, "dur": 0.067, + "args": { + "External id": 4682191,"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": 1708038716441.331, "dur": 0.068, + "args": { + "External id": 4682192,"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": 1708038716441.814, "dur": 0.274, + "args": { + "External id": 4682193,"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": 1708038716442.499, "dur": 0.320, + "args": { + "External id": 4682194,"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": 1708038716443.155, "dur": 0.287, + "args": { + "External id": 4682195,"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": 1708038716443.898, "dur": 0.095, + "args": { + "External id": 4682196,"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": 1708038716444.434, "dur": 0.055, + "args": { + "External id": 4682197,"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": 1708038716445.085, "dur": 0.260, + "args": { + "External id": 4682198,"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": 1708038716445.810, "dur": 0.256, + "args": { + "External id": 4682199,"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": 1708038716446.489, "dur": 0.076, + "args": { + "External id": 4682200,"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": 1708038716446.902, "dur": 0.096, + "args": { + "External id": 4682201,"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": 1708038716447.392, "dur": 0.076, + "args": { + "External id": 4682202,"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": 1708038716448.106, "dur": 0.293, + "args": { + "External id": 4682203,"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": 1708038716448.789, "dur": 0.272, + "args": { + "External id": 4682204,"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": 1708038716449.512, "dur": 0.065, + "args": { + "External id": 4682205,"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": 1708038716450.119, "dur": 0.067, + "args": { + "External id": 4682206,"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": 1708038716450.626, "dur": 0.066, + "args": { + "External id": 4682207,"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": 1708038716451.043, "dur": 0.066, + "args": { + "External id": 4682208,"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": 1708038716451.692, "dur": 0.060, + "args": { + "External id": 4682209,"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": 1708038716452.106, "dur": 0.065, + "args": { + "External id": 4682210,"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": 1708038716452.501, "dur": 0.061, + "args": { + "External id": 4682211,"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": 1708038716452.982, "dur": 0.057, + "args": { + "External id": 4682212,"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": 1708038716453.373, "dur": 0.068, + "args": { + "External id": 4682213,"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": 1708038716453.847, "dur": 0.068, + "args": { + "External id": 4682214,"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": 1708038716454.302, "dur": 0.065, + "args": { + "External id": 4682215,"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": 1708038716454.694, "dur": 0.066, + "args": { + "External id": 4682216,"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": 1708038716455.117, "dur": 0.065, + "args": { + "External id": 4682217,"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": 1708038716455.542, "dur": 0.065, + "args": { + "External id": 4682218,"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": 1708038716456.048, "dur": 0.054, + "args": { + "External id": 4682219,"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": 1708038716456.536, "dur": 0.065, + "args": { + "External id": 4682220,"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": 1708038716457.034, "dur": 0.063, + "args": { + "External id": 4682221,"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": 1708038716457.719, "dur": 0.063, + "args": { + "External id": 4682222,"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": 1708038716458.109, "dur": 0.066, + "args": { + "External id": 4682223,"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": 1708038716458.542, "dur": 0.064, + "args": { + "External id": 4682224,"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": 1708038716459.478, "dur": 0.290, + "args": { + "External id": 4682225,"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": 1708038716460.071, "dur": 0.282, + "args": { + "External id": 4682226,"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": 1708038716460.703, "dur": 0.069, + "args": { + "External id": 4682227,"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": 1708038716461.110, "dur": 0.097, + "args": { + "External id": 4682228,"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": 1708038716461.592, "dur": 0.065, + "args": { + "External id": 4682229,"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": 1708038716462.448, "dur": 0.065, + "args": { + "External id": 4682230,"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": 1708038716462.961, "dur": 0.089, + "args": { + "External id": 4682231,"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": 1708038716463.492, "dur": 0.090, + "args": { + "External id": 4682232,"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": 1708038716463.872, "dur": 0.070, + "args": { + "External id": 4682233,"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": 1708038716464.217, "dur": 0.065, + "args": { + "External id": 4682234,"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": 1708038716464.671, "dur": 0.066, + "args": { + "External id": 4682235,"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": 1708038716465.079, "dur": 0.071, + "args": { + "External id": 4682236,"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": 1708038716465.601, "dur": 0.064, + "args": { + "External id": 4682237,"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": 1708038716466.016, "dur": 0.061, + "args": { + "External id": 4682238,"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": 1708038716466.447, "dur": 0.061, + "args": { + "External id": 4682239,"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": 1708038716466.927, "dur": 0.065, + "args": { + "External id": 4682240,"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": 1708038716555.864, "dur": 0.542, + "args": { + "External id": 4682241,"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": 1708038716558.526, "dur": 0.077, + "args": { + "External id": 4682242,"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": 1708038716559.019, "dur": 0.066, + "args": { + "External id": 4682243,"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": 1708038716559.469, "dur": 0.045, + "args": { + "External id": 4682244,"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": 1708038716559.951, "dur": 0.057, + "args": { + "External id": 4682245,"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": 1708038716560.665, "dur": 0.057, + "args": { + "External id": 4682246,"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": 1708038716561.109, "dur": 0.055, + "args": { + "External id": 4682247,"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": 1708038716561.704, "dur": 0.062, + "args": { + "External id": 4682248,"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": 1708038716562.260, "dur": 0.057, + "args": { + "External id": 4682249,"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": 1708038716562.720, "dur": 0.068, + "args": { + "External id": 4682250,"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": 1708038716563.216, "dur": 0.068, + "args": { + "External id": 4682251,"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": 1708038716563.740, "dur": 0.066, + "args": { + "External id": 4682252,"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": 1708038716564.283, "dur": 0.055, + "args": { + "External id": 4682253,"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": 1708038716564.752, "dur": 0.064, + "args": { + "External id": 4682254,"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": 1708038716565.177, "dur": 0.069, + "args": { + "External id": 4682255,"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": 1708038716565.581, "dur": 0.061, + "args": { + "External id": 4682256,"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": 1708038716566.051, "dur": 0.068, + "args": { + "External id": 4682257,"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": 1708038716566.652, "dur": 0.058, + "args": { + "External id": 4682258,"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": 1708038716567.076, "dur": 0.065, + "args": { + "External id": 4682259,"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": 1708038716567.619, "dur": 0.070, + "args": { + "External id": 4682260,"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": 1708038716568.010, "dur": 0.069, + "args": { + "External id": 4682261,"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": 1708038716568.428, "dur": 0.067, + "args": { + "External id": 4682262,"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": 1708038716568.804, "dur": 0.063, + "args": { + "External id": 4682263,"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": 1708038716569.192, "dur": 0.062, + "args": { + "External id": 4682264,"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": 1708038716569.603, "dur": 0.069, + "args": { + "External id": 4682265,"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": 1708038716570.139, "dur": 0.064, + "args": { + "External id": 4682266,"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": 1708038716570.771, "dur": 0.074, + "args": { + "External id": 4682267,"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": 1708038716571.241, "dur": 0.065, + "args": { + "External id": 4682268,"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": 1708038716571.742, "dur": 0.053, + "args": { + "External id": 4682269,"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": 1708038716572.126, "dur": 0.070, + "args": { + "External id": 4682270,"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": 1708038716572.682, "dur": 0.059, + "args": { + "External id": 4682271,"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": 1708038716573.128, "dur": 0.066, + "args": { + "External id": 4682272,"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": 1708038716573.596, "dur": 0.069, + "args": { + "External id": 4682273,"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": 1708038716574.043, "dur": 0.049, + "args": { + "External id": 4682274,"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": 1708038716574.476, "dur": 0.057, + "args": { + "External id": 4682275,"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": 1708038716574.864, "dur": 0.068, + "args": { + "External id": 4682276,"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": 1708038716575.291, "dur": 0.062, + "args": { + "External id": 4682277,"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": 1708038716575.736, "dur": 0.067, + "args": { + "External id": 4682278,"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": 1708038716576.251, "dur": 0.064, + "args": { + "External id": 4682279,"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": 1708038716576.726, "dur": 0.065, + "args": { + "External id": 4682280,"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": 1708038716577.147, "dur": 0.065, + "args": { + "External id": 4682281,"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": 1708038716577.518, "dur": 0.064, + "args": { + "External id": 4682282,"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": 1708038716578.193, "dur": 0.069, + "args": { + "External id": 4682283,"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": 1708038716578.622, "dur": 0.063, + "args": { + "External id": 4682284,"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": 1708038716578.997, "dur": 0.053, + "args": { + "External id": 4682285,"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": 1708038716579.425, "dur": 0.063, + "args": { + "External id": 4682286,"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": 1708038716579.832, "dur": 0.066, + "args": { + "External id": 4682287,"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": 1708038716580.509, "dur": 0.054, + "args": { + "External id": 4682288,"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": 1708038716580.916, "dur": 0.065, + "args": { + "External id": 4682289,"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": 1708038716581.386, "dur": 0.068, + "args": { + "External id": 4682290,"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": 1708038716581.803, "dur": 0.069, + "args": { + "External id": 4682291,"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": 1708038716582.294, "dur": 0.069, + "args": { + "External id": 4682292,"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": 1708038716582.652, "dur": 0.068, + "args": { + "External id": 4682293,"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": 1708038716609.382, "dur": 0.196, + "args": { + "External id": 4682294,"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": 1708038716611.174, "dur": 0.064, + "args": { + "External id": 4682295,"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": 1708038716611.774, "dur": 0.046, + "args": { + "External id": 4682296,"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": 1708038716612.198, "dur": 0.053, + "args": { + "External id": 4682297,"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": 1708038716612.712, "dur": 0.045, + "args": { + "External id": 4682298,"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": 1708038716613.362, "dur": 0.068, + "args": { + "External id": 4682299,"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": 1708038716613.841, "dur": 0.066, + "args": { + "External id": 4682300,"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": 1708038716614.292, "dur": 0.058, + "args": { + "External id": 4682301,"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": 1708038716614.861, "dur": 0.097, + "args": { + "External id": 4682302,"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": 1708038716615.396, "dur": 0.061, + "args": { + "External id": 4682303,"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": 1708038716616.009, "dur": 0.067, + "args": { + "External id": 4682304,"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": 1708038716616.456, "dur": 0.066, + "args": { + "External id": 4682305,"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": 1708038716616.896, "dur": 0.065, + "args": { + "External id": 4682306,"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": 1708038716617.271, "dur": 0.067, + "args": { + "External id": 4682307,"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": 1708038716617.715, "dur": 0.066, + "args": { + "External id": 4682308,"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": 1708038716618.192, "dur": 0.055, + "args": { + "External id": 4682309,"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": 1708038716618.581, "dur": 0.068, + "args": { + "External id": 4682310,"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": 1708038716619.040, "dur": 0.069, + "args": { + "External id": 4682311,"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": 1708038716619.487, "dur": 0.063, + "args": { + "External id": 4682312,"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": 1708038716619.891, "dur": 0.065, + "args": { + "External id": 4682313,"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": 1708038716620.281, "dur": 0.067, + "args": { + "External id": 4682314,"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": 1708038716620.636, "dur": 0.070, + "args": { + "External id": 4682315,"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": 1708038716621.062, "dur": 0.063, + "args": { + "External id": 4682316,"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": 1708038716621.584, "dur": 0.067, + "args": { + "External id": 4682317,"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": 1708038716622.131, "dur": 0.065, + "args": { + "External id": 4682318,"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": 1708038716622.568, "dur": 0.066, + "args": { + "External id": 4682319,"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": 1708038716622.970, "dur": 0.068, + "args": { + "External id": 4682320,"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": 1708038716623.596, "dur": 0.063, + "args": { + "External id": 4682321,"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": 1708038716624.154, "dur": 0.063, + "args": { + "External id": 4682322,"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": 1708038716624.597, "dur": 0.067, + "args": { + "External id": 4682323,"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": 1708038716625.083, "dur": 0.063, + "args": { + "External id": 4682324,"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": 1708038716625.607, "dur": 0.090, + "args": { + "External id": 4682325,"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": 1708038716626.067, "dur": 0.063, + "args": { + "External id": 4682326,"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": 1708038716626.616, "dur": 0.069, + "args": { + "External id": 4682327,"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": 1708038716627.035, "dur": 0.063, + "args": { + "External id": 4682328,"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": 1708038716627.525, "dur": 0.062, + "args": { + "External id": 4682329,"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": 1708038716628.002, "dur": 0.067, + "args": { + "External id": 4682330,"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": 1708038716628.431, "dur": 0.065, + "args": { + "External id": 4682331,"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": 1708038716628.868, "dur": 0.066, + "args": { + "External id": 4682332,"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": 1708038716629.385, "dur": 0.064, + "args": { + "External id": 4682333,"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": 1708038716629.921, "dur": 0.065, + "args": { + "External id": 4682334,"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": 1708038716630.359, "dur": 0.066, + "args": { + "External id": 4682335,"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": 1708038716630.705, "dur": 0.059, + "args": { + "External id": 4682336,"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": 1708038716631.371, "dur": 0.063, + "args": { + "External id": 4682337,"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": 1708038716631.843, "dur": 0.066, + "args": { + "External id": 4682338,"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": 1708038716632.330, "dur": 0.052, + "args": { + "External id": 4682339,"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": 1708038716632.823, "dur": 0.055, + "args": { + "External id": 4682340,"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": 1708038716633.264, "dur": 0.068, + "args": { + "External id": 4682341,"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": 1708038716633.674, "dur": 0.069, + "args": { + "External id": 4682342,"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": 1708038716634.062, "dur": 0.069, + "args": { + "External id": 4682343,"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": 1708038716634.461, "dur": 0.062, + "args": { + "External id": 4682344,"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": 1708038716634.981, "dur": 0.066, + "args": { + "External id": 4682345,"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": 1708038716635.465, "dur": 0.066, + "args": { + "External id": 4682346,"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": 1708038716635.937, "dur": 0.069, + "args": { + "External id": 4682347,"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": 1708038716636.382, "dur": 0.068, + "args": { + "External id": 4682348,"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": 1708038716636.728, "dur": 0.068, + "args": { + "External id": 4682349,"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": 1708038716637.217, "dur": 0.057, + "args": { + "External id": 4682350,"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": 1708038716637.635, "dur": 0.056, + "args": { + "External id": 4682351,"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": 1708038716638.078, "dur": 0.071, + "args": { + "External id": 4682352,"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": 1708038716638.518, "dur": 0.069, + "args": { + "External id": 4682353,"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": 1708038716639.004, "dur": 0.065, + "args": { + "External id": 4682354,"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": 1708038716639.469, "dur": 0.064, + "args": { + "External id": 4682355,"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": 1708038716639.929, "dur": 0.066, + "args": { + "External id": 4682356,"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": 1708038716640.329, "dur": 0.060, + "args": { + "External id": 4682357,"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": 1708038716640.753, "dur": 0.064, + "args": { + "External id": 4682358,"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": 1708038716641.318, "dur": 0.063, + "args": { + "External id": 4682359,"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": 1708038716641.849, "dur": 0.066, + "args": { + "External id": 4682360,"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": 1708038716642.175, "dur": 0.068, + "args": { + "External id": 4682361,"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": 1708038716642.781, "dur": 0.070, + "args": { + "External id": 4682362,"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": 1708038716643.275, "dur": 0.070, + "args": { + "External id": 4682363,"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": 1708038716643.812, "dur": 0.064, + "args": { + "External id": 4682364,"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": 1708038716644.496, "dur": 0.059, + "args": { + "External id": 4682365,"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": 1708038716644.931, "dur": 0.064, + "args": { + "External id": 4682366,"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": 1708038716645.364, "dur": 0.063, + "args": { + "External id": 4682367,"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": 1708038716645.753, "dur": 0.069, + "args": { + "External id": 4682368,"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": 1708038716646.616, "dur": 0.066, + "args": { + "External id": 4682369,"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": 1708038716647.029, "dur": 0.066, + "args": { + "External id": 4682370,"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": 1708038716647.622, "dur": 0.067, + "args": { + "External id": 4682371,"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": 1708038716648.013, "dur": 0.065, + "args": { + "External id": 4682372,"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": 1708038716648.416, "dur": 0.066, + "args": { + "External id": 4682373,"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": 1708038716649.048, "dur": 0.066, + "args": { + "External id": 4682374,"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": 1708038716649.723, "dur": 0.072, + "args": { + "External id": 4682375,"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": 1708038716650.092, "dur": 0.069, + "args": { + "External id": 4682376,"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": 1708038716650.681, "dur": 0.067, + "args": { + "External id": 4682377,"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": 1708038716651.137, "dur": 0.068, + "args": { + "External id": 4682378,"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": 1708038716651.911, "dur": 0.067, + "args": { + "External id": 4682379,"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": 1708038716652.301, "dur": 0.067, + "args": { + "External id": 4682380,"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": 1708038716652.702, "dur": 0.069, + "args": { + "External id": 4682381,"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": 1708038716653.113, "dur": 0.058, + "args": { + "External id": 4682382,"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": 1708038716653.465, "dur": 0.061, + "args": { + "External id": 4682383,"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": 1708038716653.965, "dur": 0.056, + "args": { + "External id": 4682384,"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": 1708038716654.781, "dur": 0.047, + "args": { + "External id": 4682385,"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": 1708038716655.102, "dur": 0.056, + "args": { + "External id": 4682386,"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": 1708038716655.538, "dur": 0.057, + "args": { + "External id": 4682387,"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": 1708038716656.038, "dur": 0.056, + "args": { + "External id": 4682388,"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": 1708038716656.576, "dur": 0.059, + "args": { + "External id": 4682389,"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": 1708038716657.195, "dur": 0.057, + "args": { + "External id": 4682390,"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": 1708038716657.580, "dur": 0.053, + "args": { + "External id": 4682391,"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": 1708038716657.961, "dur": 0.083, + "args": { + "External id": 4682392,"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": 1708038716658.768, "dur": 0.046, + "args": { + "External id": 4682393,"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": 1708038716659.178, "dur": 0.064, + "args": { + "External id": 4682394,"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": 1708038716659.513, "dur": 0.049, + "args": { + "External id": 4682395,"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": 1708038716660.194, "dur": 0.067, + "args": { + "External id": 4682396,"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": 1708038716660.561, "dur": 0.054, + "args": { + "External id": 4682397,"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": 1708038716661.132, "dur": 0.065, + "args": { + "External id": 4682398,"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": 1708038716661.492, "dur": 0.051, + "args": { + "External id": 4682399,"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": 1708038716662.038, "dur": 0.070, + "args": { + "External id": 4682400,"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": 1708038716662.361, "dur": 0.049, + "args": { + "External id": 4682401,"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": 1708038716662.863, "dur": 0.063, + "args": { + "External id": 4682402,"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": 1708038716663.169, "dur": 0.057, + "args": { + "External id": 4682403,"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": 1708038716663.879, "dur": 0.065, + "args": { + "External id": 4682404,"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": 1708038716664.203, "dur": 0.051, + "args": { + "External id": 4682405,"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": 1708038716664.847, "dur": 0.064, + "args": { + "External id": 4682406,"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": 1708038716665.160, "dur": 0.051, + "args": { + "External id": 4682407,"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": 1708038716665.799, "dur": 0.068, + "args": { + "External id": 4682408,"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": 1708038716666.125, "dur": 0.052, + "args": { + "External id": 4682409,"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": 1708038716666.743, "dur": 0.065, + "args": { + "External id": 4682410,"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": 1708038716667.048, "dur": 0.054, + "args": { + "External id": 4682411,"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": 1708038716667.549, "dur": 0.064, + "args": { + "External id": 4682412,"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": 1708038716667.852, "dur": 0.055, + "args": { + "External id": 4682413,"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": 1708038716668.535, "dur": 0.066, + "args": { + "External id": 4682414,"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": 1708038716668.840, "dur": 0.055, + "args": { + "External id": 4682415,"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": 1708038716669.377, "dur": 0.068, + "args": { + "External id": 4682416,"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": 1708038716669.690, "dur": 0.058, + "args": { + "External id": 4682417,"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": 1708038716670.387, "dur": 0.069, + "args": { + "External id": 4682418,"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": 1708038716670.726, "dur": 0.054, + "args": { + "External id": 4682419,"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": 1708038716671.211, "dur": 0.064, + "args": { + "External id": 4682420,"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": 1708038716671.521, "dur": 0.055, + "args": { + "External id": 4682421,"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": 1708038716672.029, "dur": 0.063, + "args": { + "External id": 4682422,"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": 1708038716672.334, "dur": 0.051, + "args": { + "External id": 4682423,"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": 1708038716672.960, "dur": 0.068, + "args": { + "External id": 4682424,"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": 1708038716673.271, "dur": 0.056, + "args": { + "External id": 4682425,"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": 1708038716673.788, "dur": 0.065, + "args": { + "External id": 4682426,"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": 1708038716674.094, "dur": 0.053, + "args": { + "External id": 4682427,"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": 1708038716674.608, "dur": 0.062, + "args": { + "External id": 4682428,"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": 1708038716674.909, "dur": 0.053, + "args": { + "External id": 4682429,"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": 1708038716675.573, "dur": 0.058, + "args": { + "External id": 4682430,"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": 1708038716675.874, "dur": 0.054, + "args": { + "External id": 4682431,"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": 1708038716676.526, "dur": 0.069, + "args": { + "External id": 4682432,"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": 1708038716676.840, "dur": 0.053, + "args": { + "External id": 4682433,"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": 1708038716677.372, "dur": 0.064, + "args": { + "External id": 4682434,"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": 1708038716677.678, "dur": 0.053, + "args": { + "External id": 4682435,"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": 1708038716678.200, "dur": 0.065, + "args": { + "External id": 4682436,"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": 1708038716678.536, "dur": 0.053, + "args": { + "External id": 4682437,"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": 1708038716679.112, "dur": 0.063, + "args": { + "External id": 4682438,"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": 1708038716679.416, "dur": 0.055, + "args": { + "External id": 4682439,"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": 1708038716680.051, "dur": 0.064, + "args": { + "External id": 4682440,"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": 1708038716680.359, "dur": 0.054, + "args": { + "External id": 4682441,"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": 1708038716680.882, "dur": 0.067, + "args": { + "External id": 4682442,"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": 1708038716681.188, "dur": 0.052, + "args": { + "External id": 4682443,"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": 1708038716681.820, "dur": 0.065, + "args": { + "External id": 4682444,"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": 1708038716682.126, "dur": 0.055, + "args": { + "External id": 4682445,"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": 1708038716682.750, "dur": 0.065, + "args": { + "External id": 4682446,"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": 1708038716683.060, "dur": 0.054, + "args": { + "External id": 4682447,"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": 1708038716683.571, "dur": 0.070, + "args": { + "External id": 4682448,"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": 1708038716683.882, "dur": 0.061, + "args": { + "External id": 4682449,"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": 1708038716684.411, "dur": 0.067, + "args": { + "External id": 4682450,"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": 1708038716684.722, "dur": 0.054, + "args": { + "External id": 4682451,"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": 1708038716685.376, "dur": 0.055, + "args": { + "External id": 4682452,"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": 1708038716685.670, "dur": 0.056, + "args": { + "External id": 4682453,"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": 1708038716686.487, "dur": 0.049, + "args": { + "External id": 4682454,"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": 1708038716686.778, "dur": 0.053, + "args": { + "External id": 4682455,"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": 1708038716687.464, "dur": 0.067, + "args": { + "External id": 4682456,"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": 1708038716687.798, "dur": 0.059, + "args": { + "External id": 4682457,"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": 1708038717291.085, "dur": 3568.171, + "args": { + "External id": 4682458,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "2.0473079043131424e-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": 1708038720346.867, "dur": 336.943, + "args": { + "External id": 4682459,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "2.0473079043131424e-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": 1708036593663.202, "pid": 1336753, "tid": 0, + "args": { + "name": "python3.12" + } + }, + { + "name": "process_labels", "ph": "M", "ts": 1708036593663.202, "pid": 1336753, "tid": 0, + "args": { + "labels": "CPU" + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 1708036593663.202, "pid": 1336753, "tid": 0, + "args": { + "sort_index": 1336753 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1708036593663.202, "pid": 1336753, "tid": 1381210, + "args": { + "name": "thread 1381210 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1708036593663.202, "pid": 1336753, "tid": 1381210, + "args": { + "sort_index": 1381210 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1708036593663.202, "pid": 1336753, "tid": 1336753, + "args": { + "name": "thread 1336753 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1708036593663.202, "pid": 1336753, "tid": 1336753, + "args": { + "sort_index": 1336753 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1708036593663.202, "pid": 1336753, "tid": 1381210, + "args": { + "name": "thread 1381210 (pt_autograd_0)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1708036593663.202, "pid": 1336753, "tid": 1381210, + "args": { + "sort_index": 1381210 + } + }, + { + "ph": "X", "cat": "Trace", "ts": 1708036593584.438, "dur": 2129007.584, + "pid": "Spans", "tid": "PyTorch Profiler", + "name": "PyTorch Profiler (0)", + "args": { + "Op count": 0 + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 1708036593584.438, + "pid": "Spans", "tid": 0, + "args": { + "sort_index": 536870912 + } + }, + { + "name": "Iteration Start: PyTorch Profiler", "ph": "i", "s": "g", + "pid": "Traces", "tid": "Trace PyTorch Profiler", "ts": 1708036593584.438 + }, + { + "name": "Record Window End", "ph": "i", "s": "g", + "pid": "", "tid": "", "ts": 1708038787655.572 + } + ], + "traceName": "exp/mtp.1B.batch16.seqlen4096.context4096.warmup2000.update1.steps200000.lr2e-4.cosine/profile_trace/iteration_193536/rank0_trace.json", + "displayTimeUnit": "ms", + "baseTimeNanoseconds": 1751410836000000000 +} \ No newline at end of file