==================================================Ascend ============================= test session starts ============================== platform linux -- Python 3.9.19, pytest-6.2.5, py-1.11.0, pluggy-1.5.0 rootdir: /home/jenkins/mindspore/testcases/testcases/tests/st/infer/ops/test_internal_ops, configfile: ../../../../../../../../sault/virtual_test/virtualenv_008/sault/config/pytest.ini plugins: mock-3.14.0, hydra-core-1.3.2, forked-1.6.0, anyio-4.9.0, xdist-1.32.0 collected 16 items test_swiglu_dyn_quant.py [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:38:02.667.659 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 4.96743, [21] [bootstrap]: 0.260932 [type_inference]: 4.29685 [event_method]: 0.00076081 [auto_monad]: 0.00021999 [graph_reusing]: 8.07e-06 [inline]: 7.18e-06 [add_attr]: 0.132255, [1] [add_attr_with_inline]: 0.132239, [1] [Cycle 1]: 0.00012146, [2] [tag_attr]: 3.572e-05 [meta_addattr_fg_expand]: 8.13999e-06 [parallel-infer-symbol]: 4.901e-05 [pre_auto_parallel]: 8.279e-05 [insert-virtual-dataset]: 3.16001e-06 [parallel-infer-symbol-second]: 9.09989e-07 [dataset_repeat_opt]: 2.01998e-06 [pipeline_split]: 1.71e-06 [optimize]: 0.275178, [53] [py_interpret_to_execute]: 4.15e-05 [rewriter_before_opt_a]: 0.00028659 [opt_a]: 0.270904, [2] [Cycle 1]: 0.0205403, [45] [expand_dump_flag]: 5.37999e-06 [switch_simplify]: 5.563e-05 [loop_unroll]: 3.976e-05 [a_1]: 0.00110255 [with_stream_mark]: 2.752e-05 [recompute_prepare]: 1.91e-05 [updatestate_depend_eliminate]: 1.103e-05 [updatestate_assign_eliminate]: 8.50999e-06 [updatestate_loads_eliminate]: 8.62e-06 [parameter_eliminate]: 2.15002e-06 [a_2]: 0.00024456 [accelerated_algorithm]: 3.757e-05 [shard]: 2.54999e-06 [meta_shard_fg_expand]: 4.23001e-06 [shard_inline]: 1.6e-05 [merge_send_recv]: 3.628e-05 [auto_parallel]: 1.428e-05 [parallel]: 4.34e-05 [flash_sp]: 2.012e-05 [merge_comm]: 1.073e-05 [allreduce_fusion]: 9.98998e-06 [matmul_add_comm_reduction]: 1.748e-05 [allreduce_slice_to_reducescatter]: 8.60018e-07 [virtual_shard_identity]: 1.873e-05 [virtual_dataset]: 1.553e-05 [get_grad_eliminate_]: 1.575e-05 [virtual_output]: 1.48e-05 [merge_forward]: 2.838e-05 [cell_reuse_recompute_pass]: 1.60001e-06 [offload_activation]: 1.972e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.45e-05 [merge_recompute_call_nodes]: 2.39001e-06 [before_grad]: 2.856e-05 [set_forward_comm_id_for_comm_node_pass]: 1.126e-05 [meta_fg_expand]: 7.51001e-06 [flash_sp_send_recv_attached]: 5.66e-06 [receive_attached]: 1.099e-05 [after_resolve]: 1.955e-05 [a_after_grad]: 2.467e-05 [renormalize]: 0.00499622 [add_forward_monad_depend]: 1.644e-05 [auto_monad_grad]: 3.23e-06 [auto_monad_eliminator]: 0.0122981 [cse]: 0.00070986 [a_3]: 0.0001455 [Cycle 2]: 0.250346, [45] [expand_dump_flag]: 4.48999e-06 [switch_simplify]: 0.248549 [loop_unroll]: 3.76e-05 [a_1]: 0.00054256 [with_stream_mark]: 4.35e-05 [recompute_prepare]: 1.924e-05 [updatestate_depend_eliminate]: 1.26e-05 [updatestate_assign_eliminate]: 8.23999e-06 [updatestate_loads_eliminate]: 8.77e-06 [parameter_eliminate]: 2.81999e-06 [a_2]: 0.0002487 [accelerated_algorithm]: 2.228e-05 [shard]: 3.33e-06 [meta_shard_fg_expand]: 6.93e-06 [shard_inline]: 1.514e-05 [merge_send_recv]: 1.652e-05 [auto_parallel]: 1.721e-05 [parallel]: 1.266e-05 [flash_sp]: 4.55001e-06 [merge_comm]: 9.69999e-06 [allreduce_fusion]: 1.008e-05 [matmul_add_comm_reduction]: 1.783e-05 [allreduce_slice_to_reducescatter]: 1.52999e-06 [virtual_shard_identity]: 1.705e-05 [virtual_dataset]: 1.513e-05 [get_grad_eliminate_]: 1.505e-05 [virtual_output]: 1.459e-05 [merge_forward]: 9.47001e-06 [cell_reuse_recompute_pass]: 2.83e-06 [offload_activation]: 1.886e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.049e-05 [merge_recompute_call_nodes]: 1.97001e-06 [before_grad]: 2.676e-05 [set_forward_comm_id_for_comm_node_pass]: 9.97999e-06 [meta_fg_expand]: 8.32e-06 [flash_sp_send_recv_attached]: 1.92001e-06 [receive_attached]: 2.48e-06 [after_resolve]: 1.908e-05 [a_after_grad]: 2.449e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 3.73001e-06 [auto_monad_grad]: 4.12e-06 [auto_monad_eliminator]: 3.379e-05 [cse]: 8.091e-05 [a_3]: 9.924e-05 [py_interpret_to_execute_after_opt_a]: 3.145e-05 [slice_cell_reuse_recomputed_activation]: 2.46e-06 [rewriter_after_opt_a]: 0.00046642 [convert_after_rewriter]: 1.722e-05 [order_py_execute_after_rewriter]: 1.135e-05 [mutable_eliminate]: 0.00081409 [opt_b]: 0.00060102, [1] [Cycle 1]: 0.00059174, [7] [b_1]: 0.00041477 [b_2]: 1.859e-05 [updatestate_depend_eliminate]: 1.413e-05 [updatestate_assign_eliminate]: 7.84002e-06 [updatestate_loads_eliminate]: 7.9e-06 [renormalize]: 8.70001e-07 [cse]: 8.579e-05 [optimize_parallel_all_gather_comm]: 3.523e-05 [overlap_param_gather]: 3.65998e-06 [cconv]: 4.263e-05 [loop_unroll]: 0.00055827 [opt_after_cconv]: 0.00022063, [1] [Cycle 1]: 0.0002132, [7] [c_1]: 8.018e-05 [parameter_eliminate]: 4.22998e-06 [updatestate_depend_eliminate]: 1.268e-05 [updatestate_assign_eliminate]: 8.32e-06 [updatestate_loads_eliminate]: 7.61999e-06 [cse]: 6.306e-05 [renormalize]: 5.10016e-07 [remove_dup_value]: 8.717e-05 [tuple_transform]: 0.00021615, [1] [Cycle 1]: 0.00021063, [4] [d_1]: 0.00016996 [none_parameter_eliminate]: 2.14e-06 [renormalize]: 3.10014e-07 [switch_simplify]: 1.722e-05 [partial_unused_args_eliminate]: 2.24001e-06 [add_recomputation]: 0.00012916 [cse_after_recomputation]: 5.2e-05, [1] [Cycle 1]: 4.606e-05, [1] [cse]: 3.954e-05 [environ_conv]: 2.793e-05 [swap_dp_allreduce_reducescatter]: 1.452e-05 [bias_add_comm_swap]: 3.16001e-06 [label_micro_interleaved_index]: 5.82999e-06 [label_fine_grained_interleaved_index]: 3.56001e-06 [merge_cast_opt]: 1.67001e-06 [slice_recompute_activation]: 2.55002e-06 [micro_interleaved_order_control]: 2.79001e-06 [assign_add_opt]: 1.62001e-06 [ForceFp32Comm]: 9.50007e-07 [remove_cast_before_assign_add]: 1.17e-06 [full_micro_interleaved_order_control]: 2.26e-06 [reorder_send_recv_between_fp_bp]: 2.86e-06 [comm_op_add_attrs]: 1.39e-06 [add_comm_op_reuse_tag]: 1.12e-06 [interleave_split_concat_branches]: 1.37999e-06 [interleave_parallel_branches]: 1.09e-06 [overlap_opt_shard_in_pipeline]: 2.595e-05 [overlap_opt_shard_grad_in_pipeline]: 2.11e-06 [control_data_broadcast_order]: 3.019e-05 [grouped_pairwise_exchange_alltoall]: 2.43e-06 [offloading_packed_experts]: 8.67998e-06 [overlap_recompute_and_grad_model_parallel]: 8.67e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.17e-06 [overlap_recompute_allgather_and_fa_grad]: 1.52001e-06 [overlap_recompute_comm]: 2.57001e-06 [overlap_grad_ring_attention]: 7.77002e-06 [overlap_grad_flash_sp]: 5.444e-05 [begin_end_overlap_inline]: 6.89994e-07 [split_matmul_comm_elemetwise]: 2.46e-06 [split_layernorm_comm]: 2.04e-06 [handle_group_info]: 1.09003e-06 [symbol_engine_optimizer]: 0.00016099, [1] [Cycle 1]: 0.0001552, [6] [build]: 2.781e-05 [elim_shapecalc]: 2.364e-05 [elim_not_effective]: 3.074e-05 [opt_reshape]: 1.612e-05 [fold_const_symbol]: 2.557e-05 [renormalize]: 2.20025e-07 [detach_backward]: 2.63e-06 [pipeline_parallel_scheduler]: 2.11e-06 [auto_monad_reorder]: 4.111e-05 [get_jit_bprop_graph]: 2.04e-06 [rewriter_after_jit_bprop_graph]: 5.22999e-06 [opt_after_jit_grad]: 0.00066894 [validate]: 0.00010989 Sums bootstrap : 0.260932s : 5.40% type_inference : 4.296850s : 88.89% event_method : 0.000761s : 0.02% auto_monad : 0.000220s : 0.00% graph_reusing : 0.000008s : 0.00% inline : 0.000007s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000036s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000008s : 0.00% parallel-infer-symbol : 0.000049s : 0.00% pre_auto_parallel : 0.000083s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000041s : 0.00% optimize.rewriter_before_opt_a : 0.000287s : 0.01% optimize.opt_a.expand_dump_flag : 0.000010s : 0.00% optimize.opt_a.switch_simplify : 0.248604s : 5.14% optimize.opt_a.loop_unroll : 0.000077s : 0.00% optimize.opt_a.a_1 : 0.001645s : 0.03% optimize.opt_a.with_stream_mark : 0.000071s : 0.00% optimize.opt_a.recompute_prepare : 0.000038s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000024s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000017s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000493s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000060s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000011s : 0.00% optimize.opt_a.shard_inline : 0.000031s : 0.00% optimize.opt_a.merge_send_recv : 0.000053s : 0.00% optimize.opt_a.auto_parallel : 0.000031s : 0.00% optimize.opt_a.parallel : 0.000056s : 0.00% optimize.opt_a.flash_sp : 0.000025s : 0.00% optimize.opt_a.merge_comm : 0.000020s : 0.00% optimize.opt_a.allreduce_fusion : 0.000020s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000035s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000036s : 0.00% optimize.opt_a.virtual_dataset : 0.000031s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000031s : 0.00% optimize.opt_a.virtual_output : 0.000029s : 0.00% optimize.opt_a.merge_forward : 0.000038s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000039s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000065s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000055s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000021s : 0.00% optimize.opt_a.meta_fg_expand : 0.000016s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000013s : 0.00% optimize.opt_a.after_resolve : 0.000039s : 0.00% optimize.opt_a.a_after_grad : 0.000049s : 0.00% optimize.opt_a.renormalize : 0.004996s : 0.10% optimize.opt_a.add_forward_monad_depend : 0.000020s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.012332s : 0.26% optimize.opt_a.cse : 0.000791s : 0.02% optimize.opt_a.a_3 : 0.000245s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000031s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000466s : 0.01% optimize.convert_after_rewriter : 0.000017s : 0.00% optimize.order_py_execute_after_rewriter : 0.000011s : 0.00% optimize.mutable_eliminate : 0.000814s : 0.02% optimize.opt_b.b_1 : 0.000415s : 0.01% optimize.opt_b.b_2 : 0.000019s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000086s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000035s : 0.00% optimize.overlap_param_gather : 0.000004s : 0.00% optimize.cconv : 0.000043s : 0.00% optimize.loop_unroll : 0.000558s : 0.01% optimize.opt_after_cconv.c_1 : 0.000080s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.cse : 0.000063s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000087s : 0.00% optimize.tuple_transform.d_1 : 0.000170s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000017s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000129s : 0.00% optimize.cse_after_recomputation.cse : 0.000040s : 0.00% optimize.environ_conv : 0.000028s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000015s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000004s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000026s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000030s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000009s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000054s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000028s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000024s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000031s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000016s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000026s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000041s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000669s : 0.01% validate : 0.000110s : 0.00% Time group info: ------[substitution.] 0.000599 197 7.84% : 0.000047s : 6: substitution.arithmetic_simplify 0.74% : 0.000004s : 10: substitution.elim_not_effective 2.50% : 0.000015s : 12: substitution.float_tuple_getitem_switch 0.67% : 0.000004s : 10: substitution.fold_const_symbol 2.08% : 0.000012s : 12: substitution.graph_param_transform 40.75% : 0.000244s : 7: substitution.inline 1.86% : 0.000011s : 20: substitution.j_node_and_user_rematch 3.53% : 0.000021s : 2: substitution.less_batch_normalization 2.83% : 0.000017s : 8: substitution.minmaximum_grad 2.34% : 0.000014s : 20: substitution.remove_not_recompute_node 0.94% : 0.000006s : 2: substitution.replace_old_param 8.01% : 0.000048s : 16: substitution.tuple_list_convert_item_index_to_positive 4.03% : 0.000024s : 16: substitution.tuple_list_get_item_const_eliminator 5.45% : 0.000033s : 16: substitution.tuple_list_get_item_depend_reorder 11.06% : 0.000066s : 24: substitution.tuple_list_get_item_eliminator 5.38% : 0.000032s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 4.296727 2 99.91% : 4.292921s : 1: type_inference.infer 0.09% : 0.003806s : 1: type_inference.specialize ------[replace.] 0.000061 7 100.00% : 0.000061s : 7: replace.inline ------[match.] 0.000240 7 100.00% : 0.000240s : 7: match.inline ------[predicate.] 0.000534 3093 0.84% : 0.000004s : 30: predicate.accumulaten_eliminater 0.88% : 0.000005s : 12: predicate.ad_related_special_op_eliminate 0.66% : 0.000004s : 24: predicate.addn_check_dump 0.79% : 0.000004s : 30: predicate.addn_zero_filter 0.73% : 0.000004s : 30: predicate.adjust_all_reduce_mul_add 2.20% : 0.000012s : 54: predicate.arithmetic_simplify 0.85% : 0.000005s : 30: predicate.cast_eliminate 0.72% : 0.000004s : 24: predicate.check_bprop_eliminate 0.67% : 0.000004s : 24: predicate.compare_switch_simplify 0.19% : 0.000001s : 12: predicate.const_output_eliminate 0.66% : 0.000004s : 24: predicate.depend_value_elim 0.84% : 0.000004s : 30: predicate.dict_get_item_const_eliminator 1.00% : 0.000005s : 30: predicate.dict_get_item_eliminator 0.80% : 0.000004s : 30: predicate.dict_set_item_eliminator 1.59% : 0.000008s : 24: predicate.dumpgradient_eliminate 0.19% : 0.000001s : 12: predicate.elim_not_effective 0.45% : 0.000002s : 12: predicate.elim_shapecalc_of_broadcastargs 1.12% : 0.000006s : 42: predicate.environ_add_const_eliminate 1.06% : 0.000006s : 42: predicate.environ_get_add_eliminate 1.06% : 0.000006s : 42: predicate.environ_get_depend_swap 1.79% : 0.000010s : 66: predicate.environ_get_eliminate 1.12% : 0.000006s : 42: predicate.environ_get_set_eliminate 0.96% : 0.000005s : 37: predicate.exchange_switch_depend_value 1.69% : 0.000009s : 37: predicate.float_depend_g_call 0.66% : 0.000004s : 24: predicate.float_environ_get_switch 1.14% : 0.000006s : 36: predicate.float_tuple_getitem_switch 0.16% : 0.000001s : 12: predicate.fold_const_symbol 0.76% : 0.000004s : 24: predicate.get_grad_eliminate 0.19% : 0.000001s : 12: predicate.graph_param_transform 0.66% : 0.000004s : 24: predicate.incorporate_call 0.60% : 0.000003s : 24: predicate.incorporate_call_switch 5.24% : 0.000028s : 139: predicate.inline 0.85% : 0.000005s : 24: predicate.inline_without_move 0.31% : 0.000002s : 24: predicate.j_node_and_user_rematch 0.98% : 0.000005s : 24: predicate.less_batch_normalization 1.57% : 0.000008s : 54: predicate.list_to_tuple_eliminator_ 2.18% : 0.000012s : 84: predicate.load_eliminater 0.72% : 0.000004s : 12: predicate.loop_unroll_after_grad 1.99% : 0.000011s : 52: predicate.loop_unroll_before_grad 1.60% : 0.000009s : 54: predicate.make_slice_get_slice_eliminator 0.71% : 0.000004s : 24: predicate.merge_addn 0.68% : 0.000004s : 24: predicate.micro_step_allgather_replace 0.72% : 0.000004s : 24: predicate.mini_step_allgather_replace 0.84% : 0.000004s : 30: predicate.minmaximum_grad 0.80% : 0.000004s : 12: predicate.mutable_eliminate 0.39% : 0.000002s : 12: predicate.opt_reshape 0.39% : 0.000002s : 12: predicate.parallel_virtual_node 1.48% : 0.000008s : 37: predicate.partial_defer_inline 1.24% : 0.000007s : 42: predicate.partial_eliminate 0.82% : 0.000004s : 30: predicate.print_const_string_wrapper 0.68% : 0.000004s : 24: predicate.reduce_all_const_elim 1.19% : 0.000006s : 30: predicate.reduce_eliminate 5.81% : 0.000031s : 84: predicate.redundant_stop_gradient_eliminater 0.36% : 0.000002s : 24: predicate.remove_not_recompute_node 1.16% : 0.000006s : 54: predicate.replace_applicator 0.38% : 0.000002s : 24: predicate.replace_old_param 0.23% : 0.000001s : 12: predicate.reset_defer_inline 0.86% : 0.000005s : 30: predicate.reshape_eliminate 0.74% : 0.000004s : 24: predicate.row_tensor_add_zeros_like 0.44% : 0.000002s : 12: predicate.row_tensor_eliminate 1.04% : 0.000006s : 24: predicate.same_eliminate 0.42% : 0.000002s : 24: predicate.set_cell_output_no_recompute 0.77% : 0.000004s : 24: predicate.shard_identity_eliminate 0.77% : 0.000004s : 24: predicate.special_op_eliminate 0.77% : 0.000004s : 24: predicate.specialize_transform 0.90% : 0.000005s : 24: predicate.split_environ_get_set_with_tuple_value 0.81% : 0.000004s : 24: predicate.stack_unstack_eliminate 0.38% : 0.000002s : 12: predicate.switch_call_monad_eliminater 1.08% : 0.000006s : 37: predicate.switch_defer_inline 1.85% : 0.000010s : 61: predicate.switch_layer_defer_inline 5.15% : 0.000027s : 125: predicate.switch_simplify 0.82% : 0.000004s : 30: predicate.tile_eliminate 0.80% : 0.000004s : 30: predicate.transpose_eliminate 1.84% : 0.000010s : 54: predicate.tuple_list_convert_item_index_to_positive 1.72% : 0.000009s : 54: predicate.tuple_list_get_item_const_eliminator 1.63% : 0.000009s : 54: predicate.tuple_list_get_item_depend_reorder 3.31% : 0.000018s : 78: predicate.tuple_list_get_item_eliminator 1.71% : 0.000009s : 54: predicate.tuple_list_get_set_item_eliminator 2.45% : 0.000013s : 78: predicate.tuple_list_set_item_eliminator 1.63% : 0.000009s : 54: predicate.tuple_to_list_eliminator_ 2.10% : 0.000011s : 84: predicate.updatestate_pure_node_eliminater 3.00% : 0.000016s : 108: predicate.updatestate_useless_node_eliminater 0.39% : 0.000002s : 12: predicate.value_based_eliminate 0.74% : 0.000004s : 24: predicate.virtual_dataset_eliminate 0.74% : 0.000004s : 24: predicate.virtual_output_eliminate 0.33% : 0.000002s : 12: predicate.virtual_view_grad_eliminate 0.50% : 0.000003s : 12: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.004814 38 73.67% : 0.003546s : 29: func_graph_cloner_run.FuncGraphClonerGraph 26.33% : 0.001268s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 5.631884 192 0.00% : 0.000004s : 1: ForceFp32Comm 2.35% : 0.132262s : 1: add_attr 2.35% : 0.132245s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000135s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.00% : 0.000235s : 1: auto_monad 0.00% : 0.000046s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 4.63% : 0.260983s : 1: bootstrap 0.00% : 0.000047s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000034s : 1: control_data_broadcast_order 0.00% : 0.000022s : 1: convert_after_rewriter 0.00% : 0.000055s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000032s : 1: environ_conv 0.01% : 0.000784s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000010s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.01% : 0.000567s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.01% : 0.000823s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.00% : 0.000027s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000031s : 1: opt.transform.mutable_eliminate 4.46% : 0.251394s : 78: opt.transform.opt_a 0.00% : 0.000079s : 1: opt.transform.opt_after_cconv 0.00% : 0.000073s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000399s : 28: opt.transform.opt_b 0.00% : 0.000184s : 2: opt.transform.opt_trans_graph 0.00% : 0.000092s : 4: opt.transform.symbol_engine_opt 4.81% : 0.270908s : 1: opt_a 0.00% : 0.000225s : 1: opt_after_cconv 0.01% : 0.000679s : 1: opt_after_jit_grad 0.01% : 0.000605s : 1: opt_b 4.89% : 0.275184s : 1: optimize 0.00% : 0.000039s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.00% : 0.000058s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000030s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000054s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000088s : 1: pre_auto_parallel 0.00% : 0.000046s : 1: py_interpret_to_execute 0.00% : 0.000035s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000092s : 1: remove_dup_value 0.06% : 0.003410s : 1: renormalize.infer 0.03% : 0.001570s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000474s : 1: rewriter_after_opt_a 0.01% : 0.000296s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000018s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000164s : 1: symbol_engine_optimizer 0.00% : 0.000220s : 1: tuple_transform 76.30% : 4.296886s : 1: type_inference mki_log delete old file:/home/jenkins/ascend/log/atb/atb_70271_20260129172059.log . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[False-False-bfloat16--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[False-False-bfloat16--1-shape0],max_mem:100.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:39:02.354.067 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 3.65074, [21] [bootstrap]: 0.00086101 [type_inference]: 3.22681 [event_method]: 0.00111676 [auto_monad]: 0.00011717 [graph_reusing]: 7.57002e-06 [inline]: 2.35002e-06 [add_attr]: 0.00459307, [1] [add_attr_with_inline]: 0.00457839, [1] [Cycle 1]: 8.369e-05, [2] [tag_attr]: 3.58e-05 [meta_addattr_fg_expand]: 8e-06 [parallel-infer-symbol]: 3.8e-06 [pre_auto_parallel]: 4.843e-05 [insert-virtual-dataset]: 3.50998e-06 [parallel-infer-symbol-second]: 6.89994e-07 [dataset_repeat_opt]: 2.02001e-06 [pipeline_split]: 2.94001e-06 [optimize]: 0.416173, [53] [py_interpret_to_execute]: 3.492e-05 [rewriter_before_opt_a]: 0.00011867 [opt_a]: 0.412003, [2] [Cycle 1]: 0.410214, [45] [expand_dump_flag]: 4.34997e-06 [switch_simplify]: 5.393e-05 [loop_unroll]: 3.838e-05 [a_1]: 0.00133044 [with_stream_mark]: 0.399804 [recompute_prepare]: 5.743e-05 [updatestate_depend_eliminate]: 1.474e-05 [updatestate_assign_eliminate]: 9.04e-06 [updatestate_loads_eliminate]: 8.20999e-06 [parameter_eliminate]: 3.48e-06 [a_2]: 0.00031371 [accelerated_algorithm]: 4.118e-05 [shard]: 3.66999e-06 [meta_shard_fg_expand]: 9.00001e-06 [shard_inline]: 1.641e-05 [merge_send_recv]: 1.7e-05 [auto_parallel]: 1.713e-05 [parallel]: 3.917e-05 [flash_sp]: 1.393e-05 [merge_comm]: 1.018e-05 [allreduce_fusion]: 9.51e-06 [matmul_add_comm_reduction]: 1.871e-05 [allreduce_slice_to_reducescatter]: 1.59e-06 [virtual_shard_identity]: 1.856e-05 [virtual_dataset]: 1.8e-05 [get_grad_eliminate_]: 1.808e-05 [virtual_output]: 1.748e-05 [merge_forward]: 9.79e-06 [cell_reuse_recompute_pass]: 3.53e-06 [offload_activation]: 1.939e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.541e-05 [merge_recompute_call_nodes]: 1.52001e-06 [before_grad]: 3.085e-05 [set_forward_comm_id_for_comm_node_pass]: 1.037e-05 [meta_fg_expand]: 7.92e-06 [flash_sp_send_recv_attached]: 6.12001e-06 [receive_attached]: 3.10002e-06 [after_resolve]: 2.273e-05 [a_after_grad]: 2.802e-05 [renormalize]: 0.00737073 [add_forward_monad_depend]: 2.006e-05 [auto_monad_grad]: 2.66e-06 [auto_monad_eliminator]: 4.381e-05 [cse]: 0.00015857 [a_3]: 0.00014032 [Cycle 2]: 0.00177421, [45] [expand_dump_flag]: 3.02002e-06 [switch_simplify]: 1.933e-05 [loop_unroll]: 1.608e-05 [a_1]: 0.00050212 [with_stream_mark]: 3.113e-05 [recompute_prepare]: 2.017e-05 [updatestate_depend_eliminate]: 1.146e-05 [updatestate_assign_eliminate]: 8.44998e-06 [updatestate_loads_eliminate]: 9.17999e-06 [parameter_eliminate]: 2.64999e-06 [a_2]: 0.0002404 [accelerated_algorithm]: 2.358e-05 [shard]: 2.77002e-06 [meta_shard_fg_expand]: 4.63999e-06 [shard_inline]: 1.558e-05 [merge_send_recv]: 2.35e-05 [auto_parallel]: 2.079e-05 [parallel]: 1.003e-05 [flash_sp]: 5.47999e-06 [merge_comm]: 1.032e-05 [allreduce_fusion]: 1.104e-05 [matmul_add_comm_reduction]: 1.873e-05 [allreduce_slice_to_reducescatter]: 9.00007e-07 [virtual_shard_identity]: 2.131e-05 [virtual_dataset]: 1.642e-05 [get_grad_eliminate_]: 1.471e-05 [virtual_output]: 1.494e-05 [merge_forward]: 1.063e-05 [cell_reuse_recompute_pass]: 3.65e-06 [offload_activation]: 1.962e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.538e-05 [merge_recompute_call_nodes]: 1.94999e-06 [before_grad]: 2.711e-05 [set_forward_comm_id_for_comm_node_pass]: 1.134e-05 [meta_fg_expand]: 7.86001e-06 [flash_sp_send_recv_attached]: 2.01998e-06 [receive_attached]: 2.25002e-06 [after_resolve]: 2.033e-05 [a_after_grad]: 2.674e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 3.73001e-06 [auto_monad_grad]: 2.37999e-06 [auto_monad_eliminator]: 2.71e-05 [cse]: 6.057e-05 [a_3]: 0.00010245 [py_interpret_to_execute_after_opt_a]: 2.966e-05 [slice_cell_reuse_recomputed_activation]: 1.94e-06 [rewriter_after_opt_a]: 0.00044869 [convert_after_rewriter]: 2.037e-05 [order_py_execute_after_rewriter]: 1.192e-05 [mutable_eliminate]: 0.00085023 [opt_b]: 0.00059888, [1] [Cycle 1]: 0.00059054, [7] [b_1]: 0.00042346 [b_2]: 1.973e-05 [updatestate_depend_eliminate]: 1.418e-05 [updatestate_assign_eliminate]: 7.97e-06 [updatestate_loads_eliminate]: 7.75e-06 [renormalize]: 7.29982e-07 [cse]: 6.866e-05 [optimize_parallel_all_gather_comm]: 3.439e-05 [overlap_param_gather]: 2.12999e-06 [cconv]: 3.833e-05 [loop_unroll]: 0.00058511 [opt_after_cconv]: 0.0002195, [1] [Cycle 1]: 0.00021083, [7] [c_1]: 8.026e-05 [parameter_eliminate]: 4.68001e-06 [updatestate_depend_eliminate]: 1.489e-05 [updatestate_assign_eliminate]: 8.13999e-06 [updatestate_loads_eliminate]: 7.11001e-06 [cse]: 5.805e-05 [renormalize]: 7.79983e-07 [remove_dup_value]: 8.408e-05 [tuple_transform]: 0.0002636, [1] [Cycle 1]: 0.00025878, [4] [d_1]: 0.00021051 [none_parameter_eliminate]: 2.48998e-06 [renormalize]: 5.19998e-07 [switch_simplify]: 1.94e-05 [partial_unused_args_eliminate]: 2.01e-06 [add_recomputation]: 0.00013704 [cse_after_recomputation]: 6.302e-05, [1] [Cycle 1]: 5.515e-05, [1] [cse]: 4.544e-05 [environ_conv]: 1.646e-05 [swap_dp_allreduce_reducescatter]: 1.407e-05 [bias_add_comm_swap]: 3.91999e-06 [label_micro_interleaved_index]: 5.72001e-06 [label_fine_grained_interleaved_index]: 2.73e-06 [merge_cast_opt]: 1.60001e-06 [slice_recompute_activation]: 2.14e-06 [micro_interleaved_order_control]: 2.79001e-06 [assign_add_opt]: 1.82001e-06 [ForceFp32Comm]: 8.70001e-07 [remove_cast_before_assign_add]: 1.49998e-06 [full_micro_interleaved_order_control]: 2.34001e-06 [reorder_send_recv_between_fp_bp]: 3.03e-06 [comm_op_add_attrs]: 1.05999e-06 [add_comm_op_reuse_tag]: 1.26002e-06 [interleave_split_concat_branches]: 1.24998e-06 [interleave_parallel_branches]: 1.07e-06 [overlap_opt_shard_in_pipeline]: 3.11999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.39999e-06 [control_data_broadcast_order]: 3.246e-05 [grouped_pairwise_exchange_alltoall]: 1.60999e-06 [offloading_packed_experts]: 8.99e-06 [overlap_recompute_and_grad_model_parallel]: 8.80999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.24e-06 [overlap_recompute_allgather_and_fa_grad]: 1.42e-06 [overlap_recompute_comm]: 2.34001e-06 [overlap_grad_ring_attention]: 7.95998e-06 [overlap_grad_flash_sp]: 4.621e-05 [begin_end_overlap_inline]: 7.2e-07 [split_matmul_comm_elemetwise]: 2.34001e-06 [split_layernorm_comm]: 1.92999e-06 [handle_group_info]: 1.02e-06 [symbol_engine_optimizer]: 0.00016642, [1] [Cycle 1]: 0.00016134, [6] [build]: 1.778e-05 [elim_shapecalc]: 2.762e-05 [elim_not_effective]: 3.281e-05 [opt_reshape]: 1.772e-05 [fold_const_symbol]: 2.717e-05 [renormalize]: 2.19996e-07 [detach_backward]: 3.32002e-06 [pipeline_parallel_scheduler]: 1.44e-06 [auto_monad_reorder]: 4.298e-05 [get_jit_bprop_graph]: 1.77999e-06 [rewriter_after_jit_bprop_graph]: 7.53999e-06 [opt_after_jit_grad]: 0.00062029 [validate]: 9.689e-05 Sums bootstrap : 0.000861s : 0.02% type_inference : 3.226814s : 88.53% event_method : 0.001117s : 0.03% auto_monad : 0.000117s : 0.00% graph_reusing : 0.000008s : 0.00% inline : 0.000002s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000036s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000008s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000048s : 0.00% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000035s : 0.00% optimize.rewriter_before_opt_a : 0.000119s : 0.00% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000073s : 0.00% optimize.opt_a.loop_unroll : 0.000054s : 0.00% optimize.opt_a.a_1 : 0.001833s : 0.05% optimize.opt_a.with_stream_mark : 0.399835s : 10.97% optimize.opt_a.recompute_prepare : 0.000078s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000026s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000017s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000554s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000065s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000014s : 0.00% optimize.opt_a.shard_inline : 0.000032s : 0.00% optimize.opt_a.merge_send_recv : 0.000040s : 0.00% optimize.opt_a.auto_parallel : 0.000038s : 0.00% optimize.opt_a.parallel : 0.000049s : 0.00% optimize.opt_a.flash_sp : 0.000019s : 0.00% optimize.opt_a.merge_comm : 0.000021s : 0.00% optimize.opt_a.allreduce_fusion : 0.000021s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000037s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000040s : 0.00% optimize.opt_a.virtual_dataset : 0.000034s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000033s : 0.00% optimize.opt_a.virtual_output : 0.000032s : 0.00% optimize.opt_a.merge_forward : 0.000020s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000007s : 0.00% optimize.opt_a.offload_activation : 0.000039s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000071s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000058s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000022s : 0.00% optimize.opt_a.meta_fg_expand : 0.000016s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000043s : 0.00% optimize.opt_a.a_after_grad : 0.000055s : 0.00% optimize.opt_a.renormalize : 0.007371s : 0.20% optimize.opt_a.add_forward_monad_depend : 0.000024s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000071s : 0.00% optimize.opt_a.cse : 0.000219s : 0.01% optimize.opt_a.a_3 : 0.000243s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000030s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000449s : 0.01% optimize.convert_after_rewriter : 0.000020s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000850s : 0.02% optimize.opt_b.b_1 : 0.000423s : 0.01% optimize.opt_b.b_2 : 0.000020s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000069s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000034s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000038s : 0.00% optimize.loop_unroll : 0.000585s : 0.02% optimize.opt_after_cconv.c_1 : 0.000080s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000058s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000084s : 0.00% optimize.tuple_transform.d_1 : 0.000211s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000001s : 0.00% optimize.tuple_transform.switch_simplify : 0.000019s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000137s : 0.00% optimize.cse_after_recomputation.cse : 0.000045s : 0.00% optimize.environ_conv : 0.000016s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000014s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000032s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000009s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000046s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000028s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000033s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000018s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000027s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000043s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000620s : 0.02% validate : 0.000097s : 0.00% Time group info: ------[substitution.] 0.000671 197 9.00% : 0.000060s : 6: substitution.arithmetic_simplify 0.71% : 0.000005s : 10: substitution.elim_not_effective 2.47% : 0.000017s : 12: substitution.float_tuple_getitem_switch 0.54% : 0.000004s : 10: substitution.fold_const_symbol 1.94% : 0.000013s : 12: substitution.graph_param_transform 36.97% : 0.000248s : 7: substitution.inline 1.57% : 0.000011s : 20: substitution.j_node_and_user_rematch 3.26% : 0.000022s : 2: substitution.less_batch_normalization 2.83% : 0.000019s : 8: substitution.minmaximum_grad 2.27% : 0.000015s : 20: substitution.remove_not_recompute_node 1.09% : 0.000007s : 2: substitution.replace_old_param 8.38% : 0.000056s : 16: substitution.tuple_list_convert_item_index_to_positive 4.52% : 0.000030s : 16: substitution.tuple_list_get_item_const_eliminator 5.94% : 0.000040s : 16: substitution.tuple_list_get_item_depend_reorder 12.79% : 0.000086s : 24: substitution.tuple_list_get_item_eliminator 5.74% : 0.000039s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 3.226712 2 99.88% : 3.222758s : 1: type_inference.infer 0.12% : 0.003954s : 1: type_inference.specialize ------[replace.] 0.000067 7 100.00% : 0.000067s : 7: replace.inline ------[match.] 0.000243 7 100.00% : 0.000243s : 7: match.inline ------[predicate.] 0.000532 3093 0.86% : 0.000005s : 30: predicate.accumulaten_eliminater 0.84% : 0.000004s : 12: predicate.ad_related_special_op_eliminate 0.67% : 0.000004s : 24: predicate.addn_check_dump 0.80% : 0.000004s : 30: predicate.addn_zero_filter 0.75% : 0.000004s : 30: predicate.adjust_all_reduce_mul_add 2.53% : 0.000013s : 54: predicate.arithmetic_simplify 0.89% : 0.000005s : 30: predicate.cast_eliminate 0.71% : 0.000004s : 24: predicate.check_bprop_eliminate 0.72% : 0.000004s : 24: predicate.compare_switch_simplify 0.23% : 0.000001s : 12: predicate.const_output_eliminate 0.70% : 0.000004s : 24: predicate.depend_value_elim 0.95% : 0.000005s : 30: predicate.dict_get_item_const_eliminator 1.17% : 0.000006s : 30: predicate.dict_get_item_eliminator 0.82% : 0.000004s : 30: predicate.dict_set_item_eliminator 1.73% : 0.000009s : 24: predicate.dumpgradient_eliminate 0.22% : 0.000001s : 12: predicate.elim_not_effective 0.48% : 0.000003s : 12: predicate.elim_shapecalc_of_broadcastargs 1.15% : 0.000006s : 42: predicate.environ_add_const_eliminate 1.14% : 0.000006s : 42: predicate.environ_get_add_eliminate 1.09% : 0.000006s : 42: predicate.environ_get_depend_swap 1.91% : 0.000010s : 66: predicate.environ_get_eliminate 1.11% : 0.000006s : 42: predicate.environ_get_set_eliminate 0.95% : 0.000005s : 37: predicate.exchange_switch_depend_value 1.55% : 0.000008s : 37: predicate.float_depend_g_call 0.70% : 0.000004s : 24: predicate.float_environ_get_switch 1.53% : 0.000008s : 36: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 12: predicate.fold_const_symbol 0.77% : 0.000004s : 24: predicate.get_grad_eliminate 0.26% : 0.000001s : 12: predicate.graph_param_transform 0.76% : 0.000004s : 24: predicate.incorporate_call 0.59% : 0.000003s : 24: predicate.incorporate_call_switch 5.47% : 0.000029s : 139: predicate.inline 0.97% : 0.000005s : 24: predicate.inline_without_move 0.33% : 0.000002s : 24: predicate.j_node_and_user_rematch 1.00% : 0.000005s : 24: predicate.less_batch_normalization 1.63% : 0.000009s : 54: predicate.list_to_tuple_eliminator_ 2.18% : 0.000012s : 84: predicate.load_eliminater 1.04% : 0.000006s : 12: predicate.loop_unroll_after_grad 1.46% : 0.000008s : 52: predicate.loop_unroll_before_grad 1.56% : 0.000008s : 54: predicate.make_slice_get_slice_eliminator 0.74% : 0.000004s : 24: predicate.merge_addn 0.72% : 0.000004s : 24: predicate.micro_step_allgather_replace 0.70% : 0.000004s : 24: predicate.mini_step_allgather_replace 0.93% : 0.000005s : 30: predicate.minmaximum_grad 1.11% : 0.000006s : 12: predicate.mutable_eliminate 0.44% : 0.000002s : 12: predicate.opt_reshape 0.44% : 0.000002s : 12: predicate.parallel_virtual_node 1.48% : 0.000008s : 37: predicate.partial_defer_inline 1.20% : 0.000006s : 42: predicate.partial_eliminate 0.81% : 0.000004s : 30: predicate.print_const_string_wrapper 0.81% : 0.000004s : 24: predicate.reduce_all_const_elim 1.29% : 0.000007s : 30: predicate.reduce_eliminate 2.26% : 0.000012s : 84: predicate.redundant_stop_gradient_eliminater 0.42% : 0.000002s : 24: predicate.remove_not_recompute_node 1.10% : 0.000006s : 54: predicate.replace_applicator 0.49% : 0.000003s : 24: predicate.replace_old_param 0.24% : 0.000001s : 12: predicate.reset_defer_inline 0.87% : 0.000005s : 30: predicate.reshape_eliminate 0.83% : 0.000004s : 24: predicate.row_tensor_add_zeros_like 0.49% : 0.000003s : 12: predicate.row_tensor_eliminate 0.93% : 0.000005s : 24: predicate.same_eliminate 0.74% : 0.000004s : 24: predicate.set_cell_output_no_recompute 0.87% : 0.000005s : 24: predicate.shard_identity_eliminate 0.78% : 0.000004s : 24: predicate.special_op_eliminate 0.92% : 0.000005s : 24: predicate.specialize_transform 1.08% : 0.000006s : 24: predicate.split_environ_get_set_with_tuple_value 0.97% : 0.000005s : 24: predicate.stack_unstack_eliminate 0.36% : 0.000002s : 12: predicate.switch_call_monad_eliminater 1.07% : 0.000006s : 37: predicate.switch_defer_inline 1.72% : 0.000009s : 61: predicate.switch_layer_defer_inline 4.17% : 0.000022s : 125: predicate.switch_simplify 0.78% : 0.000004s : 30: predicate.tile_eliminate 0.85% : 0.000005s : 30: predicate.transpose_eliminate 1.82% : 0.000010s : 54: predicate.tuple_list_convert_item_index_to_positive 1.84% : 0.000010s : 54: predicate.tuple_list_get_item_const_eliminator 1.80% : 0.000010s : 54: predicate.tuple_list_get_item_depend_reorder 3.35% : 0.000018s : 78: predicate.tuple_list_get_item_eliminator 1.86% : 0.000010s : 54: predicate.tuple_list_get_set_item_eliminator 2.55% : 0.000014s : 78: predicate.tuple_list_set_item_eliminator 1.54% : 0.000008s : 54: predicate.tuple_to_list_eliminator_ 2.13% : 0.000011s : 84: predicate.updatestate_pure_node_eliminater 3.12% : 0.000017s : 108: predicate.updatestate_useless_node_eliminater 0.44% : 0.000002s : 12: predicate.value_based_eliminate 0.83% : 0.000004s : 24: predicate.virtual_dataset_eliminate 0.83% : 0.000004s : 24: predicate.virtual_output_eliminate 0.43% : 0.000002s : 12: predicate.virtual_view_grad_eliminate 0.44% : 0.000002s : 12: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.286538 38 99.18% : 0.284183s : 29: func_graph_cloner_run.FuncGraphClonerGraph 0.82% : 0.002355s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 4.082747 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.11% : 0.004599s : 1: add_attr 0.11% : 0.004582s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000142s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.00% : 0.000126s : 1: auto_monad 0.00% : 0.000048s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.02% : 0.000910s : 1: bootstrap 0.00% : 0.000042s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000037s : 1: control_data_broadcast_order 0.00% : 0.000026s : 1: convert_after_rewriter 0.00% : 0.000066s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000021s : 1: environ_conv 0.03% : 0.001135s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000005s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.01% : 0.000595s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.02% : 0.000861s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.00% : 0.000034s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000037s : 1: opt.transform.mutable_eliminate 0.08% : 0.003165s : 78: opt.transform.opt_a 0.00% : 0.000078s : 1: opt.transform.opt_after_cconv 0.00% : 0.000066s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000404s : 28: opt.transform.opt_b 0.01% : 0.000226s : 2: opt.transform.opt_trans_graph 0.00% : 0.000101s : 4: opt.transform.symbol_engine_opt 10.09% : 0.412007s : 1: opt_a 0.01% : 0.000224s : 1: opt_after_cconv 0.02% : 0.000631s : 1: opt_after_jit_grad 0.01% : 0.000603s : 1: opt_b 10.19% : 0.416181s : 1: optimize 0.00% : 0.000039s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.00% : 0.000050s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000053s : 1: pre_auto_parallel 0.00% : 0.000039s : 1: py_interpret_to_execute 0.00% : 0.000034s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000089s : 1: remove_dup_value 0.10% : 0.003989s : 1: renormalize.infer 0.08% : 0.003362s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000457s : 1: rewriter_after_opt_a 0.00% : 0.000123s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000017s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000171s : 1: symbol_engine_optimizer 0.01% : 0.000268s : 1: tuple_transform 79.04% : 3.226842s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[False-False-bfloat16--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[False-False-bfloat16--1-shape1],max_mem:106.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:39:16.508.541 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 3.99681, [21] [bootstrap]: 0.00087711 [type_inference]: 3.48759 [event_method]: 0.00046489 [auto_monad]: 0.00011977 [graph_reusing]: 7.27002e-06 [inline]: 6.28e-06 [add_attr]: 0.491487, [1] [add_attr_with_inline]: 0.491474, [1] [Cycle 1]: 6.943e-05, [2] [tag_attr]: 2.95e-05 [meta_addattr_fg_expand]: 6.34999e-06 [parallel-infer-symbol]: 2.93998e-06 [pre_auto_parallel]: 4.667e-05 [insert-virtual-dataset]: 3.31999e-06 [parallel-infer-symbol-second]: 6.60017e-07 [dataset_repeat_opt]: 1.67999e-06 [pipeline_split]: 3.04001e-06 [optimize]: 0.0152778, [53] [py_interpret_to_execute]: 3.22e-05 [rewriter_before_opt_a]: 0.00011837 [opt_a]: 0.0115488, [2] [Cycle 1]: 0.00992054, [45] [expand_dump_flag]: 2.87002e-06 [switch_simplify]: 5.006e-05 [loop_unroll]: 3.813e-05 [a_1]: 0.00133621 [with_stream_mark]: 2.316e-05 [recompute_prepare]: 2.111e-05 [updatestate_depend_eliminate]: 1.093e-05 [updatestate_assign_eliminate]: 8.28999e-06 [updatestate_loads_eliminate]: 7.6e-06 [parameter_eliminate]: 1.99e-06 [a_2]: 0.0002632 [accelerated_algorithm]: 3.794e-05 [shard]: 1.87999e-06 [meta_shard_fg_expand]: 4.18999e-06 [shard_inline]: 1.668e-05 [merge_send_recv]: 1.382e-05 [auto_parallel]: 1.38e-05 [parallel]: 2.965e-05 [flash_sp]: 9.72001e-06 [merge_comm]: 1.078e-05 [allreduce_fusion]: 9.33002e-06 [matmul_add_comm_reduction]: 1.397e-05 [allreduce_slice_to_reducescatter]: 4.99975e-07 [virtual_shard_identity]: 1.925e-05 [virtual_dataset]: 1.694e-05 [get_grad_eliminate_]: 1.795e-05 [virtual_output]: 1.667e-05 [merge_forward]: 1.007e-05 [cell_reuse_recompute_pass]: 1.36002e-06 [offload_activation]: 1.712e-05 [cell_reuse_handle_not_recompute_node_pass]: 6.006e-05 [merge_recompute_call_nodes]: 1.37e-06 [before_grad]: 2.945e-05 [set_forward_comm_id_for_comm_node_pass]: 1.084e-05 [meta_fg_expand]: 7.26999e-06 [flash_sp_send_recv_attached]: 4.15999e-06 [receive_attached]: 1.99999e-06 [after_resolve]: 2.192e-05 [a_after_grad]: 2.78e-05 [renormalize]: 0.00670232 [add_forward_monad_depend]: 1.629e-05 [auto_monad_grad]: 2.66e-06 [auto_monad_eliminator]: 3.579e-05 [cse]: 0.00053118 [a_3]: 0.00013039 [Cycle 2]: 0.00161475, [45] [expand_dump_flag]: 2.80002e-06 [switch_simplify]: 1.889e-05 [loop_unroll]: 1.617e-05 [a_1]: 0.00052744 [with_stream_mark]: 2.462e-05 [recompute_prepare]: 1.66e-05 [updatestate_depend_eliminate]: 9.65002e-06 [updatestate_assign_eliminate]: 8.29002e-06 [updatestate_loads_eliminate]: 7.88001e-06 [parameter_eliminate]: 1.92999e-06 [a_2]: 0.00024091 [accelerated_algorithm]: 2.107e-05 [shard]: 2.01e-06 [meta_shard_fg_expand]: 4.39002e-06 [shard_inline]: 1.508e-05 [merge_send_recv]: 1.52e-05 [auto_parallel]: 1.555e-05 [parallel]: 8.80999e-06 [flash_sp]: 3.76001e-06 [merge_comm]: 9.91e-06 [allreduce_fusion]: 9.79999e-06 [matmul_add_comm_reduction]: 1.624e-05 [allreduce_slice_to_reducescatter]: 6.90023e-07 [virtual_shard_identity]: 1.556e-05 [virtual_dataset]: 1.569e-05 [get_grad_eliminate_]: 1.473e-05 [virtual_output]: 1.422e-05 [merge_forward]: 9.00001e-06 [cell_reuse_recompute_pass]: 3.30003e-06 [offload_activation]: 1.842e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.084e-05 [merge_recompute_call_nodes]: 1.67001e-06 [before_grad]: 2.601e-05 [set_forward_comm_id_for_comm_node_pass]: 9.60001e-06 [meta_fg_expand]: 7.5e-06 [flash_sp_send_recv_attached]: 1.40001e-06 [receive_attached]: 2.52001e-06 [after_resolve]: 2.003e-05 [a_after_grad]: 2.695e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 2.39001e-06 [auto_monad_grad]: 1.69e-06 [auto_monad_eliminator]: 2.22e-05 [cse]: 5.347e-05 [a_3]: 9.902e-05 [py_interpret_to_execute_after_opt_a]: 2.373e-05 [slice_cell_reuse_recomputed_activation]: 2.39999e-06 [rewriter_after_opt_a]: 0.00041076 [convert_after_rewriter]: 1.658e-05 [order_py_execute_after_rewriter]: 1.167e-05 [mutable_eliminate]: 0.00076084 [opt_b]: 0.00055622, [1] [Cycle 1]: 0.00054864, [7] [b_1]: 0.00040474 [b_2]: 1.746e-05 [updatestate_depend_eliminate]: 1.223e-05 [updatestate_assign_eliminate]: 7.71999e-06 [updatestate_loads_eliminate]: 7.45e-06 [renormalize]: 8.59989e-07 [cse]: 5.805e-05 [optimize_parallel_all_gather_comm]: 2.855e-05 [overlap_param_gather]: 5.90002e-06 [cconv]: 3.172e-05 [loop_unroll]: 0.00048255 [opt_after_cconv]: 0.0002067, [1] [Cycle 1]: 0.00019984, [7] [c_1]: 8.052e-05 [parameter_eliminate]: 3.11999e-06 [updatestate_depend_eliminate]: 1.338e-05 [updatestate_assign_eliminate]: 7.73001e-06 [updatestate_loads_eliminate]: 7.06001e-06 [cse]: 5.27e-05 [renormalize]: 4.49974e-07 [remove_dup_value]: 9.142e-05 [tuple_transform]: 0.00021455, [1] [Cycle 1]: 0.00020921, [4] [d_1]: 0.00016802 [none_parameter_eliminate]: 2.23002e-06 [renormalize]: 3.19997e-07 [switch_simplify]: 1.63e-05 [partial_unused_args_eliminate]: 2.13002e-06 [add_recomputation]: 0.00011096 [cse_after_recomputation]: 5.422e-05, [1] [Cycle 1]: 4.827e-05, [1] [cse]: 4.195e-05 [environ_conv]: 1.388e-05 [swap_dp_allreduce_reducescatter]: 1.209e-05 [bias_add_comm_swap]: 2.54999e-06 [label_micro_interleaved_index]: 4.66002e-06 [label_fine_grained_interleaved_index]: 2.91e-06 [merge_cast_opt]: 1.48002e-06 [slice_recompute_activation]: 2.24001e-06 [micro_interleaved_order_control]: 2.70997e-06 [assign_add_opt]: 1.22999e-06 [ForceFp32Comm]: 9.49978e-07 [remove_cast_before_assign_add]: 1.44e-06 [full_micro_interleaved_order_control]: 2.13998e-06 [reorder_send_recv_between_fp_bp]: 2.92002e-06 [comm_op_add_attrs]: 1.05001e-06 [add_comm_op_reuse_tag]: 1.04e-06 [interleave_split_concat_branches]: 1.22999e-06 [interleave_parallel_branches]: 1.09e-06 [overlap_opt_shard_in_pipeline]: 3.20998e-06 [overlap_opt_shard_grad_in_pipeline]: 2.12999e-06 [control_data_broadcast_order]: 2.792e-05 [grouped_pairwise_exchange_alltoall]: 1.59e-06 [offloading_packed_experts]: 8.74e-06 [overlap_recompute_and_grad_model_parallel]: 7.91001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.27e-06 [overlap_recompute_allgather_and_fa_grad]: 1.50001e-06 [overlap_recompute_comm]: 3.01001e-06 [overlap_grad_ring_attention]: 7.43999e-06 [overlap_grad_flash_sp]: 4.24e-05 [begin_end_overlap_inline]: 5.59987e-07 [split_matmul_comm_elemetwise]: 2.31998e-06 [split_layernorm_comm]: 1.81e-06 [handle_group_info]: 9.39996e-07 [symbol_engine_optimizer]: 0.0001426, [1] [Cycle 1]: 0.00013783, [6] [build]: 1.364e-05 [elim_shapecalc]: 2.094e-05 [elim_not_effective]: 3.018e-05 [opt_reshape]: 1.606e-05 [fold_const_symbol]: 2.696e-05 [renormalize]: 2.00002e-07 [detach_backward]: 2.36e-06 [pipeline_parallel_scheduler]: 1.59e-06 [auto_monad_reorder]: 3.404e-05 [get_jit_bprop_graph]: 2.05002e-06 [rewriter_after_jit_bprop_graph]: 5.51e-06 [opt_after_jit_grad]: 0.00054559 [validate]: 8.361e-05 Sums bootstrap : 0.000877s : 0.03% type_inference : 3.487594s : 99.53% event_method : 0.000465s : 0.01% auto_monad : 0.000120s : 0.00% graph_reusing : 0.000007s : 0.00% inline : 0.000006s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000029s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000003s : 0.00% pre_auto_parallel : 0.000047s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000032s : 0.00% optimize.rewriter_before_opt_a : 0.000118s : 0.00% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000069s : 0.00% optimize.opt_a.loop_unroll : 0.000054s : 0.00% optimize.opt_a.a_1 : 0.001864s : 0.05% optimize.opt_a.with_stream_mark : 0.000048s : 0.00% optimize.opt_a.recompute_prepare : 0.000038s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000015s : 0.00% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000504s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000059s : 0.00% optimize.opt_a.shard : 0.000004s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.00% optimize.opt_a.shard_inline : 0.000032s : 0.00% optimize.opt_a.merge_send_recv : 0.000029s : 0.00% optimize.opt_a.auto_parallel : 0.000029s : 0.00% optimize.opt_a.parallel : 0.000038s : 0.00% optimize.opt_a.flash_sp : 0.000013s : 0.00% optimize.opt_a.merge_comm : 0.000021s : 0.00% optimize.opt_a.allreduce_fusion : 0.000019s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000030s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000035s : 0.00% optimize.opt_a.virtual_dataset : 0.000033s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000033s : 0.00% optimize.opt_a.virtual_output : 0.000031s : 0.00% optimize.opt_a.merge_forward : 0.000019s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000036s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000091s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000055s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000020s : 0.00% optimize.opt_a.meta_fg_expand : 0.000015s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000042s : 0.00% optimize.opt_a.a_after_grad : 0.000055s : 0.00% optimize.opt_a.renormalize : 0.006702s : 0.19% optimize.opt_a.add_forward_monad_depend : 0.000019s : 0.00% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000058s : 0.00% optimize.opt_a.cse : 0.000585s : 0.02% optimize.opt_a.a_3 : 0.000229s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000024s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000411s : 0.01% optimize.convert_after_rewriter : 0.000017s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000761s : 0.02% optimize.opt_b.b_1 : 0.000405s : 0.01% optimize.opt_b.b_2 : 0.000017s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000058s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000029s : 0.00% optimize.overlap_param_gather : 0.000006s : 0.00% optimize.cconv : 0.000032s : 0.00% optimize.loop_unroll : 0.000483s : 0.01% optimize.opt_after_cconv.c_1 : 0.000081s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000053s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000091s : 0.00% optimize.tuple_transform.d_1 : 0.000168s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000016s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000111s : 0.00% optimize.cse_after_recomputation.cse : 0.000042s : 0.00% optimize.environ_conv : 0.000014s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000012s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000028s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000009s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000042s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000014s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000021s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000030s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000016s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000027s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000034s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000546s : 0.02% validate : 0.000084s : 0.00% Time group info: ------[substitution.] 0.000594 197 6.98% : 0.000041s : 6: substitution.arithmetic_simplify 0.74% : 0.000004s : 10: substitution.elim_not_effective 2.60% : 0.000015s : 12: substitution.float_tuple_getitem_switch 0.65% : 0.000004s : 10: substitution.fold_const_symbol 2.06% : 0.000012s : 12: substitution.graph_param_transform 40.41% : 0.000240s : 7: substitution.inline 1.58% : 0.000009s : 20: substitution.j_node_and_user_rematch 3.31% : 0.000020s : 2: substitution.less_batch_normalization 2.80% : 0.000017s : 8: substitution.minmaximum_grad 2.47% : 0.000015s : 20: substitution.remove_not_recompute_node 1.01% : 0.000006s : 2: substitution.replace_old_param 8.47% : 0.000050s : 16: substitution.tuple_list_convert_item_index_to_positive 4.29% : 0.000025s : 16: substitution.tuple_list_get_item_const_eliminator 5.78% : 0.000034s : 16: substitution.tuple_list_get_item_depend_reorder 11.45% : 0.000068s : 24: substitution.tuple_list_get_item_eliminator 5.39% : 0.000032s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 3.487478 2 99.86% : 3.482549s : 1: type_inference.infer 0.14% : 0.004930s : 1: type_inference.specialize ------[replace.] 0.000060 7 100.00% : 0.000060s : 7: replace.inline ------[match.] 0.000235 7 100.00% : 0.000235s : 7: match.inline ------[predicate.] 0.000494 3093 1.03% : 0.000005s : 30: predicate.accumulaten_eliminater 0.79% : 0.000004s : 12: predicate.ad_related_special_op_eliminate 0.71% : 0.000004s : 24: predicate.addn_check_dump 1.01% : 0.000005s : 30: predicate.addn_zero_filter 0.81% : 0.000004s : 30: predicate.adjust_all_reduce_mul_add 2.30% : 0.000011s : 54: predicate.arithmetic_simplify 0.86% : 0.000004s : 30: predicate.cast_eliminate 0.75% : 0.000004s : 24: predicate.check_bprop_eliminate 0.73% : 0.000004s : 24: predicate.compare_switch_simplify 0.21% : 0.000001s : 12: predicate.const_output_eliminate 0.76% : 0.000004s : 24: predicate.depend_value_elim 0.92% : 0.000005s : 30: predicate.dict_get_item_const_eliminator 1.06% : 0.000005s : 30: predicate.dict_get_item_eliminator 0.85% : 0.000004s : 30: predicate.dict_set_item_eliminator 0.95% : 0.000005s : 24: predicate.dumpgradient_eliminate 0.20% : 0.000001s : 12: predicate.elim_not_effective 0.42% : 0.000002s : 12: predicate.elim_shapecalc_of_broadcastargs 1.25% : 0.000006s : 42: predicate.environ_add_const_eliminate 1.13% : 0.000006s : 42: predicate.environ_get_add_eliminate 1.18% : 0.000006s : 42: predicate.environ_get_depend_swap 1.96% : 0.000010s : 66: predicate.environ_get_eliminate 1.16% : 0.000006s : 42: predicate.environ_get_set_eliminate 1.07% : 0.000005s : 37: predicate.exchange_switch_depend_value 1.71% : 0.000008s : 37: predicate.float_depend_g_call 0.74% : 0.000004s : 24: predicate.float_environ_get_switch 1.37% : 0.000007s : 36: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 12: predicate.fold_const_symbol 0.86% : 0.000004s : 24: predicate.get_grad_eliminate 0.22% : 0.000001s : 12: predicate.graph_param_transform 0.68% : 0.000003s : 24: predicate.incorporate_call 0.62% : 0.000003s : 24: predicate.incorporate_call_switch 5.54% : 0.000027s : 139: predicate.inline 1.01% : 0.000005s : 24: predicate.inline_without_move 0.35% : 0.000002s : 24: predicate.j_node_and_user_rematch 0.92% : 0.000005s : 24: predicate.less_batch_normalization 1.77% : 0.000009s : 54: predicate.list_to_tuple_eliminator_ 2.26% : 0.000011s : 84: predicate.load_eliminater 0.84% : 0.000004s : 12: predicate.loop_unroll_after_grad 1.49% : 0.000007s : 52: predicate.loop_unroll_before_grad 1.65% : 0.000008s : 54: predicate.make_slice_get_slice_eliminator 0.75% : 0.000004s : 24: predicate.merge_addn 0.75% : 0.000004s : 24: predicate.micro_step_allgather_replace 0.71% : 0.000004s : 24: predicate.mini_step_allgather_replace 0.86% : 0.000004s : 30: predicate.minmaximum_grad 0.98% : 0.000005s : 12: predicate.mutable_eliminate 0.42% : 0.000002s : 12: predicate.opt_reshape 0.43% : 0.000002s : 12: predicate.parallel_virtual_node 1.52% : 0.000007s : 37: predicate.partial_defer_inline 1.30% : 0.000006s : 42: predicate.partial_eliminate 0.89% : 0.000004s : 30: predicate.print_const_string_wrapper 0.70% : 0.000003s : 24: predicate.reduce_all_const_elim 1.26% : 0.000006s : 30: predicate.reduce_eliminate 2.27% : 0.000011s : 84: predicate.redundant_stop_gradient_eliminater 0.39% : 0.000002s : 24: predicate.remove_not_recompute_node 1.09% : 0.000005s : 54: predicate.replace_applicator 0.42% : 0.000002s : 24: predicate.replace_old_param 0.22% : 0.000001s : 12: predicate.reset_defer_inline 0.93% : 0.000005s : 30: predicate.reshape_eliminate 0.75% : 0.000004s : 24: predicate.row_tensor_add_zeros_like 0.44% : 0.000002s : 12: predicate.row_tensor_eliminate 0.98% : 0.000005s : 24: predicate.same_eliminate 0.43% : 0.000002s : 24: predicate.set_cell_output_no_recompute 0.91% : 0.000004s : 24: predicate.shard_identity_eliminate 0.83% : 0.000004s : 24: predicate.special_op_eliminate 0.85% : 0.000004s : 24: predicate.specialize_transform 0.97% : 0.000005s : 24: predicate.split_environ_get_set_with_tuple_value 0.89% : 0.000004s : 24: predicate.stack_unstack_eliminate 0.39% : 0.000002s : 12: predicate.switch_call_monad_eliminater 1.13% : 0.000006s : 37: predicate.switch_defer_inline 1.83% : 0.000009s : 61: predicate.switch_layer_defer_inline 4.03% : 0.000020s : 125: predicate.switch_simplify 0.92% : 0.000005s : 30: predicate.tile_eliminate 0.90% : 0.000004s : 30: predicate.transpose_eliminate 1.82% : 0.000009s : 54: predicate.tuple_list_convert_item_index_to_positive 1.90% : 0.000009s : 54: predicate.tuple_list_get_item_const_eliminator 1.85% : 0.000009s : 54: predicate.tuple_list_get_item_depend_reorder 3.38% : 0.000017s : 78: predicate.tuple_list_get_item_eliminator 1.74% : 0.000009s : 54: predicate.tuple_list_get_set_item_eliminator 2.52% : 0.000012s : 78: predicate.tuple_list_set_item_eliminator 1.67% : 0.000008s : 54: predicate.tuple_to_list_eliminator_ 2.35% : 0.000012s : 84: predicate.updatestate_pure_node_eliminater 3.33% : 0.000016s : 108: predicate.updatestate_useless_node_eliminater 0.50% : 0.000002s : 12: predicate.value_based_eliminate 0.89% : 0.000004s : 24: predicate.virtual_dataset_eliminate 0.74% : 0.000004s : 24: predicate.virtual_output_eliminate 0.38% : 0.000002s : 12: predicate.virtual_view_grad_eliminate 0.48% : 0.000002s : 12: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.006495 38 69.80% : 0.004534s : 29: func_graph_cloner_run.FuncGraphClonerGraph 30.20% : 0.001961s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 4.513997 192 0.00% : 0.000004s : 1: ForceFp32Comm 10.89% : 0.491493s : 1: add_attr 10.89% : 0.491478s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.00% : 0.000116s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.00% : 0.000129s : 1: auto_monad 0.00% : 0.000039s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000005s : 1: bias_add_comm_swap 0.02% : 0.000932s : 1: bootstrap 0.00% : 0.000035s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000031s : 1: control_data_broadcast_order 0.00% : 0.000021s : 1: convert_after_rewriter 0.00% : 0.000057s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000005s : 1: detach_backward 0.00% : 0.000018s : 1: environ_conv 0.01% : 0.000482s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000009s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000007s : 1: label_micro_interleaved_index 0.01% : 0.000491s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.02% : 0.000770s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.00% : 0.000027s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000032s : 1: opt.transform.mutable_eliminate 0.07% : 0.003092s : 78: opt.transform.opt_a 0.00% : 0.000079s : 1: opt.transform.opt_after_cconv 0.00% : 0.000062s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000391s : 28: opt.transform.opt_b 0.00% : 0.000182s : 2: opt.transform.opt_trans_graph 0.00% : 0.000090s : 4: opt.transform.symbol_engine_opt 0.26% : 0.011553s : 1: opt_a 0.00% : 0.000210s : 1: opt_after_cconv 0.01% : 0.000556s : 1: opt_after_jit_grad 0.01% : 0.000560s : 1: opt_b 0.34% : 0.015284s : 1: optimize 0.00% : 0.000032s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.00% : 0.000046s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000010s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000051s : 1: pre_auto_parallel 0.00% : 0.000036s : 1: py_interpret_to_execute 0.00% : 0.000027s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000097s : 1: remove_dup_value 0.10% : 0.004303s : 1: renormalize.infer 0.05% : 0.002385s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000418s : 1: rewriter_after_opt_a 0.00% : 0.000123s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000146s : 1: symbol_engine_optimizer 0.00% : 0.000219s : 1: tuple_transform 77.26% : 3.487626s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[False-False-bfloat16--1-shape2] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[False-False-bfloat16--1-shape2],max_mem:106.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:39:27.870.596 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 4.41676, [21] [bootstrap]: 0.00081211 [type_inference]: 4.02179 [event_method]: 0.00147622 [auto_monad]: 0.00013442 [graph_reusing]: 8.72998e-06 [inline]: 5.82999e-06 [add_attr]: 0.216847, [1] [add_attr_with_inline]: 0.21683, [1] [Cycle 1]: 8.858e-05, [2] [tag_attr]: 3.478e-05 [meta_addattr_fg_expand]: 7.39002e-06 [parallel-infer-symbol]: 3.91001e-06 [pre_auto_parallel]: 5.471e-05 [insert-virtual-dataset]: 3.5e-06 [parallel-infer-symbol-second]: 7.09988e-07 [dataset_repeat_opt]: 2.14e-06 [pipeline_split]: 2.59001e-06 [optimize]: 0.174721, [53] [py_interpret_to_execute]: 3.964e-05 [rewriter_before_opt_a]: 0.00012695 [opt_a]: 0.170977, [2] [Cycle 1]: 0.169409, [45] [expand_dump_flag]: 3.77002e-06 [switch_simplify]: 5.505e-05 [loop_unroll]: 3.838e-05 [a_1]: 0.00150986 [with_stream_mark]: 2.9e-05 [recompute_prepare]: 2.15e-05 [updatestate_depend_eliminate]: 1.128e-05 [updatestate_assign_eliminate]: 9.76e-06 [updatestate_loads_eliminate]: 8.18001e-06 [parameter_eliminate]: 2.30997e-06 [a_2]: 0.0002687 [accelerated_algorithm]: 3.858e-05 [shard]: 2.66e-06 [meta_shard_fg_expand]: 4.79e-06 [shard_inline]: 1.573e-05 [merge_send_recv]: 1.53e-05 [auto_parallel]: 1.273e-05 [parallel]: 2.974e-05 [flash_sp]: 1.099e-05 [merge_comm]: 9.96e-06 [allreduce_fusion]: 1.023e-05 [matmul_add_comm_reduction]: 1.805e-05 [allreduce_slice_to_reducescatter]: 9.90025e-07 [virtual_shard_identity]: 1.868e-05 [virtual_dataset]: 1.72e-05 [get_grad_eliminate_]: 1.784e-05 [virtual_output]: 1.676e-05 [merge_forward]: 1.001e-05 [cell_reuse_recompute_pass]: 1.30001e-06 [offload_activation]: 1.854e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.464e-05 [merge_recompute_call_nodes]: 1.60001e-06 [before_grad]: 2.943e-05 [set_forward_comm_id_for_comm_node_pass]: 1.027e-05 [meta_fg_expand]: 7.60998e-06 [flash_sp_send_recv_attached]: 5.05999e-06 [receive_attached]: 2.78e-06 [after_resolve]: 2.253e-05 [a_after_grad]: 2.784e-05 [renormalize]: 0.16605 [add_forward_monad_depend]: 2.145e-05 [auto_monad_grad]: 3.30998e-06 [auto_monad_eliminator]: 4.606e-05 [cse]: 0.00045663 [a_3]: 0.00013714 [Cycle 2]: 0.0015554, [45] [expand_dump_flag]: 3.30003e-06 [switch_simplify]: 1.917e-05 [loop_unroll]: 1.626e-05 [a_1]: 0.00049267 [with_stream_mark]: 2.719e-05 [recompute_prepare]: 1.492e-05 [updatestate_depend_eliminate]: 1.021e-05 [updatestate_assign_eliminate]: 7.90998e-06 [updatestate_loads_eliminate]: 7.87e-06 [parameter_eliminate]: 2.56998e-06 [a_2]: 0.00022734 [accelerated_algorithm]: 2.101e-05 [shard]: 2.27001e-06 [meta_shard_fg_expand]: 4.23999e-06 [shard_inline]: 1.479e-05 [merge_send_recv]: 1.591e-05 [auto_parallel]: 1.605e-05 [parallel]: 1.021e-05 [flash_sp]: 4.50001e-06 [merge_comm]: 9.67999e-06 [allreduce_fusion]: 1.046e-05 [matmul_add_comm_reduction]: 1.768e-05 [allreduce_slice_to_reducescatter]: 9.30013e-07 [virtual_shard_identity]: 1.687e-05 [virtual_dataset]: 1.486e-05 [get_grad_eliminate_]: 1.443e-05 [virtual_output]: 1.422e-05 [merge_forward]: 9.05001e-06 [cell_reuse_recompute_pass]: 3.96001e-06 [offload_activation]: 1.791e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.934e-05 [merge_recompute_call_nodes]: 1.57999e-06 [before_grad]: 2.668e-05 [set_forward_comm_id_for_comm_node_pass]: 1.009e-05 [meta_fg_expand]: 7.32002e-06 [flash_sp_send_recv_attached]: 1.91e-06 [receive_attached]: 2.44999e-06 [after_resolve]: 2.048e-05 [a_after_grad]: 2.384e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 1.84e-06 [auto_monad_grad]: 1.81998e-06 [auto_monad_eliminator]: 1.93e-05 [cse]: 4.779e-05 [a_3]: 9.717e-05 [py_interpret_to_execute_after_opt_a]: 2.848e-05 [slice_cell_reuse_recomputed_activation]: 1.94999e-06 [rewriter_after_opt_a]: 0.00042891 [convert_after_rewriter]: 1.663e-05 [order_py_execute_after_rewriter]: 1.133e-05 [mutable_eliminate]: 0.00075222 [opt_b]: 0.0005683, [1] [Cycle 1]: 0.00056113, [7] [b_1]: 0.00041832 [b_2]: 1.767e-05 [updatestate_depend_eliminate]: 1.218e-05 [updatestate_assign_eliminate]: 7.63001e-06 [updatestate_loads_eliminate]: 7.36999e-06 [renormalize]: 5.8001e-07 [cse]: 5.519e-05 [optimize_parallel_all_gather_comm]: 2.951e-05 [overlap_param_gather]: 2.11998e-06 [cconv]: 3.536e-05 [loop_unroll]: 0.00047789 [opt_after_cconv]: 0.00019951, [1] [Cycle 1]: 0.00019253, [7] [c_1]: 7.799e-05 [parameter_eliminate]: 2.73e-06 [updatestate_depend_eliminate]: 1.275e-05 [updatestate_assign_eliminate]: 7.35e-06 [updatestate_loads_eliminate]: 7.25e-06 [cse]: 4.938e-05 [renormalize]: 3.89991e-07 [remove_dup_value]: 7.858e-05 [tuple_transform]: 0.00020635, [1] [Cycle 1]: 0.00020112, [4] [d_1]: 0.00016074 [none_parameter_eliminate]: 2.43e-06 [renormalize]: 2.19996e-07 [switch_simplify]: 1.651e-05 [partial_unused_args_eliminate]: 2.21e-06 [add_recomputation]: 0.0001131 [cse_after_recomputation]: 5.179e-05, [1] [Cycle 1]: 4.568e-05, [1] [cse]: 3.942e-05 [environ_conv]: 1.48e-05 [swap_dp_allreduce_reducescatter]: 1.247e-05 [bias_add_comm_swap]: 2.94999e-06 [label_micro_interleaved_index]: 4.74e-06 [label_fine_grained_interleaved_index]: 3.60998e-06 [merge_cast_opt]: 1.39e-06 [slice_recompute_activation]: 2.02999e-06 [micro_interleaved_order_control]: 2.51e-06 [assign_add_opt]: 1.49e-06 [ForceFp32Comm]: 7.89994e-07 [remove_cast_before_assign_add]: 1.04998e-06 [full_micro_interleaved_order_control]: 2.15002e-06 [reorder_send_recv_between_fp_bp]: 2.94001e-06 [comm_op_add_attrs]: 1.10001e-06 [add_comm_op_reuse_tag]: 1.02e-06 [interleave_split_concat_branches]: 1.22999e-06 [interleave_parallel_branches]: 1.04e-06 [overlap_opt_shard_in_pipeline]: 1.55999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.02999e-06 [control_data_broadcast_order]: 2.7e-05 [grouped_pairwise_exchange_alltoall]: 1.71998e-06 [offloading_packed_experts]: 7.28e-06 [overlap_recompute_and_grad_model_parallel]: 8.12998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.25001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.40001e-06 [overlap_recompute_comm]: 2.87002e-06 [overlap_grad_ring_attention]: 7.20998e-06 [overlap_grad_flash_sp]: 4.414e-05 [begin_end_overlap_inline]: 5.00004e-07 [split_matmul_comm_elemetwise]: 2.32001e-06 [split_layernorm_comm]: 1.79e-06 [handle_group_info]: 1.18001e-06 [symbol_engine_optimizer]: 0.00014682, [1] [Cycle 1]: 0.00014217, [6] [build]: 1.571e-05 [elim_shapecalc]: 2.127e-05 [elim_not_effective]: 3.036e-05 [opt_reshape]: 1.578e-05 [fold_const_symbol]: 2.701e-05 [renormalize]: 2.00002e-07 [detach_backward]: 2.59999e-06 [pipeline_parallel_scheduler]: 1.65001e-06 [auto_monad_reorder]: 3.358e-05 [get_jit_bprop_graph]: 1.87999e-06 [rewriter_after_jit_bprop_graph]: 5.04e-06 [opt_after_jit_grad]: 0.00052131 [validate]: 8.732e-05 Sums bootstrap : 0.000812s : 0.02% type_inference : 4.021795s : 95.79% event_method : 0.001476s : 0.04% auto_monad : 0.000134s : 0.00% graph_reusing : 0.000009s : 0.00% inline : 0.000006s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000035s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000055s : 0.00% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000040s : 0.00% optimize.rewriter_before_opt_a : 0.000127s : 0.00% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000074s : 0.00% optimize.opt_a.loop_unroll : 0.000055s : 0.00% optimize.opt_a.a_1 : 0.002003s : 0.05% optimize.opt_a.with_stream_mark : 0.000056s : 0.00% optimize.opt_a.recompute_prepare : 0.000036s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000018s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000016s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000496s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000060s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.00% optimize.opt_a.shard_inline : 0.000031s : 0.00% optimize.opt_a.merge_send_recv : 0.000031s : 0.00% optimize.opt_a.auto_parallel : 0.000029s : 0.00% optimize.opt_a.parallel : 0.000040s : 0.00% optimize.opt_a.flash_sp : 0.000015s : 0.00% optimize.opt_a.merge_comm : 0.000020s : 0.00% optimize.opt_a.allreduce_fusion : 0.000021s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000036s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000036s : 0.00% optimize.opt_a.virtual_dataset : 0.000032s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000032s : 0.00% optimize.opt_a.virtual_output : 0.000031s : 0.00% optimize.opt_a.merge_forward : 0.000019s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000036s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000064s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000056s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000020s : 0.00% optimize.opt_a.meta_fg_expand : 0.000015s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000043s : 0.00% optimize.opt_a.a_after_grad : 0.000052s : 0.00% optimize.opt_a.renormalize : 0.166050s : 3.95% optimize.opt_a.add_forward_monad_depend : 0.000023s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000065s : 0.00% optimize.opt_a.cse : 0.000504s : 0.01% optimize.opt_a.a_3 : 0.000234s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000028s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000429s : 0.01% optimize.convert_after_rewriter : 0.000017s : 0.00% optimize.order_py_execute_after_rewriter : 0.000011s : 0.00% optimize.mutable_eliminate : 0.000752s : 0.02% optimize.opt_b.b_1 : 0.000418s : 0.01% optimize.opt_b.b_2 : 0.000018s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000055s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000030s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000035s : 0.00% optimize.loop_unroll : 0.000478s : 0.01% optimize.opt_after_cconv.c_1 : 0.000078s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000049s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000079s : 0.00% optimize.tuple_transform.d_1 : 0.000161s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000017s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000113s : 0.00% optimize.cse_after_recomputation.cse : 0.000039s : 0.00% optimize.environ_conv : 0.000015s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000012s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000004s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000027s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000044s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000016s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000021s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000030s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000016s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000027s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000034s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000521s : 0.01% validate : 0.000087s : 0.00% Time group info: ------[substitution.] 0.000654 197 6.79% : 0.000044s : 6: substitution.arithmetic_simplify 0.64% : 0.000004s : 10: substitution.elim_not_effective 2.51% : 0.000016s : 12: substitution.float_tuple_getitem_switch 0.64% : 0.000004s : 10: substitution.fold_const_symbol 1.75% : 0.000011s : 12: substitution.graph_param_transform 42.21% : 0.000276s : 7: substitution.inline 1.56% : 0.000010s : 20: substitution.j_node_and_user_rematch 3.11% : 0.000020s : 2: substitution.less_batch_normalization 2.86% : 0.000019s : 8: substitution.minmaximum_grad 2.28% : 0.000015s : 20: substitution.remove_not_recompute_node 1.05% : 0.000007s : 2: substitution.replace_old_param 7.65% : 0.000050s : 16: substitution.tuple_list_convert_item_index_to_positive 5.21% : 0.000034s : 16: substitution.tuple_list_get_item_const_eliminator 5.13% : 0.000034s : 16: substitution.tuple_list_get_item_depend_reorder 11.60% : 0.000076s : 24: substitution.tuple_list_get_item_eliminator 5.01% : 0.000033s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 4.021662 2 99.89% : 4.017352s : 1: type_inference.infer 0.11% : 0.004310s : 1: type_inference.specialize ------[replace.] 0.000069 7 100.00% : 0.000069s : 7: replace.inline ------[match.] 0.000271 7 100.00% : 0.000271s : 7: match.inline ------[predicate.] 0.000495 3093 0.90% : 0.000004s : 30: predicate.accumulaten_eliminater 0.74% : 0.000004s : 12: predicate.ad_related_special_op_eliminate 0.67% : 0.000003s : 24: predicate.addn_check_dump 0.91% : 0.000005s : 30: predicate.addn_zero_filter 0.84% : 0.000004s : 30: predicate.adjust_all_reduce_mul_add 2.49% : 0.000012s : 54: predicate.arithmetic_simplify 0.97% : 0.000005s : 30: predicate.cast_eliminate 0.74% : 0.000004s : 24: predicate.check_bprop_eliminate 0.72% : 0.000004s : 24: predicate.compare_switch_simplify 0.22% : 0.000001s : 12: predicate.const_output_eliminate 0.72% : 0.000004s : 24: predicate.depend_value_elim 0.93% : 0.000005s : 30: predicate.dict_get_item_const_eliminator 1.03% : 0.000005s : 30: predicate.dict_get_item_eliminator 0.86% : 0.000004s : 30: predicate.dict_set_item_eliminator 1.46% : 0.000007s : 24: predicate.dumpgradient_eliminate 0.19% : 0.000001s : 12: predicate.elim_not_effective 0.49% : 0.000002s : 12: predicate.elim_shapecalc_of_broadcastargs 1.21% : 0.000006s : 42: predicate.environ_add_const_eliminate 1.16% : 0.000006s : 42: predicate.environ_get_add_eliminate 1.21% : 0.000006s : 42: predicate.environ_get_depend_swap 1.91% : 0.000009s : 66: predicate.environ_get_eliminate 1.14% : 0.000006s : 42: predicate.environ_get_set_eliminate 1.05% : 0.000005s : 37: predicate.exchange_switch_depend_value 1.60% : 0.000008s : 37: predicate.float_depend_g_call 0.71% : 0.000004s : 24: predicate.float_environ_get_switch 1.23% : 0.000006s : 36: predicate.float_tuple_getitem_switch 0.19% : 0.000001s : 12: predicate.fold_const_symbol 0.79% : 0.000004s : 24: predicate.get_grad_eliminate 0.24% : 0.000001s : 12: predicate.graph_param_transform 0.66% : 0.000003s : 24: predicate.incorporate_call 0.62% : 0.000003s : 24: predicate.incorporate_call_switch 5.52% : 0.000027s : 139: predicate.inline 0.91% : 0.000004s : 24: predicate.inline_without_move 0.34% : 0.000002s : 24: predicate.j_node_and_user_rematch 0.94% : 0.000005s : 24: predicate.less_batch_normalization 1.66% : 0.000008s : 54: predicate.list_to_tuple_eliminator_ 2.40% : 0.000012s : 84: predicate.load_eliminater 0.76% : 0.000004s : 12: predicate.loop_unroll_after_grad 1.56% : 0.000008s : 52: predicate.loop_unroll_before_grad 1.73% : 0.000009s : 54: predicate.make_slice_get_slice_eliminator 0.73% : 0.000004s : 24: predicate.merge_addn 0.78% : 0.000004s : 24: predicate.micro_step_allgather_replace 0.71% : 0.000004s : 24: predicate.mini_step_allgather_replace 0.88% : 0.000004s : 30: predicate.minmaximum_grad 0.87% : 0.000004s : 12: predicate.mutable_eliminate 0.42% : 0.000002s : 12: predicate.opt_reshape 0.48% : 0.000002s : 12: predicate.parallel_virtual_node 1.57% : 0.000008s : 37: predicate.partial_defer_inline 1.27% : 0.000006s : 42: predicate.partial_eliminate 0.91% : 0.000005s : 30: predicate.print_const_string_wrapper 0.72% : 0.000004s : 24: predicate.reduce_all_const_elim 1.33% : 0.000007s : 30: predicate.reduce_eliminate 2.50% : 0.000012s : 84: predicate.redundant_stop_gradient_eliminater 0.46% : 0.000002s : 24: predicate.remove_not_recompute_node 1.27% : 0.000006s : 54: predicate.replace_applicator 0.51% : 0.000003s : 24: predicate.replace_old_param 0.22% : 0.000001s : 12: predicate.reset_defer_inline 0.91% : 0.000005s : 30: predicate.reshape_eliminate 0.72% : 0.000004s : 24: predicate.row_tensor_add_zeros_like 0.41% : 0.000002s : 12: predicate.row_tensor_eliminate 0.93% : 0.000005s : 24: predicate.same_eliminate 0.42% : 0.000002s : 24: predicate.set_cell_output_no_recompute 0.87% : 0.000004s : 24: predicate.shard_identity_eliminate 0.82% : 0.000004s : 24: predicate.special_op_eliminate 0.83% : 0.000004s : 24: predicate.specialize_transform 0.90% : 0.000004s : 24: predicate.split_environ_get_set_with_tuple_value 0.87% : 0.000004s : 24: predicate.stack_unstack_eliminate 0.40% : 0.000002s : 12: predicate.switch_call_monad_eliminater 1.14% : 0.000006s : 37: predicate.switch_defer_inline 1.83% : 0.000009s : 61: predicate.switch_layer_defer_inline 3.99% : 0.000020s : 125: predicate.switch_simplify 0.83% : 0.000004s : 30: predicate.tile_eliminate 0.92% : 0.000005s : 30: predicate.transpose_eliminate 1.99% : 0.000010s : 54: predicate.tuple_list_convert_item_index_to_positive 1.86% : 0.000009s : 54: predicate.tuple_list_get_item_const_eliminator 1.66% : 0.000008s : 54: predicate.tuple_list_get_item_depend_reorder 3.20% : 0.000016s : 78: predicate.tuple_list_get_item_eliminator 1.73% : 0.000009s : 54: predicate.tuple_list_get_set_item_eliminator 2.67% : 0.000013s : 78: predicate.tuple_list_set_item_eliminator 1.69% : 0.000008s : 54: predicate.tuple_to_list_eliminator_ 2.29% : 0.000011s : 84: predicate.updatestate_pure_node_eliminater 3.14% : 0.000016s : 108: predicate.updatestate_useless_node_eliminater 0.49% : 0.000002s : 12: predicate.value_based_eliminate 0.83% : 0.000004s : 24: predicate.virtual_dataset_eliminate 0.81% : 0.000004s : 24: predicate.virtual_output_eliminate 0.39% : 0.000002s : 12: predicate.virtual_view_grad_eliminate 0.42% : 0.000002s : 12: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.006853 38 70.29% : 0.004817s : 29: func_graph_cloner_run.FuncGraphClonerGraph 29.71% : 0.002036s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 4.978229 192 0.00% : 0.000003s : 1: ForceFp32Comm 4.36% : 0.216854s : 1: add_attr 4.36% : 0.216835s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.00% : 0.000118s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.00% : 0.000146s : 1: auto_monad 0.00% : 0.000038s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.02% : 0.000864s : 1: bootstrap 0.00% : 0.000039s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000030s : 1: control_data_broadcast_order 0.00% : 0.000021s : 1: convert_after_rewriter 0.00% : 0.000055s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000019s : 1: environ_conv 0.03% : 0.001501s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000009s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.01% : 0.000486s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000761s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000025s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000028s : 1: opt.transform.mutable_eliminate 0.06% : 0.003221s : 78: opt.transform.opt_a 0.00% : 0.000076s : 1: opt.transform.opt_after_cconv 0.00% : 0.000066s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000403s : 28: opt.transform.opt_b 0.00% : 0.000174s : 2: opt.transform.opt_trans_graph 0.00% : 0.000091s : 4: opt.transform.symbol_engine_opt 3.43% : 0.170982s : 1: opt_a 0.00% : 0.000203s : 1: opt_after_cconv 0.01% : 0.000530s : 1: opt_after_jit_grad 0.01% : 0.000572s : 1: opt_b 3.51% : 0.174728s : 1: optimize 0.00% : 0.000033s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.00% : 0.000048s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000060s : 1: pre_auto_parallel 0.00% : 0.000043s : 1: py_interpret_to_execute 0.00% : 0.000032s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000083s : 1: remove_dup_value 0.08% : 0.004024s : 1: renormalize.infer 3.25% : 0.162008s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000436s : 1: rewriter_after_opt_a 0.00% : 0.000131s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000016s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000151s : 1: symbol_engine_optimizer 0.00% : 0.000210s : 1: tuple_transform 80.79% : 4.021828s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[False-False-bfloat16--1-shape3] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[False-False-bfloat16--1-shape3],max_mem:100.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:39:40.121.790 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 6.12098, [21] [bootstrap]: 0.00119356 [type_inference]: 5.90117 [event_method]: 0.00233191 [auto_monad]: 0.00015252 [graph_reusing]: 8.17e-06 [inline]: 3.03e-06 [add_attr]: 0.0990039, [1] [add_attr_with_inline]: 0.0989856, [1] [Cycle 1]: 9e-05, [2] [tag_attr]: 3.857e-05 [meta_addattr_fg_expand]: 6.94999e-06 [parallel-infer-symbol]: 5.79999e-06 [pre_auto_parallel]: 5.927e-05 [insert-virtual-dataset]: 3.76999e-06 [parallel-infer-symbol-second]: 7.80012e-07 [dataset_repeat_opt]: 2.09e-06 [pipeline_split]: 2.91e-06 [optimize]: 0.115938, [53] [py_interpret_to_execute]: 4.423e-05 [rewriter_before_opt_a]: 0.0001405 [opt_a]: 0.11138, [2] [Cycle 1]: 0.109528, [45] [expand_dump_flag]: 3.67002e-06 [switch_simplify]: 5.45e-05 [loop_unroll]: 0.00015068 [a_1]: 0.00166279 [with_stream_mark]: 4.164e-05 [recompute_prepare]: 2.78e-05 [updatestate_depend_eliminate]: 1.326e-05 [updatestate_assign_eliminate]: 8.48999e-06 [updatestate_loads_eliminate]: 8.41002e-06 [parameter_eliminate]: 2.63e-06 [a_2]: 0.00028084 [accelerated_algorithm]: 4.675e-05 [shard]: 3.09999e-06 [meta_shard_fg_expand]: 6.57002e-06 [shard_inline]: 1.678e-05 [merge_send_recv]: 1.775e-05 [auto_parallel]: 1.839e-05 [parallel]: 3.408e-05 [flash_sp]: 1.4e-05 [merge_comm]: 1.103e-05 [allreduce_fusion]: 9.66e-06 [matmul_add_comm_reduction]: 1.866e-05 [allreduce_slice_to_reducescatter]: 1.02998e-06 [virtual_shard_identity]: 2.361e-05 [virtual_dataset]: 1.916e-05 [get_grad_eliminate_]: 1.907e-05 [virtual_output]: 1.834e-05 [merge_forward]: 1.082e-05 [cell_reuse_recompute_pass]: 2.12999e-06 [offload_activation]: 2.01e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.977e-05 [merge_recompute_call_nodes]: 1.74e-06 [before_grad]: 3.121e-05 [set_forward_comm_id_for_comm_node_pass]: 1.161e-05 [meta_fg_expand]: 7.28e-06 [flash_sp_send_recv_attached]: 5.59e-06 [receive_attached]: 3.14999e-06 [after_resolve]: 2.339e-05 [a_after_grad]: 2.998e-05 [renormalize]: 0.0851976 [add_forward_monad_depend]: 1.995e-05 [auto_monad_grad]: 3.45e-06 [auto_monad_eliminator]: 4.625e-05 [cse]: 0.00111759 [a_3]: 0.00014933 [Cycle 2]: 0.00183731, [45] [expand_dump_flag]: 3.46001e-06 [switch_simplify]: 1.999e-05 [loop_unroll]: 1.639e-05 [a_1]: 0.00051543 [with_stream_mark]: 3.826e-05 [recompute_prepare]: 2.261e-05 [updatestate_depend_eliminate]: 1.224e-05 [updatestate_assign_eliminate]: 8.69e-06 [updatestate_loads_eliminate]: 8.32e-06 [parameter_eliminate]: 3.14001e-06 [a_2]: 0.00025298 [accelerated_algorithm]: 2.633e-05 [shard]: 2.87002e-06 [meta_shard_fg_expand]: 5.64998e-06 [shard_inline]: 1.746e-05 [merge_send_recv]: 1.859e-05 [auto_parallel]: 1.778e-05 [parallel]: 1.238e-05 [flash_sp]: 4.60999e-06 [merge_comm]: 9.94999e-06 [allreduce_fusion]: 1.122e-05 [matmul_add_comm_reduction]: 1.911e-05 [allreduce_slice_to_reducescatter]: 1.00001e-06 [virtual_shard_identity]: 2.168e-05 [virtual_dataset]: 1.599e-05 [get_grad_eliminate_]: 1.558e-05 [virtual_output]: 1.598e-05 [merge_forward]: 1.069e-05 [cell_reuse_recompute_pass]: 3.93999e-06 [offload_activation]: 2e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.683e-05 [merge_recompute_call_nodes]: 2.73e-06 [before_grad]: 3.035e-05 [set_forward_comm_id_for_comm_node_pass]: 3.82e-05 [meta_fg_expand]: 8.27e-06 [flash_sp_send_recv_attached]: 2.64999e-06 [receive_attached]: 3.03998e-06 [after_resolve]: 2.742e-05 [a_after_grad]: 2.649e-05 [renormalize]: 9.99717e-08 [add_forward_monad_depend]: 4.75001e-06 [auto_monad_grad]: 3.02002e-06 [auto_monad_eliminator]: 3.246e-05 [cse]: 7.312e-05 [a_3]: 0.0001064 [py_interpret_to_execute_after_opt_a]: 3.318e-05 [slice_cell_reuse_recomputed_activation]: 2.08998e-06 [rewriter_after_opt_a]: 0.00046368 [convert_after_rewriter]: 2.294e-05 [order_py_execute_after_rewriter]: 1.224e-05 [mutable_eliminate]: 0.00087259 [opt_b]: 0.00062503, [1] [Cycle 1]: 0.00061468, [7] [b_1]: 0.00042775 [b_2]: 2.244e-05 [updatestate_depend_eliminate]: 1.702e-05 [updatestate_assign_eliminate]: 8.33999e-06 [updatestate_loads_eliminate]: 8.25999e-06 [renormalize]: 9.79984e-07 [cse]: 7.828e-05 [optimize_parallel_all_gather_comm]: 3.441e-05 [overlap_param_gather]: 1.99e-06 [cconv]: 4.119e-05 [loop_unroll]: 0.00055569 [opt_after_cconv]: 0.00022703, [1] [Cycle 1]: 0.00021756, [7] [c_1]: 7.891e-05 [parameter_eliminate]: 5.71e-06 [updatestate_depend_eliminate]: 1.63e-05 [updatestate_assign_eliminate]: 7.51999e-06 [updatestate_loads_eliminate]: 7.36001e-06 [cse]: 6.123e-05 [renormalize]: 5.50004e-07 [remove_dup_value]: 8.631e-05 [tuple_transform]: 0.00022958, [1] [Cycle 1]: 0.00022348, [4] [d_1]: 0.00017336 [none_parameter_eliminate]: 3.28e-06 [renormalize]: 3.50003e-07 [switch_simplify]: 1.901e-05 [partial_unused_args_eliminate]: 1.84998e-06 [add_recomputation]: 0.00012485 [cse_after_recomputation]: 6.399e-05, [1] [Cycle 1]: 5.557e-05, [1] [cse]: 4.665e-05 [environ_conv]: 1.677e-05 [swap_dp_allreduce_reducescatter]: 1.425e-05 [bias_add_comm_swap]: 3.35e-06 [label_micro_interleaved_index]: 5.96e-06 [label_fine_grained_interleaved_index]: 2.278e-05 [merge_cast_opt]: 1.34e-06 [slice_recompute_activation]: 2.58e-06 [micro_interleaved_order_control]: 2.63e-06 [assign_add_opt]: 1.30001e-06 [ForceFp32Comm]: 1.86003e-06 [remove_cast_before_assign_add]: 1.29e-06 [full_micro_interleaved_order_control]: 2.88e-06 [reorder_send_recv_between_fp_bp]: 3.04001e-06 [comm_op_add_attrs]: 1.13001e-06 [add_comm_op_reuse_tag]: 1.06997e-06 [interleave_split_concat_branches]: 1.40001e-06 [interleave_parallel_branches]: 1.30001e-06 [overlap_opt_shard_in_pipeline]: 1.29e-06 [overlap_opt_shard_grad_in_pipeline]: 1.89e-06 [control_data_broadcast_order]: 3.345e-05 [grouped_pairwise_exchange_alltoall]: 2.04e-06 [offloading_packed_experts]: 9.75002e-06 [overlap_recompute_and_grad_model_parallel]: 9.47999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.84998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.89e-06 [overlap_recompute_comm]: 2.89999e-06 [overlap_grad_ring_attention]: 8.59e-06 [overlap_grad_flash_sp]: 4.528e-05 [begin_end_overlap_inline]: 8.00006e-07 [split_matmul_comm_elemetwise]: 2.33998e-06 [split_layernorm_comm]: 1.84998e-06 [handle_group_info]: 1.09998e-06 [symbol_engine_optimizer]: 0.00047612, [1] [Cycle 1]: 0.00046756, [6] [build]: 0.00025141 [elim_shapecalc]: 3.515e-05 [elim_not_effective]: 5.66e-05 [opt_reshape]: 1.793e-05 [fold_const_symbol]: 4.864e-05 [renormalize]: 2.10013e-07 [detach_backward]: 4.99e-06 [pipeline_parallel_scheduler]: 1.44e-06 [auto_monad_reorder]: 4.531e-05 [get_jit_bprop_graph]: 2.43998e-06 [rewriter_after_jit_bprop_graph]: 6.63998e-06 [opt_after_jit_grad]: 0.00067722 [validate]: 0.00010283 Sums bootstrap : 0.001194s : 0.02% type_inference : 5.901169s : 98.34% event_method : 0.002332s : 0.04% auto_monad : 0.000153s : 0.00% graph_reusing : 0.000008s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000039s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000006s : 0.00% pre_auto_parallel : 0.000059s : 0.00% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000044s : 0.00% optimize.rewriter_before_opt_a : 0.000140s : 0.00% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000074s : 0.00% optimize.opt_a.loop_unroll : 0.000167s : 0.00% optimize.opt_a.a_1 : 0.002178s : 0.04% optimize.opt_a.with_stream_mark : 0.000080s : 0.00% optimize.opt_a.recompute_prepare : 0.000050s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000026s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000017s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000534s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000073s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000012s : 0.00% optimize.opt_a.shard_inline : 0.000034s : 0.00% optimize.opt_a.merge_send_recv : 0.000036s : 0.00% optimize.opt_a.auto_parallel : 0.000036s : 0.00% optimize.opt_a.parallel : 0.000046s : 0.00% optimize.opt_a.flash_sp : 0.000019s : 0.00% optimize.opt_a.merge_comm : 0.000021s : 0.00% optimize.opt_a.allreduce_fusion : 0.000021s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000038s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000045s : 0.00% optimize.opt_a.virtual_dataset : 0.000035s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000035s : 0.00% optimize.opt_a.virtual_output : 0.000034s : 0.00% optimize.opt_a.merge_forward : 0.000022s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000040s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000077s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000062s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000050s : 0.00% optimize.opt_a.meta_fg_expand : 0.000016s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000051s : 0.00% optimize.opt_a.a_after_grad : 0.000056s : 0.00% optimize.opt_a.renormalize : 0.085198s : 1.42% optimize.opt_a.add_forward_monad_depend : 0.000025s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000079s : 0.00% optimize.opt_a.cse : 0.001191s : 0.02% optimize.opt_a.a_3 : 0.000256s : 0.00% optimize.py_interpret_to_execute_after_opt_a : 0.000033s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000464s : 0.01% optimize.convert_after_rewriter : 0.000023s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000873s : 0.01% optimize.opt_b.b_1 : 0.000428s : 0.01% optimize.opt_b.b_2 : 0.000022s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000017s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000078s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000034s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000041s : 0.00% optimize.loop_unroll : 0.000556s : 0.01% optimize.opt_after_cconv.c_1 : 0.000079s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000016s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000061s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000086s : 0.00% optimize.tuple_transform.d_1 : 0.000173s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000019s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000125s : 0.00% optimize.cse_after_recomputation.cse : 0.000047s : 0.00% optimize.environ_conv : 0.000017s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000014s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000023s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000002s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000033s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000010s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000009s : 0.00% optimize.overlap_grad_flash_sp : 0.000045s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000251s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000035s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000057s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000018s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000049s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000005s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000045s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000677s : 0.01% validate : 0.000103s : 0.00% Time group info: ------[substitution.] 0.000874 197 6.44% : 0.000056s : 6: substitution.arithmetic_simplify 3.05% : 0.000027s : 10: substitution.elim_not_effective 2.11% : 0.000018s : 12: substitution.float_tuple_getitem_switch 2.58% : 0.000023s : 10: substitution.fold_const_symbol 1.38% : 0.000012s : 12: substitution.graph_param_transform 44.66% : 0.000391s : 7: substitution.inline 1.20% : 0.000010s : 20: substitution.j_node_and_user_rematch 2.59% : 0.000023s : 2: substitution.less_batch_normalization 2.29% : 0.000020s : 8: substitution.minmaximum_grad 1.81% : 0.000016s : 20: substitution.remove_not_recompute_node 0.93% : 0.000008s : 2: substitution.replace_old_param 7.69% : 0.000067s : 16: substitution.tuple_list_convert_item_index_to_positive 3.39% : 0.000030s : 16: substitution.tuple_list_get_item_const_eliminator 5.17% : 0.000045s : 16: substitution.tuple_list_get_item_depend_reorder 10.35% : 0.000091s : 24: substitution.tuple_list_get_item_eliminator 4.35% : 0.000038s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 5.901014 2 99.90% : 5.895202s : 1: type_inference.infer 0.10% : 0.005812s : 1: type_inference.specialize ------[replace.] 0.000091 7 100.00% : 0.000091s : 7: replace.inline ------[match.] 0.000385 7 100.00% : 0.000385s : 7: match.inline ------[predicate.] 0.000550 3093 0.97% : 0.000005s : 30: predicate.accumulaten_eliminater 0.88% : 0.000005s : 12: predicate.ad_related_special_op_eliminate 0.68% : 0.000004s : 24: predicate.addn_check_dump 0.81% : 0.000004s : 30: predicate.addn_zero_filter 0.82% : 0.000004s : 30: predicate.adjust_all_reduce_mul_add 2.20% : 0.000012s : 54: predicate.arithmetic_simplify 0.84% : 0.000005s : 30: predicate.cast_eliminate 0.73% : 0.000004s : 24: predicate.check_bprop_eliminate 0.71% : 0.000004s : 24: predicate.compare_switch_simplify 0.17% : 0.000001s : 12: predicate.const_output_eliminate 0.66% : 0.000004s : 24: predicate.depend_value_elim 0.88% : 0.000005s : 30: predicate.dict_get_item_const_eliminator 0.91% : 0.000005s : 30: predicate.dict_get_item_eliminator 0.82% : 0.000005s : 30: predicate.dict_set_item_eliminator 0.97% : 0.000005s : 24: predicate.dumpgradient_eliminate 0.23% : 0.000001s : 12: predicate.elim_not_effective 0.42% : 0.000002s : 12: predicate.elim_shapecalc_of_broadcastargs 1.13% : 0.000006s : 42: predicate.environ_add_const_eliminate 1.06% : 0.000006s : 42: predicate.environ_get_add_eliminate 1.07% : 0.000006s : 42: predicate.environ_get_depend_swap 1.75% : 0.000010s : 66: predicate.environ_get_eliminate 1.05% : 0.000006s : 42: predicate.environ_get_set_eliminate 0.96% : 0.000005s : 37: predicate.exchange_switch_depend_value 1.78% : 0.000010s : 37: predicate.float_depend_g_call 0.74% : 0.000004s : 24: predicate.float_environ_get_switch 1.23% : 0.000007s : 36: predicate.float_tuple_getitem_switch 0.16% : 0.000001s : 12: predicate.fold_const_symbol 0.73% : 0.000004s : 24: predicate.get_grad_eliminate 0.20% : 0.000001s : 12: predicate.graph_param_transform 0.63% : 0.000003s : 24: predicate.incorporate_call 0.57% : 0.000003s : 24: predicate.incorporate_call_switch 5.44% : 0.000030s : 139: predicate.inline 0.97% : 0.000005s : 24: predicate.inline_without_move 0.32% : 0.000002s : 24: predicate.j_node_and_user_rematch 1.04% : 0.000006s : 24: predicate.less_batch_normalization 1.62% : 0.000009s : 54: predicate.list_to_tuple_eliminator_ 2.12% : 0.000012s : 84: predicate.load_eliminater 0.80% : 0.000004s : 12: predicate.loop_unroll_after_grad 5.06% : 0.000028s : 52: predicate.loop_unroll_before_grad 1.59% : 0.000009s : 54: predicate.make_slice_get_slice_eliminator 0.79% : 0.000004s : 24: predicate.merge_addn 0.64% : 0.000004s : 24: predicate.micro_step_allgather_replace 0.65% : 0.000004s : 24: predicate.mini_step_allgather_replace 0.89% : 0.000005s : 30: predicate.minmaximum_grad 1.02% : 0.000006s : 12: predicate.mutable_eliminate 0.45% : 0.000003s : 12: predicate.opt_reshape 0.43% : 0.000002s : 12: predicate.parallel_virtual_node 1.78% : 0.000010s : 37: predicate.partial_defer_inline 1.18% : 0.000007s : 42: predicate.partial_eliminate 0.80% : 0.000004s : 30: predicate.print_const_string_wrapper 0.73% : 0.000004s : 24: predicate.reduce_all_const_elim 1.16% : 0.000006s : 30: predicate.reduce_eliminate 2.23% : 0.000012s : 84: predicate.redundant_stop_gradient_eliminater 0.42% : 0.000002s : 24: predicate.remove_not_recompute_node 1.08% : 0.000006s : 54: predicate.replace_applicator 0.40% : 0.000002s : 24: predicate.replace_old_param 0.25% : 0.000001s : 12: predicate.reset_defer_inline 0.88% : 0.000005s : 30: predicate.reshape_eliminate 0.72% : 0.000004s : 24: predicate.row_tensor_add_zeros_like 0.45% : 0.000002s : 12: predicate.row_tensor_eliminate 1.13% : 0.000006s : 24: predicate.same_eliminate 0.42% : 0.000002s : 24: predicate.set_cell_output_no_recompute 0.96% : 0.000005s : 24: predicate.shard_identity_eliminate 0.80% : 0.000004s : 24: predicate.special_op_eliminate 0.78% : 0.000004s : 24: predicate.specialize_transform 1.07% : 0.000006s : 24: predicate.split_environ_get_set_with_tuple_value 0.88% : 0.000005s : 24: predicate.stack_unstack_eliminate 0.33% : 0.000002s : 12: predicate.switch_call_monad_eliminater 1.19% : 0.000007s : 37: predicate.switch_defer_inline 1.85% : 0.000010s : 61: predicate.switch_layer_defer_inline 4.05% : 0.000022s : 125: predicate.switch_simplify 0.77% : 0.000004s : 30: predicate.tile_eliminate 0.80% : 0.000004s : 30: predicate.transpose_eliminate 1.80% : 0.000010s : 54: predicate.tuple_list_convert_item_index_to_positive 1.91% : 0.000011s : 54: predicate.tuple_list_get_item_const_eliminator 1.80% : 0.000010s : 54: predicate.tuple_list_get_item_depend_reorder 3.31% : 0.000018s : 78: predicate.tuple_list_get_item_eliminator 1.64% : 0.000009s : 54: predicate.tuple_list_get_set_item_eliminator 2.32% : 0.000013s : 78: predicate.tuple_list_set_item_eliminator 1.71% : 0.000009s : 54: predicate.tuple_to_list_eliminator_ 2.06% : 0.000011s : 84: predicate.updatestate_pure_node_eliminater 2.90% : 0.000016s : 108: predicate.updatestate_useless_node_eliminater 0.39% : 0.000002s : 12: predicate.value_based_eliminate 0.80% : 0.000004s : 24: predicate.virtual_dataset_eliminate 0.83% : 0.000005s : 24: predicate.virtual_output_eliminate 0.38% : 0.000002s : 12: predicate.virtual_view_grad_eliminate 0.42% : 0.000002s : 12: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.024540 38 24.53% : 0.006019s : 29: func_graph_cloner_run.FuncGraphClonerGraph 75.47% : 0.018521s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 6.425433 192 0.00% : 0.000004s : 1: ForceFp32Comm 1.54% : 0.099012s : 1: add_attr 1.54% : 0.098990s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000131s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.00% : 0.000165s : 1: auto_monad 0.00% : 0.000050s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.02% : 0.001251s : 1: bootstrap 0.00% : 0.000045s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000037s : 1: control_data_broadcast_order 0.00% : 0.000028s : 1: convert_after_rewriter 0.00% : 0.000067s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000022s : 1: environ_conv 0.04% : 0.002367s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000027s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.01% : 0.000566s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.01% : 0.000884s : 1: mutable_eliminate 0.00% : 0.000013s : 1: offloading_packed_experts 0.00% : 0.000033s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000039s : 1: opt.transform.mutable_eliminate 0.06% : 0.003602s : 78: opt.transform.opt_a 0.00% : 0.000078s : 1: opt.transform.opt_after_cconv 0.00% : 0.000069s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000415s : 28: opt.transform.opt_b 0.00% : 0.000188s : 2: opt.transform.opt_trans_graph 0.00% : 0.000153s : 4: opt.transform.symbol_engine_opt 1.73% : 0.111386s : 1: opt_a 0.00% : 0.000230s : 1: opt_after_cconv 0.01% : 0.000689s : 1: opt_after_jit_grad 0.01% : 0.000630s : 1: opt_b 1.80% : 0.115946s : 1: optimize 0.00% : 0.000039s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000016s : 1: order_py_execute_after_rewriter 0.00% : 0.000049s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000013s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000064s : 1: pre_auto_parallel 0.00% : 0.000049s : 1: py_interpret_to_execute 0.00% : 0.000038s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000092s : 1: remove_dup_value 1.03% : 0.066306s : 1: renormalize.infer 0.29% : 0.018871s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000475s : 1: rewriter_after_opt_a 0.00% : 0.000145s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000017s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000480s : 1: symbol_engine_optimizer 0.00% : 0.000234s : 1: tuple_transform 91.84% : 5.901205s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[False-True-bfloat16--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[False-True-bfloat16--1-shape0],max_mem:100.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:40:01.597.272 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 16.4556, [21] [bootstrap]: 0.00085664 [type_inference]: 15.6688 [event_method]: 0.00137413 [auto_monad]: 0.00050383 [graph_reusing]: 9.28002e-06 [inline]: 7.73999e-06 [add_attr]: 0.00463444, [1] [add_attr_with_inline]: 0.00461801, [1] [Cycle 1]: 8.686e-05, [2] [tag_attr]: 3.488e-05 [meta_addattr_fg_expand]: 7.46999e-06 [parallel-infer-symbol]: 4.77e-06 [pre_auto_parallel]: 5.268e-05 [insert-virtual-dataset]: 4.11001e-06 [parallel-infer-symbol-second]: 8.30012e-07 [dataset_repeat_opt]: 1.92001e-06 [pipeline_split]: 2.81999e-06 [optimize]: 0.778328, [53] [py_interpret_to_execute]: 3.497e-05 [rewriter_before_opt_a]: 0.0001285 [opt_a]: 0.773593, [2] [Cycle 1]: 0.771897, [45] [expand_dump_flag]: 3.83001e-06 [switch_simplify]: 5.594e-05 [loop_unroll]: 3.806e-05 [a_1]: 0.00210114 [with_stream_mark]: 3.453e-05 [recompute_prepare]: 2.391e-05 [updatestate_depend_eliminate]: 1.18e-05 [updatestate_assign_eliminate]: 8.84e-06 [updatestate_loads_eliminate]: 8.28999e-06 [parameter_eliminate]: 2.32001e-06 [a_2]: 0.00027425 [accelerated_algorithm]: 4.081e-05 [shard]: 2.89001e-06 [meta_shard_fg_expand]: 5.82999e-06 [shard_inline]: 1.944e-05 [merge_send_recv]: 1.605e-05 [auto_parallel]: 1.488e-05 [parallel]: 3.593e-05 [flash_sp]: 1.184e-05 [merge_comm]: 1.016e-05 [allreduce_fusion]: 9.59e-06 [matmul_add_comm_reduction]: 1.69e-05 [allreduce_slice_to_reducescatter]: 8.39995e-07 [virtual_shard_identity]: 1.98e-05 [virtual_dataset]: 1.807e-05 [get_grad_eliminate_]: 1.834e-05 [virtual_output]: 1.671e-05 [merge_forward]: 9.69999e-06 [cell_reuse_recompute_pass]: 1.54998e-06 [offload_activation]: 1.907e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.604e-05 [merge_recompute_call_nodes]: 1.87001e-06 [before_grad]: 2.9e-05 [set_forward_comm_id_for_comm_node_pass]: 1.096e-05 [meta_fg_expand]: 7.61999e-06 [flash_sp_send_recv_attached]: 5.14998e-06 [receive_attached]: 2.44001e-06 [after_resolve]: 2.093e-05 [a_after_grad]: 2.924e-05 [renormalize]: 0.767661 [add_forward_monad_depend]: 1.806e-05 [auto_monad_grad]: 3.06999e-06 [auto_monad_eliminator]: 3.912e-05 [cse]: 0.00066966 [a_3]: 0.00014133 [Cycle 2]: 0.00168049, [45] [expand_dump_flag]: 3.34001e-06 [switch_simplify]: 2.246e-05 [loop_unroll]: 1.765e-05 [a_1]: 0.00049986 [with_stream_mark]: 2.652e-05 [recompute_prepare]: 1.613e-05 [updatestate_depend_eliminate]: 1.176e-05 [updatestate_assign_eliminate]: 8.07e-06 [updatestate_loads_eliminate]: 7.96001e-06 [parameter_eliminate]: 2.32001e-06 [a_2]: 0.00025665 [accelerated_algorithm]: 2.318e-05 [shard]: 2.54999e-06 [meta_shard_fg_expand]: 5.72999e-06 [shard_inline]: 1.586e-05 [merge_send_recv]: 1.823e-05 [auto_parallel]: 1.841e-05 [parallel]: 1.157e-05 [flash_sp]: 4.85999e-06 [merge_comm]: 1.057e-05 [allreduce_fusion]: 1.028e-05 [matmul_add_comm_reduction]: 1.697e-05 [allreduce_slice_to_reducescatter]: 1.14003e-06 [virtual_shard_identity]: 1.679e-05 [virtual_dataset]: 1.51e-05 [get_grad_eliminate_]: 1.468e-05 [virtual_output]: 1.4e-05 [merge_forward]: 9.47999e-06 [cell_reuse_recompute_pass]: 3.54002e-06 [offload_activation]: 1.812e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.02e-05 [merge_recompute_call_nodes]: 1.89e-06 [before_grad]: 2.652e-05 [set_forward_comm_id_for_comm_node_pass]: 1.005e-05 [meta_fg_expand]: 7.8e-06 [flash_sp_send_recv_attached]: 1.90001e-06 [receive_attached]: 3.04999e-06 [after_resolve]: 1.948e-05 [a_after_grad]: 2.479e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 2.01e-06 [auto_monad_grad]: 1.82999e-06 [auto_monad_eliminator]: 2.387e-05 [cse]: 9.228e-05 [a_3]: 0.00010062 [py_interpret_to_execute_after_opt_a]: 2.999e-05 [slice_cell_reuse_recomputed_activation]: 2.68998e-06 [rewriter_after_opt_a]: 0.00043108 [convert_after_rewriter]: 1.647e-05 [order_py_execute_after_rewriter]: 1.151e-05 [mutable_eliminate]: 0.00078776 [opt_b]: 0.00058281, [1] [Cycle 1]: 0.00057516, [7] [b_1]: 0.00042698 [b_2]: 1.794e-05 [updatestate_depend_eliminate]: 1.326e-05 [updatestate_assign_eliminate]: 7.63001e-06 [updatestate_loads_eliminate]: 7.27002e-06 [renormalize]: 7.10017e-07 [cse]: 5.999e-05 [optimize_parallel_all_gather_comm]: 0.00030816 [overlap_param_gather]: 5.77999e-06 [cconv]: 4.525e-05 [loop_unroll]: 0.00057729 [opt_after_cconv]: 0.00021362, [1] [Cycle 1]: 0.00020539, [7] [c_1]: 7.908e-05 [parameter_eliminate]: 4.32e-06 [updatestate_depend_eliminate]: 1.376e-05 [updatestate_assign_eliminate]: 7.84002e-06 [updatestate_loads_eliminate]: 7.06001e-06 [cse]: 5.621e-05 [renormalize]: 3.80009e-07 [remove_dup_value]: 8.753e-05 [tuple_transform]: 0.00034148, [1] [Cycle 1]: 0.00023233, [4] [d_1]: 0.00018714 [none_parameter_eliminate]: 2.48e-06 [renormalize]: 3.09985e-07 [switch_simplify]: 1.713e-05 [partial_unused_args_eliminate]: 2.53e-06 [add_recomputation]: 0.00012659 [cse_after_recomputation]: 6.038e-05, [1] [Cycle 1]: 5.389e-05, [1] [cse]: 4.681e-05 [environ_conv]: 1.671e-05 [swap_dp_allreduce_reducescatter]: 1.397e-05 [bias_add_comm_swap]: 3.23998e-06 [label_micro_interleaved_index]: 6.51e-06 [label_fine_grained_interleaved_index]: 3.01999e-06 [merge_cast_opt]: 1.84e-06 [slice_recompute_activation]: 2.27999e-06 [micro_interleaved_order_control]: 2.60002e-06 [assign_add_opt]: 1.57001e-06 [ForceFp32Comm]: 1.07998e-06 [remove_cast_before_assign_add]: 9.10019e-07 [full_micro_interleaved_order_control]: 2.42001e-06 [reorder_send_recv_between_fp_bp]: 3.88999e-06 [comm_op_add_attrs]: 1.06002e-06 [add_comm_op_reuse_tag]: 1.05999e-06 [interleave_split_concat_branches]: 1.52001e-06 [interleave_parallel_branches]: 1.49998e-06 [overlap_opt_shard_in_pipeline]: 3.83001e-06 [overlap_opt_shard_grad_in_pipeline]: 2.36e-06 [control_data_broadcast_order]: 3.051e-05 [grouped_pairwise_exchange_alltoall]: 2.26e-06 [offloading_packed_experts]: 1.432e-05 [overlap_recompute_and_grad_model_parallel]: 1.031e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.29998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.60001e-06 [overlap_recompute_comm]: 2.32999e-06 [overlap_grad_ring_attention]: 8.81002e-06 [overlap_grad_flash_sp]: 4.458e-05 [begin_end_overlap_inline]: 5.19998e-07 [split_matmul_comm_elemetwise]: 2.39999e-06 [split_layernorm_comm]: 2.01e-06 [handle_group_info]: 1.13001e-06 [symbol_engine_optimizer]: 0.00045781, [1] [Cycle 1]: 0.00045161, [6] [build]: 0.00022759 [elim_shapecalc]: 6.517e-05 [elim_not_effective]: 4.332e-05 [opt_reshape]: 1.938e-05 [fold_const_symbol]: 4.884e-05 [renormalize]: 3.00002e-07 [detach_backward]: 4.43001e-06 [pipeline_parallel_scheduler]: 2.04e-06 [auto_monad_reorder]: 4.491e-05 [get_jit_bprop_graph]: 2.01e-06 [rewriter_after_jit_bprop_graph]: 5.74999e-06 [opt_after_jit_grad]: 0.00062636 [validate]: 9.514e-05 Sums bootstrap : 0.000857s : 0.01% type_inference : 15.668828s : 95.25% event_method : 0.001374s : 0.01% auto_monad : 0.000504s : 0.00% graph_reusing : 0.000009s : 0.00% inline : 0.000008s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000035s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000053s : 0.00% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000035s : 0.00% optimize.rewriter_before_opt_a : 0.000128s : 0.00% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000078s : 0.00% optimize.opt_a.loop_unroll : 0.000056s : 0.00% optimize.opt_a.a_1 : 0.002601s : 0.02% optimize.opt_a.with_stream_mark : 0.000061s : 0.00% optimize.opt_a.recompute_prepare : 0.000040s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000024s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000016s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000531s : 0.00% optimize.opt_a.accelerated_algorithm : 0.000064s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000012s : 0.00% optimize.opt_a.shard_inline : 0.000035s : 0.00% optimize.opt_a.merge_send_recv : 0.000034s : 0.00% optimize.opt_a.auto_parallel : 0.000033s : 0.00% optimize.opt_a.parallel : 0.000048s : 0.00% optimize.opt_a.flash_sp : 0.000017s : 0.00% optimize.opt_a.merge_comm : 0.000021s : 0.00% optimize.opt_a.allreduce_fusion : 0.000020s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000034s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000037s : 0.00% optimize.opt_a.virtual_dataset : 0.000033s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000033s : 0.00% optimize.opt_a.virtual_output : 0.000031s : 0.00% optimize.opt_a.merge_forward : 0.000019s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000037s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000066s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000056s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000021s : 0.00% optimize.opt_a.meta_fg_expand : 0.000015s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000040s : 0.00% optimize.opt_a.a_after_grad : 0.000054s : 0.00% optimize.opt_a.renormalize : 0.767661s : 4.67% optimize.opt_a.add_forward_monad_depend : 0.000020s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000063s : 0.00% optimize.opt_a.cse : 0.000762s : 0.00% optimize.opt_a.a_3 : 0.000242s : 0.00% optimize.py_interpret_to_execute_after_opt_a : 0.000030s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000431s : 0.00% optimize.convert_after_rewriter : 0.000016s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000788s : 0.00% optimize.opt_b.b_1 : 0.000427s : 0.00% optimize.opt_b.b_2 : 0.000018s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000060s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000308s : 0.00% optimize.overlap_param_gather : 0.000006s : 0.00% optimize.cconv : 0.000045s : 0.00% optimize.loop_unroll : 0.000577s : 0.00% optimize.opt_after_cconv.c_1 : 0.000079s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000056s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000088s : 0.00% optimize.tuple_transform.d_1 : 0.000187s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000017s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000127s : 0.00% optimize.cse_after_recomputation.cse : 0.000047s : 0.00% optimize.environ_conv : 0.000017s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000014s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000004s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000004s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000031s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000014s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000010s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000009s : 0.00% optimize.overlap_grad_flash_sp : 0.000045s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000228s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000065s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000043s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000019s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000049s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000045s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000626s : 0.00% validate : 0.000095s : 0.00% Time group info: ------[substitution.] 0.001039 197 4.80% : 0.000050s : 6: substitution.arithmetic_simplify 1.12% : 0.000012s : 10: substitution.elim_not_effective 1.62% : 0.000017s : 12: substitution.float_tuple_getitem_switch 2.08% : 0.000022s : 10: substitution.fold_const_symbol 1.25% : 0.000013s : 12: substitution.graph_param_transform 32.78% : 0.000340s : 7: substitution.inline 0.97% : 0.000010s : 20: substitution.j_node_and_user_rematch 2.04% : 0.000021s : 2: substitution.less_batch_normalization 1.79% : 0.000019s : 8: substitution.minmaximum_grad 1.38% : 0.000014s : 20: substitution.remove_not_recompute_node 0.59% : 0.000006s : 2: substitution.replace_old_param 5.26% : 0.000055s : 16: substitution.tuple_list_convert_item_index_to_positive 2.72% : 0.000028s : 16: substitution.tuple_list_get_item_const_eliminator 3.59% : 0.000037s : 16: substitution.tuple_list_get_item_depend_reorder 34.41% : 0.000357s : 24: substitution.tuple_list_get_item_eliminator 3.60% : 0.000037s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 15.668678 2 94.29% : 14.773269s : 1: type_inference.infer 5.71% : 0.895409s : 1: type_inference.specialize ------[replace.] 0.000081 7 100.00% : 0.000081s : 7: replace.inline ------[match.] 0.000335 7 100.00% : 0.000335s : 7: match.inline ------[predicate.] 0.000566 3093 6.83% : 0.000039s : 30: predicate.accumulaten_eliminater 0.67% : 0.000004s : 12: predicate.ad_related_special_op_eliminate 0.64% : 0.000004s : 24: predicate.addn_check_dump 0.81% : 0.000005s : 30: predicate.addn_zero_filter 0.75% : 0.000004s : 30: predicate.adjust_all_reduce_mul_add 2.07% : 0.000012s : 54: predicate.arithmetic_simplify 0.85% : 0.000005s : 30: predicate.cast_eliminate 0.66% : 0.000004s : 24: predicate.check_bprop_eliminate 0.62% : 0.000004s : 24: predicate.compare_switch_simplify 0.18% : 0.000001s : 12: predicate.const_output_eliminate 0.63% : 0.000004s : 24: predicate.depend_value_elim 4.18% : 0.000024s : 30: predicate.dict_get_item_const_eliminator 0.87% : 0.000005s : 30: predicate.dict_get_item_eliminator 0.93% : 0.000005s : 30: predicate.dict_set_item_eliminator 0.89% : 0.000005s : 24: predicate.dumpgradient_eliminate 0.19% : 0.000001s : 12: predicate.elim_not_effective 0.55% : 0.000003s : 12: predicate.elim_shapecalc_of_broadcastargs 1.10% : 0.000006s : 42: predicate.environ_add_const_eliminate 1.23% : 0.000007s : 42: predicate.environ_get_add_eliminate 1.05% : 0.000006s : 42: predicate.environ_get_depend_swap 1.82% : 0.000010s : 66: predicate.environ_get_eliminate 1.06% : 0.000006s : 42: predicate.environ_get_set_eliminate 0.92% : 0.000005s : 37: predicate.exchange_switch_depend_value 1.54% : 0.000009s : 37: predicate.float_depend_g_call 0.64% : 0.000004s : 24: predicate.float_environ_get_switch 1.09% : 0.000006s : 36: predicate.float_tuple_getitem_switch 0.16% : 0.000001s : 12: predicate.fold_const_symbol 0.68% : 0.000004s : 24: predicate.get_grad_eliminate 0.26% : 0.000001s : 12: predicate.graph_param_transform 0.61% : 0.000003s : 24: predicate.incorporate_call 0.56% : 0.000003s : 24: predicate.incorporate_call_switch 5.15% : 0.000029s : 139: predicate.inline 0.86% : 0.000005s : 24: predicate.inline_without_move 0.30% : 0.000002s : 24: predicate.j_node_and_user_rematch 1.00% : 0.000006s : 24: predicate.less_batch_normalization 1.54% : 0.000009s : 54: predicate.list_to_tuple_eliminator_ 2.17% : 0.000012s : 84: predicate.load_eliminater 0.77% : 0.000004s : 12: predicate.loop_unroll_after_grad 1.34% : 0.000008s : 52: predicate.loop_unroll_before_grad 1.75% : 0.000010s : 54: predicate.make_slice_get_slice_eliminator 0.65% : 0.000004s : 24: predicate.merge_addn 0.63% : 0.000004s : 24: predicate.micro_step_allgather_replace 0.65% : 0.000004s : 24: predicate.mini_step_allgather_replace 0.76% : 0.000004s : 30: predicate.minmaximum_grad 0.77% : 0.000004s : 12: predicate.mutable_eliminate 0.42% : 0.000002s : 12: predicate.opt_reshape 0.42% : 0.000002s : 12: predicate.parallel_virtual_node 1.70% : 0.000010s : 37: predicate.partial_defer_inline 1.13% : 0.000006s : 42: predicate.partial_eliminate 0.75% : 0.000004s : 30: predicate.print_const_string_wrapper 0.63% : 0.000004s : 24: predicate.reduce_all_const_elim 1.14% : 0.000006s : 30: predicate.reduce_eliminate 2.12% : 0.000012s : 84: predicate.redundant_stop_gradient_eliminater 0.34% : 0.000002s : 24: predicate.remove_not_recompute_node 0.99% : 0.000006s : 54: predicate.replace_applicator 0.35% : 0.000002s : 24: predicate.replace_old_param 0.18% : 0.000001s : 12: predicate.reset_defer_inline 0.79% : 0.000004s : 30: predicate.reshape_eliminate 0.69% : 0.000004s : 24: predicate.row_tensor_add_zeros_like 0.41% : 0.000002s : 12: predicate.row_tensor_eliminate 0.94% : 0.000005s : 24: predicate.same_eliminate 0.40% : 0.000002s : 24: predicate.set_cell_output_no_recompute 0.75% : 0.000004s : 24: predicate.shard_identity_eliminate 0.73% : 0.000004s : 24: predicate.special_op_eliminate 0.76% : 0.000004s : 24: predicate.specialize_transform 0.91% : 0.000005s : 24: predicate.split_environ_get_set_with_tuple_value 0.76% : 0.000004s : 24: predicate.stack_unstack_eliminate 0.37% : 0.000002s : 12: predicate.switch_call_monad_eliminater 1.00% : 0.000006s : 37: predicate.switch_defer_inline 1.68% : 0.000010s : 61: predicate.switch_layer_defer_inline 3.51% : 0.000020s : 125: predicate.switch_simplify 0.75% : 0.000004s : 30: predicate.tile_eliminate 0.79% : 0.000004s : 30: predicate.transpose_eliminate 1.78% : 0.000010s : 54: predicate.tuple_list_convert_item_index_to_positive 1.82% : 0.000010s : 54: predicate.tuple_list_get_item_const_eliminator 1.69% : 0.000010s : 54: predicate.tuple_list_get_item_depend_reorder 3.00% : 0.000017s : 78: predicate.tuple_list_get_item_eliminator 1.64% : 0.000009s : 54: predicate.tuple_list_get_set_item_eliminator 2.26% : 0.000013s : 78: predicate.tuple_list_set_item_eliminator 1.48% : 0.000008s : 54: predicate.tuple_to_list_eliminator_ 2.02% : 0.000011s : 84: predicate.updatestate_pure_node_eliminater 2.88% : 0.000016s : 108: predicate.updatestate_useless_node_eliminater 0.46% : 0.000003s : 12: predicate.value_based_eliminate 0.74% : 0.000004s : 24: predicate.virtual_dataset_eliminate 0.68% : 0.000004s : 24: predicate.virtual_output_eliminate 0.34% : 0.000002s : 12: predicate.virtual_view_grad_eliminate 0.40% : 0.000002s : 12: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.007977 38 76.21% : 0.006079s : 29: func_graph_cloner_run.FuncGraphClonerGraph 23.79% : 0.001898s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 18.010872 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.03% : 0.004641s : 1: add_attr 0.03% : 0.004622s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000132s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.00% : 0.000519s : 1: auto_monad 0.00% : 0.000049s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.01% : 0.000911s : 1: bootstrap 0.00% : 0.000049s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000034s : 1: control_data_broadcast_order 0.00% : 0.000021s : 1: convert_after_rewriter 0.00% : 0.000064s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000022s : 1: environ_conv 0.01% : 0.001402s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000014s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000011s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.00% : 0.000588s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.00% : 0.000797s : 1: mutable_eliminate 0.00% : 0.000018s : 1: offloading_packed_experts 0.00% : 0.000030s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000033s : 1: opt.transform.mutable_eliminate 0.02% : 0.003877s : 78: opt.transform.opt_a 0.00% : 0.000077s : 1: opt.transform.opt_after_cconv 0.00% : 0.000063s : 1: opt.transform.opt_after_jit_grad 0.00% : 0.000408s : 28: opt.transform.opt_b 0.00% : 0.000201s : 2: opt.transform.opt_trans_graph 0.00% : 0.000172s : 4: opt.transform.symbol_engine_opt 4.30% : 0.773597s : 1: opt_a 0.00% : 0.000218s : 1: opt_after_cconv 0.00% : 0.000636s : 1: opt_after_jit_grad 0.00% : 0.000587s : 1: opt_b 4.32% : 0.778335s : 1: optimize 0.00% : 0.000320s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.00% : 0.000048s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000013s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000007s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000012s : 1: overlap_param_gather 0.00% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000014s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000057s : 1: pre_auto_parallel 0.00% : 0.000039s : 1: py_interpret_to_execute 0.00% : 0.000033s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000092s : 1: remove_dup_value 4.25% : 0.765388s : 1: renormalize.infer 0.01% : 0.002253s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000438s : 1: rewriter_after_opt_a 0.00% : 0.000133s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000017s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000462s : 1: symbol_engine_optimizer 0.00% : 0.000346s : 1: tuple_transform 87.00% : 15.668863s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[False-True-bfloat16--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[False-True-bfloat16--1-shape1],max_mem:106.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:40:29.939.362 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 5.35088, [21] [bootstrap]: 0.00094815 [type_inference]: 4.70985 [event_method]: 0.00144835 [auto_monad]: 0.00398861 [graph_reusing]: 9.69e-06 [inline]: 2.86e-06 [add_attr]: 0.00450047, [1] [add_attr_with_inline]: 0.00448376, [1] [Cycle 1]: 8.175e-05, [2] [tag_attr]: 3.514e-05 [meta_addattr_fg_expand]: 7.63999e-06 [parallel-infer-symbol]: 3.91999e-06 [pre_auto_parallel]: 5.401e-05 [insert-virtual-dataset]: 3.58999e-06 [parallel-infer-symbol-second]: 1.04e-06 [dataset_repeat_opt]: 2.24999e-06 [pipeline_split]: 2.85998e-06 [optimize]: 0.629042, [53] [py_interpret_to_execute]: 3.814e-05 [rewriter_before_opt_a]: 0.00012414 [opt_a]: 0.39258, [2] [Cycle 1]: 0.390908, [45] [expand_dump_flag]: 4.18001e-06 [switch_simplify]: 5.681e-05 [loop_unroll]: 3.728e-05 [a_1]: 0.382182 [with_stream_mark]: 5.69e-05 [recompute_prepare]: 2.992e-05 [updatestate_depend_eliminate]: 1.32e-05 [updatestate_assign_eliminate]: 9.34e-06 [updatestate_loads_eliminate]: 8.31002e-06 [parameter_eliminate]: 2.78998e-06 [a_2]: 0.00028754 [accelerated_algorithm]: 4.085e-05 [shard]: 2.76e-06 [meta_shard_fg_expand]: 8.45999e-06 [shard_inline]: 1.643e-05 [merge_send_recv]: 1.636e-05 [auto_parallel]: 1.978e-05 [parallel]: 3.471e-05 [flash_sp]: 1.41e-05 [merge_comm]: 1.018e-05 [allreduce_fusion]: 1.014e-05 [matmul_add_comm_reduction]: 1.857e-05 [allreduce_slice_to_reducescatter]: 1.23002e-06 [virtual_shard_identity]: 1.957e-05 [virtual_dataset]: 1.712e-05 [get_grad_eliminate_]: 1.824e-05 [virtual_output]: 2.094e-05 [merge_forward]: 1.088e-05 [cell_reuse_recompute_pass]: 1.87001e-06 [offload_activation]: 1.979e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.741e-05 [merge_recompute_call_nodes]: 1.81998e-06 [before_grad]: 3.077e-05 [set_forward_comm_id_for_comm_node_pass]: 1.121e-05 [meta_fg_expand]: 8.00999e-06 [flash_sp_send_recv_attached]: 5.83997e-06 [receive_attached]: 2.91e-06 [after_resolve]: 2.21e-05 [a_after_grad]: 2.913e-05 [renormalize]: 0.00651697 [add_forward_monad_depend]: 1.68e-05 [auto_monad_grad]: 2.72001e-06 [auto_monad_eliminator]: 3.771e-05 [cse]: 0.00069823 [a_3]: 0.00013628 [Cycle 2]: 0.00165711, [45] [expand_dump_flag]: 3.04999e-06 [switch_simplify]: 1.891e-05 [loop_unroll]: 1.784e-05 [a_1]: 0.00052629 [with_stream_mark]: 3.001e-05 [recompute_prepare]: 1.748e-05 [updatestate_depend_eliminate]: 1.157e-05 [updatestate_assign_eliminate]: 8.15e-06 [updatestate_loads_eliminate]: 8.64e-06 [parameter_eliminate]: 2.24001e-06 [a_2]: 0.00024413 [accelerated_algorithm]: 2.084e-05 [shard]: 2.69001e-06 [meta_shard_fg_expand]: 5.79999e-06 [shard_inline]: 1.699e-05 [merge_send_recv]: 1.672e-05 [auto_parallel]: 1.577e-05 [parallel]: 9.86e-06 [flash_sp]: 4.57e-06 [merge_comm]: 1.013e-05 [allreduce_fusion]: 1.082e-05 [matmul_add_comm_reduction]: 1.848e-05 [allreduce_slice_to_reducescatter]: 1.12e-06 [virtual_shard_identity]: 1.731e-05 [virtual_dataset]: 1.607e-05 [get_grad_eliminate_]: 1.608e-05 [virtual_output]: 1.548e-05 [merge_forward]: 9.72001e-06 [cell_reuse_recompute_pass]: 3.7e-06 [offload_activation]: 1.892e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.057e-05 [merge_recompute_call_nodes]: 1.86e-06 [before_grad]: 2.698e-05 [set_forward_comm_id_for_comm_node_pass]: 1.005e-05 [meta_fg_expand]: 7.71999e-06 [flash_sp_send_recv_attached]: 1.69e-06 [receive_attached]: 2.79999e-06 [after_resolve]: 1.955e-05 [a_after_grad]: 2.534e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 2.44999e-06 [auto_monad_grad]: 2.65002e-06 [auto_monad_eliminator]: 2.352e-05 [cse]: 5.533e-05 [a_3]: 9.872e-05 [py_interpret_to_execute_after_opt_a]: 2.964e-05 [slice_cell_reuse_recomputed_activation]: 1.97001e-06 [rewriter_after_opt_a]: 0.00042185 [convert_after_rewriter]: 9.651e-05 [order_py_execute_after_rewriter]: 1.674e-05 [mutable_eliminate]: 0.00085261 [opt_b]: 0.00064276, [1] [Cycle 1]: 0.00063144, [7] [b_1]: 0.00044362 [b_2]: 1.883e-05 [updatestate_depend_eliminate]: 1.452e-05 [updatestate_assign_eliminate]: 8.45001e-06 [updatestate_loads_eliminate]: 8.47998e-06 [renormalize]: 7.59988e-07 [cse]: 9.41e-05 [optimize_parallel_all_gather_comm]: 3.826e-05 [overlap_param_gather]: 2.61999e-06 [cconv]: 4.506e-05 [loop_unroll]: 0.00052089 [opt_after_cconv]: 0.00021145, [1] [Cycle 1]: 0.00020346, [7] [c_1]: 7.908e-05 [parameter_eliminate]: 4.75001e-06 [updatestate_depend_eliminate]: 1.374e-05 [updatestate_assign_eliminate]: 7.73001e-06 [updatestate_loads_eliminate]: 7.56999e-06 [cse]: 5.328e-05 [renormalize]: 4.69998e-07 [remove_dup_value]: 9.132e-05 [tuple_transform]: 0.00021303, [1] [Cycle 1]: 0.00020803, [4] [d_1]: 0.00016623 [none_parameter_eliminate]: 2.38002e-06 [renormalize]: 2.30008e-07 [switch_simplify]: 1.709e-05 [partial_unused_args_eliminate]: 2.24999e-06 [add_recomputation]: 0.00012744 [cse_after_recomputation]: 5.542e-05, [1] [Cycle 1]: 4.879e-05, [1] [cse]: 4.173e-05 [environ_conv]: 1.855e-05 [swap_dp_allreduce_reducescatter]: 1.385e-05 [bias_add_comm_swap]: 3.38e-06 [label_micro_interleaved_index]: 4.53999e-06 [label_fine_grained_interleaved_index]: 2.88e-06 [merge_cast_opt]: 1.54e-06 [slice_recompute_activation]: 2.71999e-06 [micro_interleaved_order_control]: 2.78998e-06 [assign_add_opt]: 1.38002e-06 [ForceFp32Comm]: 9.00007e-07 [remove_cast_before_assign_add]: 1.32e-06 [full_micro_interleaved_order_control]: 2.75002e-06 [reorder_send_recv_between_fp_bp]: 3.23e-06 [comm_op_add_attrs]: 1.24e-06 [add_comm_op_reuse_tag]: 1.09998e-06 [interleave_split_concat_branches]: 1.37e-06 [interleave_parallel_branches]: 1.50001e-06 [overlap_opt_shard_in_pipeline]: 1.67001e-06 [overlap_opt_shard_grad_in_pipeline]: 2.20002e-06 [control_data_broadcast_order]: 3.196e-05 [grouped_pairwise_exchange_alltoall]: 2.02999e-06 [offloading_packed_experts]: 9.69999e-06 [overlap_recompute_and_grad_model_parallel]: 8.94e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.35001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.42e-06 [overlap_recompute_comm]: 2.63003e-06 [overlap_grad_ring_attention]: 7.56999e-06 [overlap_grad_flash_sp]: 4.654e-05 [begin_end_overlap_inline]: 5.19998e-07 [split_matmul_comm_elemetwise]: 2.46998e-06 [split_layernorm_comm]: 2.04999e-06 [handle_group_info]: 1.01002e-06 [symbol_engine_optimizer]: 0.00039618, [1] [Cycle 1]: 0.00038926, [6] [build]: 0.00022156 [elim_shapecalc]: 2.636e-05 [elim_not_effective]: 3.585e-05 [opt_reshape]: 1.631e-05 [fold_const_symbol]: 4.824e-05 [renormalize]: 2.40019e-07 [detach_backward]: 3.58999e-06 [pipeline_parallel_scheduler]: 1.60001e-06 [auto_monad_reorder]: 3.936e-05 [get_jit_bprop_graph]: 2.38002e-06 [rewriter_after_jit_bprop_graph]: 5.18002e-06 [opt_after_jit_grad]: 0.00062145 [validate]: 0.00010128 Sums bootstrap : 0.000948s : 0.02% type_inference : 4.709854s : 92.11% event_method : 0.001448s : 0.03% auto_monad : 0.003989s : 0.08% graph_reusing : 0.000010s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000035s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000008s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000054s : 0.00% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000038s : 0.00% optimize.rewriter_before_opt_a : 0.000124s : 0.00% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000076s : 0.00% optimize.opt_a.loop_unroll : 0.000055s : 0.00% optimize.opt_a.a_1 : 0.382709s : 7.48% optimize.opt_a.with_stream_mark : 0.000087s : 0.00% optimize.opt_a.recompute_prepare : 0.000047s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000025s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000017s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000532s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000062s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000014s : 0.00% optimize.opt_a.shard_inline : 0.000033s : 0.00% optimize.opt_a.merge_send_recv : 0.000033s : 0.00% optimize.opt_a.auto_parallel : 0.000036s : 0.00% optimize.opt_a.parallel : 0.000045s : 0.00% optimize.opt_a.flash_sp : 0.000019s : 0.00% optimize.opt_a.merge_comm : 0.000020s : 0.00% optimize.opt_a.allreduce_fusion : 0.000021s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000037s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000037s : 0.00% optimize.opt_a.virtual_dataset : 0.000033s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000034s : 0.00% optimize.opt_a.virtual_output : 0.000036s : 0.00% optimize.opt_a.merge_forward : 0.000021s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000039s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000068s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000058s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000021s : 0.00% optimize.opt_a.meta_fg_expand : 0.000016s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000042s : 0.00% optimize.opt_a.a_after_grad : 0.000054s : 0.00% optimize.opt_a.renormalize : 0.006517s : 0.13% optimize.opt_a.add_forward_monad_depend : 0.000019s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000061s : 0.00% optimize.opt_a.cse : 0.000754s : 0.01% optimize.opt_a.a_3 : 0.000235s : 0.00% optimize.py_interpret_to_execute_after_opt_a : 0.000030s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000422s : 0.01% optimize.convert_after_rewriter : 0.000097s : 0.00% optimize.order_py_execute_after_rewriter : 0.000017s : 0.00% optimize.mutable_eliminate : 0.000853s : 0.02% optimize.opt_b.b_1 : 0.000444s : 0.01% optimize.opt_b.b_2 : 0.000019s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000094s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000038s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000045s : 0.00% optimize.loop_unroll : 0.000521s : 0.01% optimize.opt_after_cconv.c_1 : 0.000079s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.cse : 0.000053s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000091s : 0.00% optimize.tuple_transform.d_1 : 0.000166s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000017s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000127s : 0.00% optimize.cse_after_recomputation.cse : 0.000042s : 0.00% optimize.environ_conv : 0.000019s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000014s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000002s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000032s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000010s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000047s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000222s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000026s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000036s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000016s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000048s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000039s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000621s : 0.01% validate : 0.000101s : 0.00% Time group info: ------[substitution.] 0.000850 197 6.91% : 0.000059s : 6: substitution.arithmetic_simplify 0.98% : 0.000008s : 10: substitution.elim_not_effective 2.07% : 0.000018s : 12: substitution.float_tuple_getitem_switch 2.68% : 0.000023s : 10: substitution.fold_const_symbol 1.51% : 0.000013s : 12: substitution.graph_param_transform 45.00% : 0.000383s : 7: substitution.inline 1.17% : 0.000010s : 20: substitution.j_node_and_user_rematch 2.57% : 0.000022s : 2: substitution.less_batch_normalization 2.28% : 0.000019s : 8: substitution.minmaximum_grad 1.87% : 0.000016s : 20: substitution.remove_not_recompute_node 0.80% : 0.000007s : 2: substitution.replace_old_param 7.64% : 0.000065s : 16: substitution.tuple_list_convert_item_index_to_positive 3.16% : 0.000027s : 16: substitution.tuple_list_get_item_const_eliminator 5.06% : 0.000043s : 16: substitution.tuple_list_get_item_depend_reorder 11.36% : 0.000097s : 24: substitution.tuple_list_get_item_eliminator 4.94% : 0.000042s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 4.709718 2 99.91% : 4.705268s : 1: type_inference.infer 0.09% : 0.004451s : 1: type_inference.specialize ------[replace.] 0.000085 7 100.00% : 0.000085s : 7: replace.inline ------[match.] 0.000376 7 100.00% : 0.000376s : 7: match.inline ------[predicate.] 0.380978 3093 0.00% : 0.000006s : 30: predicate.accumulaten_eliminater 0.00% : 0.000004s : 12: predicate.ad_related_special_op_eliminate 0.00% : 0.000004s : 24: predicate.addn_check_dump 0.00% : 0.000005s : 30: predicate.addn_zero_filter 0.00% : 0.000005s : 30: predicate.adjust_all_reduce_mul_add 0.00% : 0.000012s : 54: predicate.arithmetic_simplify 0.00% : 0.000005s : 30: predicate.cast_eliminate 0.00% : 0.000004s : 24: predicate.check_bprop_eliminate 0.00% : 0.000004s : 24: predicate.compare_switch_simplify 0.00% : 0.000001s : 12: predicate.const_output_eliminate 0.00% : 0.000004s : 24: predicate.depend_value_elim 0.00% : 0.000005s : 30: predicate.dict_get_item_const_eliminator 0.00% : 0.000005s : 30: predicate.dict_get_item_eliminator 0.00% : 0.000005s : 30: predicate.dict_set_item_eliminator 0.00% : 0.000010s : 24: predicate.dumpgradient_eliminate 0.00% : 0.000001s : 12: predicate.elim_not_effective 0.00% : 0.000003s : 12: predicate.elim_shapecalc_of_broadcastargs 0.00% : 0.000007s : 42: predicate.environ_add_const_eliminate 0.00% : 0.000006s : 42: predicate.environ_get_add_eliminate 0.00% : 0.000006s : 42: predicate.environ_get_depend_swap 0.00% : 0.000010s : 66: predicate.environ_get_eliminate 0.00% : 0.000006s : 42: predicate.environ_get_set_eliminate 0.00% : 0.000006s : 37: predicate.exchange_switch_depend_value 99.86% : 0.380447s : 37: predicate.float_depend_g_call 0.00% : 0.000004s : 24: predicate.float_environ_get_switch 0.00% : 0.000006s : 36: predicate.float_tuple_getitem_switch 0.00% : 0.000001s : 12: predicate.fold_const_symbol 0.00% : 0.000004s : 24: predicate.get_grad_eliminate 0.00% : 0.000001s : 12: predicate.graph_param_transform 0.00% : 0.000004s : 24: predicate.incorporate_call 0.00% : 0.000003s : 24: predicate.incorporate_call_switch 0.01% : 0.000033s : 139: predicate.inline 0.00% : 0.000005s : 24: predicate.inline_without_move 0.00% : 0.000002s : 24: predicate.j_node_and_user_rematch 0.00% : 0.000005s : 24: predicate.less_batch_normalization 0.00% : 0.000009s : 54: predicate.list_to_tuple_eliminator_ 0.00% : 0.000012s : 84: predicate.load_eliminater 0.00% : 0.000005s : 12: predicate.loop_unroll_after_grad 0.00% : 0.000008s : 52: predicate.loop_unroll_before_grad 0.00% : 0.000010s : 54: predicate.make_slice_get_slice_eliminator 0.00% : 0.000004s : 24: predicate.merge_addn 0.00% : 0.000004s : 24: predicate.micro_step_allgather_replace 0.00% : 0.000004s : 24: predicate.mini_step_allgather_replace 0.00% : 0.000005s : 30: predicate.minmaximum_grad 0.00% : 0.000005s : 12: predicate.mutable_eliminate 0.00% : 0.000002s : 12: predicate.opt_reshape 0.00% : 0.000003s : 12: predicate.parallel_virtual_node 0.00% : 0.000010s : 37: predicate.partial_defer_inline 0.00% : 0.000006s : 42: predicate.partial_eliminate 0.00% : 0.000004s : 30: predicate.print_const_string_wrapper 0.00% : 0.000004s : 24: predicate.reduce_all_const_elim 0.00% : 0.000007s : 30: predicate.reduce_eliminate 0.00% : 0.000013s : 84: predicate.redundant_stop_gradient_eliminater 0.00% : 0.000002s : 24: predicate.remove_not_recompute_node 0.00% : 0.000006s : 54: predicate.replace_applicator 0.00% : 0.000002s : 24: predicate.replace_old_param 0.00% : 0.000001s : 12: predicate.reset_defer_inline 0.00% : 0.000006s : 30: predicate.reshape_eliminate 0.00% : 0.000004s : 24: predicate.row_tensor_add_zeros_like 0.00% : 0.000002s : 12: predicate.row_tensor_eliminate 0.00% : 0.000005s : 24: predicate.same_eliminate 0.00% : 0.000002s : 24: predicate.set_cell_output_no_recompute 0.00% : 0.000005s : 24: predicate.shard_identity_eliminate 0.00% : 0.000004s : 24: predicate.special_op_eliminate 0.00% : 0.000004s : 24: predicate.specialize_transform 0.00% : 0.000005s : 24: predicate.split_environ_get_set_with_tuple_value 0.00% : 0.000004s : 24: predicate.stack_unstack_eliminate 0.00% : 0.000002s : 12: predicate.switch_call_monad_eliminater 0.00% : 0.000006s : 37: predicate.switch_defer_inline 0.00% : 0.000009s : 61: predicate.switch_layer_defer_inline 0.01% : 0.000020s : 125: predicate.switch_simplify 0.00% : 0.000005s : 30: predicate.tile_eliminate 0.00% : 0.000005s : 30: predicate.transpose_eliminate 0.00% : 0.000010s : 54: predicate.tuple_list_convert_item_index_to_positive 0.00% : 0.000010s : 54: predicate.tuple_list_get_item_const_eliminator 0.00% : 0.000009s : 54: predicate.tuple_list_get_item_depend_reorder 0.01% : 0.000019s : 78: predicate.tuple_list_get_item_eliminator 0.00% : 0.000009s : 54: predicate.tuple_list_get_set_item_eliminator 0.00% : 0.000015s : 78: predicate.tuple_list_set_item_eliminator 0.00% : 0.000009s : 54: predicate.tuple_to_list_eliminator_ 0.00% : 0.000012s : 84: predicate.updatestate_pure_node_eliminater 0.01% : 0.000020s : 108: predicate.updatestate_useless_node_eliminater 0.00% : 0.000002s : 12: predicate.value_based_eliminate 0.00% : 0.000004s : 24: predicate.virtual_dataset_eliminate 0.00% : 0.000004s : 24: predicate.virtual_output_eliminate 0.00% : 0.000002s : 12: predicate.virtual_view_grad_eliminate 0.00% : 0.000002s : 12: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.824398 38 99.75% : 0.822368s : 29: func_graph_cloner_run.FuncGraphClonerGraph 0.25% : 0.002030s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 6.143572 192 0.00% : 0.000003s : 1: ForceFp32Comm 0.07% : 0.004507s : 1: add_attr 0.07% : 0.004488s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000132s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.07% : 0.004015s : 1: auto_monad 0.00% : 0.000044s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.02% : 0.001000s : 1: bootstrap 0.00% : 0.000049s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000035s : 1: control_data_broadcast_order 0.00% : 0.000144s : 1: convert_after_rewriter 0.00% : 0.000059s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000023s : 1: environ_conv 0.02% : 0.001470s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000016s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000007s : 1: label_micro_interleaved_index 0.01% : 0.000529s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.01% : 0.000862s : 1: mutable_eliminate 0.00% : 0.000013s : 1: offloading_packed_experts 0.00% : 0.000028s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000047s : 1: opt.transform.mutable_eliminate 6.25% : 0.383988s : 78: opt.transform.opt_a 0.00% : 0.000077s : 1: opt.transform.opt_after_cconv 0.00% : 0.000056s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000424s : 28: opt.transform.opt_b 0.00% : 0.000181s : 2: opt.transform.opt_trans_graph 0.00% : 0.000122s : 4: opt.transform.symbol_engine_opt 6.39% : 0.392584s : 1: opt_a 0.00% : 0.000215s : 1: opt_after_cconv 0.01% : 0.000631s : 1: opt_after_jit_grad 0.01% : 0.000646s : 1: opt_b 10.24% : 0.629050s : 1: optimize 0.00% : 0.000043s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000023s : 1: order_py_execute_after_rewriter 0.00% : 0.000050s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000059s : 1: pre_auto_parallel 0.00% : 0.000042s : 1: py_interpret_to_execute 0.00% : 0.000033s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000096s : 1: remove_dup_value 0.07% : 0.004115s : 1: renormalize.infer 0.04% : 0.002385s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000429s : 1: rewriter_after_opt_a 0.00% : 0.000128s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000017s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000399s : 1: symbol_engine_optimizer 0.00% : 0.000217s : 1: tuple_transform 76.66% : 4.709878s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[False-True-bfloat16--1-shape2] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[False-True-bfloat16--1-shape2],max_mem:106.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:40:51.331.327 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 5.96244, [21] [bootstrap]: 0.00086784 [type_inference]: 5.14195 [event_method]: 0.00130236 [auto_monad]: 0.00012372 [graph_reusing]: 7.61001e-06 [inline]: 2.51998e-06 [add_attr]: 0.388382, [1] [add_attr_with_inline]: 0.388243, [1] [Cycle 1]: 0.00013869, [2] [tag_attr]: 5.557e-05 [meta_addattr_fg_expand]: 1.593e-05 [parallel-infer-symbol]: 3.8e-06 [pre_auto_parallel]: 0.00020538 [insert-virtual-dataset]: 4.26001e-06 [parallel-infer-symbol-second]: 6.89994e-07 [dataset_repeat_opt]: 2.04999e-06 [pipeline_split]: 2.94999e-06 [optimize]: 0.428143, [53] [py_interpret_to_execute]: 4.953e-05 [rewriter_before_opt_a]: 0.0001445 [opt_a]: 0.0395541, [2] [Cycle 1]: 0.0378619, [45] [expand_dump_flag]: 4.05998e-06 [switch_simplify]: 5.537e-05 [loop_unroll]: 3.853e-05 [a_1]: 0.00365977 [with_stream_mark]: 0.0249152 [recompute_prepare]: 5.622e-05 [updatestate_depend_eliminate]: 2.339e-05 [updatestate_assign_eliminate]: 8.87999e-06 [updatestate_loads_eliminate]: 8.77999e-06 [parameter_eliminate]: 6.94999e-06 [a_2]: 0.0004067 [accelerated_algorithm]: 4.224e-05 [shard]: 4.13001e-06 [meta_shard_fg_expand]: 7.55e-06 [shard_inline]: 1.591e-05 [merge_send_recv]: 1.585e-05 [auto_parallel]: 1.754e-05 [parallel]: 0.00032103 [flash_sp]: 1.259e-05 [merge_comm]: 1.035e-05 [allreduce_fusion]: 9.58997e-06 [matmul_add_comm_reduction]: 1.979e-05 [allreduce_slice_to_reducescatter]: 1.15999e-06 [virtual_shard_identity]: 1.957e-05 [virtual_dataset]: 1.753e-05 [get_grad_eliminate_]: 1.75e-05 [virtual_output]: 1.717e-05 [merge_forward]: 9.78998e-06 [cell_reuse_recompute_pass]: 3.11999e-06 [offload_activation]: 1.938e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.533e-05 [merge_recompute_call_nodes]: 1.56002e-06 [before_grad]: 2.959e-05 [set_forward_comm_id_for_comm_node_pass]: 1.034e-05 [meta_fg_expand]: 8.15999e-06 [flash_sp_send_recv_attached]: 5.49e-06 [receive_attached]: 2.12999e-06 [after_resolve]: 2.311e-05 [a_after_grad]: 3.504e-05 [renormalize]: 0.00650923 [add_forward_monad_depend]: 8.026e-05 [auto_monad_grad]: 2.73e-06 [auto_monad_eliminator]: 3.56e-05 [cse]: 0.0005925 [a_3]: 0.00021174 [Cycle 2]: 0.00167638, [45] [expand_dump_flag]: 2.88998e-06 [switch_simplify]: 1.935e-05 [loop_unroll]: 1.613e-05 [a_1]: 0.00059998 [with_stream_mark]: 2.412e-05 [recompute_prepare]: 1.704e-05 [updatestate_depend_eliminate]: 1.103e-05 [updatestate_assign_eliminate]: 8.28999e-06 [updatestate_loads_eliminate]: 7.90998e-06 [parameter_eliminate]: 1.82001e-06 [a_2]: 0.00023168 [accelerated_algorithm]: 2.011e-05 [shard]: 1.66e-06 [meta_shard_fg_expand]: 4.36002e-06 [shard_inline]: 1.498e-05 [merge_send_recv]: 1.519e-05 [auto_parallel]: 1.61e-05 [parallel]: 8.15e-06 [flash_sp]: 4.17e-06 [merge_comm]: 9.81e-06 [allreduce_fusion]: 1.021e-05 [matmul_add_comm_reduction]: 1.642e-05 [allreduce_slice_to_reducescatter]: 8.79983e-07 [virtual_shard_identity]: 1.592e-05 [virtual_dataset]: 1.459e-05 [get_grad_eliminate_]: 1.453e-05 [virtual_output]: 1.444e-05 [merge_forward]: 9.12001e-06 [cell_reuse_recompute_pass]: 3.3e-06 [offload_activation]: 1.703e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.946e-05 [merge_recompute_call_nodes]: 8.59989e-07 [before_grad]: 2.539e-05 [set_forward_comm_id_for_comm_node_pass]: 9.84001e-06 [meta_fg_expand]: 7.11001e-06 [flash_sp_send_recv_attached]: 1.48002e-06 [receive_attached]: 2.26e-06 [after_resolve]: 1.823e-05 [a_after_grad]: 2.477e-05 [renormalize]: 1.19995e-07 [add_forward_monad_depend]: 1.91e-06 [auto_monad_grad]: 2.22001e-06 [auto_monad_eliminator]: 2.189e-05 [cse]: 5.452e-05 [a_3]: 9.815e-05 [py_interpret_to_execute_after_opt_a]: 2.614e-05 [slice_cell_reuse_recomputed_activation]: 1.92999e-06 [rewriter_after_opt_a]: 0.00180853 [convert_after_rewriter]: 1.76e-05 [order_py_execute_after_rewriter]: 1.14e-05 [mutable_eliminate]: 0.00088598 [opt_b]: 0.00055847, [1] [Cycle 1]: 0.00055103, [7] [b_1]: 0.00040438 [b_2]: 1.707e-05 [updatestate_depend_eliminate]: 1.304e-05 [updatestate_assign_eliminate]: 7.43e-06 [updatestate_loads_eliminate]: 7.48e-06 [renormalize]: 6.10016e-07 [cse]: 6.099e-05 [optimize_parallel_all_gather_comm]: 2.939e-05 [overlap_param_gather]: 2.12999e-06 [cconv]: 3.252e-05 [loop_unroll]: 0.00050489 [opt_after_cconv]: 0.00023598, [1] [Cycle 1]: 0.00022868, [7] [c_1]: 7.9e-05 [parameter_eliminate]: 3.08e-06 [updatestate_depend_eliminate]: 1.319e-05 [updatestate_assign_eliminate]: 7.6e-06 [updatestate_loads_eliminate]: 3.395e-05 [cse]: 5.282e-05 [renormalize]: 4.59986e-07 [remove_dup_value]: 8.225e-05 [tuple_transform]: 0.00020904, [1] [Cycle 1]: 0.0002037, [4] [d_1]: 0.00016235 [none_parameter_eliminate]: 2.24999e-06 [renormalize]: 1.50001e-07 [switch_simplify]: 1.691e-05 [partial_unused_args_eliminate]: 1.94e-06 [add_recomputation]: 0.00011057 [cse_after_recomputation]: 5.403e-05, [1] [Cycle 1]: 4.835e-05, [1] [cse]: 4.134e-05 [environ_conv]: 1.372e-05 [swap_dp_allreduce_reducescatter]: 1.273e-05 [bias_add_comm_swap]: 2.69001e-06 [label_micro_interleaved_index]: 4.87e-06 [label_fine_grained_interleaved_index]: 2.68e-06 [merge_cast_opt]: 1.44e-06 [slice_recompute_activation]: 2.26e-06 [micro_interleaved_order_control]: 2.61e-06 [assign_add_opt]: 1.44e-06 [ForceFp32Comm]: 1.24e-06 [remove_cast_before_assign_add]: 9.50007e-07 [full_micro_interleaved_order_control]: 3.08e-06 [reorder_send_recv_between_fp_bp]: 2.89001e-06 [comm_op_add_attrs]: 1.37999e-06 [add_comm_op_reuse_tag]: 9.59e-06 [interleave_split_concat_branches]: 8.24002e-06 [interleave_parallel_branches]: 1.35999e-06 [overlap_opt_shard_in_pipeline]: 2.382e-05 [overlap_opt_shard_grad_in_pipeline]: 4.34002e-06 [control_data_broadcast_order]: 6.356e-05 [grouped_pairwise_exchange_alltoall]: 1.99999e-06 [offloading_packed_experts]: 1.077e-05 [overlap_recompute_and_grad_model_parallel]: 8.69998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.32e-06 [overlap_recompute_allgather_and_fa_grad]: 1.49e-06 [overlap_recompute_comm]: 2.76e-06 [overlap_grad_ring_attention]: 7.50998e-06 [overlap_grad_flash_sp]: 5.58e-05 [begin_end_overlap_inline]: 6.69999e-07 [split_matmul_comm_elemetwise]: 2.30002e-06 [split_layernorm_comm]: 1.94999e-06 [handle_group_info]: 9.70002e-07 [symbol_engine_optimizer]: 0.00063609, [1] [Cycle 1]: 0.00062061, [6] [build]: 0.00035448 [elim_shapecalc]: 9.07e-05 [elim_not_effective]: 5.305e-05 [opt_reshape]: 1.791e-05 [fold_const_symbol]: 4.654e-05 [renormalize]: 7.60017e-07 [detach_backward]: 3.55003e-06 [pipeline_parallel_scheduler]: 1.61002e-06 [auto_monad_reorder]: 4.557e-05 [get_jit_bprop_graph]: 2.28998e-06 [rewriter_after_jit_bprop_graph]: 7.26001e-06 [opt_after_jit_grad]: 0.00088727 [validate]: 0.00025354 Sums bootstrap : 0.000868s : 0.02% type_inference : 5.141952s : 99.07% event_method : 0.001302s : 0.03% auto_monad : 0.000124s : 0.00% graph_reusing : 0.000008s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000056s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000016s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000205s : 0.00% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000050s : 0.00% optimize.rewriter_before_opt_a : 0.000144s : 0.00% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000075s : 0.00% optimize.opt_a.loop_unroll : 0.000055s : 0.00% optimize.opt_a.a_1 : 0.004260s : 0.08% optimize.opt_a.with_stream_mark : 0.024939s : 0.48% optimize.opt_a.recompute_prepare : 0.000073s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000034s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000017s : 0.00% optimize.opt_a.parameter_eliminate : 0.000009s : 0.00% optimize.opt_a.a_2 : 0.000638s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000062s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000012s : 0.00% optimize.opt_a.shard_inline : 0.000031s : 0.00% optimize.opt_a.merge_send_recv : 0.000031s : 0.00% optimize.opt_a.auto_parallel : 0.000034s : 0.00% optimize.opt_a.parallel : 0.000329s : 0.01% optimize.opt_a.flash_sp : 0.000017s : 0.00% optimize.opt_a.merge_comm : 0.000020s : 0.00% optimize.opt_a.allreduce_fusion : 0.000020s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000036s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000035s : 0.00% optimize.opt_a.virtual_dataset : 0.000032s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000032s : 0.00% optimize.opt_a.virtual_output : 0.000032s : 0.00% optimize.opt_a.merge_forward : 0.000019s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000036s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000065s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000002s : 0.00% optimize.opt_a.before_grad : 0.000055s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000020s : 0.00% optimize.opt_a.meta_fg_expand : 0.000015s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000041s : 0.00% optimize.opt_a.a_after_grad : 0.000060s : 0.00% optimize.opt_a.renormalize : 0.006509s : 0.13% optimize.opt_a.add_forward_monad_depend : 0.000082s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000057s : 0.00% optimize.opt_a.cse : 0.000647s : 0.01% optimize.opt_a.a_3 : 0.000310s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000026s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.001809s : 0.03% optimize.convert_after_rewriter : 0.000018s : 0.00% optimize.order_py_execute_after_rewriter : 0.000011s : 0.00% optimize.mutable_eliminate : 0.000886s : 0.02% optimize.opt_b.b_1 : 0.000404s : 0.01% optimize.opt_b.b_2 : 0.000017s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000061s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000029s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000033s : 0.00% optimize.loop_unroll : 0.000505s : 0.01% optimize.opt_after_cconv.c_1 : 0.000079s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000034s : 0.00% optimize.opt_after_cconv.cse : 0.000053s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000082s : 0.00% optimize.tuple_transform.d_1 : 0.000162s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000017s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000111s : 0.00% optimize.cse_after_recomputation.cse : 0.000041s : 0.00% optimize.environ_conv : 0.000014s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000013s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000010s : 0.00% optimize.interleave_split_concat_branches : 0.000008s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000024s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000004s : 0.00% optimize.control_data_broadcast_order : 0.000064s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000011s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000056s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000354s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000091s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000053s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000018s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000047s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000046s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000887s : 0.02% validate : 0.000254s : 0.00% Time group info: ------[substitution.] 0.000922 197 5.94% : 0.000055s : 6: substitution.arithmetic_simplify 1.79% : 0.000016s : 10: substitution.elim_not_effective 1.79% : 0.000016s : 12: substitution.float_tuple_getitem_switch 2.28% : 0.000021s : 10: substitution.fold_const_symbol 1.26% : 0.000012s : 12: substitution.graph_param_transform 42.97% : 0.000396s : 7: substitution.inline 1.09% : 0.000010s : 20: substitution.j_node_and_user_rematch 2.24% : 0.000021s : 2: substitution.less_batch_normalization 1.99% : 0.000018s : 8: substitution.minmaximum_grad 1.67% : 0.000015s : 20: substitution.remove_not_recompute_node 0.75% : 0.000007s : 2: substitution.replace_old_param 17.71% : 0.000163s : 16: substitution.tuple_list_convert_item_index_to_positive 2.80% : 0.000026s : 16: substitution.tuple_list_get_item_const_eliminator 3.68% : 0.000034s : 16: substitution.tuple_list_get_item_depend_reorder 8.34% : 0.000077s : 24: substitution.tuple_list_get_item_eliminator 3.72% : 0.000034s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 5.141700 2 88.48% : 4.549206s : 1: type_inference.infer 11.52% : 0.592494s : 1: type_inference.specialize ------[replace.] 0.000068 7 100.00% : 0.000068s : 7: replace.inline ------[match.] 0.000392 7 100.00% : 0.000392s : 7: match.inline ------[predicate.] 0.000693 3093 0.65% : 0.000005s : 30: predicate.accumulaten_eliminater 0.66% : 0.000005s : 12: predicate.ad_related_special_op_eliminate 0.50% : 0.000003s : 24: predicate.addn_check_dump 0.77% : 0.000005s : 30: predicate.addn_zero_filter 0.76% : 0.000005s : 30: predicate.adjust_all_reduce_mul_add 16.75% : 0.000116s : 54: predicate.arithmetic_simplify 0.65% : 0.000004s : 30: predicate.cast_eliminate 0.54% : 0.000004s : 24: predicate.check_bprop_eliminate 0.49% : 0.000003s : 24: predicate.compare_switch_simplify 0.14% : 0.000001s : 12: predicate.const_output_eliminate 0.54% : 0.000004s : 24: predicate.depend_value_elim 0.64% : 0.000004s : 30: predicate.dict_get_item_const_eliminator 0.75% : 0.000005s : 30: predicate.dict_get_item_eliminator 0.73% : 0.000005s : 30: predicate.dict_set_item_eliminator 0.70% : 0.000005s : 24: predicate.dumpgradient_eliminate 0.26% : 0.000002s : 12: predicate.elim_not_effective 0.43% : 0.000003s : 12: predicate.elim_shapecalc_of_broadcastargs 0.91% : 0.000006s : 42: predicate.environ_add_const_eliminate 0.86% : 0.000006s : 42: predicate.environ_get_add_eliminate 0.86% : 0.000006s : 42: predicate.environ_get_depend_swap 1.48% : 0.000010s : 66: predicate.environ_get_eliminate 0.86% : 0.000006s : 42: predicate.environ_get_set_eliminate 0.74% : 0.000005s : 37: predicate.exchange_switch_depend_value 1.25% : 0.000009s : 37: predicate.float_depend_g_call 0.50% : 0.000003s : 24: predicate.float_environ_get_switch 0.93% : 0.000006s : 36: predicate.float_tuple_getitem_switch 0.13% : 0.000001s : 12: predicate.fold_const_symbol 0.58% : 0.000004s : 24: predicate.get_grad_eliminate 0.16% : 0.000001s : 12: predicate.graph_param_transform 0.55% : 0.000004s : 24: predicate.incorporate_call 0.45% : 0.000003s : 24: predicate.incorporate_call_switch 4.06% : 0.000028s : 139: predicate.inline 0.73% : 0.000005s : 24: predicate.inline_without_move 0.26% : 0.000002s : 24: predicate.j_node_and_user_rematch 0.81% : 0.000006s : 24: predicate.less_batch_normalization 1.20% : 0.000008s : 54: predicate.list_to_tuple_eliminator_ 1.65% : 0.000011s : 84: predicate.load_eliminater 0.57% : 0.000004s : 12: predicate.loop_unroll_after_grad 1.08% : 0.000007s : 52: predicate.loop_unroll_before_grad 1.27% : 0.000009s : 54: predicate.make_slice_get_slice_eliminator 0.56% : 0.000004s : 24: predicate.merge_addn 0.52% : 0.000004s : 24: predicate.micro_step_allgather_replace 0.50% : 0.000003s : 24: predicate.mini_step_allgather_replace 0.66% : 0.000005s : 30: predicate.minmaximum_grad 0.66% : 0.000005s : 12: predicate.mutable_eliminate 0.31% : 0.000002s : 12: predicate.opt_reshape 0.29% : 0.000002s : 12: predicate.parallel_virtual_node 1.16% : 0.000008s : 37: predicate.partial_defer_inline 0.96% : 0.000007s : 42: predicate.partial_eliminate 0.63% : 0.000004s : 30: predicate.print_const_string_wrapper 0.50% : 0.000003s : 24: predicate.reduce_all_const_elim 1.03% : 0.000007s : 30: predicate.reduce_eliminate 1.69% : 0.000012s : 84: predicate.redundant_stop_gradient_eliminater 0.28% : 0.000002s : 24: predicate.remove_not_recompute_node 0.87% : 0.000006s : 54: predicate.replace_applicator 0.34% : 0.000002s : 24: predicate.replace_old_param 0.16% : 0.000001s : 12: predicate.reset_defer_inline 0.69% : 0.000005s : 30: predicate.reshape_eliminate 0.53% : 0.000004s : 24: predicate.row_tensor_add_zeros_like 0.30% : 0.000002s : 12: predicate.row_tensor_eliminate 0.68% : 0.000005s : 24: predicate.same_eliminate 0.48% : 0.000003s : 24: predicate.set_cell_output_no_recompute 0.59% : 0.000004s : 24: predicate.shard_identity_eliminate 0.63% : 0.000004s : 24: predicate.special_op_eliminate 0.68% : 0.000005s : 24: predicate.specialize_transform 11.98% : 0.000083s : 24: predicate.split_environ_get_set_with_tuple_value 0.69% : 0.000005s : 24: predicate.stack_unstack_eliminate 0.26% : 0.000002s : 12: predicate.switch_call_monad_eliminater 0.83% : 0.000006s : 37: predicate.switch_defer_inline 1.32% : 0.000009s : 61: predicate.switch_layer_defer_inline 2.92% : 0.000020s : 125: predicate.switch_simplify 0.68% : 0.000005s : 30: predicate.tile_eliminate 0.63% : 0.000004s : 30: predicate.transpose_eliminate 1.33% : 0.000009s : 54: predicate.tuple_list_convert_item_index_to_positive 1.40% : 0.000010s : 54: predicate.tuple_list_get_item_const_eliminator 1.23% : 0.000009s : 54: predicate.tuple_list_get_item_depend_reorder 2.47% : 0.000017s : 78: predicate.tuple_list_get_item_eliminator 1.36% : 0.000009s : 54: predicate.tuple_list_get_set_item_eliminator 2.09% : 0.000014s : 78: predicate.tuple_list_set_item_eliminator 1.26% : 0.000009s : 54: predicate.tuple_to_list_eliminator_ 1.64% : 0.000011s : 84: predicate.updatestate_pure_node_eliminater 2.29% : 0.000016s : 108: predicate.updatestate_useless_node_eliminater 0.30% : 0.000002s : 12: predicate.value_based_eliminate 0.56% : 0.000004s : 24: predicate.virtual_dataset_eliminate 0.56% : 0.000004s : 24: predicate.virtual_output_eliminate 0.28% : 0.000002s : 12: predicate.virtual_view_grad_eliminate 0.32% : 0.000002s : 12: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.290427 38 98.70% : 0.286662s : 29: func_graph_cloner_run.FuncGraphClonerGraph 1.30% : 0.003764s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 6.791512 192 0.00% : 0.000004s : 1: ForceFp32Comm 5.72% : 0.388389s : 1: add_attr 5.72% : 0.388248s : 1: add_attr_with_inline 0.00% : 0.000042s : 1: add_comm_op_reuse_tag 0.00% : 0.000116s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.00% : 0.000132s : 1: auto_monad 0.00% : 0.000050s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000005s : 1: bias_add_comm_swap 0.01% : 0.000914s : 1: bootstrap 0.00% : 0.000036s : 1: cconv 5.63% : 0.382488s : 1: comm_op_add_attrs 0.00% : 0.000068s : 1: control_data_broadcast_order 0.00% : 0.000022s : 1: convert_after_rewriter 0.00% : 0.000057s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000018s : 1: environ_conv 0.02% : 0.001325s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000009s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000013s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.01% : 0.000514s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.01% : 0.000896s : 1: mutable_eliminate 0.00% : 0.000014s : 1: offloading_packed_experts 0.00% : 0.000028s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000033s : 1: opt.transform.mutable_eliminate 0.08% : 0.005737s : 78: opt.transform.opt_a 0.00% : 0.000078s : 1: opt.transform.opt_after_cconv 0.00% : 0.000060s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000389s : 28: opt.transform.opt_b 0.00% : 0.000177s : 2: opt.transform.opt_trans_graph 0.00% : 0.000199s : 4: opt.transform.symbol_engine_opt 0.58% : 0.039558s : 1: opt_a 0.00% : 0.000240s : 1: opt_after_cconv 0.01% : 0.000898s : 1: opt_after_jit_grad 0.01% : 0.000562s : 1: opt_b 6.30% : 0.428150s : 1: optimize 0.00% : 0.000033s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.00% : 0.000060s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000008s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000028s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000211s : 1: pre_auto_parallel 0.00% : 0.000054s : 1: py_interpret_to_execute 0.00% : 0.000030s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000088s : 1: remove_dup_value 0.06% : 0.004159s : 1: renormalize.infer 0.03% : 0.002334s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.001817s : 1: rewriter_after_opt_a 0.00% : 0.000149s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000016s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000639s : 1: symbol_engine_optimizer 0.00% : 0.000213s : 1: tuple_transform 75.71% : 5.141994s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[False-True-bfloat16--1-shape3] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[False-True-bfloat16--1-shape3],max_mem:100.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:41:15.232.99 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 4.63905, [21] [bootstrap]: 0.00105399 [type_inference]: 4.42221 [event_method]: 0.0300883 [auto_monad]: 0.00094913 [graph_reusing]: 8.65001e-06 [inline]: 2.91e-06 [add_attr]: 0.0295613, [1] [add_attr_with_inline]: 0.0295434, [1] [Cycle 1]: 8.987e-05, [2] [tag_attr]: 3.562e-05 [meta_addattr_fg_expand]: 7.28e-06 [parallel-infer-symbol]: 4.17e-06 [pre_auto_parallel]: 5.596e-05 [insert-virtual-dataset]: 4.03999e-06 [parallel-infer-symbol-second]: 7.49977e-07 [dataset_repeat_opt]: 2.49001e-06 [pipeline_split]: 3.93999e-06 [optimize]: 0.154036, [53] [py_interpret_to_execute]: 4.501e-05 [rewriter_before_opt_a]: 0.00013487 [opt_a]: 0.108802, [2] [Cycle 1]: 0.0821816, [45] [expand_dump_flag]: 3.48e-06 [switch_simplify]: 5.515e-05 [loop_unroll]: 3.947e-05 [a_1]: 0.022383 [with_stream_mark]: 4.496e-05 [recompute_prepare]: 2.942e-05 [updatestate_depend_eliminate]: 1.185e-05 [updatestate_assign_eliminate]: 8.59998e-06 [updatestate_loads_eliminate]: 9.16002e-06 [parameter_eliminate]: 2.68e-06 [a_2]: 0.00029512 [accelerated_algorithm]: 4.619e-05 [shard]: 2.98e-06 [meta_shard_fg_expand]: 8.20999e-06 [shard_inline]: 1.732e-05 [merge_send_recv]: 1.565e-05 [auto_parallel]: 1.791e-05 [parallel]: 3.391e-05 [flash_sp]: 1.324e-05 [merge_comm]: 1.088e-05 [allreduce_fusion]: 9.54e-06 [matmul_add_comm_reduction]: 1.87e-05 [allreduce_slice_to_reducescatter]: 1.54e-06 [virtual_shard_identity]: 2.214e-05 [virtual_dataset]: 1.927e-05 [get_grad_eliminate_]: 1.891e-05 [virtual_output]: 2.451e-05 [merge_forward]: 1.264e-05 [cell_reuse_recompute_pass]: 2.21e-06 [offload_activation]: 1.906e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.063e-05 [merge_recompute_call_nodes]: 1.59e-06 [before_grad]: 3.265e-05 [set_forward_comm_id_for_comm_node_pass]: 1.153e-05 [meta_fg_expand]: 7.36999e-06 [flash_sp_send_recv_attached]: 5.47001e-06 [receive_attached]: 2.31998e-06 [after_resolve]: 2.701e-05 [a_after_grad]: 3.169e-05 [renormalize]: 0.0572943 [add_forward_monad_depend]: 1.908e-05 [auto_monad_grad]: 2.98998e-06 [auto_monad_eliminator]: 4.599e-05 [cse]: 0.00092761 [a_3]: 0.00014612 [Cycle 2]: 0.0266031, [45] [expand_dump_flag]: 3.61001e-06 [switch_simplify]: 1.972e-05 [loop_unroll]: 0.00012407 [a_1]: 0.0251517 [with_stream_mark]: 4.545e-05 [recompute_prepare]: 2.844e-05 [updatestate_depend_eliminate]: 1.154e-05 [updatestate_assign_eliminate]: 8.25999e-06 [updatestate_loads_eliminate]: 8.40001e-06 [parameter_eliminate]: 3.14999e-06 [a_2]: 0.00026477 [accelerated_algorithm]: 2.481e-05 [shard]: 3.60998e-06 [meta_shard_fg_expand]: 1.033e-05 [shard_inline]: 1.669e-05 [merge_send_recv]: 1.806e-05 [auto_parallel]: 1.662e-05 [parallel]: 1.111e-05 [flash_sp]: 5.20001e-06 [merge_comm]: 9.47999e-06 [allreduce_fusion]: 1.06e-05 [matmul_add_comm_reduction]: 2.169e-05 [allreduce_slice_to_reducescatter]: 1.38002e-06 [virtual_shard_identity]: 1.999e-05 [virtual_dataset]: 1.651e-05 [get_grad_eliminate_]: 1.564e-05 [virtual_output]: 1.569e-05 [merge_forward]: 1.033e-05 [cell_reuse_recompute_pass]: 3.66999e-06 [offload_activation]: 2.038e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.569e-05 [merge_recompute_call_nodes]: 2.12001e-06 [before_grad]: 2.857e-05 [set_forward_comm_id_for_comm_node_pass]: 1.009e-05 [meta_fg_expand]: 7.69002e-06 [flash_sp_send_recv_attached]: 1.96e-06 [receive_attached]: 2.97002e-06 [after_resolve]: 2.221e-05 [a_after_grad]: 2.633e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 3.5e-06 [auto_monad_grad]: 4.57e-06 [auto_monad_eliminator]: 3.57e-05 [cse]: 8.819e-05 [a_3]: 0.00010648 [py_interpret_to_execute_after_opt_a]: 3.603e-05 [slice_cell_reuse_recomputed_activation]: 2.98e-06 [rewriter_after_opt_a]: 0.00047092 [convert_after_rewriter]: 2.151e-05 [order_py_execute_after_rewriter]: 1.205e-05 [mutable_eliminate]: 0.00088696 [opt_b]: 0.0411368, [1] [Cycle 1]: 0.0411231, [7] [b_1]: 0.00042812 [b_2]: 2.064e-05 [updatestate_depend_eliminate]: 1.702e-05 [updatestate_assign_eliminate]: 9.10999e-06 [updatestate_loads_eliminate]: 8.43999e-06 [renormalize]: 7.2e-07 [cse]: 0.0405475 [optimize_parallel_all_gather_comm]: 5.923e-05 [overlap_param_gather]: 2.16e-06 [cconv]: 4.773e-05 [loop_unroll]: 0.00092073 [opt_after_cconv]: 0.00025542, [1] [Cycle 1]: 0.00024386, [7] [c_1]: 9.487e-05 [parameter_eliminate]: 6.35002e-06 [updatestate_depend_eliminate]: 1.824e-05 [updatestate_assign_eliminate]: 8.54e-06 [updatestate_loads_eliminate]: 7.88999e-06 [cse]: 6.746e-05 [renormalize]: 6.59988e-07 [remove_dup_value]: 0.00011541 [tuple_transform]: 0.00025582, [1] [Cycle 1]: 0.00024987, [4] [d_1]: 0.00020424 [none_parameter_eliminate]: 2.34001e-06 [renormalize]: 1.69995e-07 [switch_simplify]: 1.891e-05 [partial_unused_args_eliminate]: 2.12001e-06 [add_recomputation]: 0.00012769 [cse_after_recomputation]: 5.87e-05, [1] [Cycle 1]: 5.103e-05, [1] [cse]: 4.431e-05 [environ_conv]: 1.837e-05 [swap_dp_allreduce_reducescatter]: 1.327e-05 [bias_add_comm_swap]: 3.09999e-06 [label_micro_interleaved_index]: 6.07999e-06 [label_fine_grained_interleaved_index]: 3.56001e-06 [merge_cast_opt]: 1.45001e-06 [slice_recompute_activation]: 2.15002e-06 [micro_interleaved_order_control]: 2.72001e-06 [assign_add_opt]: 1.42999e-06 [ForceFp32Comm]: 1.09e-06 [remove_cast_before_assign_add]: 1.15999e-06 [full_micro_interleaved_order_control]: 2.93998e-06 [reorder_send_recv_between_fp_bp]: 3.05998e-06 [comm_op_add_attrs]: 1.02e-06 [add_comm_op_reuse_tag]: 1.03001e-06 [interleave_split_concat_branches]: 1.16002e-06 [interleave_parallel_branches]: 1.20001e-06 [overlap_opt_shard_in_pipeline]: 1.25999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.32999e-06 [control_data_broadcast_order]: 2.916e-05 [grouped_pairwise_exchange_alltoall]: 1.79998e-06 [offloading_packed_experts]: 9.24998e-06 [overlap_recompute_and_grad_model_parallel]: 8.70999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.18001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.32999e-06 [overlap_recompute_comm]: 2.36e-06 [overlap_grad_ring_attention]: 7.23e-06 [overlap_grad_flash_sp]: 4.48e-05 [begin_end_overlap_inline]: 5.60016e-07 [split_matmul_comm_elemetwise]: 2.40002e-06 [split_layernorm_comm]: 1.77001e-06 [handle_group_info]: 1.22e-06 [symbol_engine_optimizer]: 0.00015796, [1] [Cycle 1]: 0.00015309, [6] [build]: 1.714e-05 [elim_shapecalc]: 2.456e-05 [elim_not_effective]: 3.268e-05 [opt_reshape]: 1.705e-05 [fold_const_symbol]: 2.693e-05 [renormalize]: 3.29979e-07 [detach_backward]: 2.56998e-06 [pipeline_parallel_scheduler]: 1.84998e-06 [auto_monad_reorder]: 3.467e-05 [get_jit_bprop_graph]: 2.43e-06 [rewriter_after_jit_bprop_graph]: 8.57e-06 [opt_after_jit_grad]: 0.00062011 [validate]: 9.492e-05 Sums bootstrap : 0.001054s : 0.02% type_inference : 4.422206s : 95.97% event_method : 0.030088s : 0.65% auto_monad : 0.000949s : 0.02% graph_reusing : 0.000009s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000036s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000056s : 0.00% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000004s : 0.00% optimize.py_interpret_to_execute : 0.000045s : 0.00% optimize.rewriter_before_opt_a : 0.000135s : 0.00% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000075s : 0.00% optimize.opt_a.loop_unroll : 0.000164s : 0.00% optimize.opt_a.a_1 : 0.047535s : 1.03% optimize.opt_a.with_stream_mark : 0.000090s : 0.00% optimize.opt_a.recompute_prepare : 0.000058s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000023s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000018s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000560s : 0.01% optimize.opt_a.accelerated_algorithm : 0.000071s : 0.00% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000019s : 0.00% optimize.opt_a.shard_inline : 0.000034s : 0.00% optimize.opt_a.merge_send_recv : 0.000034s : 0.00% optimize.opt_a.auto_parallel : 0.000035s : 0.00% optimize.opt_a.parallel : 0.000045s : 0.00% optimize.opt_a.flash_sp : 0.000018s : 0.00% optimize.opt_a.merge_comm : 0.000020s : 0.00% optimize.opt_a.allreduce_fusion : 0.000020s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000040s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000042s : 0.00% optimize.opt_a.virtual_dataset : 0.000036s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000035s : 0.00% optimize.opt_a.virtual_output : 0.000040s : 0.00% optimize.opt_a.merge_forward : 0.000023s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000039s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000076s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000061s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000022s : 0.00% optimize.opt_a.meta_fg_expand : 0.000015s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000049s : 0.00% optimize.opt_a.a_after_grad : 0.000058s : 0.00% optimize.opt_a.renormalize : 0.057294s : 1.24% optimize.opt_a.add_forward_monad_depend : 0.000023s : 0.00% optimize.opt_a.auto_monad_grad : 0.000008s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000082s : 0.00% optimize.opt_a.cse : 0.001016s : 0.02% optimize.opt_a.a_3 : 0.000253s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000036s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000471s : 0.01% optimize.convert_after_rewriter : 0.000022s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000887s : 0.02% optimize.opt_b.b_1 : 0.000428s : 0.01% optimize.opt_b.b_2 : 0.000021s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000017s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.040548s : 0.88% optimize.optimize_parallel_all_gather_comm : 0.000059s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000048s : 0.00% optimize.loop_unroll : 0.000921s : 0.02% optimize.opt_after_cconv.c_1 : 0.000095s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000018s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.cse : 0.000067s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000115s : 0.00% optimize.tuple_transform.d_1 : 0.000204s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000019s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000128s : 0.00% optimize.cse_after_recomputation.cse : 0.000044s : 0.00% optimize.environ_conv : 0.000018s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000013s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000004s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000029s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000009s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000045s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000017s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000025s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000033s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000017s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000027s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000035s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000009s : 0.00% opt_after_jit_grad : 0.000620s : 0.01% validate : 0.000095s : 0.00% Time group info: ------[substitution.] 0.000895 200 7.45% : 0.000067s : 6: substitution.arithmetic_simplify 0.49% : 0.000004s : 10: substitution.elim_not_effective 1.91% : 0.000017s : 12: substitution.float_tuple_getitem_switch 0.41% : 0.000004s : 10: substitution.fold_const_symbol 1.52% : 0.000014s : 13: substitution.graph_param_transform 46.71% : 0.000418s : 7: substitution.inline 1.27% : 0.000011s : 20: substitution.j_node_and_user_rematch 2.83% : 0.000025s : 2: substitution.less_batch_normalization 2.85% : 0.000025s : 8: substitution.minmaximum_grad 1.70% : 0.000015s : 20: substitution.remove_not_recompute_node 0.83% : 0.000007s : 4: substitution.replace_old_param 6.88% : 0.000062s : 16: substitution.tuple_list_convert_item_index_to_positive 3.26% : 0.000029s : 16: substitution.tuple_list_get_item_const_eliminator 5.14% : 0.000046s : 16: substitution.tuple_list_get_item_depend_reorder 11.82% : 0.000106s : 24: substitution.tuple_list_get_item_eliminator 4.92% : 0.000044s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 4.422073 2 99.41% : 4.395766s : 1: type_inference.infer 0.59% : 0.026307s : 1: type_inference.specialize ------[replace.] 0.000088 7 100.00% : 0.000088s : 7: replace.inline ------[match.] 0.000411 7 100.00% : 0.000411s : 7: match.inline ------[predicate.] 0.025189 3321 0.02% : 0.000005s : 32: predicate.accumulaten_eliminater 0.02% : 0.000005s : 13: predicate.ad_related_special_op_eliminate 0.02% : 0.000004s : 26: predicate.addn_check_dump 0.04% : 0.000011s : 32: predicate.addn_zero_filter 0.02% : 0.000005s : 32: predicate.adjust_all_reduce_mul_add 0.06% : 0.000014s : 58: predicate.arithmetic_simplify 0.02% : 0.000005s : 32: predicate.cast_eliminate 0.02% : 0.000004s : 26: predicate.check_bprop_eliminate 0.02% : 0.000004s : 26: predicate.compare_switch_simplify 0.00% : 0.000001s : 13: predicate.const_output_eliminate 0.01% : 0.000004s : 26: predicate.depend_value_elim 0.04% : 0.000011s : 32: predicate.dict_get_item_const_eliminator 97.24% : 0.024494s : 32: predicate.dict_get_item_eliminator 0.02% : 0.000005s : 32: predicate.dict_set_item_eliminator 0.02% : 0.000006s : 26: predicate.dumpgradient_eliminate 0.00% : 0.000001s : 13: predicate.elim_not_effective 0.01% : 0.000003s : 13: predicate.elim_shapecalc_of_broadcastargs 0.03% : 0.000007s : 45: predicate.environ_add_const_eliminate 0.02% : 0.000006s : 45: predicate.environ_get_add_eliminate 0.03% : 0.000007s : 45: predicate.environ_get_depend_swap 0.04% : 0.000011s : 71: predicate.environ_get_eliminate 0.03% : 0.000007s : 45: predicate.environ_get_set_eliminate 0.02% : 0.000006s : 39: predicate.exchange_switch_depend_value 0.04% : 0.000010s : 39: predicate.float_depend_g_call 0.02% : 0.000004s : 26: predicate.float_environ_get_switch 0.03% : 0.000007s : 39: predicate.float_tuple_getitem_switch 0.00% : 0.000001s : 13: predicate.fold_const_symbol 0.02% : 0.000005s : 26: predicate.get_grad_eliminate 0.01% : 0.000001s : 13: predicate.graph_param_transform 0.02% : 0.000004s : 26: predicate.incorporate_call 0.01% : 0.000003s : 26: predicate.incorporate_call_switch 0.15% : 0.000039s : 149: predicate.inline 0.02% : 0.000005s : 26: predicate.inline_without_move 0.01% : 0.000002s : 26: predicate.j_node_and_user_rematch 0.02% : 0.000006s : 26: predicate.less_batch_normalization 0.04% : 0.000010s : 58: predicate.list_to_tuple_eliminator_ 0.05% : 0.000014s : 90: predicate.load_eliminater 0.02% : 0.000005s : 13: predicate.loop_unroll_after_grad 0.43% : 0.000109s : 55: predicate.loop_unroll_before_grad 0.04% : 0.000011s : 58: predicate.make_slice_get_slice_eliminator 0.02% : 0.000004s : 26: predicate.merge_addn 0.02% : 0.000004s : 26: predicate.micro_step_allgather_replace 0.02% : 0.000004s : 26: predicate.mini_step_allgather_replace 0.02% : 0.000005s : 32: predicate.minmaximum_grad 0.02% : 0.000006s : 13: predicate.mutable_eliminate 0.01% : 0.000002s : 13: predicate.opt_reshape 0.01% : 0.000002s : 13: predicate.parallel_virtual_node 0.06% : 0.000016s : 39: predicate.partial_defer_inline 0.03% : 0.000007s : 45: predicate.partial_eliminate 0.02% : 0.000005s : 32: predicate.print_const_string_wrapper 0.02% : 0.000004s : 26: predicate.reduce_all_const_elim 0.03% : 0.000009s : 32: predicate.reduce_eliminate 0.05% : 0.000014s : 90: predicate.redundant_stop_gradient_eliminater 0.01% : 0.000002s : 26: predicate.remove_not_recompute_node 0.03% : 0.000006s : 58: predicate.replace_applicator 0.01% : 0.000003s : 26: predicate.replace_old_param 0.01% : 0.000001s : 13: predicate.reset_defer_inline 0.02% : 0.000006s : 32: predicate.reshape_eliminate 0.02% : 0.000004s : 26: predicate.row_tensor_add_zeros_like 0.01% : 0.000003s : 13: predicate.row_tensor_eliminate 0.02% : 0.000005s : 26: predicate.same_eliminate 0.01% : 0.000003s : 26: predicate.set_cell_output_no_recompute 0.02% : 0.000005s : 26: predicate.shard_identity_eliminate 0.02% : 0.000005s : 26: predicate.special_op_eliminate 0.02% : 0.000004s : 26: predicate.specialize_transform 0.02% : 0.000006s : 26: predicate.split_environ_get_set_with_tuple_value 0.02% : 0.000005s : 26: predicate.stack_unstack_eliminate 0.01% : 0.000002s : 13: predicate.switch_call_monad_eliminater 0.03% : 0.000008s : 39: predicate.switch_defer_inline 0.04% : 0.000011s : 65: predicate.switch_layer_defer_inline 0.08% : 0.000021s : 133: predicate.switch_simplify 0.02% : 0.000005s : 32: predicate.tile_eliminate 0.02% : 0.000005s : 32: predicate.transpose_eliminate 0.04% : 0.000011s : 58: predicate.tuple_list_convert_item_index_to_positive 0.04% : 0.000011s : 58: predicate.tuple_list_get_item_const_eliminator 0.04% : 0.000011s : 58: predicate.tuple_list_get_item_depend_reorder 0.08% : 0.000021s : 84: predicate.tuple_list_get_item_eliminator 0.04% : 0.000011s : 58: predicate.tuple_list_get_set_item_eliminator 0.06% : 0.000015s : 84: predicate.tuple_list_set_item_eliminator 0.04% : 0.000010s : 58: predicate.tuple_to_list_eliminator_ 0.05% : 0.000012s : 90: predicate.updatestate_pure_node_eliminater 0.07% : 0.000018s : 116: predicate.updatestate_useless_node_eliminater 0.01% : 0.000002s : 13: predicate.value_based_eliminate 0.02% : 0.000005s : 26: predicate.virtual_dataset_eliminate 0.02% : 0.000005s : 26: predicate.virtual_output_eliminate 0.01% : 0.000002s : 13: predicate.virtual_view_grad_eliminate 0.01% : 0.000002s : 13: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.029586 38 20.93% : 0.006193s : 29: func_graph_cloner_run.FuncGraphClonerGraph 79.07% : 0.023392s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 4.929654 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.60% : 0.029569s : 1: add_attr 0.60% : 0.029548s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000132s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.02% : 0.000965s : 1: auto_monad 0.00% : 0.000040s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.02% : 0.001164s : 1: bootstrap 0.00% : 0.000052s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000033s : 1: control_data_broadcast_order 0.00% : 0.000027s : 1: convert_after_rewriter 0.00% : 0.000062s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000023s : 1: environ_conv 0.61% : 0.030123s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000009s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.02% : 0.000930s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000898s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.00% : 0.000042s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000039s : 1: opt.transform.mutable_eliminate 0.99% : 0.048998s : 78: opt.transform.opt_a 0.00% : 0.000093s : 1: opt.transform.opt_after_cconv 0.00% : 0.000063s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000413s : 28: opt.transform.opt_b 0.00% : 0.000220s : 2: opt.transform.opt_trans_graph 0.00% : 0.000097s : 4: opt.transform.symbol_engine_opt 2.21% : 0.108806s : 1: opt_a 0.01% : 0.000259s : 1: opt_after_cconv 0.01% : 0.000630s : 1: opt_after_jit_grad 0.83% : 0.041146s : 1: opt_b 3.12% : 0.154043s : 1: optimize 0.00% : 0.000067s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000016s : 1: order_py_execute_after_rewriter 0.00% : 0.000049s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000008s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000007s : 1: pipeline_split 0.00% : 0.000061s : 1: pre_auto_parallel 0.00% : 0.000049s : 1: py_interpret_to_execute 0.00% : 0.000050s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000121s : 1: remove_dup_value 0.68% : 0.033390s : 1: renormalize.infer 0.48% : 0.023883s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000480s : 1: rewriter_after_opt_a 0.00% : 0.000140s : 1: rewriter_before_opt_a 0.00% : 0.000007s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000017s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000162s : 1: symbol_engine_optimizer 0.01% : 0.000260s : 1: tuple_transform 89.71% : 4.422241s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[True-False-bfloat16--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[True-False-bfloat16--1-shape0],max_mem:100.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:41:34.207.711 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 13.5302, [21] [bootstrap]: 0.00084727 [type_inference]: 12.7243 [event_method]: 0.00090209 [auto_monad]: 0.00036917 [graph_reusing]: 8.13999e-06 [inline]: 3.21999e-06 [add_attr]: 0.174034, [1] [add_attr_with_inline]: 0.174016, [1] [Cycle 1]: 7.83e-05, [2] [tag_attr]: 3.314e-05 [meta_addattr_fg_expand]: 7.55998e-06 [parallel-infer-symbol]: 5.15999e-06 [pre_auto_parallel]: 4.843e-05 [insert-virtual-dataset]: 4.44002e-06 [parallel-infer-symbol-second]: 8.10018e-07 [dataset_repeat_opt]: 2.31e-06 [pipeline_split]: 3.14001e-06 [optimize]: 0.628587, [53] [py_interpret_to_execute]: 3.654e-05 [rewriter_before_opt_a]: 0.00012786 [opt_a]: 0.62467, [2] [Cycle 1]: 0.622996, [45] [expand_dump_flag]: 3.31999e-06 [switch_simplify]: 5.539e-05 [loop_unroll]: 4.195e-05 [a_1]: 0.00147831 [with_stream_mark]: 2.477e-05 [recompute_prepare]: 2.2e-05 [updatestate_depend_eliminate]: 1.09e-05 [updatestate_assign_eliminate]: 8.32e-06 [updatestate_loads_eliminate]: 8.46002e-06 [parameter_eliminate]: 2.26e-06 [a_2]: 0.00027728 [accelerated_algorithm]: 3.96e-05 [shard]: 2.61e-06 [meta_shard_fg_expand]: 4.43001e-06 [shard_inline]: 1.576e-05 [merge_send_recv]: 1.62e-05 [auto_parallel]: 1.381e-05 [parallel]: 4.005e-05 [flash_sp]: 1.063e-05 [merge_comm]: 1.002e-05 [allreduce_fusion]: 9.88002e-06 [matmul_add_comm_reduction]: 1.8e-05 [allreduce_slice_to_reducescatter]: 6.80011e-07 [virtual_shard_identity]: 2.331e-05 [virtual_dataset]: 1.886e-05 [get_grad_eliminate_]: 1.718e-05 [virtual_output]: 1.692e-05 [merge_forward]: 1.029e-05 [cell_reuse_recompute_pass]: 1.70001e-06 [offload_activation]: 1.792e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.539e-05 [merge_recompute_call_nodes]: 1.94999e-06 [before_grad]: 3.023e-05 [set_forward_comm_id_for_comm_node_pass]: 9.82999e-06 [meta_fg_expand]: 7.35e-06 [flash_sp_send_recv_attached]: 4.92e-06 [receive_attached]: 2.28998e-06 [after_resolve]: 2.399e-05 [a_after_grad]: 2.88e-05 [renormalize]: 0.619036 [add_forward_monad_depend]: 2.132e-05 [auto_monad_grad]: 3.90998e-06 [auto_monad_eliminator]: 4.184e-05 [cse]: 0.00103846 [a_3]: 0.00014542 [Cycle 2]: 0.00165929, [45] [expand_dump_flag]: 3.30003e-06 [switch_simplify]: 1.901e-05 [loop_unroll]: 1.613e-05 [a_1]: 0.00052709 [with_stream_mark]: 2.879e-05 [recompute_prepare]: 1.672e-05 [updatestate_depend_eliminate]: 1.016e-05 [updatestate_assign_eliminate]: 8.30999e-06 [updatestate_loads_eliminate]: 8.09002e-06 [parameter_eliminate]: 2.44001e-06 [a_2]: 0.00023608 [accelerated_algorithm]: 2.118e-05 [shard]: 2.22999e-06 [meta_shard_fg_expand]: 4.88001e-06 [shard_inline]: 1.571e-05 [merge_send_recv]: 1.742e-05 [auto_parallel]: 1.603e-05 [parallel]: 1.07e-05 [flash_sp]: 5.29e-06 [merge_comm]: 9.22999e-06 [allreduce_fusion]: 1.012e-05 [matmul_add_comm_reduction]: 1.776e-05 [allreduce_slice_to_reducescatter]: 8.80013e-07 [virtual_shard_identity]: 1.853e-05 [virtual_dataset]: 1.586e-05 [get_grad_eliminate_]: 1.57e-05 [virtual_output]: 1.459e-05 [merge_forward]: 9.74999e-06 [cell_reuse_recompute_pass]: 4.25e-06 [offload_activation]: 1.9e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.131e-05 [merge_recompute_call_nodes]: 1.91e-06 [before_grad]: 2.772e-05 [set_forward_comm_id_for_comm_node_pass]: 1.049e-05 [meta_fg_expand]: 7.65998e-06 [flash_sp_send_recv_attached]: 1.92999e-06 [receive_attached]: 2.72001e-06 [after_resolve]: 2.176e-05 [a_after_grad]: 2.685e-05 [renormalize]: 1.10012e-07 [add_forward_monad_depend]: 2.05002e-06 [auto_monad_grad]: 1.94e-06 [auto_monad_eliminator]: 2.308e-05 [cse]: 5.465e-05 [a_3]: 0.00010342 [py_interpret_to_execute_after_opt_a]: 2.991e-05 [slice_cell_reuse_recomputed_activation]: 2.21e-06 [rewriter_after_opt_a]: 0.00043774 [convert_after_rewriter]: 1.759e-05 [order_py_execute_after_rewriter]: 1.197e-05 [mutable_eliminate]: 0.00077949 [opt_b]: 0.00057694, [1] [Cycle 1]: 0.00056834, [7] [b_1]: 0.0004231 [b_2]: 1.811e-05 [updatestate_depend_eliminate]: 1.219e-05 [updatestate_assign_eliminate]: 7.67998e-06 [updatestate_loads_eliminate]: 7.45998e-06 [renormalize]: 8.2e-07 [cse]: 5.964e-05 [optimize_parallel_all_gather_comm]: 2.978e-05 [overlap_param_gather]: 4.99003e-06 [cconv]: 3.633e-05 [loop_unroll]: 0.00047722 [opt_after_cconv]: 0.00020938, [1] [Cycle 1]: 0.00020251, [7] [c_1]: 8.373e-05 [parameter_eliminate]: 3.48e-06 [updatestate_depend_eliminate]: 1.31e-05 [updatestate_assign_eliminate]: 7.81001e-06 [updatestate_loads_eliminate]: 7.11001e-06 [cse]: 5.014e-05 [renormalize]: 3.80009e-07 [remove_dup_value]: 7.936e-05 [tuple_transform]: 0.00023292, [1] [Cycle 1]: 0.00022776, [4] [d_1]: 0.00018354 [none_parameter_eliminate]: 2.02999e-06 [renormalize]: 2.19996e-07 [switch_simplify]: 1.867e-05 [partial_unused_args_eliminate]: 2.11998e-06 [add_recomputation]: 0.00011973 [cse_after_recomputation]: 9.487e-05, [1] [Cycle 1]: 8.83e-05, [1] [cse]: 7.843e-05 [environ_conv]: 1.383e-05 [swap_dp_allreduce_reducescatter]: 1.597e-05 [bias_add_comm_swap]: 2.48e-06 [label_micro_interleaved_index]: 4.32e-06 [label_fine_grained_interleaved_index]: 2.68998e-06 [merge_cast_opt]: 1.35001e-06 [slice_recompute_activation]: 2.37999e-06 [micro_interleaved_order_control]: 2.32001e-06 [assign_add_opt]: 1.71002e-06 [ForceFp32Comm]: 1.21002e-06 [remove_cast_before_assign_add]: 1.04998e-06 [full_micro_interleaved_order_control]: 2.22001e-06 [reorder_send_recv_between_fp_bp]: 2.79001e-06 [comm_op_add_attrs]: 1.09e-06 [add_comm_op_reuse_tag]: 1.32e-06 [interleave_split_concat_branches]: 1.44e-06 [interleave_parallel_branches]: 1.05001e-06 [overlap_opt_shard_in_pipeline]: 3.65998e-06 [overlap_opt_shard_grad_in_pipeline]: 1.78002e-06 [control_data_broadcast_order]: 2.718e-05 [grouped_pairwise_exchange_alltoall]: 2.38998e-06 [offloading_packed_experts]: 8.2e-06 [overlap_recompute_and_grad_model_parallel]: 8.67e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.20999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.63997e-06 [overlap_recompute_comm]: 2.78e-06 [overlap_grad_ring_attention]: 7.44002e-06 [overlap_grad_flash_sp]: 4.176e-05 [begin_end_overlap_inline]: 5.29981e-07 [split_matmul_comm_elemetwise]: 2.47001e-06 [split_layernorm_comm]: 2.37001e-06 [handle_group_info]: 1.16002e-06 [symbol_engine_optimizer]: 0.00017394, [1] [Cycle 1]: 0.00015295, [6] [build]: 1.581e-05 [elim_shapecalc]: 2.454e-05 [elim_not_effective]: 3.276e-05 [opt_reshape]: 1.717e-05 [fold_const_symbol]: 2.823e-05 [renormalize]: 2.29978e-07 [detach_backward]: 2.31e-06 [pipeline_parallel_scheduler]: 1.52999e-06 [auto_monad_reorder]: 3.459e-05 [get_jit_bprop_graph]: 1.71002e-06 [rewriter_after_jit_bprop_graph]: 7.20998e-06 [opt_after_jit_grad]: 0.00063164 [validate]: 9.019e-05 Sums bootstrap : 0.000847s : 0.01% type_inference : 12.724289s : 95.28% event_method : 0.000902s : 0.01% auto_monad : 0.000369s : 0.00% graph_reusing : 0.000008s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000033s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000008s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000048s : 0.00% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000037s : 0.00% optimize.rewriter_before_opt_a : 0.000128s : 0.00% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000074s : 0.00% optimize.opt_a.loop_unroll : 0.000058s : 0.00% optimize.opt_a.a_1 : 0.002005s : 0.02% optimize.opt_a.with_stream_mark : 0.000054s : 0.00% optimize.opt_a.recompute_prepare : 0.000039s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000017s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000513s : 0.00% optimize.opt_a.accelerated_algorithm : 0.000061s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.00% optimize.opt_a.shard_inline : 0.000031s : 0.00% optimize.opt_a.merge_send_recv : 0.000034s : 0.00% optimize.opt_a.auto_parallel : 0.000030s : 0.00% optimize.opt_a.parallel : 0.000051s : 0.00% optimize.opt_a.flash_sp : 0.000016s : 0.00% optimize.opt_a.merge_comm : 0.000019s : 0.00% optimize.opt_a.allreduce_fusion : 0.000020s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000036s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000042s : 0.00% optimize.opt_a.virtual_dataset : 0.000035s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000033s : 0.00% optimize.opt_a.virtual_output : 0.000032s : 0.00% optimize.opt_a.merge_forward : 0.000020s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000037s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000067s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000058s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000020s : 0.00% optimize.opt_a.meta_fg_expand : 0.000015s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000046s : 0.00% optimize.opt_a.a_after_grad : 0.000056s : 0.00% optimize.opt_a.renormalize : 0.619036s : 4.64% optimize.opt_a.add_forward_monad_depend : 0.000023s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000065s : 0.00% optimize.opt_a.cse : 0.001093s : 0.01% optimize.opt_a.a_3 : 0.000249s : 0.00% optimize.py_interpret_to_execute_after_opt_a : 0.000030s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000438s : 0.00% optimize.convert_after_rewriter : 0.000018s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000779s : 0.01% optimize.opt_b.b_1 : 0.000423s : 0.00% optimize.opt_b.b_2 : 0.000018s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000060s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000030s : 0.00% optimize.overlap_param_gather : 0.000005s : 0.00% optimize.cconv : 0.000036s : 0.00% optimize.loop_unroll : 0.000477s : 0.00% optimize.opt_after_cconv.c_1 : 0.000084s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000050s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000079s : 0.00% optimize.tuple_transform.d_1 : 0.000184s : 0.00% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000019s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000120s : 0.00% optimize.cse_after_recomputation.cse : 0.000078s : 0.00% optimize.environ_conv : 0.000014s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000016s : 0.00% optimize.bias_add_comm_swap : 0.000002s : 0.00% optimize.label_micro_interleaved_index : 0.000004s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000004s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000027s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000042s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000016s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000025s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000033s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000017s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000028s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000035s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000632s : 0.00% validate : 0.000090s : 0.00% Time group info: ------[substitution.] 0.000670 200 6.79% : 0.000045s : 6: substitution.arithmetic_simplify 0.64% : 0.000004s : 10: substitution.elim_not_effective 2.33% : 0.000016s : 12: substitution.float_tuple_getitem_switch 0.55% : 0.000004s : 10: substitution.fold_const_symbol 2.04% : 0.000014s : 13: substitution.graph_param_transform 42.57% : 0.000285s : 7: substitution.inline 1.48% : 0.000010s : 20: substitution.j_node_and_user_rematch 3.01% : 0.000020s : 2: substitution.less_batch_normalization 2.42% : 0.000016s : 8: substitution.minmaximum_grad 2.29% : 0.000015s : 20: substitution.remove_not_recompute_node 1.02% : 0.000007s : 4: substitution.replace_old_param 7.97% : 0.000053s : 16: substitution.tuple_list_convert_item_index_to_positive 4.06% : 0.000027s : 16: substitution.tuple_list_get_item_const_eliminator 6.00% : 0.000040s : 16: substitution.tuple_list_get_item_depend_reorder 10.85% : 0.000073s : 24: substitution.tuple_list_get_item_eliminator 5.97% : 0.000040s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 12.724140 2 99.97% : 12.720109s : 1: type_inference.infer 0.03% : 0.004030s : 1: type_inference.specialize ------[replace.] 0.000066 7 100.00% : 0.000066s : 7: replace.inline ------[match.] 0.000280 7 100.00% : 0.000280s : 7: match.inline ------[predicate.] 0.000527 3321 0.92% : 0.000005s : 32: predicate.accumulaten_eliminater 0.78% : 0.000004s : 13: predicate.ad_related_special_op_eliminate 0.71% : 0.000004s : 26: predicate.addn_check_dump 0.93% : 0.000005s : 32: predicate.addn_zero_filter 0.89% : 0.000005s : 32: predicate.adjust_all_reduce_mul_add 2.38% : 0.000013s : 58: predicate.arithmetic_simplify 0.93% : 0.000005s : 32: predicate.cast_eliminate 0.80% : 0.000004s : 26: predicate.check_bprop_eliminate 0.80% : 0.000004s : 26: predicate.compare_switch_simplify 0.21% : 0.000001s : 13: predicate.const_output_eliminate 0.71% : 0.000004s : 26: predicate.depend_value_elim 0.92% : 0.000005s : 32: predicate.dict_get_item_const_eliminator 1.03% : 0.000005s : 32: predicate.dict_get_item_eliminator 0.90% : 0.000005s : 32: predicate.dict_set_item_eliminator 0.95% : 0.000005s : 26: predicate.dumpgradient_eliminate 0.21% : 0.000001s : 13: predicate.elim_not_effective 0.45% : 0.000002s : 13: predicate.elim_shapecalc_of_broadcastargs 1.20% : 0.000006s : 45: predicate.environ_add_const_eliminate 1.20% : 0.000006s : 45: predicate.environ_get_add_eliminate 1.20% : 0.000006s : 45: predicate.environ_get_depend_swap 1.94% : 0.000010s : 71: predicate.environ_get_eliminate 1.17% : 0.000006s : 45: predicate.environ_get_set_eliminate 1.04% : 0.000005s : 39: predicate.exchange_switch_depend_value 1.53% : 0.000008s : 39: predicate.float_depend_g_call 0.71% : 0.000004s : 26: predicate.float_environ_get_switch 1.21% : 0.000006s : 39: predicate.float_tuple_getitem_switch 0.20% : 0.000001s : 13: predicate.fold_const_symbol 0.82% : 0.000004s : 26: predicate.get_grad_eliminate 0.23% : 0.000001s : 13: predicate.graph_param_transform 0.68% : 0.000004s : 26: predicate.incorporate_call 0.62% : 0.000003s : 26: predicate.incorporate_call_switch 5.52% : 0.000029s : 149: predicate.inline 0.93% : 0.000005s : 26: predicate.inline_without_move 0.34% : 0.000002s : 26: predicate.j_node_and_user_rematch 0.97% : 0.000005s : 26: predicate.less_batch_normalization 1.79% : 0.000009s : 58: predicate.list_to_tuple_eliminator_ 2.41% : 0.000013s : 90: predicate.load_eliminater 0.75% : 0.000004s : 13: predicate.loop_unroll_after_grad 1.52% : 0.000008s : 55: predicate.loop_unroll_before_grad 1.81% : 0.000010s : 58: predicate.make_slice_get_slice_eliminator 0.72% : 0.000004s : 26: predicate.merge_addn 0.74% : 0.000004s : 26: predicate.micro_step_allgather_replace 0.69% : 0.000004s : 26: predicate.mini_step_allgather_replace 0.89% : 0.000005s : 32: predicate.minmaximum_grad 0.80% : 0.000004s : 13: predicate.mutable_eliminate 0.43% : 0.000002s : 13: predicate.opt_reshape 0.43% : 0.000002s : 13: predicate.parallel_virtual_node 1.52% : 0.000008s : 39: predicate.partial_defer_inline 1.28% : 0.000007s : 45: predicate.partial_eliminate 0.93% : 0.000005s : 32: predicate.print_const_string_wrapper 0.72% : 0.000004s : 26: predicate.reduce_all_const_elim 1.35% : 0.000007s : 32: predicate.reduce_eliminate 2.35% : 0.000012s : 90: predicate.redundant_stop_gradient_eliminater 0.40% : 0.000002s : 26: predicate.remove_not_recompute_node 1.13% : 0.000006s : 58: predicate.replace_applicator 0.46% : 0.000002s : 26: predicate.replace_old_param 0.22% : 0.000001s : 13: predicate.reset_defer_inline 0.90% : 0.000005s : 32: predicate.reshape_eliminate 0.74% : 0.000004s : 26: predicate.row_tensor_add_zeros_like 0.43% : 0.000002s : 13: predicate.row_tensor_eliminate 1.10% : 0.000006s : 26: predicate.same_eliminate 0.41% : 0.000002s : 26: predicate.set_cell_output_no_recompute 0.87% : 0.000005s : 26: predicate.shard_identity_eliminate 0.80% : 0.000004s : 26: predicate.special_op_eliminate 0.82% : 0.000004s : 26: predicate.specialize_transform 0.91% : 0.000005s : 26: predicate.split_environ_get_set_with_tuple_value 0.87% : 0.000005s : 26: predicate.stack_unstack_eliminate 0.38% : 0.000002s : 13: predicate.switch_call_monad_eliminater 1.15% : 0.000006s : 39: predicate.switch_defer_inline 1.91% : 0.000010s : 65: predicate.switch_layer_defer_inline 4.04% : 0.000021s : 133: predicate.switch_simplify 0.96% : 0.000005s : 32: predicate.tile_eliminate 0.87% : 0.000005s : 32: predicate.transpose_eliminate 1.83% : 0.000010s : 58: predicate.tuple_list_convert_item_index_to_positive 2.04% : 0.000011s : 58: predicate.tuple_list_get_item_const_eliminator 1.68% : 0.000009s : 58: predicate.tuple_list_get_item_depend_reorder 3.25% : 0.000017s : 84: predicate.tuple_list_get_item_eliminator 1.78% : 0.000009s : 58: predicate.tuple_list_get_set_item_eliminator 2.74% : 0.000014s : 84: predicate.tuple_list_set_item_eliminator 1.78% : 0.000009s : 58: predicate.tuple_to_list_eliminator_ 2.30% : 0.000012s : 90: predicate.updatestate_pure_node_eliminater 3.20% : 0.000017s : 116: predicate.updatestate_useless_node_eliminater 0.45% : 0.000002s : 13: predicate.value_based_eliminate 0.83% : 0.000004s : 26: predicate.virtual_dataset_eliminate 0.77% : 0.000004s : 26: predicate.virtual_output_eliminate 0.41% : 0.000002s : 13: predicate.virtual_view_grad_eliminate 0.43% : 0.000002s : 13: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.007048 38 72.47% : 0.005107s : 29: func_graph_cloner_run.FuncGraphClonerGraph 27.53% : 0.001941s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 14.955779 192 0.00% : 0.000004s : 1: ForceFp32Comm 1.16% : 0.174040s : 1: add_attr 1.16% : 0.174021s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000125s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.00% : 0.000383s : 1: auto_monad 0.00% : 0.000040s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000005s : 1: bias_add_comm_swap 0.01% : 0.000966s : 1: bootstrap 0.00% : 0.000040s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000031s : 1: control_data_broadcast_order 0.00% : 0.000022s : 1: convert_after_rewriter 0.00% : 0.000098s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000005s : 1: detach_backward 0.00% : 0.000019s : 1: environ_conv 0.01% : 0.000919s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000009s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000007s : 1: label_micro_interleaved_index 0.00% : 0.000485s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.01% : 0.000789s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000028s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000031s : 1: opt.transform.mutable_eliminate 0.02% : 0.003284s : 78: opt.transform.opt_a 0.00% : 0.000082s : 1: opt.transform.opt_after_cconv 0.00% : 0.000062s : 1: opt.transform.opt_after_jit_grad 0.00% : 0.000408s : 28: opt.transform.opt_b 0.00% : 0.000199s : 2: opt.transform.opt_trans_graph 0.00% : 0.000098s : 4: opt.transform.symbol_engine_opt 4.18% : 0.624675s : 1: opt_a 0.00% : 0.000213s : 1: opt_after_cconv 0.00% : 0.000644s : 1: opt_after_jit_grad 0.00% : 0.000581s : 1: opt_b 4.20% : 0.628594s : 1: optimize 0.00% : 0.000034s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.00% : 0.000045s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000007s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000009s : 1: overlap_param_gather 0.00% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000053s : 1: pre_auto_parallel 0.00% : 0.000040s : 1: py_interpret_to_execute 0.00% : 0.000033s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000084s : 1: remove_dup_value 0.03% : 0.003850s : 1: renormalize.infer 4.11% : 0.615169s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.00% : 0.000444s : 1: rewriter_after_opt_a 0.00% : 0.000133s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000019s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000178s : 1: symbol_engine_optimizer 0.00% : 0.000238s : 1: tuple_transform 85.08% : 12.724315s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[True-False-bfloat16--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[True-False-bfloat16--1-shape1],max_mem:106.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:42:06.834.559 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 2.36426, [21] [bootstrap]: 0.00085477 [type_inference]: 2.13949 [event_method]: 0.00101785 [auto_monad]: 0.0831385 [graph_reusing]: 1.035e-05 [inline]: 5.70001e-06 [add_attr]: 0.00472058, [1] [add_attr_with_inline]: 0.00470532, [1] [Cycle 1]: 7.65e-05, [2] [tag_attr]: 3.407e-05 [meta_addattr_fg_expand]: 6.91001e-06 [parallel-infer-symbol]: 3.55e-06 [pre_auto_parallel]: 5.405e-05 [insert-virtual-dataset]: 3.58e-06 [parallel-infer-symbol-second]: 6.69999e-07 [dataset_repeat_opt]: 2.07999e-06 [pipeline_split]: 2.73e-06 [optimize]: 0.133949, [53] [py_interpret_to_execute]: 3.809e-05 [rewriter_before_opt_a]: 0.00012186 [opt_a]: 0.0175502, [2] [Cycle 1]: 0.0158219, [45] [expand_dump_flag]: 3.61999e-06 [switch_simplify]: 5.402e-05 [loop_unroll]: 4.012e-05 [a_1]: 0.00152405 [with_stream_mark]: 3.453e-05 [recompute_prepare]: 2.364e-05 [updatestate_depend_eliminate]: 1.223e-05 [updatestate_assign_eliminate]: 8.72e-06 [updatestate_loads_eliminate]: 8.70001e-06 [parameter_eliminate]: 2.66e-06 [a_2]: 0.00028514 [accelerated_algorithm]: 4.077e-05 [shard]: 2.99001e-06 [meta_shard_fg_expand]: 4.50999e-06 [shard_inline]: 1.717e-05 [merge_send_recv]: 1.572e-05 [auto_parallel]: 1.431e-05 [parallel]: 3.302e-05 [flash_sp]: 1.128e-05 [merge_comm]: 1.056e-05 [allreduce_fusion]: 9.87001e-06 [matmul_add_comm_reduction]: 1.859e-05 [allreduce_slice_to_reducescatter]: 8.59989e-07 [virtual_shard_identity]: 2.008e-05 [virtual_dataset]: 1.861e-05 [get_grad_eliminate_]: 1.73e-05 [virtual_output]: 1.71e-05 [merge_forward]: 1.107e-05 [cell_reuse_recompute_pass]: 1.66998e-06 [offload_activation]: 2.106e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.476e-05 [merge_recompute_call_nodes]: 1.67001e-06 [before_grad]: 0.00350213 [set_forward_comm_id_for_comm_node_pass]: 2.6e-05 [meta_fg_expand]: 1.296e-05 [flash_sp_send_recv_attached]: 1.258e-05 [receive_attached]: 2.43e-06 [after_resolve]: 3.622e-05 [a_after_grad]: 3.222e-05 [renormalize]: 0.00849237 [add_forward_monad_depend]: 1.66e-05 [auto_monad_grad]: 2.59999e-06 [auto_monad_eliminator]: 3.464e-05 [cse]: 0.00079977 [a_3]: 0.00013477 [Cycle 2]: 0.00171495, [45] [expand_dump_flag]: 2.54001e-06 [switch_simplify]: 1.873e-05 [loop_unroll]: 1.598e-05 [a_1]: 0.00055181 [with_stream_mark]: 2.481e-05 [recompute_prepare]: 1.628e-05 [updatestate_depend_eliminate]: 1.094e-05 [updatestate_assign_eliminate]: 8.43999e-06 [updatestate_loads_eliminate]: 8.2e-06 [parameter_eliminate]: 2.14999e-06 [a_2]: 0.00023979 [accelerated_algorithm]: 2.077e-05 [shard]: 2.29999e-06 [meta_shard_fg_expand]: 4.10998e-06 [shard_inline]: 1.55e-05 [merge_send_recv]: 1.449e-05 [auto_parallel]: 1.618e-05 [parallel]: 8.88002e-06 [flash_sp]: 4.57e-06 [merge_comm]: 9.15001e-06 [allreduce_fusion]: 1.041e-05 [matmul_add_comm_reduction]: 1.716e-05 [allreduce_slice_to_reducescatter]: 7.89994e-07 [virtual_shard_identity]: 1.925e-05 [virtual_dataset]: 1.577e-05 [get_grad_eliminate_]: 3.251e-05 [virtual_output]: 1.705e-05 [merge_forward]: 8.70001e-06 [cell_reuse_recompute_pass]: 2.58e-06 [offload_activation]: 1.923e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.046e-05 [merge_recompute_call_nodes]: 1.63002e-06 [before_grad]: 2.594e-05 [set_forward_comm_id_for_comm_node_pass]: 1.062e-05 [meta_fg_expand]: 7.78999e-06 [flash_sp_send_recv_attached]: 1.70001e-06 [receive_attached]: 2.37999e-06 [after_resolve]: 1.985e-05 [a_after_grad]: 2.496e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 1.68002e-06 [auto_monad_grad]: 1.10999e-06 [auto_monad_eliminator]: 2.013e-05 [cse]: 8.909e-05 [a_3]: 0.00010331 [py_interpret_to_execute_after_opt_a]: 2.162e-05 [slice_cell_reuse_recomputed_activation]: 2.19001e-06 [rewriter_after_opt_a]: 0.00041529 [convert_after_rewriter]: 1.511e-05 [order_py_execute_after_rewriter]: 1.16e-05 [mutable_eliminate]: 0.113036 [opt_b]: 0.00068741, [1] [Cycle 1]: 0.00067713, [7] [b_1]: 0.00047278 [b_2]: 1.886e-05 [updatestate_depend_eliminate]: 2.268e-05 [updatestate_assign_eliminate]: 8.60999e-06 [updatestate_loads_eliminate]: 8.13999e-06 [renormalize]: 1.55001e-06 [cse]: 9.547e-05 [optimize_parallel_all_gather_comm]: 3.8e-05 [overlap_param_gather]: 2.02001e-06 [cconv]: 4.535e-05 [loop_unroll]: 0.00055235 [opt_after_cconv]: 0.00022265, [1] [Cycle 1]: 0.00021462, [7] [c_1]: 8.358e-05 [parameter_eliminate]: 6.40002e-06 [updatestate_depend_eliminate]: 1.501e-05 [updatestate_assign_eliminate]: 7.93999e-06 [updatestate_loads_eliminate]: 7.05e-06 [cse]: 5.697e-05 [renormalize]: 4.19997e-07 [remove_dup_value]: 8.815e-05 [tuple_transform]: 0.00024323, [1] [Cycle 1]: 0.00023789, [4] [d_1]: 0.00017662 [none_parameter_eliminate]: 2.47001e-06 [renormalize]: 1.8999e-07 [switch_simplify]: 1.83e-05 [partial_unused_args_eliminate]: 2.02001e-06 [add_recomputation]: 0.00017102 [cse_after_recomputation]: 7.135e-05, [1] [Cycle 1]: 6.482e-05, [1] [cse]: 5.788e-05 [environ_conv]: 1.734e-05 [swap_dp_allreduce_reducescatter]: 1.361e-05 [bias_add_comm_swap]: 3.44001e-06 [label_micro_interleaved_index]: 5.36998e-06 [label_fine_grained_interleaved_index]: 2.89999e-06 [merge_cast_opt]: 1.50001e-06 [slice_recompute_activation]: 2.31998e-06 [micro_interleaved_order_control]: 3.41001e-06 [assign_add_opt]: 1.45999e-06 [ForceFp32Comm]: 8.79983e-07 [remove_cast_before_assign_add]: 1.34998e-06 [full_micro_interleaved_order_control]: 2.54999e-06 [reorder_send_recv_between_fp_bp]: 2.96999e-06 [comm_op_add_attrs]: 1.02998e-06 [add_comm_op_reuse_tag]: 1.40999e-06 [interleave_split_concat_branches]: 1.20999e-06 [interleave_parallel_branches]: 1.01002e-06 [overlap_opt_shard_in_pipeline]: 1.20001e-06 [overlap_opt_shard_grad_in_pipeline]: 2.26e-06 [control_data_broadcast_order]: 2.981e-05 [grouped_pairwise_exchange_alltoall]: 1.98002e-06 [offloading_packed_experts]: 8.99e-06 [overlap_recompute_and_grad_model_parallel]: 8.25999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.20001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.59e-06 [overlap_recompute_comm]: 2.43e-06 [overlap_grad_ring_attention]: 7.05e-06 [overlap_grad_flash_sp]: 4.421e-05 [begin_end_overlap_inline]: 6.39993e-07 [split_matmul_comm_elemetwise]: 2.35002e-06 [split_layernorm_comm]: 1.92001e-06 [handle_group_info]: 9.70002e-07 [symbol_engine_optimizer]: 0.00015949, [1] [Cycle 1]: 0.00015415, [6] [build]: 1.812e-05 [elim_shapecalc]: 2.399e-05 [elim_not_effective]: 3.271e-05 [opt_reshape]: 1.684e-05 [fold_const_symbol]: 2.844e-05 [renormalize]: 2.80008e-07 [detach_backward]: 2.57001e-06 [pipeline_parallel_scheduler]: 1.40999e-06 [auto_monad_reorder]: 3.684e-05 [get_jit_bprop_graph]: 2.18998e-06 [rewriter_after_jit_bprop_graph]: 8.02e-06 [opt_after_jit_grad]: 0.00057281 [validate]: 9.369e-05 Sums bootstrap : 0.000855s : 0.04% type_inference : 2.139488s : 90.73% event_method : 0.001018s : 0.04% auto_monad : 0.083138s : 3.53% graph_reusing : 0.000010s : 0.00% inline : 0.000006s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000034s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000054s : 0.00% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000038s : 0.00% optimize.rewriter_before_opt_a : 0.000122s : 0.01% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000073s : 0.00% optimize.opt_a.loop_unroll : 0.000056s : 0.00% optimize.opt_a.a_1 : 0.002076s : 0.09% optimize.opt_a.with_stream_mark : 0.000059s : 0.00% optimize.opt_a.recompute_prepare : 0.000040s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000023s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000017s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000525s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000062s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.00% optimize.opt_a.shard_inline : 0.000033s : 0.00% optimize.opt_a.merge_send_recv : 0.000030s : 0.00% optimize.opt_a.auto_parallel : 0.000030s : 0.00% optimize.opt_a.parallel : 0.000042s : 0.00% optimize.opt_a.flash_sp : 0.000016s : 0.00% optimize.opt_a.merge_comm : 0.000020s : 0.00% optimize.opt_a.allreduce_fusion : 0.000020s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000036s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000039s : 0.00% optimize.opt_a.virtual_dataset : 0.000034s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000050s : 0.00% optimize.opt_a.virtual_output : 0.000034s : 0.00% optimize.opt_a.merge_forward : 0.000020s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000040s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000075s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.003528s : 0.15% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000037s : 0.00% optimize.opt_a.meta_fg_expand : 0.000021s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000014s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000056s : 0.00% optimize.opt_a.a_after_grad : 0.000057s : 0.00% optimize.opt_a.renormalize : 0.008492s : 0.36% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.00% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000055s : 0.00% optimize.opt_a.cse : 0.000889s : 0.04% optimize.opt_a.a_3 : 0.000238s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000022s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000415s : 0.02% optimize.convert_after_rewriter : 0.000015s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.113036s : 4.79% optimize.opt_b.b_1 : 0.000473s : 0.02% optimize.opt_b.b_2 : 0.000019s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000023s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_b.renormalize : 0.000002s : 0.00% optimize.opt_b.cse : 0.000095s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000038s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000045s : 0.00% optimize.loop_unroll : 0.000552s : 0.02% optimize.opt_after_cconv.c_1 : 0.000084s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000057s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000088s : 0.00% optimize.tuple_transform.d_1 : 0.000177s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000018s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000171s : 0.01% optimize.cse_after_recomputation.cse : 0.000058s : 0.00% optimize.environ_conv : 0.000017s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000014s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000030s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000009s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000044s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000018s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000024s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000033s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000017s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000028s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000037s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000573s : 0.02% validate : 0.000094s : 0.00% Time group info: ------[substitution.] 0.000691 200 6.92% : 0.000048s : 6: substitution.arithmetic_simplify 0.62% : 0.000004s : 10: substitution.elim_not_effective 3.24% : 0.000022s : 12: substitution.float_tuple_getitem_switch 0.56% : 0.000004s : 10: substitution.fold_const_symbol 1.82% : 0.000013s : 13: substitution.graph_param_transform 40.65% : 0.000281s : 7: substitution.inline 3.33% : 0.000023s : 20: substitution.j_node_and_user_rematch 2.89% : 0.000020s : 2: substitution.less_batch_normalization 2.39% : 0.000017s : 8: substitution.minmaximum_grad 2.12% : 0.000015s : 20: substitution.remove_not_recompute_node 0.96% : 0.000007s : 4: substitution.replace_old_param 7.81% : 0.000054s : 16: substitution.tuple_list_convert_item_index_to_positive 4.51% : 0.000031s : 16: substitution.tuple_list_get_item_const_eliminator 5.30% : 0.000037s : 16: substitution.tuple_list_get_item_depend_reorder 11.78% : 0.000081s : 24: substitution.tuple_list_get_item_eliminator 5.09% : 0.000035s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.139396 2 99.80% : 2.135110s : 1: type_inference.infer 0.20% : 0.004286s : 1: type_inference.specialize ------[replace.] 0.000069 7 100.00% : 0.000069s : 7: replace.inline ------[match.] 0.000276 7 100.00% : 0.000276s : 7: match.inline ------[predicate.] 0.000572 3321 1.01% : 0.000006s : 32: predicate.accumulaten_eliminater 0.74% : 0.000004s : 13: predicate.ad_related_special_op_eliminate 0.64% : 0.000004s : 26: predicate.addn_check_dump 0.80% : 0.000005s : 32: predicate.addn_zero_filter 0.72% : 0.000004s : 32: predicate.adjust_all_reduce_mul_add 2.12% : 0.000012s : 58: predicate.arithmetic_simplify 0.89% : 0.000005s : 32: predicate.cast_eliminate 0.68% : 0.000004s : 26: predicate.check_bprop_eliminate 0.65% : 0.000004s : 26: predicate.compare_switch_simplify 0.18% : 0.000001s : 13: predicate.const_output_eliminate 0.66% : 0.000004s : 26: predicate.depend_value_elim 0.87% : 0.000005s : 32: predicate.dict_get_item_const_eliminator 0.93% : 0.000005s : 32: predicate.dict_get_item_eliminator 0.85% : 0.000005s : 32: predicate.dict_set_item_eliminator 1.53% : 0.000009s : 26: predicate.dumpgradient_eliminate 0.20% : 0.000001s : 13: predicate.elim_not_effective 0.47% : 0.000003s : 13: predicate.elim_shapecalc_of_broadcastargs 1.13% : 0.000006s : 45: predicate.environ_add_const_eliminate 1.09% : 0.000006s : 45: predicate.environ_get_add_eliminate 1.07% : 0.000006s : 45: predicate.environ_get_depend_swap 1.85% : 0.000011s : 71: predicate.environ_get_eliminate 1.05% : 0.000006s : 45: predicate.environ_get_set_eliminate 0.93% : 0.000005s : 39: predicate.exchange_switch_depend_value 1.52% : 0.000009s : 39: predicate.float_depend_g_call 0.66% : 0.000004s : 26: predicate.float_environ_get_switch 1.20% : 0.000007s : 39: predicate.float_tuple_getitem_switch 0.17% : 0.000001s : 13: predicate.fold_const_symbol 0.78% : 0.000004s : 26: predicate.get_grad_eliminate 0.25% : 0.000001s : 13: predicate.graph_param_transform 0.71% : 0.000004s : 26: predicate.incorporate_call 0.57% : 0.000003s : 26: predicate.incorporate_call_switch 5.21% : 0.000030s : 149: predicate.inline 0.91% : 0.000005s : 26: predicate.inline_without_move 0.39% : 0.000002s : 26: predicate.j_node_and_user_rematch 0.88% : 0.000005s : 26: predicate.less_batch_normalization 1.71% : 0.000010s : 58: predicate.list_to_tuple_eliminator_ 2.16% : 0.000012s : 90: predicate.load_eliminater 0.86% : 0.000005s : 13: predicate.loop_unroll_after_grad 1.41% : 0.000008s : 55: predicate.loop_unroll_before_grad 1.58% : 0.000009s : 58: predicate.make_slice_get_slice_eliminator 0.71% : 0.000004s : 26: predicate.merge_addn 0.64% : 0.000004s : 26: predicate.micro_step_allgather_replace 0.65% : 0.000004s : 26: predicate.mini_step_allgather_replace 0.84% : 0.000005s : 32: predicate.minmaximum_grad 2.08% : 0.000012s : 13: predicate.mutable_eliminate 0.38% : 0.000002s : 13: predicate.opt_reshape 0.39% : 0.000002s : 13: predicate.parallel_virtual_node 1.52% : 0.000009s : 39: predicate.partial_defer_inline 1.17% : 0.000007s : 45: predicate.partial_eliminate 0.80% : 0.000005s : 32: predicate.print_const_string_wrapper 0.65% : 0.000004s : 26: predicate.reduce_all_const_elim 1.14% : 0.000007s : 32: predicate.reduce_eliminate 2.10% : 0.000012s : 90: predicate.redundant_stop_gradient_eliminater 0.43% : 0.000002s : 26: predicate.remove_not_recompute_node 1.02% : 0.000006s : 58: predicate.replace_applicator 0.43% : 0.000002s : 26: predicate.replace_old_param 0.29% : 0.000002s : 13: predicate.reset_defer_inline 0.92% : 0.000005s : 32: predicate.reshape_eliminate 0.68% : 0.000004s : 26: predicate.row_tensor_add_zeros_like 0.49% : 0.000003s : 13: predicate.row_tensor_eliminate 0.96% : 0.000005s : 26: predicate.same_eliminate 0.39% : 0.000002s : 26: predicate.set_cell_output_no_recompute 0.85% : 0.000005s : 26: predicate.shard_identity_eliminate 0.73% : 0.000004s : 26: predicate.special_op_eliminate 0.75% : 0.000004s : 26: predicate.specialize_transform 0.87% : 0.000005s : 26: predicate.split_environ_get_set_with_tuple_value 0.85% : 0.000005s : 26: predicate.stack_unstack_eliminate 0.36% : 0.000002s : 13: predicate.switch_call_monad_eliminater 1.07% : 0.000006s : 39: predicate.switch_defer_inline 1.69% : 0.000010s : 65: predicate.switch_layer_defer_inline 8.78% : 0.000050s : 133: predicate.switch_simplify 0.77% : 0.000004s : 32: predicate.tile_eliminate 0.83% : 0.000005s : 32: predicate.transpose_eliminate 1.74% : 0.000010s : 58: predicate.tuple_list_convert_item_index_to_positive 1.76% : 0.000010s : 58: predicate.tuple_list_get_item_const_eliminator 1.63% : 0.000009s : 58: predicate.tuple_list_get_item_depend_reorder 3.17% : 0.000018s : 84: predicate.tuple_list_get_item_eliminator 1.57% : 0.000009s : 58: predicate.tuple_list_get_set_item_eliminator 2.35% : 0.000013s : 84: predicate.tuple_list_set_item_eliminator 1.64% : 0.000009s : 58: predicate.tuple_to_list_eliminator_ 2.12% : 0.000012s : 90: predicate.updatestate_pure_node_eliminater 3.04% : 0.000017s : 116: predicate.updatestate_useless_node_eliminater 0.39% : 0.000002s : 13: predicate.value_based_eliminate 0.78% : 0.000004s : 26: predicate.virtual_dataset_eliminate 0.79% : 0.000005s : 26: predicate.virtual_output_eliminate 0.35% : 0.000002s : 13: predicate.virtual_view_grad_eliminate 0.44% : 0.000003s : 13: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.008025 38 73.85% : 0.005926s : 29: func_graph_cloner_run.FuncGraphClonerGraph 26.15% : 0.002098s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.519028 192 0.00% : 0.000003s : 1: ForceFp32Comm 0.19% : 0.004727s : 1: add_attr 0.19% : 0.004710s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000177s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 3.30% : 0.083187s : 1: auto_monad 0.00% : 0.000042s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.04% : 0.000943s : 1: bootstrap 0.00% : 0.000049s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000033s : 1: control_data_broadcast_order 0.00% : 0.000019s : 1: convert_after_rewriter 0.00% : 0.000075s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000022s : 1: environ_conv 0.04% : 0.001037s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000019s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000010s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000003s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.02% : 0.000561s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 4.49% : 0.113056s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.00% : 0.000029s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000061s : 1: opt.transform.mutable_eliminate 0.27% : 0.006861s : 78: opt.transform.opt_a 0.00% : 0.000082s : 1: opt.transform.opt_after_cconv 0.00% : 0.000061s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000451s : 28: opt.transform.opt_b 0.01% : 0.000192s : 2: opt.transform.opt_trans_graph 0.00% : 0.000097s : 4: opt.transform.symbol_engine_opt 0.70% : 0.017554s : 1: opt_a 0.01% : 0.000227s : 1: opt_after_cconv 0.02% : 0.000582s : 1: opt_after_jit_grad 0.03% : 0.000693s : 1: opt_b 5.32% : 0.133956s : 1: optimize 0.00% : 0.000042s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.00% : 0.000048s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000059s : 1: pre_auto_parallel 0.00% : 0.000042s : 1: py_interpret_to_execute 0.00% : 0.000025s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000093s : 1: remove_dup_value 0.24% : 0.005982s : 1: renormalize.infer 0.10% : 0.002494s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000421s : 1: rewriter_after_opt_a 0.01% : 0.000126s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000017s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000163s : 1: symbol_engine_optimizer 0.01% : 0.000247s : 1: tuple_transform 84.93% : 2.139511s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[True-False-bfloat16--1-shape2] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[True-False-bfloat16--1-shape2],max_mem:106.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:42:12.599.497 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 3.64978, [21] [bootstrap]: 0.113169 [type_inference]: 2.87655 [event_method]: 0.00164419 [auto_monad]: 0.00012185 [graph_reusing]: 7.44002e-06 [inline]: 8.90001e-06 [add_attr]: 0.298594, [1] [add_attr_with_inline]: 0.298573, [1] [Cycle 1]: 0.00010883, [2] [tag_attr]: 3.812e-05 [meta_addattr_fg_expand]: 1.525e-05 [parallel-infer-symbol]: 3.70998e-06 [pre_auto_parallel]: 6.241e-05 [insert-virtual-dataset]: 3.81001e-06 [parallel-infer-symbol-second]: 8.00006e-07 [dataset_repeat_opt]: 3.11999e-06 [pipeline_split]: 3.38999e-06 [optimize]: 0.358606, [53] [py_interpret_to_execute]: 4.727e-05 [rewriter_before_opt_a]: 0.00013794 [opt_a]: 0.0126358, [2] [Cycle 1]: 0.0108858, [45] [expand_dump_flag]: 3.63e-06 [switch_simplify]: 5.628e-05 [loop_unroll]: 4.016e-05 [a_1]: 0.00159778 [with_stream_mark]: 3.23e-05 [recompute_prepare]: 2.412e-05 [updatestate_depend_eliminate]: 1.146e-05 [updatestate_assign_eliminate]: 9.05999e-06 [updatestate_loads_eliminate]: 8.55001e-06 [parameter_eliminate]: 2.08002e-06 [a_2]: 0.00030208 [accelerated_algorithm]: 4.595e-05 [shard]: 3.30998e-06 [meta_shard_fg_expand]: 4.84e-06 [shard_inline]: 1.612e-05 [merge_send_recv]: 1.643e-05 [auto_parallel]: 1.443e-05 [parallel]: 4.185e-05 [flash_sp]: 1.208e-05 [merge_comm]: 1.111e-05 [allreduce_fusion]: 9.94999e-06 [matmul_add_comm_reduction]: 1.865e-05 [allreduce_slice_to_reducescatter]: 9.39996e-07 [virtual_shard_identity]: 2.058e-05 [virtual_dataset]: 1.885e-05 [get_grad_eliminate_]: 1.966e-05 [virtual_output]: 2.024e-05 [merge_forward]: 1.161e-05 [cell_reuse_recompute_pass]: 2.16e-06 [offload_activation]: 2.015e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.309e-05 [merge_recompute_call_nodes]: 1.82999e-06 [before_grad]: 3.071e-05 [set_forward_comm_id_for_comm_node_pass]: 1.125e-05 [meta_fg_expand]: 8.74003e-06 [flash_sp_send_recv_attached]: 5.40001e-06 [receive_attached]: 3.20002e-06 [after_resolve]: 2.409e-05 [a_after_grad]: 2.953e-05 [renormalize]: 0.00724131 [add_forward_monad_depend]: 1.882e-05 [auto_monad_grad]: 3.22002e-06 [auto_monad_eliminator]: 3.737e-05 [cse]: 0.00055591 [a_3]: 0.0001398 [Cycle 2]: 0.00173444, [45] [expand_dump_flag]: 3.31001e-06 [switch_simplify]: 1.944e-05 [loop_unroll]: 1.672e-05 [a_1]: 0.00056587 [with_stream_mark]: 2.897e-05 [recompute_prepare]: 1.787e-05 [updatestate_depend_eliminate]: 1.093e-05 [updatestate_assign_eliminate]: 8.08001e-06 [updatestate_loads_eliminate]: 8.68001e-06 [parameter_eliminate]: 2.04e-06 [a_2]: 0.00024711 [accelerated_algorithm]: 2.297e-05 [shard]: 2.36e-06 [meta_shard_fg_expand]: 5.44998e-06 [shard_inline]: 1.586e-05 [merge_send_recv]: 1.549e-05 [auto_parallel]: 1.701e-05 [parallel]: 9.79999e-06 [flash_sp]: 4.23001e-06 [merge_comm]: 9.62999e-06 [allreduce_fusion]: 1.101e-05 [matmul_add_comm_reduction]: 1.827e-05 [allreduce_slice_to_reducescatter]: 8.89995e-07 [virtual_shard_identity]: 1.763e-05 [virtual_dataset]: 1.646e-05 [get_grad_eliminate_]: 1.539e-05 [virtual_output]: 1.523e-05 [merge_forward]: 1.007e-05 [cell_reuse_recompute_pass]: 2.86e-06 [offload_activation]: 1.979e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.228e-05 [merge_recompute_call_nodes]: 1.44998e-06 [before_grad]: 2.661e-05 [set_forward_comm_id_for_comm_node_pass]: 1.005e-05 [meta_fg_expand]: 8.57e-06 [flash_sp_send_recv_attached]: 1.79998e-06 [receive_attached]: 2.48002e-06 [after_resolve]: 2.031e-05 [a_after_grad]: 2.652e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 2.46e-06 [auto_monad_grad]: 2.40002e-06 [auto_monad_eliminator]: 4.41e-05 [cse]: 5.847e-05 [a_3]: 0.00010491 [py_interpret_to_execute_after_opt_a]: 2.932e-05 [slice_cell_reuse_recomputed_activation]: 2.81999e-06 [rewriter_after_opt_a]: 0.00043252 [convert_after_rewriter]: 1.85e-05 [order_py_execute_after_rewriter]: 1.207e-05 [mutable_eliminate]: 0.00090326 [opt_b]: 0.342185, [1] [Cycle 1]: 0.342173, [7] [b_1]: 0.00042194 [b_2]: 0.341493 [updatestate_depend_eliminate]: 3.845e-05 [updatestate_assign_eliminate]: 1.023e-05 [updatestate_loads_eliminate]: 8.99998e-06 [renormalize]: 1.25999e-06 [cse]: 0.00010018 [optimize_parallel_all_gather_comm]: 4.008e-05 [overlap_param_gather]: 6.88e-06 [cconv]: 4.731e-05 [loop_unroll]: 0.00078391 [opt_after_cconv]: 0.00022309, [1] [Cycle 1]: 0.00021287, [7] [c_1]: 8.807e-05 [parameter_eliminate]: 6.69999e-06 [updatestate_depend_eliminate]: 1.349e-05 [updatestate_assign_eliminate]: 7.60998e-06 [updatestate_loads_eliminate]: 7.03e-06 [cse]: 5.339e-05 [renormalize]: 4.80009e-07 [remove_dup_value]: 8.607e-05 [tuple_transform]: 0.00023675, [1] [Cycle 1]: 0.00023122, [4] [d_1]: 0.00019013 [none_parameter_eliminate]: 2.19001e-06 [renormalize]: 1.69995e-07 [switch_simplify]: 1.701e-05 [partial_unused_args_eliminate]: 1.83002e-06 [add_recomputation]: 0.00011911 [cse_after_recomputation]: 5.144e-05, [1] [Cycle 1]: 4.56e-05, [1] [cse]: 3.899e-05 [environ_conv]: 2.806e-05 [swap_dp_allreduce_reducescatter]: 1.347e-05 [bias_add_comm_swap]: 3.46999e-06 [label_micro_interleaved_index]: 5.64e-06 [label_fine_grained_interleaved_index]: 2.97002e-06 [merge_cast_opt]: 1.45999e-06 [slice_recompute_activation]: 2.06998e-06 [micro_interleaved_order_control]: 2.61e-06 [assign_add_opt]: 1.20999e-06 [ForceFp32Comm]: 1.13001e-06 [remove_cast_before_assign_add]: 1.44e-06 [full_micro_interleaved_order_control]: 2.35002e-06 [reorder_send_recv_between_fp_bp]: 3.14999e-06 [comm_op_add_attrs]: 1.05001e-06 [add_comm_op_reuse_tag]: 1.32e-06 [interleave_split_concat_branches]: 1.42999e-06 [interleave_parallel_branches]: 1.02e-06 [overlap_opt_shard_in_pipeline]: 3.31999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.02001e-06 [control_data_broadcast_order]: 2.855e-05 [grouped_pairwise_exchange_alltoall]: 1.65001e-06 [offloading_packed_experts]: 8.45999e-06 [overlap_recompute_and_grad_model_parallel]: 8.47998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.20001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.36002e-06 [overlap_recompute_comm]: 2.30002e-06 [overlap_grad_ring_attention]: 7.17997e-06 [overlap_grad_flash_sp]: 4.183e-05 [begin_end_overlap_inline]: 5.39992e-07 [split_matmul_comm_elemetwise]: 2.04e-06 [split_layernorm_comm]: 2.04e-06 [handle_group_info]: 9.89996e-07 [symbol_engine_optimizer]: 0.00015184, [1] [Cycle 1]: 0.00014727, [6] [build]: 1.618e-05 [elim_shapecalc]: 2.322e-05 [elim_not_effective]: 3.088e-05 [opt_reshape]: 1.652e-05 [fold_const_symbol]: 2.731e-05 [renormalize]: 2.10013e-07 [detach_backward]: 2.21998e-06 [pipeline_parallel_scheduler]: 2.19001e-06 [auto_monad_reorder]: 3.572e-05 [get_jit_bprop_graph]: 2.43998e-06 [rewriter_after_jit_bprop_graph]: 7.84997e-06 [opt_after_jit_grad]: 0.00055579 [validate]: 8.98e-05 Sums bootstrap : 0.113169s : 3.38% type_inference : 2.876550s : 85.87% event_method : 0.001644s : 0.05% auto_monad : 0.000122s : 0.00% graph_reusing : 0.000007s : 0.00% inline : 0.000009s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000038s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000015s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000062s : 0.00% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000047s : 0.00% optimize.rewriter_before_opt_a : 0.000138s : 0.00% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000076s : 0.00% optimize.opt_a.loop_unroll : 0.000057s : 0.00% optimize.opt_a.a_1 : 0.002164s : 0.06% optimize.opt_a.with_stream_mark : 0.000061s : 0.00% optimize.opt_a.recompute_prepare : 0.000042s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000022s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000017s : 0.00% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000549s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000069s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000010s : 0.00% optimize.opt_a.shard_inline : 0.000032s : 0.00% optimize.opt_a.merge_send_recv : 0.000032s : 0.00% optimize.opt_a.auto_parallel : 0.000031s : 0.00% optimize.opt_a.parallel : 0.000052s : 0.00% optimize.opt_a.flash_sp : 0.000016s : 0.00% optimize.opt_a.merge_comm : 0.000021s : 0.00% optimize.opt_a.allreduce_fusion : 0.000021s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000037s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000038s : 0.00% optimize.opt_a.virtual_dataset : 0.000035s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000035s : 0.00% optimize.opt_a.virtual_output : 0.000035s : 0.00% optimize.opt_a.merge_forward : 0.000022s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000040s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000075s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000057s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000021s : 0.00% optimize.opt_a.meta_fg_expand : 0.000017s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000044s : 0.00% optimize.opt_a.a_after_grad : 0.000056s : 0.00% optimize.opt_a.renormalize : 0.007241s : 0.22% optimize.opt_a.add_forward_monad_depend : 0.000021s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000081s : 0.00% optimize.opt_a.cse : 0.000614s : 0.02% optimize.opt_a.a_3 : 0.000245s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000029s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000433s : 0.01% optimize.convert_after_rewriter : 0.000018s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000903s : 0.03% optimize.opt_b.b_1 : 0.000422s : 0.01% optimize.opt_b.b_2 : 0.341493s : 10.19% optimize.opt_b.updatestate_depend_eliminate : 0.000038s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000009s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000100s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000040s : 0.00% optimize.overlap_param_gather : 0.000007s : 0.00% optimize.cconv : 0.000047s : 0.00% optimize.loop_unroll : 0.000784s : 0.02% optimize.opt_after_cconv.c_1 : 0.000088s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000053s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000086s : 0.00% optimize.tuple_transform.d_1 : 0.000190s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000017s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000119s : 0.00% optimize.cse_after_recomputation.cse : 0.000039s : 0.00% optimize.environ_conv : 0.000028s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000013s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000029s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000042s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000016s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000023s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000031s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000017s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000027s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000036s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000556s : 0.02% validate : 0.000090s : 0.00% Time group info: ------[substitution.] 0.000705 200 6.85% : 0.000048s : 6: substitution.arithmetic_simplify 0.62% : 0.000004s : 10: substitution.elim_not_effective 2.31% : 0.000016s : 12: substitution.float_tuple_getitem_switch 0.52% : 0.000004s : 10: substitution.fold_const_symbol 1.77% : 0.000012s : 13: substitution.graph_param_transform 43.08% : 0.000304s : 7: substitution.inline 1.40% : 0.000010s : 20: substitution.j_node_and_user_rematch 3.31% : 0.000023s : 2: substitution.less_batch_normalization 2.37% : 0.000017s : 8: substitution.minmaximum_grad 2.14% : 0.000015s : 20: substitution.remove_not_recompute_node 0.80% : 0.000006s : 4: substitution.replace_old_param 7.83% : 0.000055s : 16: substitution.tuple_list_convert_item_index_to_positive 3.95% : 0.000028s : 16: substitution.tuple_list_get_item_const_eliminator 5.06% : 0.000036s : 16: substitution.tuple_list_get_item_depend_reorder 12.73% : 0.000090s : 24: substitution.tuple_list_get_item_eliminator 5.26% : 0.000037s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.876435 2 99.84% : 2.871924s : 1: type_inference.infer 0.16% : 0.004511s : 1: type_inference.specialize ------[replace.] 0.000072 7 100.00% : 0.000072s : 7: replace.inline ------[match.] 0.000299 7 100.00% : 0.000299s : 7: match.inline ------[predicate.] 0.000561 3321 0.89% : 0.000005s : 32: predicate.accumulaten_eliminater 0.83% : 0.000005s : 13: predicate.ad_related_special_op_eliminate 2.67% : 0.000015s : 26: predicate.addn_check_dump 0.92% : 0.000005s : 32: predicate.addn_zero_filter 0.75% : 0.000004s : 32: predicate.adjust_all_reduce_mul_add 2.32% : 0.000013s : 58: predicate.arithmetic_simplify 0.98% : 0.000005s : 32: predicate.cast_eliminate 0.69% : 0.000004s : 26: predicate.check_bprop_eliminate 0.71% : 0.000004s : 26: predicate.compare_switch_simplify 0.20% : 0.000001s : 13: predicate.const_output_eliminate 0.64% : 0.000004s : 26: predicate.depend_value_elim 0.96% : 0.000005s : 32: predicate.dict_get_item_const_eliminator 1.02% : 0.000006s : 32: predicate.dict_get_item_eliminator 0.82% : 0.000005s : 32: predicate.dict_set_item_eliminator 0.91% : 0.000005s : 26: predicate.dumpgradient_eliminate 0.18% : 0.000001s : 13: predicate.elim_not_effective 0.41% : 0.000002s : 13: predicate.elim_shapecalc_of_broadcastargs 1.13% : 0.000006s : 45: predicate.environ_add_const_eliminate 1.20% : 0.000007s : 45: predicate.environ_get_add_eliminate 1.21% : 0.000007s : 45: predicate.environ_get_depend_swap 1.81% : 0.000010s : 71: predicate.environ_get_eliminate 1.20% : 0.000007s : 45: predicate.environ_get_set_eliminate 1.06% : 0.000006s : 39: predicate.exchange_switch_depend_value 1.63% : 0.000009s : 39: predicate.float_depend_g_call 0.68% : 0.000004s : 26: predicate.float_environ_get_switch 1.32% : 0.000007s : 39: predicate.float_tuple_getitem_switch 0.17% : 0.000001s : 13: predicate.fold_const_symbol 0.82% : 0.000005s : 26: predicate.get_grad_eliminate 0.26% : 0.000001s : 13: predicate.graph_param_transform 0.67% : 0.000004s : 26: predicate.incorporate_call 0.60% : 0.000003s : 26: predicate.incorporate_call_switch 5.53% : 0.000031s : 149: predicate.inline 0.91% : 0.000005s : 26: predicate.inline_without_move 0.32% : 0.000002s : 26: predicate.j_node_and_user_rematch 0.96% : 0.000005s : 26: predicate.less_batch_normalization 1.60% : 0.000009s : 58: predicate.list_to_tuple_eliminator_ 2.20% : 0.000012s : 90: predicate.load_eliminater 0.87% : 0.000005s : 13: predicate.loop_unroll_after_grad 1.46% : 0.000008s : 55: predicate.loop_unroll_before_grad 1.66% : 0.000009s : 58: predicate.make_slice_get_slice_eliminator 0.68% : 0.000004s : 26: predicate.merge_addn 0.68% : 0.000004s : 26: predicate.micro_step_allgather_replace 0.70% : 0.000004s : 26: predicate.mini_step_allgather_replace 0.84% : 0.000005s : 32: predicate.minmaximum_grad 1.09% : 0.000006s : 13: predicate.mutable_eliminate 0.39% : 0.000002s : 13: predicate.opt_reshape 0.39% : 0.000002s : 13: predicate.parallel_virtual_node 1.60% : 0.000009s : 39: predicate.partial_defer_inline 1.20% : 0.000007s : 45: predicate.partial_eliminate 0.85% : 0.000005s : 32: predicate.print_const_string_wrapper 0.71% : 0.000004s : 26: predicate.reduce_all_const_elim 1.27% : 0.000007s : 32: predicate.reduce_eliminate 2.25% : 0.000013s : 90: predicate.redundant_stop_gradient_eliminater 0.44% : 0.000002s : 26: predicate.remove_not_recompute_node 1.07% : 0.000006s : 58: predicate.replace_applicator 0.42% : 0.000002s : 26: predicate.replace_old_param 0.25% : 0.000001s : 13: predicate.reset_defer_inline 0.97% : 0.000005s : 32: predicate.reshape_eliminate 0.70% : 0.000004s : 26: predicate.row_tensor_add_zeros_like 0.78% : 0.000004s : 13: predicate.row_tensor_eliminate 0.97% : 0.000005s : 26: predicate.same_eliminate 0.39% : 0.000002s : 26: predicate.set_cell_output_no_recompute 0.83% : 0.000005s : 26: predicate.shard_identity_eliminate 0.75% : 0.000004s : 26: predicate.special_op_eliminate 0.77% : 0.000004s : 26: predicate.specialize_transform 0.98% : 0.000005s : 26: predicate.split_environ_get_set_with_tuple_value 0.83% : 0.000005s : 26: predicate.stack_unstack_eliminate 0.39% : 0.000002s : 13: predicate.switch_call_monad_eliminater 1.21% : 0.000007s : 39: predicate.switch_defer_inline 1.85% : 0.000010s : 65: predicate.switch_layer_defer_inline 3.87% : 0.000022s : 133: predicate.switch_simplify 0.87% : 0.000005s : 32: predicate.tile_eliminate 0.91% : 0.000005s : 32: predicate.transpose_eliminate 1.77% : 0.000010s : 58: predicate.tuple_list_convert_item_index_to_positive 1.89% : 0.000011s : 58: predicate.tuple_list_get_item_const_eliminator 1.66% : 0.000009s : 58: predicate.tuple_list_get_item_depend_reorder 3.46% : 0.000019s : 84: predicate.tuple_list_get_item_eliminator 1.72% : 0.000010s : 58: predicate.tuple_list_get_set_item_eliminator 2.50% : 0.000014s : 84: predicate.tuple_list_set_item_eliminator 1.55% : 0.000009s : 58: predicate.tuple_to_list_eliminator_ 2.30% : 0.000013s : 90: predicate.updatestate_pure_node_eliminater 3.23% : 0.000018s : 116: predicate.updatestate_useless_node_eliminater 0.37% : 0.000002s : 13: predicate.value_based_eliminate 0.84% : 0.000005s : 26: predicate.virtual_dataset_eliminate 0.83% : 0.000005s : 26: predicate.virtual_output_eliminate 0.34% : 0.000002s : 13: predicate.virtual_view_grad_eliminate 0.48% : 0.000003s : 13: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.008126 38 69.37% : 0.005637s : 29: func_graph_cloner_run.FuncGraphClonerGraph 30.63% : 0.002489s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 4.659862 192 0.00% : 0.000004s : 1: ForceFp32Comm 6.41% : 0.298601s : 1: add_attr 6.41% : 0.298578s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000124s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.00% : 0.000130s : 1: auto_monad 0.00% : 0.000041s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 2.43% : 0.113287s : 1: bootstrap 0.00% : 0.000051s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000032s : 1: control_data_broadcast_order 0.00% : 0.000023s : 1: convert_after_rewriter 0.00% : 0.000054s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000005s : 1: detach_backward 0.00% : 0.000033s : 1: environ_conv 0.04% : 0.001671s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000013s : 1: inline 0.00% : 0.000009s : 1: insert-virtual-dataset 0.00% : 0.000003s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.02% : 0.000792s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000914s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000033s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000035s : 1: opt.transform.mutable_eliminate 0.07% : 0.003489s : 78: opt.transform.opt_a 0.00% : 0.000087s : 1: opt.transform.opt_after_cconv 0.00% : 0.000060s : 1: opt.transform.opt_after_jit_grad 7.34% : 0.341876s : 28: opt.transform.opt_b 0.00% : 0.000205s : 2: opt.transform.opt_trans_graph 0.00% : 0.000094s : 4: opt.transform.symbol_engine_opt 0.27% : 0.012640s : 1: opt_a 0.00% : 0.000227s : 1: opt_after_cconv 0.01% : 0.000565s : 1: opt_after_jit_grad 7.34% : 0.342191s : 1: opt_b 7.70% : 0.358613s : 1: optimize 0.00% : 0.000044s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000016s : 1: order_py_execute_after_rewriter 0.00% : 0.000045s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000011s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000007s : 1: pipeline_parallel_scheduler 0.00% : 0.000007s : 1: pipeline_split 0.00% : 0.000068s : 1: pre_auto_parallel 0.00% : 0.000052s : 1: py_interpret_to_execute 0.00% : 0.000033s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000091s : 1: remove_dup_value 0.09% : 0.004271s : 1: renormalize.infer 0.06% : 0.002954s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000440s : 1: rewriter_after_opt_a 0.00% : 0.000142s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000017s : 1: swap_dp_allreduce_reducescatter 0.00% : 0.000156s : 1: symbol_engine_optimizer 0.01% : 0.000241s : 1: tuple_transform 61.73% : 2.876584s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[True-False-bfloat16--1-shape3] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[True-False-bfloat16--1-shape3],max_mem:100.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:42:20.871.127 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 2.19294, [21] [bootstrap]: 0.00087876 [type_inference]: 2.04095 [event_method]: 0.00193591 [auto_monad]: 0.00014262 [graph_reusing]: 8.3e-06 [inline]: 2.93e-06 [add_attr]: 0.00544868, [1] [add_attr_with_inline]: 0.00542881, [1] [Cycle 1]: 9.097e-05, [2] [tag_attr]: 3.57e-05 [meta_addattr_fg_expand]: 7.56999e-06 [parallel-infer-symbol]: 3.73999e-06 [pre_auto_parallel]: 6.164e-05 [insert-virtual-dataset]: 4.18001e-06 [parallel-infer-symbol-second]: 8.00006e-07 [dataset_repeat_opt]: 3.08e-06 [pipeline_split]: 2.85002e-06 [optimize]: 0.142402, [53] [py_interpret_to_execute]: 8.977e-05 [rewriter_before_opt_a]: 0.00015383 [opt_a]: 0.0114834, [2] [Cycle 1]: 0.00988989, [45] [expand_dump_flag]: 8.18999e-06 [switch_simplify]: 6.211e-05 [loop_unroll]: 4.043e-05 [a_1]: 0.00154869 [with_stream_mark]: 3.955e-05 [recompute_prepare]: 2.18e-05 [updatestate_depend_eliminate]: 1.16e-05 [updatestate_assign_eliminate]: 8.80999e-06 [updatestate_loads_eliminate]: 8.50999e-06 [parameter_eliminate]: 2.39999e-06 [a_2]: 0.00028668 [accelerated_algorithm]: 4.877e-05 [shard]: 2.68998e-06 [meta_shard_fg_expand]: 6.01e-06 [shard_inline]: 1.633e-05 [merge_send_recv]: 1.67e-05 [auto_parallel]: 1.552e-05 [parallel]: 3.68e-05 [flash_sp]: 1.426e-05 [merge_comm]: 1.016e-05 [allreduce_fusion]: 9.96998e-06 [matmul_add_comm_reduction]: 1.999e-05 [allreduce_slice_to_reducescatter]: 1.02e-06 [virtual_shard_identity]: 1.962e-05 [virtual_dataset]: 1.856e-05 [get_grad_eliminate_]: 1.774e-05 [virtual_output]: 1.824e-05 [merge_forward]: 1.092e-05 [cell_reuse_recompute_pass]: 1.84e-06 [offload_activation]: 2.082e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.673e-05 [merge_recompute_call_nodes]: 1.60999e-06 [before_grad]: 3.175e-05 [set_forward_comm_id_for_comm_node_pass]: 1.076e-05 [meta_fg_expand]: 7.7e-06 [flash_sp_send_recv_attached]: 5.79999e-06 [receive_attached]: 2.33998e-06 [after_resolve]: 2.627e-05 [a_after_grad]: 3.336e-05 [renormalize]: 0.00663696 [add_forward_monad_depend]: 1.426e-05 [auto_monad_grad]: 2.54999e-06 [auto_monad_eliminator]: 3.668e-05 [cse]: 0.00025125 [a_3]: 0.00012956 [Cycle 2]: 0.00157359, [45] [expand_dump_flag]: 2.22001e-06 [switch_simplify]: 1.779e-05 [loop_unroll]: 1.58e-05 [a_1]: 0.00051802 [with_stream_mark]: 2.083e-05 [recompute_prepare]: 1.623e-05 [updatestate_depend_eliminate]: 1.028e-05 [updatestate_assign_eliminate]: 7.67002e-06 [updatestate_loads_eliminate]: 7.63001e-06 [parameter_eliminate]: 1.67999e-06 [a_2]: 0.00023535 [accelerated_algorithm]: 2.136e-05 [shard]: 1.85001e-06 [meta_shard_fg_expand]: 4.25999e-06 [shard_inline]: 1.571e-05 [merge_send_recv]: 1.302e-05 [auto_parallel]: 1.485e-05 [parallel]: 8.45999e-06 [flash_sp]: 4.18999e-06 [merge_comm]: 9.49e-06 [allreduce_fusion]: 1.016e-05 [matmul_add_comm_reduction]: 1.496e-05 [allreduce_slice_to_reducescatter]: 1.04998e-06 [virtual_shard_identity]: 1.721e-05 [virtual_dataset]: 1.511e-05 [get_grad_eliminate_]: 1.489e-05 [virtual_output]: 1.511e-05 [merge_forward]: 8.52e-06 [cell_reuse_recompute_pass]: 2.54001e-06 [offload_activation]: 1.592e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.954e-05 [merge_recompute_call_nodes]: 1.19e-06 [before_grad]: 2.573e-05 [set_forward_comm_id_for_comm_node_pass]: 9.99001e-06 [meta_fg_expand]: 7.28999e-06 [flash_sp_send_recv_attached]: 1.29998e-06 [receive_attached]: 2.04e-06 [after_resolve]: 2.078e-05 [a_after_grad]: 2.632e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 1.70001e-06 [auto_monad_grad]: 1.20999e-06 [auto_monad_eliminator]: 1.963e-05 [cse]: 4.842e-05 [a_3]: 9.928e-05 [py_interpret_to_execute_after_opt_a]: 3.868e-05 [slice_cell_reuse_recomputed_activation]: 2.06e-06 [rewriter_after_opt_a]: 0.0004297 [convert_after_rewriter]: 1.734e-05 [order_py_execute_after_rewriter]: 1.198e-05 [mutable_eliminate]: 0.00076514 [opt_b]: 0.0118933, [1] [Cycle 1]: 0.0118831, [7] [b_1]: 0.0116383 [b_2]: 2.71e-05 [updatestate_depend_eliminate]: 2.078e-05 [updatestate_assign_eliminate]: 9.00001e-06 [updatestate_loads_eliminate]: 8.48001e-06 [renormalize]: 8.90024e-07 [cse]: 9.574e-05 [optimize_parallel_all_gather_comm]: 4.022e-05 [overlap_param_gather]: 2.09e-06 [cconv]: 3.747e-05 [loop_unroll]: 0.00078845 [opt_after_cconv]: 0.00022925, [1] [Cycle 1]: 0.00021926, [7] [c_1]: 8.997e-05 [parameter_eliminate]: 5.77999e-06 [updatestate_depend_eliminate]: 1.508e-05 [updatestate_assign_eliminate]: 7.66999e-06 [updatestate_loads_eliminate]: 7.04001e-06 [cse]: 5.612e-05 [renormalize]: 3.9002e-07 [remove_dup_value]: 8.026e-05 [tuple_transform]: 0.00023721, [1] [Cycle 1]: 0.00023181, [4] [d_1]: 0.00018975 [none_parameter_eliminate]: 1.96e-06 [renormalize]: 2.19996e-07 [switch_simplify]: 1.791e-05 [partial_unused_args_eliminate]: 2.05002e-06 [add_recomputation]: 0.00014315 [cse_after_recomputation]: 5.479e-05, [1] [Cycle 1]: 4.78e-05, [1] [cse]: 4.127e-05 [environ_conv]: 1.709e-05 [swap_dp_allreduce_reducescatter]: 1.345e-05 [bias_add_comm_swap]: 4.08001e-06 [label_micro_interleaved_index]: 5.43002e-06 [label_fine_grained_interleaved_index]: 2.61e-06 [merge_cast_opt]: 2.06e-06 [slice_recompute_activation]: 2.30002e-06 [micro_interleaved_order_control]: 2.83e-06 [assign_add_opt]: 1.42999e-06 [ForceFp32Comm]: 1.03001e-06 [remove_cast_before_assign_add]: 1.15001e-06 [full_micro_interleaved_order_control]: 2.06998e-06 [reorder_send_recv_between_fp_bp]: 3.38e-06 [comm_op_add_attrs]: 1.39998e-06 [add_comm_op_reuse_tag]: 1.38002e-06 [interleave_split_concat_branches]: 1.47999e-06 [interleave_parallel_branches]: 1.10001e-06 [overlap_opt_shard_in_pipeline]: 1.69e-06 [overlap_opt_shard_grad_in_pipeline]: 2.14999e-06 [control_data_broadcast_order]: 2.798e-05 [grouped_pairwise_exchange_alltoall]: 1.77999e-06 [offloading_packed_experts]: 9.04e-06 [overlap_recompute_and_grad_model_parallel]: 8.02998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.23002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.35001e-06 [overlap_recompute_comm]: 2.43e-06 [overlap_grad_ring_attention]: 7.26999e-06 [overlap_grad_flash_sp]: 4.377e-05 [begin_end_overlap_inline]: 5.39992e-07 [split_matmul_comm_elemetwise]: 2.29999e-06 [split_layernorm_comm]: 1.77999e-06 [handle_group_info]: 1.04003e-06 [symbol_engine_optimizer]: 0.00038455, [1] [Cycle 1]: 0.00037823, [6] [build]: 0.00021694 [elim_shapecalc]: 2.524e-05 [elim_not_effective]: 3.779e-05 [opt_reshape]: 1.673e-05 [fold_const_symbol]: 4.448e-05 [renormalize]: 2.20025e-07 [detach_backward]: 3.48e-06 [pipeline_parallel_scheduler]: 1.57999e-06 [auto_monad_reorder]: 3.646e-05 [get_jit_bprop_graph]: 2.11998e-06 [rewriter_after_jit_bprop_graph]: 3.72002e-06 [opt_after_jit_grad]: 0.00067085 [validate]: 7.958e-05 Sums bootstrap : 0.000879s : 0.04% type_inference : 2.040951s : 98.54% event_method : 0.001936s : 0.09% auto_monad : 0.000143s : 0.01% graph_reusing : 0.000008s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000036s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000008s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000062s : 0.00% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000090s : 0.00% optimize.rewriter_before_opt_a : 0.000154s : 0.01% optimize.opt_a.expand_dump_flag : 0.000010s : 0.00% optimize.opt_a.switch_simplify : 0.000080s : 0.00% optimize.opt_a.loop_unroll : 0.000056s : 0.00% optimize.opt_a.a_1 : 0.002067s : 0.10% optimize.opt_a.with_stream_mark : 0.000060s : 0.00% optimize.opt_a.recompute_prepare : 0.000038s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000022s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000016s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000016s : 0.00% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000522s : 0.03% optimize.opt_a.accelerated_algorithm : 0.000070s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000010s : 0.00% optimize.opt_a.shard_inline : 0.000032s : 0.00% optimize.opt_a.merge_send_recv : 0.000030s : 0.00% optimize.opt_a.auto_parallel : 0.000030s : 0.00% optimize.opt_a.parallel : 0.000045s : 0.00% optimize.opt_a.flash_sp : 0.000018s : 0.00% optimize.opt_a.merge_comm : 0.000020s : 0.00% optimize.opt_a.allreduce_fusion : 0.000020s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000035s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000037s : 0.00% optimize.opt_a.virtual_dataset : 0.000034s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000033s : 0.00% optimize.opt_a.virtual_output : 0.000033s : 0.00% optimize.opt_a.merge_forward : 0.000019s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000037s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000066s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000057s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000021s : 0.00% optimize.opt_a.meta_fg_expand : 0.000015s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000047s : 0.00% optimize.opt_a.a_after_grad : 0.000060s : 0.00% optimize.opt_a.renormalize : 0.006637s : 0.32% optimize.opt_a.add_forward_monad_depend : 0.000016s : 0.00% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000056s : 0.00% optimize.opt_a.cse : 0.000300s : 0.01% optimize.opt_a.a_3 : 0.000229s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000039s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000430s : 0.02% optimize.convert_after_rewriter : 0.000017s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000765s : 0.04% optimize.opt_b.b_1 : 0.011638s : 0.56% optimize.opt_b.b_2 : 0.000027s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000021s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000096s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000040s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000037s : 0.00% optimize.loop_unroll : 0.000788s : 0.04% optimize.opt_after_cconv.c_1 : 0.000090s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000056s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000080s : 0.00% optimize.tuple_transform.d_1 : 0.000190s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000018s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000143s : 0.01% optimize.cse_after_recomputation.cse : 0.000041s : 0.00% optimize.environ_conv : 0.000017s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000013s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000028s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000009s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000044s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000217s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000025s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000038s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000017s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000044s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000036s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000004s : 0.00% opt_after_jit_grad : 0.000671s : 0.03% validate : 0.000080s : 0.00% Time group info: ------[substitution.] 0.000702 200 6.17% : 0.000043s : 6: substitution.arithmetic_simplify 1.49% : 0.000010s : 10: substitution.elim_not_effective 2.14% : 0.000015s : 12: substitution.float_tuple_getitem_switch 2.86% : 0.000020s : 10: substitution.fold_const_symbol 1.92% : 0.000013s : 13: substitution.graph_param_transform 42.54% : 0.000299s : 7: substitution.inline 1.38% : 0.000010s : 20: substitution.j_node_and_user_rematch 3.19% : 0.000022s : 2: substitution.less_batch_normalization 2.35% : 0.000017s : 8: substitution.minmaximum_grad 2.04% : 0.000014s : 20: substitution.remove_not_recompute_node 0.98% : 0.000007s : 4: substitution.replace_old_param 7.70% : 0.000054s : 16: substitution.tuple_list_convert_item_index_to_positive 4.24% : 0.000030s : 16: substitution.tuple_list_get_item_const_eliminator 5.25% : 0.000037s : 16: substitution.tuple_list_get_item_depend_reorder 11.01% : 0.000077s : 24: substitution.tuple_list_get_item_eliminator 4.76% : 0.000033s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 2.040819 2 99.73% : 2.035392s : 1: type_inference.infer 0.27% : 0.005427s : 1: type_inference.specialize ------[replace.] 0.000066 7 100.00% : 0.000066s : 7: replace.inline ------[match.] 0.000294 7 100.00% : 0.000294s : 7: match.inline ------[predicate.] 0.000550 3321 0.92% : 0.000005s : 32: predicate.accumulaten_eliminater 0.81% : 0.000004s : 13: predicate.ad_related_special_op_eliminate 0.65% : 0.000004s : 26: predicate.addn_check_dump 0.89% : 0.000005s : 32: predicate.addn_zero_filter 1.97% : 0.000011s : 32: predicate.adjust_all_reduce_mul_add 2.33% : 0.000013s : 58: predicate.arithmetic_simplify 0.88% : 0.000005s : 32: predicate.cast_eliminate 0.68% : 0.000004s : 26: predicate.check_bprop_eliminate 0.67% : 0.000004s : 26: predicate.compare_switch_simplify 0.35% : 0.000002s : 13: predicate.const_output_eliminate 0.67% : 0.000004s : 26: predicate.depend_value_elim 0.89% : 0.000005s : 32: predicate.dict_get_item_const_eliminator 1.01% : 0.000006s : 32: predicate.dict_get_item_eliminator 0.84% : 0.000005s : 32: predicate.dict_set_item_eliminator 3.10% : 0.000017s : 26: predicate.dumpgradient_eliminate 0.25% : 0.000001s : 13: predicate.elim_not_effective 0.42% : 0.000002s : 13: predicate.elim_shapecalc_of_broadcastargs 1.14% : 0.000006s : 45: predicate.environ_add_const_eliminate 1.20% : 0.000007s : 45: predicate.environ_get_add_eliminate 1.16% : 0.000006s : 45: predicate.environ_get_depend_swap 2.08% : 0.000011s : 71: predicate.environ_get_eliminate 1.26% : 0.000007s : 45: predicate.environ_get_set_eliminate 1.00% : 0.000006s : 39: predicate.exchange_switch_depend_value 1.50% : 0.000008s : 39: predicate.float_depend_g_call 0.70% : 0.000004s : 26: predicate.float_environ_get_switch 1.20% : 0.000007s : 39: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 13: predicate.fold_const_symbol 0.73% : 0.000004s : 26: predicate.get_grad_eliminate 0.22% : 0.000001s : 13: predicate.graph_param_transform 0.67% : 0.000004s : 26: predicate.incorporate_call 0.61% : 0.000003s : 26: predicate.incorporate_call_switch 5.31% : 0.000029s : 149: predicate.inline 0.88% : 0.000005s : 26: predicate.inline_without_move 0.33% : 0.000002s : 26: predicate.j_node_and_user_rematch 1.03% : 0.000006s : 26: predicate.less_batch_normalization 1.62% : 0.000009s : 58: predicate.list_to_tuple_eliminator_ 2.17% : 0.000012s : 90: predicate.load_eliminater 0.74% : 0.000004s : 13: predicate.loop_unroll_after_grad 1.49% : 0.000008s : 55: predicate.loop_unroll_before_grad 1.59% : 0.000009s : 58: predicate.make_slice_get_slice_eliminator 0.69% : 0.000004s : 26: predicate.merge_addn 0.68% : 0.000004s : 26: predicate.micro_step_allgather_replace 0.66% : 0.000004s : 26: predicate.mini_step_allgather_replace 0.85% : 0.000005s : 32: predicate.minmaximum_grad 0.80% : 0.000004s : 13: predicate.mutable_eliminate 0.40% : 0.000002s : 13: predicate.opt_reshape 0.55% : 0.000003s : 13: predicate.parallel_virtual_node 1.43% : 0.000008s : 39: predicate.partial_defer_inline 1.22% : 0.000007s : 45: predicate.partial_eliminate 0.83% : 0.000005s : 32: predicate.print_const_string_wrapper 0.69% : 0.000004s : 26: predicate.reduce_all_const_elim 1.32% : 0.000007s : 32: predicate.reduce_eliminate 2.44% : 0.000013s : 90: predicate.redundant_stop_gradient_eliminater 0.41% : 0.000002s : 26: predicate.remove_not_recompute_node 1.06% : 0.000006s : 58: predicate.replace_applicator 0.39% : 0.000002s : 26: predicate.replace_old_param 0.22% : 0.000001s : 13: predicate.reset_defer_inline 0.94% : 0.000005s : 32: predicate.reshape_eliminate 0.73% : 0.000004s : 26: predicate.row_tensor_add_zeros_like 0.47% : 0.000003s : 13: predicate.row_tensor_eliminate 0.84% : 0.000005s : 26: predicate.same_eliminate 0.42% : 0.000002s : 26: predicate.set_cell_output_no_recompute 0.78% : 0.000004s : 26: predicate.shard_identity_eliminate 0.80% : 0.000004s : 26: predicate.special_op_eliminate 0.79% : 0.000004s : 26: predicate.specialize_transform 0.89% : 0.000005s : 26: predicate.split_environ_get_set_with_tuple_value 0.90% : 0.000005s : 26: predicate.stack_unstack_eliminate 0.40% : 0.000002s : 13: predicate.switch_call_monad_eliminater 1.15% : 0.000006s : 39: predicate.switch_defer_inline 1.78% : 0.000010s : 65: predicate.switch_layer_defer_inline 3.84% : 0.000021s : 133: predicate.switch_simplify 0.91% : 0.000005s : 32: predicate.tile_eliminate 0.87% : 0.000005s : 32: predicate.transpose_eliminate 1.72% : 0.000009s : 58: predicate.tuple_list_convert_item_index_to_positive 1.77% : 0.000010s : 58: predicate.tuple_list_get_item_const_eliminator 1.68% : 0.000009s : 58: predicate.tuple_list_get_item_depend_reorder 3.19% : 0.000018s : 84: predicate.tuple_list_get_item_eliminator 1.81% : 0.000010s : 58: predicate.tuple_list_get_set_item_eliminator 2.54% : 0.000014s : 84: predicate.tuple_list_set_item_eliminator 1.65% : 0.000009s : 58: predicate.tuple_to_list_eliminator_ 2.24% : 0.000012s : 90: predicate.updatestate_pure_node_eliminater 3.13% : 0.000017s : 116: predicate.updatestate_useless_node_eliminater 0.63% : 0.000003s : 13: predicate.value_based_eliminate 0.83% : 0.000005s : 26: predicate.virtual_dataset_eliminate 0.75% : 0.000004s : 26: predicate.virtual_output_eliminate 0.33% : 0.000002s : 13: predicate.virtual_view_grad_eliminate 0.43% : 0.000002s : 13: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.007005 38 68.37% : 0.004789s : 29: func_graph_cloner_run.FuncGraphClonerGraph 31.63% : 0.002216s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.247656 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.24% : 0.005455s : 1: add_attr 0.24% : 0.005433s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000150s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000153s : 1: auto_monad 0.00% : 0.000041s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.04% : 0.000985s : 1: bootstrap 0.00% : 0.000041s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000031s : 1: control_data_broadcast_order 0.00% : 0.000022s : 1: convert_after_rewriter 0.00% : 0.000058s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000021s : 1: environ_conv 0.09% : 0.001970s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000009s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.04% : 0.000799s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.03% : 0.000776s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.00% : 0.000028s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000031s : 1: opt.transform.mutable_eliminate 0.15% : 0.003348s : 78: opt.transform.opt_a 0.00% : 0.000089s : 1: opt.transform.opt_after_cconv 0.00% : 0.000058s : 1: opt.transform.opt_after_jit_grad 0.52% : 0.011608s : 28: opt.transform.opt_b 0.01% : 0.000205s : 2: opt.transform.opt_trans_graph 0.01% : 0.000119s : 4: opt.transform.symbol_engine_opt 0.51% : 0.011488s : 1: opt_a 0.01% : 0.000233s : 1: opt_after_cconv 0.03% : 0.000681s : 1: opt_after_jit_grad 0.53% : 0.011899s : 1: opt_b 6.34% : 0.142409s : 1: optimize 0.00% : 0.000044s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000016s : 1: order_py_execute_after_rewriter 0.00% : 0.000048s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000067s : 1: pre_auto_parallel 0.01% : 0.000126s : 1: py_interpret_to_execute 0.00% : 0.000043s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000085s : 1: remove_dup_value 0.18% : 0.004048s : 1: renormalize.infer 0.11% : 0.002574s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000007s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000436s : 1: rewriter_after_opt_a 0.01% : 0.000161s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000017s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000388s : 1: symbol_engine_optimizer 0.01% : 0.000242s : 1: tuple_transform 90.81% : 2.040984s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[True-True-bfloat16--1-shape0] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[True-True-bfloat16--1-shape0],max_mem:100.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:42:29.562.060 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 2.16989, [21] [bootstrap]: 0.00090067 [type_inference]: 1.95344 [event_method]: 0.00140104 [auto_monad]: 0.00012793 [graph_reusing]: 7.78999e-06 [inline]: 2.60002e-06 [add_attr]: 0.00486067, [1] [add_attr_with_inline]: 0.00484076, [1] [Cycle 1]: 7.563e-05, [2] [tag_attr]: 3.226e-05 [meta_addattr_fg_expand]: 8.37e-06 [parallel-infer-symbol]: 5.18002e-06 [pre_auto_parallel]: 5.134e-05 [insert-virtual-dataset]: 4.32998e-06 [parallel-infer-symbol-second]: 8.30012e-07 [dataset_repeat_opt]: 2.41e-06 [pipeline_split]: 3.01999e-06 [optimize]: 0.20794, [53] [py_interpret_to_execute]: 3.817e-05 [rewriter_before_opt_a]: 0.0001248 [opt_a]: 0.203531, [2] [Cycle 1]: 0.201794, [45] [expand_dump_flag]: 4.52e-06 [switch_simplify]: 5.914e-05 [loop_unroll]: 4.211e-05 [a_1]: 0.00163056 [with_stream_mark]: 2.858e-05 [recompute_prepare]: 2.33e-05 [updatestate_depend_eliminate]: 1.21e-05 [updatestate_assign_eliminate]: 8.97999e-06 [updatestate_loads_eliminate]: 9.12001e-06 [parameter_eliminate]: 2.69001e-06 [a_2]: 0.0003347 [accelerated_algorithm]: 4.397e-05 [shard]: 3.08998e-06 [meta_shard_fg_expand]: 6.39001e-06 [shard_inline]: 1.877e-05 [merge_send_recv]: 1.735e-05 [auto_parallel]: 1.48e-05 [parallel]: 3.715e-05 [flash_sp]: 1.162e-05 [merge_comm]: 1.13e-05 [allreduce_fusion]: 1.093e-05 [matmul_add_comm_reduction]: 2e-05 [allreduce_slice_to_reducescatter]: 7.50006e-07 [virtual_shard_identity]: 2.181e-05 [virtual_dataset]: 1.961e-05 [get_grad_eliminate_]: 1.908e-05 [virtual_output]: 2.38e-05 [merge_forward]: 1.184e-05 [cell_reuse_recompute_pass]: 1.70001e-06 [offload_activation]: 2.006e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.332e-05 [merge_recompute_call_nodes]: 1.75001e-06 [before_grad]: 3.471e-05 [set_forward_comm_id_for_comm_node_pass]: 1.099e-05 [meta_fg_expand]: 8.72e-06 [flash_sp_send_recv_attached]: 5.71998e-06 [receive_attached]: 2.61e-06 [after_resolve]: 2.723e-05 [a_after_grad]: 3.272e-05 [renormalize]: 0.198012 [add_forward_monad_depend]: 2.608e-05 [auto_monad_grad]: 3.41001e-06 [auto_monad_eliminator]: 5.701e-05 [cse]: 0.00052755 [a_3]: 0.00015879 [Cycle 2]: 0.00172043, [45] [expand_dump_flag]: 2.93e-06 [switch_simplify]: 1.958e-05 [loop_unroll]: 1.784e-05 [a_1]: 0.00054215 [with_stream_mark]: 3.068e-05 [recompute_prepare]: 1.64e-05 [updatestate_depend_eliminate]: 1.185e-05 [updatestate_assign_eliminate]: 8.48999e-06 [updatestate_loads_eliminate]: 8.23001e-06 [parameter_eliminate]: 2.69001e-06 [a_2]: 0.0002593 [accelerated_algorithm]: 2.172e-05 [shard]: 3.37997e-06 [meta_shard_fg_expand]: 6.26e-06 [shard_inline]: 1.633e-05 [merge_send_recv]: 1.619e-05 [auto_parallel]: 1.739e-05 [parallel]: 1.175e-05 [flash_sp]: 4.97e-06 [merge_comm]: 1.043e-05 [allreduce_fusion]: 1.121e-05 [matmul_add_comm_reduction]: 1.886e-05 [allreduce_slice_to_reducescatter]: 8.79983e-07 [virtual_shard_identity]: 1.762e-05 [virtual_dataset]: 1.58e-05 [get_grad_eliminate_]: 1.566e-05 [virtual_output]: 1.58e-05 [merge_forward]: 1.004e-05 [cell_reuse_recompute_pass]: 3.36001e-06 [offload_activation]: 1.869e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.064e-05 [merge_recompute_call_nodes]: 1.76e-06 [before_grad]: 2.761e-05 [set_forward_comm_id_for_comm_node_pass]: 1.016e-05 [meta_fg_expand]: 8.60999e-06 [flash_sp_send_recv_attached]: 2.28002e-06 [receive_attached]: 2.46e-06 [after_resolve]: 2.367e-05 [a_after_grad]: 2.826e-05 [renormalize]: 2.19996e-07 [add_forward_monad_depend]: 2.80002e-06 [auto_monad_grad]: 1.69e-06 [auto_monad_eliminator]: 2.434e-05 [cse]: 5.682e-05 [a_3]: 0.00010831 [py_interpret_to_execute_after_opt_a]: 3.131e-05 [slice_cell_reuse_recomputed_activation]: 2.16998e-06 [rewriter_after_opt_a]: 0.00042545 [convert_after_rewriter]: 1.777e-05 [order_py_execute_after_rewriter]: 1.161e-05 [mutable_eliminate]: 0.00085162 [opt_b]: 0.00065342, [1] [Cycle 1]: 0.00064424, [7] [b_1]: 0.00048004 [b_2]: 1.989e-05 [updatestate_depend_eliminate]: 1.582e-05 [updatestate_assign_eliminate]: 8.55999e-06 [updatestate_loads_eliminate]: 7.86001e-06 [renormalize]: 6.80011e-07 [cse]: 6.956e-05 [optimize_parallel_all_gather_comm]: 3.276e-05 [overlap_param_gather]: 2.34999e-06 [cconv]: 3.85e-05 [loop_unroll]: 0.00060947 [opt_after_cconv]: 0.0002218, [1] [Cycle 1]: 0.00021366, [7] [c_1]: 8.585e-05 [parameter_eliminate]: 4.27e-06 [updatestate_depend_eliminate]: 1.445e-05 [updatestate_assign_eliminate]: 7.43e-06 [updatestate_loads_eliminate]: 6.96999e-06 [cse]: 5.824e-05 [renormalize]: 3.19997e-07 [remove_dup_value]: 8.517e-05 [tuple_transform]: 0.00023551, [1] [Cycle 1]: 0.00022997, [4] [d_1]: 0.00018711 [none_parameter_eliminate]: 2.46e-06 [renormalize]: 2.19996e-07 [switch_simplify]: 1.773e-05 [partial_unused_args_eliminate]: 2.47001e-06 [add_recomputation]: 0.00012429 [cse_after_recomputation]: 5.749e-05, [1] [Cycle 1]: 5.075e-05, [1] [cse]: 4.335e-05 [environ_conv]: 1.677e-05 [swap_dp_allreduce_reducescatter]: 1.296e-05 [bias_add_comm_swap]: 3.06999e-06 [label_micro_interleaved_index]: 6.51e-06 [label_fine_grained_interleaved_index]: 2.98e-06 [merge_cast_opt]: 1.60001e-06 [slice_recompute_activation]: 2.31998e-06 [micro_interleaved_order_control]: 3.09999e-06 [assign_add_opt]: 1.44e-06 [ForceFp32Comm]: 8.60018e-07 [remove_cast_before_assign_add]: 1.52001e-06 [full_micro_interleaved_order_control]: 2.43e-06 [reorder_send_recv_between_fp_bp]: 2.88998e-06 [comm_op_add_attrs]: 1.02998e-06 [add_comm_op_reuse_tag]: 1.35001e-06 [interleave_split_concat_branches]: 1.25999e-06 [interleave_parallel_branches]: 1.08001e-06 [overlap_opt_shard_in_pipeline]: 1.73002e-06 [overlap_opt_shard_grad_in_pipeline]: 2.14999e-06 [control_data_broadcast_order]: 3.021e-05 [grouped_pairwise_exchange_alltoall]: 1.57999e-06 [offloading_packed_experts]: 8.46997e-06 [overlap_recompute_and_grad_model_parallel]: 9.09e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.19e-06 [overlap_recompute_allgather_and_fa_grad]: 1.48002e-06 [overlap_recompute_comm]: 2.69999e-06 [overlap_grad_ring_attention]: 7.49002e-06 [overlap_grad_flash_sp]: 4.236e-05 [begin_end_overlap_inline]: 5.29981e-07 [split_matmul_comm_elemetwise]: 2.39999e-06 [split_layernorm_comm]: 1.81e-06 [handle_group_info]: 1.07e-06 [symbol_engine_optimizer]: 0.0003881, [1] [Cycle 1]: 0.00038195, [6] [build]: 0.00021189 [elim_shapecalc]: 2.76e-05 [elim_not_effective]: 3.776e-05 [opt_reshape]: 1.814e-05 [fold_const_symbol]: 4.649e-05 [renormalize]: 2.60014e-07 [detach_backward]: 3.59002e-06 [pipeline_parallel_scheduler]: 1.90001e-06 [auto_monad_reorder]: 3.816e-05 [get_jit_bprop_graph]: 1.94e-06 [rewriter_after_jit_bprop_graph]: 5.48002e-06 [opt_after_jit_grad]: 0.00068361 [validate]: 9.63e-05 Sums bootstrap : 0.000901s : 0.04% type_inference : 1.953441s : 90.28% event_method : 0.001401s : 0.06% auto_monad : 0.000128s : 0.01% graph_reusing : 0.000008s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000032s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000008s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000051s : 0.00% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000038s : 0.00% optimize.rewriter_before_opt_a : 0.000125s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000079s : 0.00% optimize.opt_a.loop_unroll : 0.000060s : 0.00% optimize.opt_a.a_1 : 0.002173s : 0.10% optimize.opt_a.with_stream_mark : 0.000059s : 0.00% optimize.opt_a.recompute_prepare : 0.000040s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000024s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000017s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000594s : 0.03% optimize.opt_a.accelerated_algorithm : 0.000066s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000013s : 0.00% optimize.opt_a.shard_inline : 0.000035s : 0.00% optimize.opt_a.merge_send_recv : 0.000034s : 0.00% optimize.opt_a.auto_parallel : 0.000032s : 0.00% optimize.opt_a.parallel : 0.000049s : 0.00% optimize.opt_a.flash_sp : 0.000017s : 0.00% optimize.opt_a.merge_comm : 0.000022s : 0.00% optimize.opt_a.allreduce_fusion : 0.000022s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000039s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000039s : 0.00% optimize.opt_a.virtual_dataset : 0.000035s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000035s : 0.00% optimize.opt_a.virtual_output : 0.000040s : 0.00% optimize.opt_a.merge_forward : 0.000022s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000039s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000074s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000062s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000021s : 0.00% optimize.opt_a.meta_fg_expand : 0.000017s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000051s : 0.00% optimize.opt_a.a_after_grad : 0.000061s : 0.00% optimize.opt_a.renormalize : 0.198012s : 9.15% optimize.opt_a.add_forward_monad_depend : 0.000029s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000081s : 0.00% optimize.opt_a.cse : 0.000584s : 0.03% optimize.opt_a.a_3 : 0.000267s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000031s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000425s : 0.02% optimize.convert_after_rewriter : 0.000018s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000852s : 0.04% optimize.opt_b.b_1 : 0.000480s : 0.02% optimize.opt_b.b_2 : 0.000020s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000016s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000070s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000033s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000039s : 0.00% optimize.loop_unroll : 0.000609s : 0.03% optimize.opt_after_cconv.c_1 : 0.000086s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000058s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000085s : 0.00% optimize.tuple_transform.d_1 : 0.000187s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000018s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000124s : 0.01% optimize.cse_after_recomputation.cse : 0.000043s : 0.00% optimize.environ_conv : 0.000017s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000013s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000002s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000030s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000042s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000212s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000028s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000038s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000018s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000046s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000038s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000684s : 0.03% validate : 0.000096s : 0.00% Time group info: ------[substitution.] 0.000704 200 6.89% : 0.000049s : 6: substitution.arithmetic_simplify 1.17% : 0.000008s : 10: substitution.elim_not_effective 2.29% : 0.000016s : 12: substitution.float_tuple_getitem_switch 2.76% : 0.000019s : 10: substitution.fold_const_symbol 1.79% : 0.000013s : 13: substitution.graph_param_transform 39.90% : 0.000281s : 7: substitution.inline 1.46% : 0.000010s : 20: substitution.j_node_and_user_rematch 3.10% : 0.000022s : 2: substitution.less_batch_normalization 2.42% : 0.000017s : 8: substitution.minmaximum_grad 2.31% : 0.000016s : 20: substitution.remove_not_recompute_node 1.00% : 0.000007s : 4: substitution.replace_old_param 7.82% : 0.000055s : 16: substitution.tuple_list_convert_item_index_to_positive 4.60% : 0.000032s : 16: substitution.tuple_list_get_item_const_eliminator 6.30% : 0.000044s : 16: substitution.tuple_list_get_item_depend_reorder 10.95% : 0.000077s : 24: substitution.tuple_list_get_item_eliminator 5.25% : 0.000037s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.953338 2 99.78% : 1.949044s : 1: type_inference.infer 0.22% : 0.004293s : 1: type_inference.specialize ------[replace.] 0.000069 7 100.00% : 0.000069s : 7: replace.inline ------[match.] 0.000276 7 100.00% : 0.000276s : 7: match.inline ------[predicate.] 0.000568 3321 0.95% : 0.000005s : 32: predicate.accumulaten_eliminater 0.75% : 0.000004s : 13: predicate.ad_related_special_op_eliminate 0.71% : 0.000004s : 26: predicate.addn_check_dump 0.93% : 0.000005s : 32: predicate.addn_zero_filter 0.82% : 0.000005s : 32: predicate.adjust_all_reduce_mul_add 2.37% : 0.000013s : 58: predicate.arithmetic_simplify 1.02% : 0.000006s : 32: predicate.cast_eliminate 0.82% : 0.000005s : 26: predicate.check_bprop_eliminate 0.72% : 0.000004s : 26: predicate.compare_switch_simplify 0.19% : 0.000001s : 13: predicate.const_output_eliminate 0.68% : 0.000004s : 26: predicate.depend_value_elim 0.96% : 0.000005s : 32: predicate.dict_get_item_const_eliminator 0.98% : 0.000006s : 32: predicate.dict_get_item_eliminator 0.90% : 0.000005s : 32: predicate.dict_set_item_eliminator 0.82% : 0.000005s : 26: predicate.dumpgradient_eliminate 0.19% : 0.000001s : 13: predicate.elim_not_effective 0.44% : 0.000002s : 13: predicate.elim_shapecalc_of_broadcastargs 1.17% : 0.000007s : 45: predicate.environ_add_const_eliminate 1.12% : 0.000006s : 45: predicate.environ_get_add_eliminate 1.32% : 0.000008s : 45: predicate.environ_get_depend_swap 2.01% : 0.000011s : 71: predicate.environ_get_eliminate 1.16% : 0.000007s : 45: predicate.environ_get_set_eliminate 1.01% : 0.000006s : 39: predicate.exchange_switch_depend_value 1.74% : 0.000010s : 39: predicate.float_depend_g_call 0.70% : 0.000004s : 26: predicate.float_environ_get_switch 1.35% : 0.000008s : 39: predicate.float_tuple_getitem_switch 0.20% : 0.000001s : 13: predicate.fold_const_symbol 0.77% : 0.000004s : 26: predicate.get_grad_eliminate 0.22% : 0.000001s : 13: predicate.graph_param_transform 0.68% : 0.000004s : 26: predicate.incorporate_call 0.64% : 0.000004s : 26: predicate.incorporate_call_switch 5.52% : 0.000031s : 149: predicate.inline 0.95% : 0.000005s : 26: predicate.inline_without_move 0.33% : 0.000002s : 26: predicate.j_node_and_user_rematch 0.96% : 0.000005s : 26: predicate.less_batch_normalization 1.79% : 0.000010s : 58: predicate.list_to_tuple_eliminator_ 2.39% : 0.000014s : 90: predicate.load_eliminater 0.78% : 0.000004s : 13: predicate.loop_unroll_after_grad 1.48% : 0.000008s : 55: predicate.loop_unroll_before_grad 1.74% : 0.000010s : 58: predicate.make_slice_get_slice_eliminator 0.76% : 0.000004s : 26: predicate.merge_addn 0.71% : 0.000004s : 26: predicate.micro_step_allgather_replace 0.69% : 0.000004s : 26: predicate.mini_step_allgather_replace 1.06% : 0.000006s : 32: predicate.minmaximum_grad 1.08% : 0.000006s : 13: predicate.mutable_eliminate 0.44% : 0.000002s : 13: predicate.opt_reshape 0.52% : 0.000003s : 13: predicate.parallel_virtual_node 1.69% : 0.000010s : 39: predicate.partial_defer_inline 1.19% : 0.000007s : 45: predicate.partial_eliminate 0.89% : 0.000005s : 32: predicate.print_const_string_wrapper 0.75% : 0.000004s : 26: predicate.reduce_all_const_elim 1.35% : 0.000008s : 32: predicate.reduce_eliminate 2.35% : 0.000013s : 90: predicate.redundant_stop_gradient_eliminater 0.41% : 0.000002s : 26: predicate.remove_not_recompute_node 1.09% : 0.000006s : 58: predicate.replace_applicator 0.45% : 0.000003s : 26: predicate.replace_old_param 0.26% : 0.000001s : 13: predicate.reset_defer_inline 0.98% : 0.000006s : 32: predicate.reshape_eliminate 0.76% : 0.000004s : 26: predicate.row_tensor_add_zeros_like 0.41% : 0.000002s : 13: predicate.row_tensor_eliminate 1.05% : 0.000006s : 26: predicate.same_eliminate 0.40% : 0.000002s : 26: predicate.set_cell_output_no_recompute 0.79% : 0.000004s : 26: predicate.shard_identity_eliminate 0.74% : 0.000004s : 26: predicate.special_op_eliminate 0.85% : 0.000005s : 26: predicate.specialize_transform 0.97% : 0.000005s : 26: predicate.split_environ_get_set_with_tuple_value 0.90% : 0.000005s : 26: predicate.stack_unstack_eliminate 0.39% : 0.000002s : 13: predicate.switch_call_monad_eliminater 1.15% : 0.000007s : 39: predicate.switch_defer_inline 1.90% : 0.000011s : 65: predicate.switch_layer_defer_inline 3.84% : 0.000022s : 133: predicate.switch_simplify 0.94% : 0.000005s : 32: predicate.tile_eliminate 0.88% : 0.000005s : 32: predicate.transpose_eliminate 1.81% : 0.000010s : 58: predicate.tuple_list_convert_item_index_to_positive 1.94% : 0.000011s : 58: predicate.tuple_list_get_item_const_eliminator 1.79% : 0.000010s : 58: predicate.tuple_list_get_item_depend_reorder 3.27% : 0.000019s : 84: predicate.tuple_list_get_item_eliminator 1.76% : 0.000010s : 58: predicate.tuple_list_get_set_item_eliminator 2.63% : 0.000015s : 84: predicate.tuple_list_set_item_eliminator 1.67% : 0.000009s : 58: predicate.tuple_to_list_eliminator_ 2.18% : 0.000012s : 90: predicate.updatestate_pure_node_eliminater 3.26% : 0.000019s : 116: predicate.updatestate_useless_node_eliminater 0.38% : 0.000002s : 13: predicate.value_based_eliminate 0.74% : 0.000004s : 26: predicate.virtual_dataset_eliminate 0.81% : 0.000005s : 26: predicate.virtual_output_eliminate 0.35% : 0.000002s : 13: predicate.virtual_view_grad_eliminate 0.50% : 0.000003s : 13: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.034885 38 13.11% : 0.004573s : 29: func_graph_cloner_run.FuncGraphClonerGraph 86.89% : 0.030311s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.585014 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.19% : 0.004867s : 1: add_attr 0.19% : 0.004845s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000129s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000136s : 1: auto_monad 0.00% : 0.000042s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.04% : 0.001010s : 1: bootstrap 0.00% : 0.000042s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000034s : 1: control_data_broadcast_order 0.00% : 0.000022s : 1: convert_after_rewriter 0.00% : 0.000061s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000022s : 1: environ_conv 0.06% : 0.001423s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000009s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.02% : 0.000619s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.03% : 0.000863s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000031s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000036s : 1: opt.transform.mutable_eliminate 0.14% : 0.003567s : 78: opt.transform.opt_a 0.00% : 0.000084s : 1: opt.transform.opt_after_cconv 0.00% : 0.000062s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000460s : 28: opt.transform.opt_b 0.01% : 0.000202s : 2: opt.transform.opt_trans_graph 0.00% : 0.000125s : 4: opt.transform.symbol_engine_opt 7.87% : 0.203535s : 1: opt_a 0.01% : 0.000226s : 1: opt_after_cconv 0.03% : 0.000696s : 1: opt_after_jit_grad 0.03% : 0.000657s : 1: opt_b 8.05% : 0.207967s : 1: optimize 0.00% : 0.000037s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.00% : 0.000046s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000056s : 1: pre_auto_parallel 0.00% : 0.000046s : 1: py_interpret_to_execute 0.00% : 0.000035s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000090s : 1: remove_dup_value 1.03% : 0.026692s : 1: renormalize.infer 6.63% : 0.171298s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000432s : 1: rewriter_after_opt_a 0.01% : 0.000130s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000016s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000392s : 1: symbol_engine_optimizer 0.01% : 0.000240s : 1: tuple_transform 75.57% : 1.953472s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[True-True-bfloat16--1-shape1] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[True-True-bfloat16--1-shape1],max_mem:106.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:42:39.762.352 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 1.49015, [21] [bootstrap]: 0.00088377 [type_inference]: 1.38544 [event_method]: 0.00147335 [auto_monad]: 0.00018207 [graph_reusing]: 8.38999e-06 [inline]: 2.36e-06 [add_attr]: 0.0845295, [1] [add_attr_with_inline]: 0.0845116, [1] [Cycle 1]: 8.692e-05, [2] [tag_attr]: 3.528e-05 [meta_addattr_fg_expand]: 7.4e-06 [parallel-infer-symbol]: 4.24002e-06 [pre_auto_parallel]: 5.133e-05 [insert-virtual-dataset]: 3.58999e-06 [parallel-infer-symbol-second]: 6.89994e-07 [dataset_repeat_opt]: 2.26e-06 [pipeline_split]: 3.11001e-06 [optimize]: 0.0163887, [53] [py_interpret_to_execute]: 4.021e-05 [rewriter_before_opt_a]: 0.00012041 [opt_a]: 0.0122525, [2] [Cycle 1]: 0.0104202, [45] [expand_dump_flag]: 3.85998e-06 [switch_simplify]: 5.254e-05 [loop_unroll]: 3.882e-05 [a_1]: 0.00147008 [with_stream_mark]: 2.852e-05 [recompute_prepare]: 2.132e-05 [updatestate_depend_eliminate]: 1.124e-05 [updatestate_assign_eliminate]: 8.65999e-06 [updatestate_loads_eliminate]: 8.47e-06 [parameter_eliminate]: 2.34001e-06 [a_2]: 0.00027598 [accelerated_algorithm]: 4.176e-05 [shard]: 3.23e-06 [meta_shard_fg_expand]: 5.00999e-06 [shard_inline]: 1.603e-05 [merge_send_recv]: 1.551e-05 [auto_parallel]: 1.438e-05 [parallel]: 3.777e-05 [flash_sp]: 1.047e-05 [merge_comm]: 1.017e-05 [allreduce_fusion]: 1.018e-05 [matmul_add_comm_reduction]: 1.799e-05 [allreduce_slice_to_reducescatter]: 9.60019e-07 [virtual_shard_identity]: 2.232e-05 [virtual_dataset]: 2.063e-05 [get_grad_eliminate_]: 1.702e-05 [virtual_output]: 1.771e-05 [merge_forward]: 1.255e-05 [cell_reuse_recompute_pass]: 1.69e-06 [offload_activation]: 1.956e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.717e-05 [merge_recompute_call_nodes]: 1.57999e-06 [before_grad]: 3.05e-05 [set_forward_comm_id_for_comm_node_pass]: 1.142e-05 [meta_fg_expand]: 7.49002e-06 [flash_sp_send_recv_attached]: 5.66998e-06 [receive_attached]: 3.03998e-06 [after_resolve]: 2.736e-05 [a_after_grad]: 3.768e-05 [renormalize]: 0.00721411 [add_forward_monad_depend]: 1.766e-05 [auto_monad_grad]: 2.80002e-06 [auto_monad_eliminator]: 3.69e-05 [cse]: 0.00030713 [a_3]: 0.00013594 [Cycle 2]: 0.00181667, [45] [expand_dump_flag]: 3.06001e-06 [switch_simplify]: 1.939e-05 [loop_unroll]: 1.663e-05 [a_1]: 0.00052112 [with_stream_mark]: 2.631e-05 [recompute_prepare]: 2.051e-05 [updatestate_depend_eliminate]: 1.111e-05 [updatestate_assign_eliminate]: 8.2e-06 [updatestate_loads_eliminate]: 8.08001e-06 [parameter_eliminate]: 1.93002e-06 [a_2]: 0.00024596 [accelerated_algorithm]: 2.147e-05 [shard]: 2.30002e-06 [meta_shard_fg_expand]: 5.05001e-06 [shard_inline]: 1.608e-05 [merge_send_recv]: 1.486e-05 [auto_parallel]: 1.516e-05 [parallel]: 9.98002e-06 [flash_sp]: 4.68999e-06 [merge_comm]: 9.91998e-06 [allreduce_fusion]: 1.022e-05 [matmul_add_comm_reduction]: 1.654e-05 [allreduce_slice_to_reducescatter]: 1.00001e-06 [virtual_shard_identity]: 1.763e-05 [virtual_dataset]: 1.606e-05 [get_grad_eliminate_]: 1.557e-05 [virtual_output]: 1.494e-05 [merge_forward]: 8.544e-05 [cell_reuse_recompute_pass]: 3.56001e-06 [offload_activation]: 1.995e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.62e-05 [merge_recompute_call_nodes]: 2.59999e-06 [before_grad]: 2.817e-05 [set_forward_comm_id_for_comm_node_pass]: 1.041e-05 [meta_fg_expand]: 8.38999e-06 [flash_sp_send_recv_attached]: 1.53002e-06 [receive_attached]: 2.56e-06 [after_resolve]: 2.159e-05 [a_after_grad]: 2.758e-05 [renormalize]: 1.30007e-07 [add_forward_monad_depend]: 2.90002e-06 [auto_monad_grad]: 1.81e-06 [auto_monad_eliminator]: 2.185e-05 [cse]: 8.422e-05 [a_3]: 0.00010611 [py_interpret_to_execute_after_opt_a]: 2.662e-05 [slice_cell_reuse_recomputed_activation]: 2.17999e-06 [rewriter_after_opt_a]: 0.00041934 [convert_after_rewriter]: 1.688e-05 [order_py_execute_after_rewriter]: 1.199e-05 [mutable_eliminate]: 0.00081513 [opt_b]: 0.00057639, [1] [Cycle 1]: 0.00056868, [7] [b_1]: 0.00041796 [b_2]: 1.818e-05 [updatestate_depend_eliminate]: 1.349e-05 [updatestate_assign_eliminate]: 7.87e-06 [updatestate_loads_eliminate]: 7.34002e-06 [renormalize]: 3.80009e-07 [cse]: 6.107e-05 [optimize_parallel_all_gather_comm]: 3.05e-05 [overlap_param_gather]: 2.43998e-06 [cconv]: 6.071e-05 [loop_unroll]: 0.00049643 [opt_after_cconv]: 0.00021268, [1] [Cycle 1]: 0.00020525, [7] [c_1]: 8.402e-05 [parameter_eliminate]: 3.4e-06 [updatestate_depend_eliminate]: 1.37e-05 [updatestate_assign_eliminate]: 7.48999e-06 [updatestate_loads_eliminate]: 7.06001e-06 [cse]: 5.334e-05 [renormalize]: 4.10015e-07 [remove_dup_value]: 9.057e-05 [tuple_transform]: 0.00025112, [1] [Cycle 1]: 0.00024531, [4] [d_1]: 0.00016918 [none_parameter_eliminate]: 2.39999e-06 [renormalize]: 3.00002e-07 [switch_simplify]: 1.993e-05 [partial_unused_args_eliminate]: 2.34001e-06 [add_recomputation]: 0.00011701 [cse_after_recomputation]: 5.512e-05, [1] [Cycle 1]: 4.857e-05, [1] [cse]: 4.182e-05 [environ_conv]: 1.476e-05 [swap_dp_allreduce_reducescatter]: 1.292e-05 [bias_add_comm_swap]: 2.76e-06 [label_micro_interleaved_index]: 5.52001e-06 [label_fine_grained_interleaved_index]: 2.73e-06 [merge_cast_opt]: 1.66e-06 [slice_recompute_activation]: 2.25002e-06 [micro_interleaved_order_control]: 2.35002e-06 [assign_add_opt]: 1.69e-06 [ForceFp32Comm]: 8.79983e-07 [remove_cast_before_assign_add]: 1.17999e-06 [full_micro_interleaved_order_control]: 2.46e-06 [reorder_send_recv_between_fp_bp]: 2.94001e-06 [comm_op_add_attrs]: 1.07e-06 [add_comm_op_reuse_tag]: 1.05999e-06 [interleave_split_concat_branches]: 1.19e-06 [interleave_parallel_branches]: 1.27e-06 [overlap_opt_shard_in_pipeline]: 1.32999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.74998e-06 [control_data_broadcast_order]: 2.82e-05 [grouped_pairwise_exchange_alltoall]: 1.87001e-06 [offloading_packed_experts]: 8.25999e-06 [overlap_recompute_and_grad_model_parallel]: 8.28999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.24e-06 [overlap_recompute_allgather_and_fa_grad]: 1.40001e-06 [overlap_recompute_comm]: 2.38998e-06 [overlap_grad_ring_attention]: 7.3e-06 [overlap_grad_flash_sp]: 4.088e-05 [begin_end_overlap_inline]: 5.10016e-07 [split_matmul_comm_elemetwise]: 2.56998e-06 [split_layernorm_comm]: 2.04e-06 [handle_group_info]: 9.39996e-07 [symbol_engine_optimizer]: 0.00035782, [1] [Cycle 1]: 0.00035139, [6] [build]: 0.00019713 [elim_shapecalc]: 2.375e-05 [elim_not_effective]: 3.443e-05 [opt_reshape]: 1.651e-05 [fold_const_symbol]: 4.266e-05 [renormalize]: 2.70025e-07 [detach_backward]: 4.60001e-06 [pipeline_parallel_scheduler]: 1.45999e-06 [auto_monad_reorder]: 3.615e-05 [get_jit_bprop_graph]: 1.84e-06 [rewriter_after_jit_bprop_graph]: 5.12e-06 [opt_after_jit_grad]: 0.00076275 [validate]: 8.365e-05 Sums bootstrap : 0.000884s : 0.06% type_inference : 1.385442s : 98.66% event_method : 0.001473s : 0.10% auto_monad : 0.000182s : 0.01% graph_reusing : 0.000008s : 0.00% inline : 0.000002s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000035s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000051s : 0.00% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000040s : 0.00% optimize.rewriter_before_opt_a : 0.000120s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000072s : 0.01% optimize.opt_a.loop_unroll : 0.000055s : 0.00% optimize.opt_a.a_1 : 0.001991s : 0.14% optimize.opt_a.with_stream_mark : 0.000055s : 0.00% optimize.opt_a.recompute_prepare : 0.000042s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000022s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000017s : 0.00% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000522s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000063s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000010s : 0.00% optimize.opt_a.shard_inline : 0.000032s : 0.00% optimize.opt_a.merge_send_recv : 0.000030s : 0.00% optimize.opt_a.auto_parallel : 0.000030s : 0.00% optimize.opt_a.parallel : 0.000048s : 0.00% optimize.opt_a.flash_sp : 0.000015s : 0.00% optimize.opt_a.merge_comm : 0.000020s : 0.00% optimize.opt_a.allreduce_fusion : 0.000020s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000035s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000040s : 0.00% optimize.opt_a.virtual_dataset : 0.000037s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000033s : 0.00% optimize.opt_a.virtual_output : 0.000033s : 0.00% optimize.opt_a.merge_forward : 0.000098s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000040s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000073s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000059s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000022s : 0.00% optimize.opt_a.meta_fg_expand : 0.000016s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000049s : 0.00% optimize.opt_a.a_after_grad : 0.000065s : 0.00% optimize.opt_a.renormalize : 0.007214s : 0.51% optimize.opt_a.add_forward_monad_depend : 0.000021s : 0.00% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000059s : 0.00% optimize.opt_a.cse : 0.000391s : 0.03% optimize.opt_a.a_3 : 0.000242s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000027s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000419s : 0.03% optimize.convert_after_rewriter : 0.000017s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000815s : 0.06% optimize.opt_b.b_1 : 0.000418s : 0.03% optimize.opt_b.b_2 : 0.000018s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_b.renormalize : 0.000000s : 0.00% optimize.opt_b.cse : 0.000061s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000030s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000061s : 0.00% optimize.loop_unroll : 0.000496s : 0.04% optimize.opt_after_cconv.c_1 : 0.000084s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000053s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000091s : 0.01% optimize.tuple_transform.d_1 : 0.000169s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000020s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000117s : 0.01% optimize.cse_after_recomputation.cse : 0.000042s : 0.00% optimize.environ_conv : 0.000015s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000013s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000028s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000041s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000197s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000024s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000034s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000017s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000043s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000005s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000036s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000763s : 0.05% validate : 0.000084s : 0.01% Time group info: ------[substitution.] 0.000687 200 6.72% : 0.000046s : 6: substitution.arithmetic_simplify 1.16% : 0.000008s : 10: substitution.elim_not_effective 2.36% : 0.000016s : 12: substitution.float_tuple_getitem_switch 2.64% : 0.000018s : 10: substitution.fold_const_symbol 1.78% : 0.000012s : 13: substitution.graph_param_transform 41.07% : 0.000282s : 7: substitution.inline 1.42% : 0.000010s : 20: substitution.j_node_and_user_rematch 2.97% : 0.000020s : 2: substitution.less_batch_normalization 3.23% : 0.000022s : 8: substitution.minmaximum_grad 2.32% : 0.000016s : 20: substitution.remove_not_recompute_node 0.84% : 0.000006s : 4: substitution.replace_old_param 8.71% : 0.000060s : 16: substitution.tuple_list_convert_item_index_to_positive 3.80% : 0.000026s : 16: substitution.tuple_list_get_item_const_eliminator 5.36% : 0.000037s : 16: substitution.tuple_list_get_item_depend_reorder 10.71% : 0.000074s : 24: substitution.tuple_list_get_item_eliminator 4.90% : 0.000034s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.385344 2 99.67% : 1.380794s : 1: type_inference.infer 0.33% : 0.004550s : 1: type_inference.specialize ------[replace.] 0.000069 7 100.00% : 0.000069s : 7: replace.inline ------[match.] 0.000277 7 100.00% : 0.000277s : 7: match.inline ------[predicate.] 0.000531 3321 0.91% : 0.000005s : 32: predicate.accumulaten_eliminater 0.85% : 0.000004s : 13: predicate.ad_related_special_op_eliminate 0.68% : 0.000004s : 26: predicate.addn_check_dump 0.90% : 0.000005s : 32: predicate.addn_zero_filter 0.79% : 0.000004s : 32: predicate.adjust_all_reduce_mul_add 2.21% : 0.000012s : 58: predicate.arithmetic_simplify 0.95% : 0.000005s : 32: predicate.cast_eliminate 0.72% : 0.000004s : 26: predicate.check_bprop_eliminate 0.70% : 0.000004s : 26: predicate.compare_switch_simplify 0.20% : 0.000001s : 13: predicate.const_output_eliminate 0.75% : 0.000004s : 26: predicate.depend_value_elim 1.07% : 0.000006s : 32: predicate.dict_get_item_const_eliminator 1.07% : 0.000006s : 32: predicate.dict_get_item_eliminator 0.84% : 0.000004s : 32: predicate.dict_set_item_eliminator 0.92% : 0.000005s : 26: predicate.dumpgradient_eliminate 0.21% : 0.000001s : 13: predicate.elim_not_effective 0.43% : 0.000002s : 13: predicate.elim_shapecalc_of_broadcastargs 1.15% : 0.000006s : 45: predicate.environ_add_const_eliminate 1.14% : 0.000006s : 45: predicate.environ_get_add_eliminate 1.15% : 0.000006s : 45: predicate.environ_get_depend_swap 1.97% : 0.000010s : 71: predicate.environ_get_eliminate 1.12% : 0.000006s : 45: predicate.environ_get_set_eliminate 1.01% : 0.000005s : 39: predicate.exchange_switch_depend_value 1.65% : 0.000009s : 39: predicate.float_depend_g_call 0.75% : 0.000004s : 26: predicate.float_environ_get_switch 1.26% : 0.000007s : 39: predicate.float_tuple_getitem_switch 0.21% : 0.000001s : 13: predicate.fold_const_symbol 0.81% : 0.000004s : 26: predicate.get_grad_eliminate 0.24% : 0.000001s : 13: predicate.graph_param_transform 0.69% : 0.000004s : 26: predicate.incorporate_call 0.62% : 0.000003s : 26: predicate.incorporate_call_switch 5.56% : 0.000030s : 149: predicate.inline 0.90% : 0.000005s : 26: predicate.inline_without_move 0.35% : 0.000002s : 26: predicate.j_node_and_user_rematch 1.06% : 0.000006s : 26: predicate.less_batch_normalization 1.77% : 0.000009s : 58: predicate.list_to_tuple_eliminator_ 2.31% : 0.000012s : 90: predicate.load_eliminater 0.89% : 0.000005s : 13: predicate.loop_unroll_after_grad 1.46% : 0.000008s : 55: predicate.loop_unroll_before_grad 1.72% : 0.000009s : 58: predicate.make_slice_get_slice_eliminator 0.72% : 0.000004s : 26: predicate.merge_addn 0.77% : 0.000004s : 26: predicate.micro_step_allgather_replace 0.70% : 0.000004s : 26: predicate.mini_step_allgather_replace 0.97% : 0.000005s : 32: predicate.minmaximum_grad 1.17% : 0.000006s : 13: predicate.mutable_eliminate 0.41% : 0.000002s : 13: predicate.opt_reshape 0.44% : 0.000002s : 13: predicate.parallel_virtual_node 1.57% : 0.000008s : 39: predicate.partial_defer_inline 1.26% : 0.000007s : 45: predicate.partial_eliminate 0.92% : 0.000005s : 32: predicate.print_const_string_wrapper 0.80% : 0.000004s : 26: predicate.reduce_all_const_elim 1.29% : 0.000007s : 32: predicate.reduce_eliminate 2.36% : 0.000013s : 90: predicate.redundant_stop_gradient_eliminater 0.50% : 0.000003s : 26: predicate.remove_not_recompute_node 1.12% : 0.000006s : 58: predicate.replace_applicator 0.45% : 0.000002s : 26: predicate.replace_old_param 0.27% : 0.000001s : 13: predicate.reset_defer_inline 0.88% : 0.000005s : 32: predicate.reshape_eliminate 0.74% : 0.000004s : 26: predicate.row_tensor_add_zeros_like 0.47% : 0.000002s : 13: predicate.row_tensor_eliminate 1.06% : 0.000006s : 26: predicate.same_eliminate 0.48% : 0.000003s : 26: predicate.set_cell_output_no_recompute 0.92% : 0.000005s : 26: predicate.shard_identity_eliminate 0.85% : 0.000004s : 26: predicate.special_op_eliminate 0.81% : 0.000004s : 26: predicate.specialize_transform 1.09% : 0.000006s : 26: predicate.split_environ_get_set_with_tuple_value 0.88% : 0.000005s : 26: predicate.stack_unstack_eliminate 0.43% : 0.000002s : 13: predicate.switch_call_monad_eliminater 1.15% : 0.000006s : 39: predicate.switch_defer_inline 1.79% : 0.000009s : 65: predicate.switch_layer_defer_inline 3.96% : 0.000021s : 133: predicate.switch_simplify 0.85% : 0.000005s : 32: predicate.tile_eliminate 0.83% : 0.000004s : 32: predicate.transpose_eliminate 1.89% : 0.000010s : 58: predicate.tuple_list_convert_item_index_to_positive 1.88% : 0.000010s : 58: predicate.tuple_list_get_item_const_eliminator 1.67% : 0.000009s : 58: predicate.tuple_list_get_item_depend_reorder 3.28% : 0.000017s : 84: predicate.tuple_list_get_item_eliminator 1.82% : 0.000010s : 58: predicate.tuple_list_get_set_item_eliminator 2.67% : 0.000014s : 84: predicate.tuple_list_set_item_eliminator 1.71% : 0.000009s : 58: predicate.tuple_to_list_eliminator_ 2.22% : 0.000012s : 90: predicate.updatestate_pure_node_eliminater 3.15% : 0.000017s : 116: predicate.updatestate_useless_node_eliminater 0.42% : 0.000002s : 13: predicate.value_based_eliminate 0.80% : 0.000004s : 26: predicate.virtual_dataset_eliminate 0.79% : 0.000004s : 26: predicate.virtual_output_eliminate 0.36% : 0.000002s : 13: predicate.virtual_view_grad_eliminate 0.47% : 0.000003s : 13: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.006846 38 66.81% : 0.004574s : 29: func_graph_cloner_run.FuncGraphClonerGraph 33.19% : 0.002272s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.602245 192 0.00% : 0.000003s : 1: ForceFp32Comm 5.28% : 0.084536s : 1: add_attr 5.27% : 0.084516s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000122s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000194s : 1: auto_monad 0.00% : 0.000040s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.06% : 0.000973s : 1: bootstrap 0.00% : 0.000067s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000032s : 1: control_data_broadcast_order 0.00% : 0.000021s : 1: convert_after_rewriter 0.00% : 0.000058s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000019s : 1: environ_conv 0.09% : 0.001498s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000014s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.03% : 0.000505s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.05% : 0.000825s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000028s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000035s : 1: opt.transform.mutable_eliminate 0.21% : 0.003293s : 78: opt.transform.opt_a 0.01% : 0.000083s : 1: opt.transform.opt_after_cconv 0.00% : 0.000060s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000403s : 28: opt.transform.opt_b 0.01% : 0.000186s : 2: opt.transform.opt_trans_graph 0.01% : 0.000113s : 4: opt.transform.symbol_engine_opt 0.76% : 0.012257s : 1: opt_a 0.01% : 0.000216s : 1: opt_after_cconv 0.05% : 0.000774s : 1: opt_after_jit_grad 0.04% : 0.000580s : 1: opt_b 1.02% : 0.016395s : 1: optimize 0.00% : 0.000034s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.00% : 0.000045s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.00% : 0.000056s : 1: pre_auto_parallel 0.00% : 0.000044s : 1: py_interpret_to_execute 0.00% : 0.000031s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000096s : 1: remove_dup_value 0.26% : 0.004215s : 1: renormalize.infer 0.19% : 0.002983s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.000425s : 1: rewriter_after_opt_a 0.01% : 0.000125s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000016s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000361s : 1: symbol_engine_optimizer 0.02% : 0.000255s : 1: tuple_transform 86.47% : 1.385467s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[True-True-bfloat16--1-shape2] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[True-True-bfloat16--1-shape2],max_mem:106.0M [WARNING] ME(169503:281473018953520,MainProcess):2026-01-29-17:42:47.421.86 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 1.54397, [21] [bootstrap]: 0.00084037 [type_inference]: 1.41382 [event_method]: 0.00101726 [auto_monad]: 0.00039209 [graph_reusing]: 7.48999e-06 [inline]: 2.73e-06 [add_attr]: 0.00537242, [1] [add_attr_with_inline]: 0.0053571, [1] [Cycle 1]: 7.482e-05, [2] [tag_attr]: 3.143e-05 [meta_addattr_fg_expand]: 7.36001e-06 [parallel-infer-symbol]: 5.29e-06 [pre_auto_parallel]: 4.633e-05 [insert-virtual-dataset]: 3.89002e-06 [parallel-infer-symbol-second]: 8.29983e-07 [dataset_repeat_opt]: 2.37999e-06 [pipeline_split]: 2.53998e-06 [optimize]: 0.121509, [53] [py_interpret_to_execute]: 7.468e-05 [rewriter_before_opt_a]: 0.00012058 [opt_a]: 0.117461, [2] [Cycle 1]: 0.115683, [45] [expand_dump_flag]: 3.97e-06 [switch_simplify]: 5.378e-05 [loop_unroll]: 3.895e-05 [a_1]: 0.00247107 [with_stream_mark]: 2.872e-05 [recompute_prepare]: 2.287e-05 [updatestate_depend_eliminate]: 1.059e-05 [updatestate_assign_eliminate]: 8.46002e-06 [updatestate_loads_eliminate]: 8.32e-06 [parameter_eliminate]: 2.17999e-06 [a_2]: 0.00027621 [accelerated_algorithm]: 4.177e-05 [shard]: 3.18e-06 [meta_shard_fg_expand]: 5.18002e-06 [shard_inline]: 1.886e-05 [merge_send_recv]: 1.58e-05 [auto_parallel]: 1.666e-05 [parallel]: 3.388e-05 [flash_sp]: 1.128e-05 [merge_comm]: 1.063e-05 [allreduce_fusion]: 9.61998e-06 [matmul_add_comm_reduction]: 1.851e-05 [allreduce_slice_to_reducescatter]: 1.14e-06 [virtual_shard_identity]: 2.033e-05 [virtual_dataset]: 1.759e-05 [get_grad_eliminate_]: 1.741e-05 [virtual_output]: 1.944e-05 [merge_forward]: 1.076e-05 [cell_reuse_recompute_pass]: 1.69e-06 [offload_activation]: 1.788e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.93e-05 [merge_recompute_call_nodes]: 1.60001e-06 [before_grad]: 5.399e-05 [set_forward_comm_id_for_comm_node_pass]: 1.174e-05 [meta_fg_expand]: 8.03999e-06 [flash_sp_send_recv_attached]: 6.17001e-06 [receive_attached]: 2.46e-06 [after_resolve]: 2.68e-05 [a_after_grad]: 3.38e-05 [renormalize]: 0.111263 [add_forward_monad_depend]: 1.879e-05 [auto_monad_grad]: 2.78e-06 [auto_monad_eliminator]: 0.00013128 [cse]: 0.00034422 [a_3]: 0.00013659 [Cycle 2]: 0.00176308, [45] [expand_dump_flag]: 2.71e-06 [switch_simplify]: 1.943e-05 [loop_unroll]: 1.687e-05 [a_1]: 0.00056139 [with_stream_mark]: 2.86e-05 [recompute_prepare]: 1.865e-05 [updatestate_depend_eliminate]: 1.768e-05 [updatestate_assign_eliminate]: 9.46e-06 [updatestate_loads_eliminate]: 8.47998e-06 [parameter_eliminate]: 2.53e-06 [a_2]: 0.00029878 [accelerated_algorithm]: 2.218e-05 [shard]: 2.29999e-06 [meta_shard_fg_expand]: 4.43001e-06 [shard_inline]: 1.606e-05 [merge_send_recv]: 1.549e-05 [auto_parallel]: 2.216e-05 [parallel]: 9.40001e-06 [flash_sp]: 4.56002e-06 [merge_comm]: 9.79999e-06 [allreduce_fusion]: 9.82999e-06 [matmul_add_comm_reduction]: 1.818e-05 [allreduce_slice_to_reducescatter]: 1.17999e-06 [virtual_shard_identity]: 1.799e-05 [virtual_dataset]: 1.591e-05 [get_grad_eliminate_]: 1.573e-05 [virtual_output]: 1.503e-05 [merge_forward]: 9.86e-06 [cell_reuse_recompute_pass]: 3.28e-06 [offload_activation]: 1.794e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.165e-05 [merge_recompute_call_nodes]: 1.91998e-06 [before_grad]: 2.89e-05 [set_forward_comm_id_for_comm_node_pass]: 1.011e-05 [meta_fg_expand]: 7.68001e-06 [flash_sp_send_recv_attached]: 2.09e-06 [receive_attached]: 2.40002e-06 [after_resolve]: 2.092e-05 [a_after_grad]: 2.621e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 2.06e-06 [auto_monad_grad]: 1.34e-06 [auto_monad_eliminator]: 2.026e-05 [cse]: 4.878e-05 [a_3]: 0.00010268 [py_interpret_to_execute_after_opt_a]: 2.815e-05 [slice_cell_reuse_recomputed_activation]: 2.19001e-06 [rewriter_after_opt_a]: 0.00040826 [convert_after_rewriter]: 1.704e-05 [order_py_execute_after_rewriter]: 1.151e-05 [mutable_eliminate]: 0.00076131 [opt_b]: 0.00056715, [1] [Cycle 1]: 0.00055936, [7] [b_1]: 0.00041207 [b_2]: 1.863e-05 [updatestate_depend_eliminate]: 1.28e-05 [updatestate_assign_eliminate]: 7.9e-06 [updatestate_loads_eliminate]: 7.48999e-06 [renormalize]: 6.69999e-07 [cse]: 5.807e-05 [optimize_parallel_all_gather_comm]: 3.077e-05 [overlap_param_gather]: 2.11998e-06 [cconv]: 3.249e-05 [loop_unroll]: 0.00049481 [opt_after_cconv]: 0.00020919, [1] [Cycle 1]: 0.00020234, [7] [c_1]: 8.323e-05 [parameter_eliminate]: 3.31001e-06 [updatestate_depend_eliminate]: 1.321e-05 [updatestate_assign_eliminate]: 7.65e-06 [updatestate_loads_eliminate]: 6.95998e-06 [cse]: 5.174e-05 [renormalize]: 4.80009e-07 [remove_dup_value]: 7.453e-05 [tuple_transform]: 0.00021927, [1] [Cycle 1]: 0.00021351, [4] [d_1]: 0.00017268 [none_parameter_eliminate]: 2.22001e-06 [renormalize]: 1.90019e-07 [switch_simplify]: 1.73e-05 [partial_unused_args_eliminate]: 1.91e-06 [add_recomputation]: 0.00011402 [cse_after_recomputation]: 5.319e-05, [1] [Cycle 1]: 4.727e-05, [1] [cse]: 4.028e-05 [environ_conv]: 1.386e-05 [swap_dp_allreduce_reducescatter]: 1.287e-05 [bias_add_comm_swap]: 2.76e-06 [label_micro_interleaved_index]: 4.17e-06 [label_fine_grained_interleaved_index]: 2.67001e-06 [merge_cast_opt]: 1.63002e-06 [slice_recompute_activation]: 2.43e-06 [micro_interleaved_order_control]: 2.73e-06 [assign_add_opt]: 1.69998e-06 [ForceFp32Comm]: 8.89995e-07 [remove_cast_before_assign_add]: 1.07e-06 [full_micro_interleaved_order_control]: 3.08e-06 [reorder_send_recv_between_fp_bp]: 2.93e-06 [comm_op_add_attrs]: 1.37e-06 [add_comm_op_reuse_tag]: 9.89996e-07 [interleave_split_concat_branches]: 1.17e-06 [interleave_parallel_branches]: 1.04e-06 [overlap_opt_shard_in_pipeline]: 4.56002e-06 [overlap_opt_shard_grad_in_pipeline]: 2.14e-06 [control_data_broadcast_order]: 2.86e-05 [grouped_pairwise_exchange_alltoall]: 1.66e-06 [offloading_packed_experts]: 7.85998e-06 [overlap_recompute_and_grad_model_parallel]: 8.01001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.20001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.39e-06 [overlap_recompute_comm]: 2.29999e-06 [overlap_grad_ring_attention]: 7.21001e-06 [overlap_grad_flash_sp]: 4.184e-05 [begin_end_overlap_inline]: 5.10016e-07 [split_matmul_comm_elemetwise]: 2.39999e-06 [split_layernorm_comm]: 1.70001e-06 [handle_group_info]: 1.49998e-06 [symbol_engine_optimizer]: 0.00038032, [1] [Cycle 1]: 0.00037452, [6] [build]: 0.00021017 [elim_shapecalc]: 2.527e-05 [elim_not_effective]: 3.686e-05 [opt_reshape]: 1.783e-05 [fold_const_symbol]: 4.548e-05 [renormalize]: 2.3999e-07 [detach_backward]: 3.06001e-06 [pipeline_parallel_scheduler]: 1.66e-06 [auto_monad_reorder]: 3.536e-05 [get_jit_bprop_graph]: 1.96e-06 [rewriter_after_jit_bprop_graph]: 4.32e-06 [opt_after_jit_grad]: 0.00055227 [validate]: 8.259e-05 Sums bootstrap : 0.000840s : 0.05% type_inference : 1.413820s : 91.97% event_method : 0.001017s : 0.07% auto_monad : 0.000392s : 0.03% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000031s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000046s : 0.00% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000075s : 0.00% optimize.rewriter_before_opt_a : 0.000121s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000073s : 0.00% optimize.opt_a.loop_unroll : 0.000056s : 0.00% optimize.opt_a.a_1 : 0.003032s : 0.20% optimize.opt_a.with_stream_mark : 0.000057s : 0.00% optimize.opt_a.recompute_prepare : 0.000042s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000028s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000018s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000017s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000575s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000064s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000010s : 0.00% optimize.opt_a.shard_inline : 0.000035s : 0.00% optimize.opt_a.merge_send_recv : 0.000031s : 0.00% optimize.opt_a.auto_parallel : 0.000039s : 0.00% optimize.opt_a.parallel : 0.000043s : 0.00% optimize.opt_a.flash_sp : 0.000016s : 0.00% optimize.opt_a.merge_comm : 0.000020s : 0.00% optimize.opt_a.allreduce_fusion : 0.000019s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000037s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000038s : 0.00% optimize.opt_a.virtual_dataset : 0.000033s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000033s : 0.00% optimize.opt_a.virtual_output : 0.000034s : 0.00% optimize.opt_a.merge_forward : 0.000021s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000036s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000071s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000083s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000022s : 0.00% optimize.opt_a.meta_fg_expand : 0.000016s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000048s : 0.00% optimize.opt_a.a_after_grad : 0.000060s : 0.00% optimize.opt_a.renormalize : 0.111264s : 7.24% optimize.opt_a.add_forward_monad_depend : 0.000021s : 0.00% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000152s : 0.01% optimize.opt_a.cse : 0.000393s : 0.03% optimize.opt_a.a_3 : 0.000239s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000028s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000408s : 0.03% optimize.convert_after_rewriter : 0.000017s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000761s : 0.05% optimize.opt_b.b_1 : 0.000412s : 0.03% optimize.opt_b.b_2 : 0.000019s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000058s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000031s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000032s : 0.00% optimize.loop_unroll : 0.000495s : 0.03% optimize.opt_after_cconv.c_1 : 0.000083s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.cse : 0.000052s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000075s : 0.00% optimize.tuple_transform.d_1 : 0.000173s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000017s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000114s : 0.01% optimize.cse_after_recomputation.cse : 0.000040s : 0.00% optimize.environ_conv : 0.000014s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000013s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000004s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000005s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000029s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000042s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000210s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000025s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000037s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000018s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000045s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000035s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000004s : 0.00% opt_after_jit_grad : 0.000552s : 0.04% validate : 0.000083s : 0.01% Time group info: ------[substitution.] 0.000705 200 7.03% : 0.000050s : 6: substitution.arithmetic_simplify 1.39% : 0.000010s : 10: substitution.elim_not_effective 2.34% : 0.000016s : 12: substitution.float_tuple_getitem_switch 2.62% : 0.000018s : 10: substitution.fold_const_symbol 1.75% : 0.000012s : 13: substitution.graph_param_transform 42.63% : 0.000300s : 7: substitution.inline 1.44% : 0.000010s : 20: substitution.j_node_and_user_rematch 2.90% : 0.000020s : 2: substitution.less_batch_normalization 2.41% : 0.000017s : 8: substitution.minmaximum_grad 2.20% : 0.000016s : 20: substitution.remove_not_recompute_node 0.95% : 0.000007s : 4: substitution.replace_old_param 7.46% : 0.000053s : 16: substitution.tuple_list_convert_item_index_to_positive 4.20% : 0.000030s : 16: substitution.tuple_list_get_item_const_eliminator 4.90% : 0.000035s : 16: substitution.tuple_list_get_item_depend_reorder 10.75% : 0.000076s : 24: substitution.tuple_list_get_item_eliminator 5.03% : 0.000035s : 16: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.413708 2 92.66% : 1.309970s : 1: type_inference.infer 7.34% : 0.103738s : 1: type_inference.specialize ------[replace.] 0.000069 7 100.00% : 0.000069s : 7: replace.inline ------[match.] 0.000295 7 100.00% : 0.000295s : 7: match.inline ------[predicate.] 0.000538 3321 1.00% : 0.000005s : 32: predicate.accumulaten_eliminater 0.84% : 0.000005s : 13: predicate.ad_related_special_op_eliminate 0.70% : 0.000004s : 26: predicate.addn_check_dump 0.96% : 0.000005s : 32: predicate.addn_zero_filter 0.87% : 0.000005s : 32: predicate.adjust_all_reduce_mul_add 2.52% : 0.000014s : 58: predicate.arithmetic_simplify 0.95% : 0.000005s : 32: predicate.cast_eliminate 0.70% : 0.000004s : 26: predicate.check_bprop_eliminate 0.71% : 0.000004s : 26: predicate.compare_switch_simplify 0.20% : 0.000001s : 13: predicate.const_output_eliminate 0.70% : 0.000004s : 26: predicate.depend_value_elim 0.91% : 0.000005s : 32: predicate.dict_get_item_const_eliminator 1.05% : 0.000006s : 32: predicate.dict_get_item_eliminator 0.81% : 0.000004s : 32: predicate.dict_set_item_eliminator 0.97% : 0.000005s : 26: predicate.dumpgradient_eliminate 0.21% : 0.000001s : 13: predicate.elim_not_effective 0.49% : 0.000003s : 13: predicate.elim_shapecalc_of_broadcastargs 1.17% : 0.000006s : 45: predicate.environ_add_const_eliminate 1.31% : 0.000007s : 45: predicate.environ_get_add_eliminate 1.17% : 0.000006s : 45: predicate.environ_get_depend_swap 1.93% : 0.000010s : 71: predicate.environ_get_eliminate 1.18% : 0.000006s : 45: predicate.environ_get_set_eliminate 1.00% : 0.000005s : 39: predicate.exchange_switch_depend_value 1.57% : 0.000008s : 39: predicate.float_depend_g_call 0.70% : 0.000004s : 26: predicate.float_environ_get_switch 1.39% : 0.000007s : 39: predicate.float_tuple_getitem_switch 0.22% : 0.000001s : 13: predicate.fold_const_symbol 0.78% : 0.000004s : 26: predicate.get_grad_eliminate 0.26% : 0.000001s : 13: predicate.graph_param_transform 0.69% : 0.000004s : 26: predicate.incorporate_call 0.65% : 0.000003s : 26: predicate.incorporate_call_switch 5.63% : 0.000030s : 149: predicate.inline 1.03% : 0.000006s : 26: predicate.inline_without_move 0.37% : 0.000002s : 26: predicate.j_node_and_user_rematch 0.90% : 0.000005s : 26: predicate.less_batch_normalization 1.69% : 0.000009s : 58: predicate.list_to_tuple_eliminator_ 2.30% : 0.000012s : 90: predicate.load_eliminater 0.88% : 0.000005s : 13: predicate.loop_unroll_after_grad 1.47% : 0.000008s : 55: predicate.loop_unroll_before_grad 1.70% : 0.000009s : 58: predicate.make_slice_get_slice_eliminator 0.70% : 0.000004s : 26: predicate.merge_addn 0.70% : 0.000004s : 26: predicate.micro_step_allgather_replace 0.74% : 0.000004s : 26: predicate.mini_step_allgather_replace 0.87% : 0.000005s : 32: predicate.minmaximum_grad 0.83% : 0.000004s : 13: predicate.mutable_eliminate 0.46% : 0.000002s : 13: predicate.opt_reshape 0.46% : 0.000002s : 13: predicate.parallel_virtual_node 1.58% : 0.000008s : 39: predicate.partial_defer_inline 1.24% : 0.000007s : 45: predicate.partial_eliminate 0.92% : 0.000005s : 32: predicate.print_const_string_wrapper 0.72% : 0.000004s : 26: predicate.reduce_all_const_elim 1.31% : 0.000007s : 32: predicate.reduce_eliminate 2.35% : 0.000013s : 90: predicate.redundant_stop_gradient_eliminater 0.48% : 0.000003s : 26: predicate.remove_not_recompute_node 1.08% : 0.000006s : 58: predicate.replace_applicator 0.40% : 0.000002s : 26: predicate.replace_old_param 0.25% : 0.000001s : 13: predicate.reset_defer_inline 1.04% : 0.000006s : 32: predicate.reshape_eliminate 0.72% : 0.000004s : 26: predicate.row_tensor_add_zeros_like 0.41% : 0.000002s : 13: predicate.row_tensor_eliminate 0.98% : 0.000005s : 26: predicate.same_eliminate 0.40% : 0.000002s : 26: predicate.set_cell_output_no_recompute 0.86% : 0.000005s : 26: predicate.shard_identity_eliminate 0.77% : 0.000004s : 26: predicate.special_op_eliminate 0.82% : 0.000004s : 26: predicate.specialize_transform 0.90% : 0.000005s : 26: predicate.split_environ_get_set_with_tuple_value 0.90% : 0.000005s : 26: predicate.stack_unstack_eliminate 0.41% : 0.000002s : 13: predicate.switch_call_monad_eliminater 1.13% : 0.000006s : 39: predicate.switch_defer_inline 1.74% : 0.000009s : 65: predicate.switch_layer_defer_inline 3.92% : 0.000021s : 133: predicate.switch_simplify 0.91% : 0.000005s : 32: predicate.tile_eliminate 0.98% : 0.000005s : 32: predicate.transpose_eliminate 1.90% : 0.000010s : 58: predicate.tuple_list_convert_item_index_to_positive 1.91% : 0.000010s : 58: predicate.tuple_list_get_item_const_eliminator 1.69% : 0.000009s : 58: predicate.tuple_list_get_item_depend_reorder 3.29% : 0.000018s : 84: predicate.tuple_list_get_item_eliminator 1.81% : 0.000010s : 58: predicate.tuple_list_get_set_item_eliminator 2.52% : 0.000014s : 84: predicate.tuple_list_set_item_eliminator 2.04% : 0.000011s : 58: predicate.tuple_to_list_eliminator_ 2.26% : 0.000012s : 90: predicate.updatestate_pure_node_eliminater 3.28% : 0.000018s : 116: predicate.updatestate_useless_node_eliminater 0.47% : 0.000003s : 13: predicate.value_based_eliminate 0.75% : 0.000004s : 26: predicate.virtual_dataset_eliminate 0.75% : 0.000004s : 26: predicate.virtual_output_eliminate 0.37% : 0.000002s : 13: predicate.virtual_view_grad_eliminate 0.45% : 0.000002s : 13: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.007475 38 63.33% : 0.004734s : 29: func_graph_cloner_run.FuncGraphClonerGraph 36.67% : 0.002741s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.787170 192 0.00% : 0.000003s : 1: ForceFp32Comm 0.30% : 0.005378s : 1: add_attr 0.30% : 0.005361s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.01% : 0.000119s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.02% : 0.000407s : 1: auto_monad 0.00% : 0.000039s : 1: auto_monad_reorder 0.00% : 0.000016s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.05% : 0.000940s : 1: bootstrap 0.00% : 0.000036s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000032s : 1: control_data_broadcast_order 0.00% : 0.000021s : 1: convert_after_rewriter 0.00% : 0.000056s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000018s : 1: environ_conv 0.06% : 0.001036s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000007s : 1: label_micro_interleaved_index 0.03% : 0.000504s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.04% : 0.000770s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000028s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000029s : 1: opt.transform.mutable_eliminate 0.24% : 0.004374s : 78: opt.transform.opt_a 0.00% : 0.000082s : 1: opt.transform.opt_after_cconv 0.00% : 0.000058s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000398s : 28: opt.transform.opt_b 0.01% : 0.000187s : 2: opt.transform.opt_trans_graph 0.01% : 0.000121s : 4: opt.transform.symbol_engine_opt 6.57% : 0.117465s : 1: opt_a 0.01% : 0.000212s : 1: opt_after_cconv 0.03% : 0.000562s : 1: opt_after_jit_grad 0.03% : 0.000571s : 1: opt_b 6.80% : 0.121516s : 1: optimize 0.00% : 0.000035s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.00% : 0.000045s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000007s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000051s : 1: pre_auto_parallel 0.00% : 0.000083s : 1: py_interpret_to_execute 0.00% : 0.000032s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000079s : 1: remove_dup_value 6.05% : 0.108119s : 1: renormalize.infer 0.17% : 0.003123s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000007s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000415s : 1: rewriter_after_opt_a 0.01% : 0.000125s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000016s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000384s : 1: symbol_engine_optimizer 0.01% : 0.000224s : 1: tuple_transform 79.11% : 1.413848s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dynamic_quant_bfloat16[True-True-bfloat16--1-shape3] tests/st/infer/ops/test_internal_ops/test_swiglu_dyn_quant.py::test_swiglu_dynamic_quant_bfloat16[True-True-bfloat16--1-shape3],max_mem:100.0M =============================== warnings summary =============================== ../../../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/classifier/transdata/transdata_classifier.py:222 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/classifier/transdata/transdata_classifier.py:222: DeprecationWarning: invalid escape sequence \B """ ../../../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:143 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:143: DeprecationWarning: invalid escape sequence \c """ ../../../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:170 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:170: DeprecationWarning: invalid escape sequence \c """ ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for type is zero. setattr(self, word, getattr(machar, word).flat[0]) ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for type is zero. setattr(self, word, getattr(machar, word).flat[0]) ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2.py:57 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2.py:57: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad.py:56 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad.py:56: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2_grad") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad_reduce.py:48 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad_reduce.py:48: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2_grad_reduce") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul.py:51 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul.py:51: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:51 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:51: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul_grad") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:143 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:143: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul_grad_reduce") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad.py:92 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad.py:92: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer_grad_d") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad_reduce.py:49 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad_reduce.py:49: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer_grad_d_reduce") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad.py:91 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad.py:91: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel_grad_d") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad_reduce.py:48 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad_reduce.py:48: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel_grad_d_reduce") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel.py:52 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel.py:52: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_perchannel") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel_grad.py:81 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel_grad.py:81: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_perchannel_grad") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer.py:54 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer.py:54: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_per_layer") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer_grad.py:81 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer_grad.py:81: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_per_layer_grad") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perchannel.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perchannel.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("minmax_update_perchannel") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perlayer.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perlayer.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("minmax_update_perlayer") -- Docs: https://docs.pytest.org/en/stable/warnings.html ================= 16 passed, 25 warnings in 356.07s (0:05:56) ==================