==================================================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_006/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 3 items test_swiglu_v2.py [WARNING] ME(157404:281473330929456,MainProcess):2026-01-29-17:37:20.205.152 [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 = 0.881465, [21] [bootstrap]: 0.0006674 [type_inference]: 0.844859 [event_method]: 2.721e-05 [auto_monad]: 0.00106345 [graph_reusing]: 9.22001e-06 [inline]: 3.16001e-06 [add_attr]: 0.00826896, [1] [add_attr_with_inline]: 0.00825002, [1] [Cycle 1]: 0.00011428, [2] [tag_attr]: 2.737e-05 [meta_addattr_fg_expand]: 5.97001e-06 [parallel-infer-symbol]: 4.2e-06 [pre_auto_parallel]: 4.656e-05 [insert-virtual-dataset]: 2.69999e-06 [parallel-infer-symbol-second]: 1.69e-06 [dataset_repeat_opt]: 1.96e-06 [pipeline_split]: 1.76e-06 [optimize]: 0.0253452, [53] [py_interpret_to_execute]: 3.581e-05 [rewriter_before_opt_a]: 0.00010569 [opt_a]: 0.0214268, [2] [Cycle 1]: 0.0201659, [45] [expand_dump_flag]: 4.2e-06 [switch_simplify]: 4.328e-05 [loop_unroll]: 2.699e-05 [a_1]: 0.00084223 [with_stream_mark]: 2.947e-05 [recompute_prepare]: 1.903e-05 [updatestate_depend_eliminate]: 8.60001e-06 [updatestate_assign_eliminate]: 6.76e-06 [updatestate_loads_eliminate]: 6.73e-06 [parameter_eliminate]: 2.59999e-06 [a_2]: 0.00018723 [accelerated_algorithm]: 1.46e-05 [shard]: 2.35002e-06 [meta_shard_fg_expand]: 4.11001e-06 [shard_inline]: 1.196e-05 [merge_send_recv]: 1.405e-05 [auto_parallel]: 1.466e-05 [parallel]: 5.895e-05 [flash_sp]: 2.398e-05 [merge_comm]: 8.84998e-06 [allreduce_fusion]: 6.84999e-06 [matmul_add_comm_reduction]: 1.601e-05 [allreduce_slice_to_reducescatter]: 1.29e-06 [virtual_shard_identity]: 1.947e-05 [virtual_dataset]: 1.174e-05 [get_grad_eliminate_]: 1.147e-05 [virtual_output]: 1.172e-05 [merge_forward]: 9.05001e-06 [cell_reuse_recompute_pass]: 2.26e-06 [offload_activation]: 1.743e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.808e-05 [merge_recompute_call_nodes]: 1.60999e-06 [before_grad]: 2.055e-05 [set_forward_comm_id_for_comm_node_pass]: 7.70998e-06 [meta_fg_expand]: 5.08002e-06 [flash_sp_send_recv_attached]: 3.66999e-06 [receive_attached]: 2.26e-06 [after_resolve]: 1.708e-05 [a_after_grad]: 1.858e-05 [renormalize]: 0.0179043 [add_forward_monad_depend]: 1.259e-05 [auto_monad_grad]: 3.46001e-06 [auto_monad_eliminator]: 3.52e-05 [cse]: 0.00017931 [a_3]: 0.00010165 [Cycle 2]: 0.0012442, [45] [expand_dump_flag]: 3.13e-06 [switch_simplify]: 1.502e-05 [loop_unroll]: 1.156e-05 [a_1]: 0.00033598 [with_stream_mark]: 2.612e-05 [recompute_prepare]: 1.313e-05 [updatestate_depend_eliminate]: 8.28999e-06 [updatestate_assign_eliminate]: 6.54001e-06 [updatestate_loads_eliminate]: 5.61e-06 [parameter_eliminate]: 2.66e-06 [a_2]: 0.00015874 [accelerated_algorithm]: 1.172e-05 [shard]: 3.04999e-06 [meta_shard_fg_expand]: 3.33e-06 [shard_inline]: 1.078e-05 [merge_send_recv]: 1.433e-05 [auto_parallel]: 1.474e-05 [parallel]: 1.047e-05 [flash_sp]: 4.44002e-06 [merge_comm]: 6.53e-06 [allreduce_fusion]: 6.43e-06 [matmul_add_comm_reduction]: 1.4e-05 [allreduce_slice_to_reducescatter]: 9.30013e-07 [virtual_shard_identity]: 1.431e-05 [virtual_dataset]: 1.12e-05 [get_grad_eliminate_]: 1.047e-05 [virtual_output]: 1.006e-05 [merge_forward]: 7.48999e-06 [cell_reuse_recompute_pass]: 3.39001e-06 [offload_activation]: 1.576e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.264e-05 [merge_recompute_call_nodes]: 1.60999e-06 [before_grad]: 1.935e-05 [set_forward_comm_id_for_comm_node_pass]: 7.58999e-06 [meta_fg_expand]: 5.54e-06 [flash_sp_send_recv_attached]: 2.53e-06 [receive_attached]: 2.71999e-06 [after_resolve]: 1.772e-05 [a_after_grad]: 1.684e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 3.08e-06 [auto_monad_grad]: 3.19001e-06 [auto_monad_eliminator]: 2.107e-05 [cse]: 6.072e-05 [a_3]: 7.167e-05 [py_interpret_to_execute_after_opt_a]: 2.648e-05 [slice_cell_reuse_recomputed_activation]: 2.56998e-06 [rewriter_after_opt_a]: 0.00040179 [convert_after_rewriter]: 1.608e-05 [order_py_execute_after_rewriter]: 8.74e-06 [mutable_eliminate]: 0.00078626 [opt_b]: 0.00047606, [1] [Cycle 1]: 0.00046647, [7] [b_1]: 0.00030383 [b_2]: 1.465e-05 [updatestate_depend_eliminate]: 1.376e-05 [updatestate_assign_eliminate]: 5.59998e-06 [updatestate_loads_eliminate]: 5.39e-06 [renormalize]: 9.70002e-07 [cse]: 7.795e-05 [optimize_parallel_all_gather_comm]: 3.186e-05 [overlap_param_gather]: 2.61999e-06 [cconv]: 4.151e-05 [loop_unroll]: 0.00057071 [opt_after_cconv]: 0.00018029, [1] [Cycle 1]: 0.00017241, [7] [c_1]: 5.815e-05 [parameter_eliminate]: 6.33998e-06 [updatestate_depend_eliminate]: 1.062e-05 [updatestate_assign_eliminate]: 5.10001e-06 [updatestate_loads_eliminate]: 5.03002e-06 [cse]: 4.902e-05 [renormalize]: 5.39992e-07 [remove_dup_value]: 6.314e-05 [tuple_transform]: 0.00016552, [1] [Cycle 1]: 0.00015978, [4] [d_1]: 0.00012228 [none_parameter_eliminate]: 2.66999e-06 [renormalize]: 3.00002e-07 [switch_simplify]: 1.244e-05 [partial_unused_args_eliminate]: 2.02001e-06 [add_recomputation]: 0.00010613 [cse_after_recomputation]: 4.804e-05, [1] [Cycle 1]: 4.307e-05, [1] [cse]: 3.563e-05 [environ_conv]: 2.887e-05 [swap_dp_allreduce_reducescatter]: 1.081e-05 [bias_add_comm_swap]: 2.94001e-06 [label_micro_interleaved_index]: 7.43e-06 [label_fine_grained_interleaved_index]: 2.79001e-06 [merge_cast_opt]: 1.29998e-06 [slice_recompute_activation]: 2.18998e-06 [micro_interleaved_order_control]: 2.49999e-06 [assign_add_opt]: 1.44e-06 [ForceFp32Comm]: 9.20001e-07 [remove_cast_before_assign_add]: 1.09e-06 [full_micro_interleaved_order_control]: 2.71e-06 [reorder_send_recv_between_fp_bp]: 2.58e-06 [comm_op_add_attrs]: 1.04998e-06 [add_comm_op_reuse_tag]: 1.09e-06 [interleave_split_concat_branches]: 1.29998e-06 [interleave_parallel_branches]: 1.34e-06 [overlap_opt_shard_in_pipeline]: 2.472e-05 [overlap_opt_shard_grad_in_pipeline]: 2.01998e-06 [control_data_broadcast_order]: 2.435e-05 [grouped_pairwise_exchange_alltoall]: 1.72999e-06 [offloading_packed_experts]: 6.06e-06 [overlap_recompute_and_grad_model_parallel]: 7.28e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.23002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.47001e-06 [overlap_recompute_comm]: 2.39001e-06 [overlap_grad_ring_attention]: 7.07002e-06 [overlap_grad_flash_sp]: 5.016e-05 [begin_end_overlap_inline]: 5.20027e-07 [split_matmul_comm_elemetwise]: 2.44001e-06 [split_layernorm_comm]: 2.17001e-06 [handle_group_info]: 1.37999e-06 [symbol_engine_optimizer]: 0.00035536, [1] [Cycle 1]: 0.0003491, [6] [build]: 0.00019836 [elim_shapecalc]: 2.406e-05 [elim_not_effective]: 3.671e-05 [opt_reshape]: 1.277e-05 [fold_const_symbol]: 3.527e-05 [renormalize]: 6.30011e-07 [detach_backward]: 3.14001e-06 [pipeline_parallel_scheduler]: 2.19999e-06 [auto_monad_reorder]: 3.872e-05 [get_jit_bprop_graph]: 2.54001e-06 [rewriter_after_jit_bprop_graph]: 6.54999e-06 [opt_after_jit_grad]: 0.00075744 [validate]: 9.411e-05 Sums bootstrap : 0.000667s : 0.08% type_inference : 0.844859s : 96.90% event_method : 0.000027s : 0.00% auto_monad : 0.001063s : 0.12% graph_reusing : 0.000009s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000027s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000047s : 0.01% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000002s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000036s : 0.00% optimize.rewriter_before_opt_a : 0.000106s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000058s : 0.01% optimize.opt_a.loop_unroll : 0.000039s : 0.00% optimize.opt_a.a_1 : 0.001178s : 0.14% optimize.opt_a.with_stream_mark : 0.000056s : 0.01% optimize.opt_a.recompute_prepare : 0.000032s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000346s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000026s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.00% optimize.opt_a.shard_inline : 0.000023s : 0.00% optimize.opt_a.merge_send_recv : 0.000028s : 0.00% optimize.opt_a.auto_parallel : 0.000029s : 0.00% optimize.opt_a.parallel : 0.000069s : 0.01% optimize.opt_a.flash_sp : 0.000028s : 0.00% optimize.opt_a.merge_comm : 0.000015s : 0.00% optimize.opt_a.allreduce_fusion : 0.000013s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000030s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000034s : 0.00% optimize.opt_a.virtual_dataset : 0.000023s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000022s : 0.00% optimize.opt_a.virtual_output : 0.000022s : 0.00% optimize.opt_a.merge_forward : 0.000017s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000033s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000051s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000040s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000015s : 0.00% optimize.opt_a.meta_fg_expand : 0.000011s : 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 : 0.000035s : 0.00% optimize.opt_a.a_after_grad : 0.000035s : 0.00% optimize.opt_a.renormalize : 0.017904s : 2.05% optimize.opt_a.add_forward_monad_depend : 0.000016s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000056s : 0.01% optimize.opt_a.cse : 0.000240s : 0.03% optimize.opt_a.a_3 : 0.000173s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000026s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000402s : 0.05% optimize.convert_after_rewriter : 0.000016s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000786s : 0.09% optimize.opt_b.b_1 : 0.000304s : 0.03% optimize.opt_b.b_2 : 0.000015s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000078s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000032s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000042s : 0.00% optimize.loop_unroll : 0.000571s : 0.07% optimize.opt_after_cconv.c_1 : 0.000058s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000049s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000063s : 0.01% optimize.tuple_transform.d_1 : 0.000122s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000012s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000106s : 0.01% optimize.cse_after_recomputation.cse : 0.000036s : 0.00% optimize.environ_conv : 0.000029s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 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 : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 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 : 0.000025s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000024s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 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 : 0.000050s : 0.01% 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 : 0.000198s : 0.02% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000024s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000037s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000013s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000035s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000039s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000757s : 0.09% validate : 0.000094s : 0.01% Time group info: ------[substitution.] 0.000512 111 9.21% : 0.000047s : 6: substitution.arithmetic_simplify 2.80% : 0.000014s : 6: substitution.elim_not_effective 2.52% : 0.000013s : 6: substitution.float_tuple_getitem_switch 3.59% : 0.000018s : 6: substitution.fold_const_symbol 2.30% : 0.000012s : 8: substitution.graph_param_transform 41.52% : 0.000213s : 5: substitution.inline 1.63% : 0.000008s : 12: substitution.j_node_and_user_rematch 1.93% : 0.000010s : 4: substitution.minmaximum_grad 2.10% : 0.000011s : 12: substitution.remove_not_recompute_node 1.18% : 0.000006s : 2: substitution.replace_old_param 6.76% : 0.000035s : 8: substitution.tuple_list_convert_item_index_to_positive 5.42% : 0.000028s : 8: substitution.tuple_list_get_item_const_eliminator 4.44% : 0.000023s : 8: substitution.tuple_list_get_item_depend_reorder 10.54% : 0.000054s : 12: substitution.tuple_list_get_item_eliminator 4.05% : 0.000021s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 0.844740 2 99.54% : 0.840860s : 1: type_inference.infer 0.46% : 0.003879s : 1: type_inference.specialize ------[replace.] 0.000048 5 100.00% : 0.000048s : 5: replace.inline ------[match.] 0.000208 5 100.00% : 0.000208s : 5: match.inline ------[predicate.] 0.000346 2113 0.82% : 0.000003s : 21: predicate.accumulaten_eliminater 1.02% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.66% : 0.000002s : 16: predicate.addn_check_dump 0.96% : 0.000003s : 21: predicate.addn_zero_filter 0.74% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.28% : 0.000008s : 37: predicate.arithmetic_simplify 0.96% : 0.000003s : 21: predicate.cast_eliminate 0.69% : 0.000002s : 16: predicate.check_bprop_eliminate 0.73% : 0.000003s : 16: predicate.compare_switch_simplify 0.20% : 0.000001s : 8: predicate.const_output_eliminate 0.66% : 0.000002s : 16: predicate.depend_value_elim 0.92% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 1.00% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.84% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.22% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.22% : 0.000001s : 8: predicate.elim_not_effective 0.55% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.17% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.08% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.09% : 0.000004s : 29: predicate.environ_get_depend_swap 1.76% : 0.000006s : 45: predicate.environ_get_eliminate 1.08% : 0.000004s : 29: predicate.environ_get_set_eliminate 1.00% : 0.000003s : 26: predicate.exchange_switch_depend_value 1.82% : 0.000006s : 26: predicate.float_depend_g_call 0.62% : 0.000002s : 16: predicate.float_environ_get_switch 1.09% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.23% : 0.000001s : 8: predicate.fold_const_symbol 0.77% : 0.000003s : 16: predicate.get_grad_eliminate 0.27% : 0.000001s : 8: predicate.graph_param_transform 0.70% : 0.000002s : 16: predicate.incorporate_call 0.57% : 0.000002s : 16: predicate.incorporate_call_switch 5.89% : 0.000020s : 95: predicate.inline 0.99% : 0.000003s : 16: predicate.inline_without_move 0.34% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.97% : 0.000003s : 16: predicate.less_batch_normalization 1.68% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.44% : 0.000008s : 58: predicate.load_eliminater 1.00% : 0.000003s : 8: predicate.loop_unroll_after_grad 1.54% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.65% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.70% : 0.000002s : 16: predicate.merge_addn 0.64% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.65% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.82% : 0.000003s : 21: predicate.minmaximum_grad 1.54% : 0.000005s : 8: predicate.mutable_eliminate 0.38% : 0.000001s : 8: predicate.opt_reshape 0.52% : 0.000002s : 8: predicate.parallel_virtual_node 1.53% : 0.000005s : 26: predicate.partial_defer_inline 1.22% : 0.000004s : 29: predicate.partial_eliminate 0.86% : 0.000003s : 21: predicate.print_const_string_wrapper 0.69% : 0.000002s : 16: predicate.reduce_all_const_elim 1.24% : 0.000004s : 21: predicate.reduce_eliminate 2.36% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.51% : 0.000002s : 16: predicate.remove_not_recompute_node 1.35% : 0.000005s : 37: predicate.replace_applicator 0.52% : 0.000002s : 16: predicate.replace_old_param 0.33% : 0.000001s : 8: predicate.reset_defer_inline 0.92% : 0.000003s : 21: predicate.reshape_eliminate 0.67% : 0.000002s : 16: predicate.row_tensor_add_zeros_like 0.45% : 0.000002s : 8: predicate.row_tensor_eliminate 1.18% : 0.000004s : 16: predicate.same_eliminate 0.51% : 0.000002s : 16: predicate.set_cell_output_no_recompute 0.91% : 0.000003s : 16: predicate.shard_identity_eliminate 0.84% : 0.000003s : 16: predicate.special_op_eliminate 0.79% : 0.000003s : 16: predicate.specialize_transform 1.18% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 0.90% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.47% : 0.000002s : 8: predicate.switch_call_monad_eliminater 1.15% : 0.000004s : 26: predicate.switch_defer_inline 1.73% : 0.000006s : 42: predicate.switch_layer_defer_inline 3.95% : 0.000014s : 86: predicate.switch_simplify 0.89% : 0.000003s : 21: predicate.tile_eliminate 0.80% : 0.000003s : 21: predicate.transpose_eliminate 1.85% : 0.000006s : 37: predicate.tuple_list_convert_item_index_to_positive 1.81% : 0.000006s : 37: predicate.tuple_list_get_item_const_eliminator 1.53% : 0.000005s : 37: predicate.tuple_list_get_item_depend_reorder 3.41% : 0.000012s : 53: predicate.tuple_list_get_item_eliminator 1.61% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.75% : 0.000010s : 53: predicate.tuple_list_set_item_eliminator 1.53% : 0.000005s : 37: predicate.tuple_to_list_eliminator_ 2.11% : 0.000007s : 58: predicate.updatestate_pure_node_eliminater 3.02% : 0.000010s : 74: predicate.updatestate_useless_node_eliminater 0.41% : 0.000001s : 8: predicate.value_based_eliminate 0.86% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.88% : 0.000003s : 16: predicate.virtual_output_eliminate 0.34% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.44% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.005129 32 69.55% : 0.003567s : 25: func_graph_cloner_run.FuncGraphClonerGraph 30.45% : 0.001562s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.935441 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.88% : 0.008275s : 1: add_attr 0.88% : 0.008255s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000111s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.12% : 0.001099s : 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 0.08% : 0.000713s : 1: bootstrap 0.00% : 0.000046s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000028s : 1: control_data_broadcast_order 0.00% : 0.000022s : 1: convert_after_rewriter 0.01% : 0.000052s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.00% : 0.000034s : 1: environ_conv 0.00% : 0.000036s : 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% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000006s : 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% : 0.000010s : 1: label_micro_interleaved_index 0.06% : 0.000583s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.09% : 0.000799s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.00% : 0.000024s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000033s : 1: opt.transform.mutable_eliminate 0.22% : 0.002019s : 78: opt.transform.opt_a 0.01% : 0.000057s : 1: opt.transform.opt_after_cconv 0.01% : 0.000049s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000282s : 28: opt.transform.opt_b 0.01% : 0.000132s : 2: opt.transform.opt_trans_graph 0.01% : 0.000103s : 4: opt.transform.symbol_engine_opt 2.29% : 0.021431s : 1: opt_a 0.02% : 0.000184s : 1: opt_after_cconv 0.08% : 0.000777s : 1: opt_after_jit_grad 0.05% : 0.000480s : 1: opt_b 2.71% : 0.025352s : 1: optimize 0.00% : 0.000036s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.01% : 0.000054s : 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% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000029s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 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% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000051s : 1: pre_auto_parallel 0.00% : 0.000041s : 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 0.01% : 0.000069s : 1: remove_dup_value 1.73% : 0.016159s : 1: renormalize.infer 0.18% : 0.001726s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000413s : 1: rewriter_after_opt_a 0.01% : 0.000112s : 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% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000359s : 1: symbol_engine_optimizer 0.02% : 0.000169s : 1: tuple_transform 90.32% : 0.844898s : 1: type_inference mki_log delete old file:/home/jenkins/ascend/log/atb/atb_56388_20260129171803.log . [hook] pytest_runtest_teardown:test_swiglu_dyn_shape[shape0] tests/st/infer/ops/test_internal_ops/test_swiglu_v2.py::test_swiglu_dyn_shape[shape0],max_mem:100.0M [WARNING] ME(157404:281473330929456,MainProcess):2026-01-29-17:38:02.105.007 [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 = 1.51838, [21] [bootstrap]: 0.00080898 [type_inference]: 1.49554 [event_method]: 5.907e-05 [auto_monad]: 0.00012924 [graph_reusing]: 6.56e-06 [inline]: 1.024e-05 [add_attr]: 0.00720494, [1] [add_attr_with_inline]: 0.0071883, [1] [Cycle 1]: 8.544e-05, [2] [tag_attr]: 2.626e-05 [meta_addattr_fg_expand]: 5.52999e-06 [parallel-infer-symbol]: 3.98001e-06 [pre_auto_parallel]: 4.464e-05 [insert-virtual-dataset]: 2.63e-06 [parallel-infer-symbol-second]: 1.20001e-06 [dataset_repeat_opt]: 1.82001e-06 [pipeline_split]: 1.74e-06 [optimize]: 0.0136545, [53] [py_interpret_to_execute]: 3.504e-05 [rewriter_before_opt_a]: 9.643e-05 [opt_a]: 0.0100521, [2] [Cycle 1]: 0.00876736, [45] [expand_dump_flag]: 3.46001e-06 [switch_simplify]: 4.293e-05 [loop_unroll]: 2.8e-05 [a_1]: 0.00100698 [with_stream_mark]: 2.498e-05 [recompute_prepare]: 1.769e-05 [updatestate_depend_eliminate]: 7.68001e-06 [updatestate_assign_eliminate]: 6.66e-06 [updatestate_loads_eliminate]: 5.89999e-06 [parameter_eliminate]: 2.00002e-06 [a_2]: 0.00019018 [accelerated_algorithm]: 1.402e-05 [shard]: 2.71999e-06 [meta_shard_fg_expand]: 3.56999e-06 [shard_inline]: 1.203e-05 [merge_send_recv]: 1.326e-05 [auto_parallel]: 1.207e-05 [parallel]: 3.267e-05 [flash_sp]: 1.175e-05 [merge_comm]: 7e-06 [allreduce_fusion]: 6.68e-06 [matmul_add_comm_reduction]: 1.64e-05 [allreduce_slice_to_reducescatter]: 6.19999e-07 [virtual_shard_identity]: 1.693e-05 [virtual_dataset]: 1.28e-05 [get_grad_eliminate_]: 1.27e-05 [virtual_output]: 1.26e-05 [merge_forward]: 8.36002e-06 [cell_reuse_recompute_pass]: 1.34998e-06 [offload_activation]: 1.685e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.516e-05 [merge_recompute_call_nodes]: 1.57001e-06 [before_grad]: 2.2e-05 [set_forward_comm_id_for_comm_node_pass]: 7.33e-06 [meta_fg_expand]: 4.54002e-06 [flash_sp_send_recv_attached]: 2.58e-06 [receive_attached]: 2.49001e-06 [after_resolve]: 1.752e-05 [a_after_grad]: 2.078e-05 [renormalize]: 0.00609577 [add_forward_monad_depend]: 1.21e-05 [auto_monad_grad]: 3.14999e-06 [auto_monad_eliminator]: 3.48e-05 [cse]: 0.00052364 [a_3]: 0.00010604 [Cycle 2]: 0.00126853, [45] [expand_dump_flag]: 2.81e-06 [switch_simplify]: 1.651e-05 [loop_unroll]: 1.194e-05 [a_1]: 0.0003443 [with_stream_mark]: 3.142e-05 [recompute_prepare]: 1.387e-05 [updatestate_depend_eliminate]: 9.36e-06 [updatestate_assign_eliminate]: 6.16e-06 [updatestate_loads_eliminate]: 5.81e-06 [parameter_eliminate]: 2.70002e-06 [a_2]: 0.00016805 [accelerated_algorithm]: 1.227e-05 [shard]: 2.81999e-06 [meta_shard_fg_expand]: 3.45e-06 [shard_inline]: 1.08e-05 [merge_send_recv]: 1.241e-05 [auto_parallel]: 1.392e-05 [parallel]: 9.66e-06 [flash_sp]: 4.95999e-06 [merge_comm]: 6.57002e-06 [allreduce_fusion]: 5.86e-06 [matmul_add_comm_reduction]: 1.472e-05 [allreduce_slice_to_reducescatter]: 9.30013e-07 [virtual_shard_identity]: 1.41e-05 [virtual_dataset]: 1.141e-05 [get_grad_eliminate_]: 1.249e-05 [virtual_output]: 1.032e-05 [merge_forward]: 6.72002e-06 [cell_reuse_recompute_pass]: 3.3e-06 [offload_activation]: 1.551e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.336e-05 [merge_recompute_call_nodes]: 1.75001e-06 [before_grad]: 1.916e-05 [set_forward_comm_id_for_comm_node_pass]: 7.18e-06 [meta_fg_expand]: 4.92e-06 [flash_sp_send_recv_attached]: 1.90001e-06 [receive_attached]: 2.73e-06 [after_resolve]: 1.706e-05 [a_after_grad]: 1.929e-05 [renormalize]: 1.10012e-07 [add_forward_monad_depend]: 2.89999e-06 [auto_monad_grad]: 2.68e-06 [auto_monad_eliminator]: 1.998e-05 [cse]: 4.87e-05 [a_3]: 7.24e-05 [py_interpret_to_execute_after_opt_a]: 2.574e-05 [slice_cell_reuse_recomputed_activation]: 2.27001e-06 [rewriter_after_opt_a]: 0.00030815 [convert_after_rewriter]: 1.643e-05 [order_py_execute_after_rewriter]: 9.38002e-06 [mutable_eliminate]: 0.00083151 [opt_b]: 0.000428, [1] [Cycle 1]: 0.00041962, [7] [b_1]: 0.00028649 [b_2]: 1.417e-05 [updatestate_depend_eliminate]: 1.258e-05 [updatestate_assign_eliminate]: 5.43002e-06 [updatestate_loads_eliminate]: 5.59998e-06 [renormalize]: 8.70001e-07 [cse]: 5.316e-05 [optimize_parallel_all_gather_comm]: 3.006e-05 [overlap_param_gather]: 1.91998e-06 [cconv]: 3.669e-05 [loop_unroll]: 0.00054813 [opt_after_cconv]: 0.00015747, [1] [Cycle 1]: 0.00015, [7] [c_1]: 5.356e-05 [parameter_eliminate]: 5.23002e-06 [updatestate_depend_eliminate]: 1.03e-05 [updatestate_assign_eliminate]: 4.92e-06 [updatestate_loads_eliminate]: 4.72e-06 [cse]: 3.706e-05 [renormalize]: 4.89992e-07 [remove_dup_value]: 6.084e-05 [tuple_transform]: 0.00015252, [1] [Cycle 1]: 0.00014727, [4] [d_1]: 0.00011122 [none_parameter_eliminate]: 1.62001e-06 [renormalize]: 1.59984e-07 [switch_simplify]: 1.214e-05 [partial_unused_args_eliminate]: 1.86998e-06 [add_recomputation]: 9.244e-05 [cse_after_recomputation]: 3.957e-05, [1] [Cycle 1]: 3.415e-05, [1] [cse]: 2.803e-05 [environ_conv]: 1.758e-05 [swap_dp_allreduce_reducescatter]: 8.73001e-06 [bias_add_comm_swap]: 2.91999e-06 [label_micro_interleaved_index]: 4.87998e-06 [label_fine_grained_interleaved_index]: 3.00998e-06 [merge_cast_opt]: 1.49e-06 [slice_recompute_activation]: 2.36998e-06 [micro_interleaved_order_control]: 2.39999e-06 [assign_add_opt]: 1.42e-06 [ForceFp32Comm]: 1.14e-06 [remove_cast_before_assign_add]: 1.10001e-06 [full_micro_interleaved_order_control]: 2.58e-06 [reorder_send_recv_between_fp_bp]: 2.85998e-06 [comm_op_add_attrs]: 1.26002e-06 [add_comm_op_reuse_tag]: 1.00999e-06 [interleave_split_concat_branches]: 1.25999e-06 [interleave_parallel_branches]: 1.10001e-06 [overlap_opt_shard_in_pipeline]: 1.23002e-06 [overlap_opt_shard_grad_in_pipeline]: 1.91003e-06 [control_data_broadcast_order]: 2.149e-05 [grouped_pairwise_exchange_alltoall]: 2.53e-06 [offloading_packed_experts]: 7.45e-06 [overlap_recompute_and_grad_model_parallel]: 7.36999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.24998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.64998e-06 [overlap_recompute_comm]: 2.28002e-06 [overlap_grad_ring_attention]: 6.09999e-06 [overlap_grad_flash_sp]: 3.282e-05 [begin_end_overlap_inline]: 5.39992e-07 [split_matmul_comm_elemetwise]: 2.26e-06 [split_layernorm_comm]: 2.02001e-06 [handle_group_info]: 1.07e-06 [symbol_engine_optimizer]: 0.00031078, [1] [Cycle 1]: 0.00030575, [6] [build]: 0.00017653 [elim_shapecalc]: 2e-05 [elim_not_effective]: 2.5e-05 [opt_reshape]: 1.251e-05 [fold_const_symbol]: 3.17e-05 [renormalize]: 2.59985e-07 [detach_backward]: 2.14e-06 [pipeline_parallel_scheduler]: 1.57999e-06 [auto_monad_reorder]: 2.786e-05 [get_jit_bprop_graph]: 2.68e-06 [rewriter_after_jit_bprop_graph]: 6.69999e-06 [opt_after_jit_grad]: 0.00056194 [validate]: 7.603e-05 Sums bootstrap : 0.000809s : 0.05% type_inference : 1.495540s : 99.05% event_method : 0.000059s : 0.00% auto_monad : 0.000129s : 0.01% graph_reusing : 0.000007s : 0.00% inline : 0.000010s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000026s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000045s : 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 : 0.000035s : 0.00% optimize.rewriter_before_opt_a : 0.000096s : 0.01% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000059s : 0.00% optimize.opt_a.loop_unroll : 0.000040s : 0.00% optimize.opt_a.a_1 : 0.001351s : 0.09% optimize.opt_a.with_stream_mark : 0.000056s : 0.00% optimize.opt_a.recompute_prepare : 0.000032s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000017s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000013s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000358s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000026s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.00% optimize.opt_a.shard_inline : 0.000023s : 0.00% optimize.opt_a.merge_send_recv : 0.000026s : 0.00% optimize.opt_a.auto_parallel : 0.000026s : 0.00% optimize.opt_a.parallel : 0.000042s : 0.00% optimize.opt_a.flash_sp : 0.000017s : 0.00% optimize.opt_a.merge_comm : 0.000014s : 0.00% optimize.opt_a.allreduce_fusion : 0.000013s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000031s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000031s : 0.00% optimize.opt_a.virtual_dataset : 0.000024s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000025s : 0.00% optimize.opt_a.virtual_output : 0.000023s : 0.00% optimize.opt_a.merge_forward : 0.000015s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000032s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000049s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000041s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000015s : 0.00% optimize.opt_a.meta_fg_expand : 0.000009s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000035s : 0.00% optimize.opt_a.a_after_grad : 0.000040s : 0.00% optimize.opt_a.renormalize : 0.006096s : 0.40% optimize.opt_a.add_forward_monad_depend : 0.000015s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000055s : 0.00% optimize.opt_a.cse : 0.000572s : 0.04% optimize.opt_a.a_3 : 0.000178s : 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 : 0.000308s : 0.02% optimize.convert_after_rewriter : 0.000016s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000832s : 0.06% optimize.opt_b.b_1 : 0.000286s : 0.02% optimize.opt_b.b_2 : 0.000014s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000053s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000030s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000037s : 0.00% optimize.loop_unroll : 0.000548s : 0.04% optimize.opt_after_cconv.c_1 : 0.000054s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000037s : 0.00% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000061s : 0.00% optimize.tuple_transform.d_1 : 0.000111s : 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 : 0.000012s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000092s : 0.01% optimize.cse_after_recomputation.cse : 0.000028s : 0.00% optimize.environ_conv : 0.000018s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 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 : 0.000002s : 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 : 0.000021s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000003s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 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 : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000033s : 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 : 0.000177s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000020s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000025s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000013s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000032s : 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 : 0.000028s : 0.00% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000562s : 0.04% validate : 0.000076s : 0.01% Time group info: ------[substitution.] 0.000504 111 9.71% : 0.000049s : 6: substitution.arithmetic_simplify 1.05% : 0.000005s : 6: substitution.elim_not_effective 2.43% : 0.000012s : 6: substitution.float_tuple_getitem_switch 3.09% : 0.000016s : 6: substitution.fold_const_symbol 1.84% : 0.000009s : 8: substitution.graph_param_transform 45.72% : 0.000231s : 5: substitution.inline 1.62% : 0.000008s : 12: substitution.j_node_and_user_rematch 2.46% : 0.000012s : 4: substitution.minmaximum_grad 2.17% : 0.000011s : 12: substitution.remove_not_recompute_node 1.15% : 0.000006s : 2: substitution.replace_old_param 6.64% : 0.000034s : 8: substitution.tuple_list_convert_item_index_to_positive 3.08% : 0.000016s : 8: substitution.tuple_list_get_item_const_eliminator 4.42% : 0.000022s : 8: substitution.tuple_list_get_item_depend_reorder 10.45% : 0.000053s : 12: substitution.tuple_list_get_item_eliminator 4.17% : 0.000021s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.347401 2 99.70% : 1.343404s : 1: type_inference.infer 0.30% : 0.003997s : 1: type_inference.specialize ------[replace.] 0.000051 5 100.00% : 0.000051s : 5: replace.inline ------[match.] 0.000227 5 100.00% : 0.000227s : 5: match.inline ------[predicate.] 0.000353 2113 0.92% : 0.000003s : 21: predicate.accumulaten_eliminater 0.94% : 0.000003s : 8: predicate.ad_related_special_op_eliminate 0.61% : 0.000002s : 16: predicate.addn_check_dump 0.86% : 0.000003s : 21: predicate.addn_zero_filter 0.88% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.42% : 0.000009s : 37: predicate.arithmetic_simplify 0.98% : 0.000003s : 21: predicate.cast_eliminate 0.72% : 0.000003s : 16: predicate.check_bprop_eliminate 0.65% : 0.000002s : 16: predicate.compare_switch_simplify 0.21% : 0.000001s : 8: predicate.const_output_eliminate 0.73% : 0.000003s : 16: predicate.depend_value_elim 0.90% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 1.01% : 0.000004s : 21: predicate.dict_get_item_eliminator 0.88% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.06% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.19% : 0.000001s : 8: predicate.elim_not_effective 0.63% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.19% : 0.000004s : 29: predicate.environ_add_const_eliminate 1.13% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.17% : 0.000004s : 29: predicate.environ_get_depend_swap 2.00% : 0.000007s : 45: predicate.environ_get_eliminate 1.10% : 0.000004s : 29: predicate.environ_get_set_eliminate 1.08% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.61% : 0.000006s : 26: predicate.float_depend_g_call 0.65% : 0.000002s : 16: predicate.float_environ_get_switch 1.10% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 8: predicate.fold_const_symbol 0.86% : 0.000003s : 16: predicate.get_grad_eliminate 0.28% : 0.000001s : 8: predicate.graph_param_transform 0.73% : 0.000003s : 16: predicate.incorporate_call 0.62% : 0.000002s : 16: predicate.incorporate_call_switch 5.62% : 0.000020s : 95: predicate.inline 0.97% : 0.000003s : 16: predicate.inline_without_move 0.33% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.91% : 0.000003s : 16: predicate.less_batch_normalization 1.64% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.32% : 0.000008s : 58: predicate.load_eliminater 1.07% : 0.000004s : 8: predicate.loop_unroll_after_grad 1.48% : 0.000005s : 36: predicate.loop_unroll_before_grad 1.95% : 0.000007s : 37: predicate.make_slice_get_slice_eliminator 0.71% : 0.000003s : 16: predicate.merge_addn 0.68% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.65% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.85% : 0.000003s : 21: predicate.minmaximum_grad 1.30% : 0.000005s : 8: predicate.mutable_eliminate 0.38% : 0.000001s : 8: predicate.opt_reshape 0.48% : 0.000002s : 8: predicate.parallel_virtual_node 1.52% : 0.000005s : 26: predicate.partial_defer_inline 1.27% : 0.000004s : 29: predicate.partial_eliminate 0.87% : 0.000003s : 21: predicate.print_const_string_wrapper 0.73% : 0.000003s : 16: predicate.reduce_all_const_elim 1.08% : 0.000004s : 21: predicate.reduce_eliminate 2.32% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.41% : 0.000001s : 16: predicate.remove_not_recompute_node 1.39% : 0.000005s : 37: predicate.replace_applicator 0.50% : 0.000002s : 16: predicate.replace_old_param 0.26% : 0.000001s : 8: predicate.reset_defer_inline 0.89% : 0.000003s : 21: predicate.reshape_eliminate 0.72% : 0.000003s : 16: predicate.row_tensor_add_zeros_like 0.49% : 0.000002s : 8: predicate.row_tensor_eliminate 1.33% : 0.000005s : 16: predicate.same_eliminate 0.50% : 0.000002s : 16: predicate.set_cell_output_no_recompute 1.11% : 0.000004s : 16: predicate.shard_identity_eliminate 0.89% : 0.000003s : 16: predicate.special_op_eliminate 0.84% : 0.000003s : 16: predicate.specialize_transform 1.04% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 1.03% : 0.000004s : 16: predicate.stack_unstack_eliminate 0.40% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.18% : 0.000004s : 26: predicate.switch_defer_inline 1.82% : 0.000006s : 42: predicate.switch_layer_defer_inline 3.96% : 0.000014s : 86: predicate.switch_simplify 1.00% : 0.000004s : 21: predicate.tile_eliminate 0.87% : 0.000003s : 21: predicate.transpose_eliminate 1.79% : 0.000006s : 37: predicate.tuple_list_convert_item_index_to_positive 1.72% : 0.000006s : 37: predicate.tuple_list_get_item_const_eliminator 1.55% : 0.000005s : 37: predicate.tuple_list_get_item_depend_reorder 3.15% : 0.000011s : 53: predicate.tuple_list_get_item_eliminator 1.61% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.46% : 0.000009s : 53: predicate.tuple_list_set_item_eliminator 1.57% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 2.15% : 0.000008s : 58: predicate.updatestate_pure_node_eliminater 3.15% : 0.000011s : 74: predicate.updatestate_useless_node_eliminater 0.39% : 0.000001s : 8: predicate.value_based_eliminate 0.77% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.88% : 0.000003s : 16: predicate.virtual_output_eliminate 0.32% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.44% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.005825 32 69.54% : 0.004050s : 25: func_graph_cloner_run.FuncGraphClonerGraph 30.46% : 0.001774s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.547976 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.47% : 0.007212s : 1: add_attr 0.46% : 0.007193s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000097s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.01% : 0.000136s : 1: auto_monad 0.00% : 0.000032s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.05% : 0.000850s : 1: bootstrap 0.00% : 0.000041s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000025s : 1: control_data_broadcast_order 0.00% : 0.000022s : 1: convert_after_rewriter 0.00% : 0.000043s : 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 0.00% : 0.000070s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000014s : 1: inline 0.00% : 0.000006s : 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% : 0.000558s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.05% : 0.000846s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.00% : 0.000022s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000031s : 1: opt.transform.mutable_eliminate 0.14% : 0.002223s : 78: opt.transform.opt_a 0.00% : 0.000052s : 1: opt.transform.opt_after_cconv 0.00% : 0.000043s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000267s : 28: opt.transform.opt_b 0.01% : 0.000121s : 2: opt.transform.opt_trans_graph 0.01% : 0.000085s : 4: opt.transform.symbol_engine_opt 0.65% : 0.010056s : 1: opt_a 0.01% : 0.000161s : 1: opt_after_cconv 0.04% : 0.000574s : 1: opt_after_jit_grad 0.03% : 0.000432s : 1: opt_b 0.88% : 0.013661s : 1: optimize 0.00% : 0.000034s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.00% : 0.000036s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 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% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 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% : 0.000005s : 1: pipeline_split 0.00% : 0.000049s : 1: pre_auto_parallel 0.00% : 0.000039s : 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 0.00% : 0.000065s : 1: remove_dup_value 0.27% : 0.004148s : 1: renormalize.infer 0.12% : 0.001931s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000318s : 1: rewriter_after_opt_a 0.01% : 0.000101s : 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% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000314s : 1: symbol_engine_optimizer 0.01% : 0.000155s : 1: tuple_transform 96.62% : 1.495606s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dyn_shape[shape1] tests/st/infer/ops/test_internal_ops/test_swiglu_v2.py::test_swiglu_dyn_shape[shape1],max_mem:102.0M [WARNING] ME(157404:281473330929456,MainProcess):2026-01-29-17:38:08.183.597 [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 = 1.73038, [21] [bootstrap]: 0.00075196 [type_inference]: 1.57037 [event_method]: 2.471e-05 [auto_monad]: 9.116e-05 [graph_reusing]: 6.76e-06 [inline]: 3.07002e-06 [add_attr]: 0.0057814, [1] [add_attr_with_inline]: 0.00576303, [1] [Cycle 1]: 8.247e-05, [2] [tag_attr]: 2.814e-05 [meta_addattr_fg_expand]: 6.01e-06 [parallel-infer-symbol]: 4.03001e-06 [pre_auto_parallel]: 4.541e-05 [insert-virtual-dataset]: 2.89001e-06 [parallel-infer-symbol-second]: 7.80012e-07 [dataset_repeat_opt]: 1.97999e-06 [pipeline_split]: 1.84998e-06 [optimize]: 0.152259, [53] [py_interpret_to_execute]: 4.117e-05 [rewriter_before_opt_a]: 0.00010054 [opt_a]: 0.148261, [2] [Cycle 1]: 0.146868, [45] [expand_dump_flag]: 3.75e-06 [switch_simplify]: 4.668e-05 [loop_unroll]: 3.085e-05 [a_1]: 0.00114912 [with_stream_mark]: 3.087e-05 [recompute_prepare]: 2.149e-05 [updatestate_depend_eliminate]: 1.106e-05 [updatestate_assign_eliminate]: 6.87002e-06 [updatestate_loads_eliminate]: 5.99e-06 [parameter_eliminate]: 3.31001e-06 [a_2]: 0.0002133 [accelerated_algorithm]: 1.552e-05 [shard]: 3.16999e-06 [meta_shard_fg_expand]: 4.01001e-06 [shard_inline]: 1.366e-05 [merge_send_recv]: 1.614e-05 [auto_parallel]: 1.362e-05 [parallel]: 3.458e-05 [flash_sp]: 1.415e-05 [merge_comm]: 8.00999e-06 [allreduce_fusion]: 7.15e-06 [matmul_add_comm_reduction]: 1.568e-05 [allreduce_slice_to_reducescatter]: 9.50007e-07 [virtual_shard_identity]: 1.795e-05 [virtual_dataset]: 1.382e-05 [get_grad_eliminate_]: 1.386e-05 [virtual_output]: 1.38e-05 [merge_forward]: 8.10999e-06 [cell_reuse_recompute_pass]: 2.07999e-06 [offload_activation]: 1.815e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.905e-05 [merge_recompute_call_nodes]: 1.81e-06 [before_grad]: 2.627e-05 [set_forward_comm_id_for_comm_node_pass]: 7.43999e-06 [meta_fg_expand]: 5.89e-06 [flash_sp_send_recv_attached]: 2.81999e-06 [receive_attached]: 2.16e-06 [after_resolve]: 1.792e-05 [a_after_grad]: 3.72e-05 [renormalize]: 0.143809 [add_forward_monad_depend]: 1.333e-05 [auto_monad_grad]: 2.94001e-06 [auto_monad_eliminator]: 3.615e-05 [cse]: 0.00063005 [a_3]: 0.00011362 [Cycle 2]: 0.00137527, [45] [expand_dump_flag]: 2.91e-06 [switch_simplify]: 1.708e-05 [loop_unroll]: 1.284e-05 [a_1]: 0.00035376 [with_stream_mark]: 3.5e-05 [recompute_prepare]: 1.43e-05 [updatestate_depend_eliminate]: 1.007e-05 [updatestate_assign_eliminate]: 6.28998e-06 [updatestate_loads_eliminate]: 5.37999e-06 [parameter_eliminate]: 3.03e-06 [a_2]: 0.0001664 [accelerated_algorithm]: 1.263e-05 [shard]: 2.74001e-06 [meta_shard_fg_expand]: 4.60999e-06 [shard_inline]: 1.099e-05 [merge_send_recv]: 1.449e-05 [auto_parallel]: 1.518e-05 [parallel]: 1.187e-05 [flash_sp]: 5.91998e-06 [merge_comm]: 7.33e-06 [allreduce_fusion]: 6.19001e-06 [matmul_add_comm_reduction]: 1.665e-05 [allreduce_slice_to_reducescatter]: 1.25001e-06 [virtual_shard_identity]: 1.75e-05 [virtual_dataset]: 1.203e-05 [get_grad_eliminate_]: 1.179e-05 [virtual_output]: 1.114e-05 [merge_forward]: 7.7e-06 [cell_reuse_recompute_pass]: 3.97e-06 [offload_activation]: 1.592e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.491e-05 [merge_recompute_call_nodes]: 1.99e-06 [before_grad]: 1.994e-05 [set_forward_comm_id_for_comm_node_pass]: 8.17e-06 [meta_fg_expand]: 6.06e-06 [flash_sp_send_recv_attached]: 1.89e-06 [receive_attached]: 2.68e-06 [after_resolve]: 1.734e-05 [a_after_grad]: 1.74e-05 [renormalize]: 5.00004e-08 [add_forward_monad_depend]: 5.12e-06 [auto_monad_grad]: 3.68999e-06 [auto_monad_eliminator]: 2.319e-05 [cse]: 8.449e-05 [a_3]: 7.671e-05 [py_interpret_to_execute_after_opt_a]: 2.919e-05 [slice_cell_reuse_recomputed_activation]: 3.42002e-06 [rewriter_after_opt_a]: 0.00029222 [convert_after_rewriter]: 1.623e-05 [order_py_execute_after_rewriter]: 9.49999e-06 [mutable_eliminate]: 0.00082474 [opt_b]: 0.00044711, [1] [Cycle 1]: 0.00043728, [7] [b_1]: 0.00029755 [b_2]: 1.286e-05 [updatestate_depend_eliminate]: 1.349e-05 [updatestate_assign_eliminate]: 5.16998e-06 [updatestate_loads_eliminate]: 6.05002e-06 [renormalize]: 6.19999e-07 [cse]: 5.85e-05 [optimize_parallel_all_gather_comm]: 3.056e-05 [overlap_param_gather]: 2.01e-06 [cconv]: 4.135e-05 [loop_unroll]: 0.00080702 [opt_after_cconv]: 0.00019157, [1] [Cycle 1]: 0.00018176, [7] [c_1]: 5.897e-05 [parameter_eliminate]: 6.88e-06 [updatestate_depend_eliminate]: 1.309e-05 [updatestate_assign_eliminate]: 5.36002e-06 [updatestate_loads_eliminate]: 5.15001e-06 [cse]: 5.213e-05 [renormalize]: 9.39996e-07 [remove_dup_value]: 6.638e-05 [tuple_transform]: 0.00016746, [1] [Cycle 1]: 0.0001625, [4] [d_1]: 0.00012386 [none_parameter_eliminate]: 2.29001e-06 [renormalize]: 1.69995e-07 [switch_simplify]: 1.334e-05 [partial_unused_args_eliminate]: 3.25002e-06 [add_recomputation]: 9.736e-05 [cse_after_recomputation]: 4.596e-05, [1] [Cycle 1]: 3.978e-05, [1] [cse]: 3.236e-05 [environ_conv]: 1.794e-05 [swap_dp_allreduce_reducescatter]: 9.89001e-06 [bias_add_comm_swap]: 3.43e-06 [label_micro_interleaved_index]: 6.97002e-06 [label_fine_grained_interleaved_index]: 3.38e-06 [merge_cast_opt]: 1.64e-06 [slice_recompute_activation]: 2.54001e-06 [micro_interleaved_order_control]: 2.59001e-06 [assign_add_opt]: 1.79e-06 [ForceFp32Comm]: 8.99978e-07 [remove_cast_before_assign_add]: 1.07e-06 [full_micro_interleaved_order_control]: 2.20002e-06 [reorder_send_recv_between_fp_bp]: 2.76999e-06 [comm_op_add_attrs]: 1.27999e-06 [add_comm_op_reuse_tag]: 1.10999e-06 [interleave_split_concat_branches]: 1.65001e-06 [interleave_parallel_branches]: 1.09e-06 [overlap_opt_shard_in_pipeline]: 1.35999e-06 [overlap_opt_shard_grad_in_pipeline]: 2.42001e-06 [control_data_broadcast_order]: 2.48e-05 [grouped_pairwise_exchange_alltoall]: 1.59e-06 [offloading_packed_experts]: 7.24001e-06 [overlap_recompute_and_grad_model_parallel]: 8.32998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.29e-06 [overlap_recompute_allgather_and_fa_grad]: 1.41998e-06 [overlap_recompute_comm]: 2.51e-06 [overlap_grad_ring_attention]: 5.86e-06 [overlap_grad_flash_sp]: 3.087e-05 [begin_end_overlap_inline]: 5.69999e-07 [split_matmul_comm_elemetwise]: 2.46998e-06 [split_layernorm_comm]: 2.18002e-06 [handle_group_info]: 1.30001e-06 [symbol_engine_optimizer]: 0.00033315, [1] [Cycle 1]: 0.00032721, [6] [build]: 0.00018179 [elim_shapecalc]: 2.252e-05 [elim_not_effective]: 2.656e-05 [opt_reshape]: 1.382e-05 [fold_const_symbol]: 3.577e-05 [renormalize]: 2.30008e-07 [detach_backward]: 2.84999e-06 [pipeline_parallel_scheduler]: 2.41998e-06 [auto_monad_reorder]: 3.082e-05 [get_jit_bprop_graph]: 3.9e-06 [rewriter_after_jit_bprop_graph]: 7.04001e-06 [opt_after_jit_grad]: 0.00067406 [validate]: 7.825e-05 Sums bootstrap : 0.000752s : 0.04% type_inference : 1.570375s : 91.13% event_method : 0.000025s : 0.00% auto_monad : 0.000091s : 0.01% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000028s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000045s : 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 : 0.000101s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000064s : 0.00% optimize.opt_a.loop_unroll : 0.000044s : 0.00% optimize.opt_a.a_1 : 0.001503s : 0.09% optimize.opt_a.with_stream_mark : 0.000066s : 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 : 0.000013s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000380s : 0.02% optimize.opt_a.accelerated_algorithm : 0.000028s : 0.00% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.00% optimize.opt_a.shard_inline : 0.000025s : 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 : 0.000046s : 0.00% optimize.opt_a.flash_sp : 0.000020s : 0.00% optimize.opt_a.merge_comm : 0.000015s : 0.00% optimize.opt_a.allreduce_fusion : 0.000013s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000032s : 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 : 0.000026s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000026s : 0.00% optimize.opt_a.virtual_output : 0.000025s : 0.00% optimize.opt_a.merge_forward : 0.000016s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000034s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000054s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000046s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000016s : 0.00% optimize.opt_a.meta_fg_expand : 0.000012s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000035s : 0.00% optimize.opt_a.a_after_grad : 0.000055s : 0.00% optimize.opt_a.renormalize : 0.143809s : 8.35% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000059s : 0.00% optimize.opt_a.cse : 0.000715s : 0.04% optimize.opt_a.a_3 : 0.000190s : 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 : 0.000292s : 0.02% optimize.convert_after_rewriter : 0.000016s : 0.00% optimize.order_py_execute_after_rewriter : 0.000009s : 0.00% optimize.mutable_eliminate : 0.000825s : 0.05% optimize.opt_b.b_1 : 0.000298s : 0.02% optimize.opt_b.b_2 : 0.000013s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000059s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000031s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000041s : 0.00% optimize.loop_unroll : 0.000807s : 0.05% optimize.opt_after_cconv.c_1 : 0.000059s : 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 : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000052s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000066s : 0.00% optimize.tuple_transform.d_1 : 0.000124s : 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 : 0.000013s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000097s : 0.01% optimize.cse_after_recomputation.cse : 0.000032s : 0.00% optimize.environ_conv : 0.000018s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 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 : 0.000003s : 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 : 0.000002s : 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 : 0.000025s : 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 : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000031s : 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 : 0.000182s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000023s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000027s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000014s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000036s : 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 : 0.000031s : 0.00% get_jit_bprop_graph : 0.000004s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000674s : 0.04% validate : 0.000078s : 0.00% Time group info: ------[substitution.] 0.000523 111 9.22% : 0.000048s : 6: substitution.arithmetic_simplify 1.04% : 0.000005s : 6: substitution.elim_not_effective 2.44% : 0.000013s : 6: substitution.float_tuple_getitem_switch 3.61% : 0.000019s : 6: substitution.fold_const_symbol 2.01% : 0.000010s : 8: substitution.graph_param_transform 44.51% : 0.000233s : 5: substitution.inline 1.78% : 0.000009s : 12: substitution.j_node_and_user_rematch 1.91% : 0.000010s : 4: substitution.minmaximum_grad 1.94% : 0.000010s : 12: substitution.remove_not_recompute_node 1.05% : 0.000005s : 2: substitution.replace_old_param 7.06% : 0.000037s : 8: substitution.tuple_list_convert_item_index_to_positive 3.31% : 0.000017s : 8: substitution.tuple_list_get_item_const_eliminator 4.45% : 0.000023s : 8: substitution.tuple_list_get_item_depend_reorder 11.36% : 0.000059s : 12: substitution.tuple_list_get_item_eliminator 4.32% : 0.000023s : 8: substitution.tuple_list_get_set_item_eliminator ------[type_inference.] 1.570250 2 99.76% : 1.566509s : 1: type_inference.infer 0.24% : 0.003741s : 1: type_inference.specialize ------[replace.] 0.000054 5 100.00% : 0.000054s : 5: replace.inline ------[match.] 0.000228 5 100.00% : 0.000228s : 5: match.inline ------[predicate.] 0.000379 2113 0.89% : 0.000003s : 21: predicate.accumulaten_eliminater 1.06% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.63% : 0.000002s : 16: predicate.addn_check_dump 1.04% : 0.000004s : 21: predicate.addn_zero_filter 0.83% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.57% : 0.000010s : 37: predicate.arithmetic_simplify 0.95% : 0.000004s : 21: predicate.cast_eliminate 0.65% : 0.000002s : 16: predicate.check_bprop_eliminate 0.70% : 0.000003s : 16: predicate.compare_switch_simplify 0.18% : 0.000001s : 8: predicate.const_output_eliminate 0.68% : 0.000003s : 16: predicate.depend_value_elim 0.93% : 0.000004s : 21: predicate.dict_get_item_const_eliminator 1.03% : 0.000004s : 21: predicate.dict_get_item_eliminator 0.83% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.09% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.18% : 0.000001s : 8: predicate.elim_not_effective 0.55% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.21% : 0.000005s : 29: predicate.environ_add_const_eliminate 1.12% : 0.000004s : 29: predicate.environ_get_add_eliminate 1.13% : 0.000004s : 29: predicate.environ_get_depend_swap 1.80% : 0.000007s : 45: predicate.environ_get_eliminate 1.09% : 0.000004s : 29: predicate.environ_get_set_eliminate 1.06% : 0.000004s : 26: predicate.exchange_switch_depend_value 1.66% : 0.000006s : 26: predicate.float_depend_g_call 0.76% : 0.000003s : 16: predicate.float_environ_get_switch 1.13% : 0.000004s : 24: predicate.float_tuple_getitem_switch 0.17% : 0.000001s : 8: predicate.fold_const_symbol 0.73% : 0.000003s : 16: predicate.get_grad_eliminate 0.27% : 0.000001s : 8: predicate.graph_param_transform 0.68% : 0.000003s : 16: predicate.incorporate_call 0.53% : 0.000002s : 16: predicate.incorporate_call_switch 5.59% : 0.000021s : 95: predicate.inline 0.99% : 0.000004s : 16: predicate.inline_without_move 0.30% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.90% : 0.000003s : 16: predicate.less_batch_normalization 1.60% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.22% : 0.000008s : 58: predicate.load_eliminater 1.22% : 0.000005s : 8: predicate.loop_unroll_after_grad 1.49% : 0.000006s : 36: predicate.loop_unroll_before_grad 1.78% : 0.000007s : 37: predicate.make_slice_get_slice_eliminator 0.72% : 0.000003s : 16: predicate.merge_addn 0.64% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.63% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.84% : 0.000003s : 21: predicate.minmaximum_grad 1.58% : 0.000006s : 8: predicate.mutable_eliminate 0.39% : 0.000001s : 8: predicate.opt_reshape 0.40% : 0.000002s : 8: predicate.parallel_virtual_node 1.72% : 0.000007s : 26: predicate.partial_defer_inline 1.15% : 0.000004s : 29: predicate.partial_eliminate 0.87% : 0.000003s : 21: predicate.print_const_string_wrapper 0.69% : 0.000003s : 16: predicate.reduce_all_const_elim 1.22% : 0.000005s : 21: predicate.reduce_eliminate 2.23% : 0.000008s : 58: predicate.redundant_stop_gradient_eliminater 0.45% : 0.000002s : 16: predicate.remove_not_recompute_node 1.30% : 0.000005s : 37: predicate.replace_applicator 0.38% : 0.000001s : 16: predicate.replace_old_param 0.22% : 0.000001s : 8: predicate.reset_defer_inline 1.01% : 0.000004s : 21: predicate.reshape_eliminate 0.64% : 0.000002s : 16: predicate.row_tensor_add_zeros_like 0.37% : 0.000001s : 8: predicate.row_tensor_eliminate 1.24% : 0.000005s : 16: predicate.same_eliminate 0.50% : 0.000002s : 16: predicate.set_cell_output_no_recompute 1.01% : 0.000004s : 16: predicate.shard_identity_eliminate 1.00% : 0.000004s : 16: predicate.special_op_eliminate 0.76% : 0.000003s : 16: predicate.specialize_transform 1.13% : 0.000004s : 16: predicate.split_environ_get_set_with_tuple_value 1.01% : 0.000004s : 16: predicate.stack_unstack_eliminate 0.36% : 0.000001s : 8: predicate.switch_call_monad_eliminater 1.27% : 0.000005s : 26: predicate.switch_defer_inline 1.83% : 0.000007s : 42: predicate.switch_layer_defer_inline 4.15% : 0.000016s : 86: predicate.switch_simplify 0.99% : 0.000004s : 21: predicate.tile_eliminate 0.82% : 0.000003s : 21: predicate.transpose_eliminate 1.67% : 0.000006s : 37: predicate.tuple_list_convert_item_index_to_positive 1.78% : 0.000007s : 37: predicate.tuple_list_get_item_const_eliminator 1.56% : 0.000006s : 37: predicate.tuple_list_get_item_depend_reorder 3.29% : 0.000012s : 53: predicate.tuple_list_get_item_eliminator 1.64% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.42% : 0.000009s : 53: predicate.tuple_list_set_item_eliminator 1.66% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 2.39% : 0.000009s : 58: predicate.updatestate_pure_node_eliminater 3.01% : 0.000011s : 74: predicate.updatestate_useless_node_eliminater 0.39% : 0.000001s : 8: predicate.value_based_eliminate 0.90% : 0.000003s : 16: predicate.virtual_dataset_eliminate 0.80% : 0.000003s : 16: predicate.virtual_output_eliminate 0.30% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.48% : 0.000002s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.224005 32 99.10% : 0.221979s : 25: func_graph_cloner_run.FuncGraphClonerGraph 0.90% : 0.002026s : 7: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 2.035121 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.28% : 0.005790s : 1: add_attr 0.28% : 0.005768s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000104s : 1: add_recomputation 0.00% : 0.000006s : 1: assign_add_opt 0.00% : 0.000097s : 1: auto_monad 0.00% : 0.000037s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.04% : 0.000807s : 1: bootstrap 0.00% : 0.000046s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000028s : 1: control_data_broadcast_order 0.00% : 0.000022s : 1: convert_after_rewriter 0.00% : 0.000049s : 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 0.00% : 0.000033s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000006s : 1: handle_group_info 0.00% : 0.000006s : 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% : 0.000010s : 1: label_micro_interleaved_index 0.04% : 0.000825s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000007s : 1: micro_interleaved_order_control 0.04% : 0.000842s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.00% : 0.000029s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000034s : 1: opt.transform.mutable_eliminate 0.12% : 0.002445s : 78: opt.transform.opt_a 0.00% : 0.000057s : 1: opt.transform.opt_after_cconv 0.00% : 0.000047s : 1: opt.transform.opt_after_jit_grad 0.01% : 0.000276s : 28: opt.transform.opt_b 0.01% : 0.000134s : 2: opt.transform.opt_trans_graph 0.00% : 0.000094s : 4: opt.transform.symbol_engine_opt 7.29% : 0.148265s : 1: opt_a 0.01% : 0.000196s : 1: opt_after_cconv 0.03% : 0.000690s : 1: opt_after_jit_grad 0.02% : 0.000451s : 1: opt_b 7.48% : 0.152267s : 1: optimize 0.00% : 0.000034s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.00% : 0.000035s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 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% : 0.000004s : 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% : 0.000010s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000007s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.00% : 0.000051s : 1: pre_auto_parallel 0.00% : 0.000046s : 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% : 0.000071s : 1: remove_dup_value 6.95% : 0.141512s : 1: renormalize.infer 0.11% : 0.002278s : 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% : 0.000304s : 1: rewriter_after_opt_a 0.01% : 0.000106s : 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% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000014s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000336s : 1: symbol_engine_optimizer 0.01% : 0.000170s : 1: tuple_transform 77.17% : 1.570405s : 1: type_inference . [hook] pytest_runtest_teardown:test_swiglu_dyn_shape[shape2] tests/st/infer/ops/test_internal_ops/test_swiglu_v2.py::test_swiglu_dyn_shape[shape2],max_mem:102.0M =============================== 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 ================== 3 passed, 25 warnings in 90.53s (0:01:30) ===================