==================================================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_002/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 6 items test_reshape_and_cache.py [WARNING] ME(161324:281473315311408,MainProcess):2026-01-29-17:37:26.399.615 [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 = 0.147094, [21] [bootstrap]: 0.00061704 [type_inference]: 0.0293055 [event_method]: 1.411e-05 [auto_monad]: 0.00013301 [graph_reusing]: 5.33002e-06 [inline]: 2.99999e-06 [add_attr]: 0.109817, [1] [add_attr_with_inline]: 0.109804, [1] [Cycle 1]: 9.077e-05, [2] [tag_attr]: 1.704e-05 [meta_addattr_fg_expand]: 3.85e-06 [parallel-infer-symbol]: 3.93999e-06 [pre_auto_parallel]: 4.587e-05 [insert-virtual-dataset]: 2.75002e-06 [parallel-infer-symbol-second]: 1.04e-06 [dataset_repeat_opt]: 2.11e-06 [pipeline_split]: 1.66e-06 [optimize]: 0.00623197, [53] [py_interpret_to_execute]: 2.486e-05 [rewriter_before_opt_a]: 6.698e-05 [opt_a]: 0.00346521, [2] [Cycle 1]: 0.00236666, [45] [expand_dump_flag]: 2.93998e-06 [switch_simplify]: 3.318e-05 [loop_unroll]: 1.901e-05 [a_1]: 0.00050401 [with_stream_mark]: 2.054e-05 [recompute_prepare]: 1.324e-05 [updatestate_depend_eliminate]: 6.91001e-06 [updatestate_assign_eliminate]: 5.67001e-06 [updatestate_loads_eliminate]: 5.80002e-06 [parameter_eliminate]: 2.29999e-06 [a_2]: 0.00016904 [accelerated_algorithm]: 1.182e-05 [shard]: 2.78998e-06 [meta_shard_fg_expand]: 2.18998e-06 [shard_inline]: 1.186e-05 [merge_send_recv]: 3.042e-05 [auto_parallel]: 9.96998e-06 [parallel]: 4.1e-05 [flash_sp]: 1.892e-05 [merge_comm]: 6.38e-06 [allreduce_fusion]: 5.24e-06 [matmul_add_comm_reduction]: 1.231e-05 [allreduce_slice_to_reducescatter]: 7.00005e-07 [virtual_shard_identity]: 1.504e-05 [virtual_dataset]: 1.114e-05 [get_grad_eliminate_]: 1.076e-05 [virtual_output]: 1.117e-05 [merge_forward]: 5.91e-06 [cell_reuse_recompute_pass]: 1.73002e-06 [offload_activation]: 1.286e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.243e-05 [merge_recompute_call_nodes]: 1.45999e-06 [before_grad]: 2.007e-05 [set_forward_comm_id_for_comm_node_pass]: 5.55001e-06 [meta_fg_expand]: 3.87998e-06 [flash_sp_send_recv_attached]: 2.84999e-06 [receive_attached]: 1.032e-05 [after_resolve]: 2.063e-05 [a_after_grad]: 1.81e-05 [renormalize]: 0.00078276 [add_forward_monad_depend]: 6.09001e-06 [auto_monad_grad]: 2.55997e-06 [auto_monad_eliminator]: 2.322e-05 [cse]: 5.655e-05 [a_3]: 0.00013932 [Cycle 2]: 0.0010871, [45] [expand_dump_flag]: 1.84e-06 [switch_simplify]: 1.338e-05 [loop_unroll]: 1.147e-05 [a_1]: 0.00032079 [with_stream_mark]: 1.585e-05 [recompute_prepare]: 1.136e-05 [updatestate_depend_eliminate]: 5.40001e-06 [updatestate_assign_eliminate]: 4.80001e-06 [updatestate_loads_eliminate]: 5.42001e-06 [parameter_eliminate]: 1.32999e-06 [a_2]: 0.00015292 [accelerated_algorithm]: 1.134e-05 [shard]: 1.60001e-06 [meta_shard_fg_expand]: 2.55002e-06 [shard_inline]: 1.156e-05 [merge_send_recv]: 8.48001e-06 [auto_parallel]: 9.27001e-06 [parallel]: 6.04001e-06 [flash_sp]: 3.98001e-06 [merge_comm]: 5.92999e-06 [allreduce_fusion]: 5.51e-06 [matmul_add_comm_reduction]: 8.77e-06 [allreduce_slice_to_reducescatter]: 6.59988e-07 [virtual_shard_identity]: 1.207e-05 [virtual_dataset]: 1.122e-05 [get_grad_eliminate_]: 1.062e-05 [virtual_output]: 1.053e-05 [merge_forward]: 5.40999e-06 [cell_reuse_recompute_pass]: 2.26003e-06 [offload_activation]: 1.006e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.792e-05 [merge_recompute_call_nodes]: 1.13001e-06 [before_grad]: 1.661e-05 [set_forward_comm_id_for_comm_node_pass]: 5.54e-06 [meta_fg_expand]: 3.23998e-06 [flash_sp_send_recv_attached]: 1.04e-06 [receive_attached]: 2.04999e-06 [after_resolve]: 1.984e-05 [a_after_grad]: 1.744e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 1.47001e-06 [auto_monad_grad]: 1.48002e-06 [auto_monad_eliminator]: 1.425e-05 [cse]: 2.588e-05 [a_3]: 7.135e-05 [py_interpret_to_execute_after_opt_a]: 1.578e-05 [slice_cell_reuse_recomputed_activation]: 2.20002e-06 [rewriter_after_opt_a]: 0.00016052 [convert_after_rewriter]: 2.396e-05 [order_py_execute_after_rewriter]: 7.96001e-06 [mutable_eliminate]: 0.00069068 [opt_b]: 0.00035826, [1] [Cycle 1]: 0.00034953, [7] [b_1]: 0.00024916 [b_2]: 1.249e-05 [updatestate_depend_eliminate]: 1.07e-05 [updatestate_assign_eliminate]: 5.02e-06 [updatestate_loads_eliminate]: 5.14e-06 [renormalize]: 8.39995e-07 [cse]: 3.128e-05 [optimize_parallel_all_gather_comm]: 2.182e-05 [overlap_param_gather]: 2.17001e-06 [cconv]: 3.359e-05 [loop_unroll]: 0.00045398 [opt_after_cconv]: 0.00015927, [1] [Cycle 1]: 0.00015292, [7] [c_1]: 6.996e-05 [parameter_eliminate]: 3.95e-06 [updatestate_depend_eliminate]: 8.30999e-06 [updatestate_assign_eliminate]: 4.74e-06 [updatestate_loads_eliminate]: 4.2e-06 [cse]: 2.727e-05 [renormalize]: 4.80009e-07 [remove_dup_value]: 1.476e-05 [tuple_transform]: 0.00011581, [1] [Cycle 1]: 0.00011139, [4] [d_1]: 7.99e-05 [none_parameter_eliminate]: 1.56002e-06 [renormalize]: 1.8999e-07 [switch_simplify]: 1.183e-05 [partial_unused_args_eliminate]: 1.64998e-06 [add_recomputation]: 7.585e-05 [cse_after_recomputation]: 2.937e-05, [1] [Cycle 1]: 2.469e-05, [1] [cse]: 1.901e-05 [environ_conv]: 1.87e-05 [swap_dp_allreduce_reducescatter]: 7.43e-06 [bias_add_comm_swap]: 2.86e-06 [label_micro_interleaved_index]: 4.4e-06 [label_fine_grained_interleaved_index]: 2.91999e-06 [merge_cast_opt]: 1.20001e-06 [slice_recompute_activation]: 2.14e-06 [micro_interleaved_order_control]: 2.79001e-06 [assign_add_opt]: 1.30999e-06 [ForceFp32Comm]: 1.29e-06 [remove_cast_before_assign_add]: 1.07998e-06 [full_micro_interleaved_order_control]: 2.16998e-06 [reorder_send_recv_between_fp_bp]: 2.88e-06 [comm_op_add_attrs]: 1.04998e-06 [add_comm_op_reuse_tag]: 9.5999e-07 [interleave_split_concat_branches]: 1.29998e-06 [interleave_parallel_branches]: 1.07e-06 [overlap_opt_shard_in_pipeline]: 2.291e-05 [overlap_opt_shard_grad_in_pipeline]: 1.89999e-06 [control_data_broadcast_order]: 1.789e-05 [grouped_pairwise_exchange_alltoall]: 1.84e-06 [offloading_packed_experts]: 5.71998e-06 [overlap_recompute_and_grad_model_parallel]: 5.99e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.28002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.74998e-06 [overlap_recompute_comm]: 2.89001e-06 [overlap_grad_ring_attention]: 5.71e-06 [overlap_grad_flash_sp]: 3.818e-05 [begin_end_overlap_inline]: 6.00005e-07 [split_matmul_comm_elemetwise]: 2.62001e-06 [split_layernorm_comm]: 1.77999e-06 [handle_group_info]: 1.26997e-06 [symbol_engine_optimizer]: 0.00010245, [1] [Cycle 1]: 9.736e-05, [6] [build]: 5.66e-06 [elim_shapecalc]: 1.49e-05 [elim_not_effective]: 1.904e-05 [opt_reshape]: 1.193e-05 [fold_const_symbol]: 1.765e-05 [renormalize]: 3.19997e-07 [detach_backward]: 2.41e-06 [pipeline_parallel_scheduler]: 1.99999e-06 [auto_monad_reorder]: 3.741e-05 [get_jit_bprop_graph]: 1.69e-06 [rewriter_after_jit_bprop_graph]: 6.38998e-06 [opt_after_jit_grad]: 0.00061831 [validate]: 7.267e-05 Sums bootstrap : 0.000617s : 1.70% type_inference : 0.029306s : 80.78% event_method : 0.000014s : 0.04% auto_monad : 0.000133s : 0.37% graph_reusing : 0.000005s : 0.01% inline : 0.000003s : 0.01% add_attr.add_attr_with_inline.tag_attr : 0.000017s : 0.05% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.01% parallel-infer-symbol : 0.000004s : 0.01% pre_auto_parallel : 0.000046s : 0.13% insert-virtual-dataset : 0.000003s : 0.01% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.01% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000025s : 0.07% optimize.rewriter_before_opt_a : 0.000067s : 0.18% optimize.opt_a.expand_dump_flag : 0.000005s : 0.01% optimize.opt_a.switch_simplify : 0.000047s : 0.13% optimize.opt_a.loop_unroll : 0.000030s : 0.08% optimize.opt_a.a_1 : 0.000825s : 2.27% optimize.opt_a.with_stream_mark : 0.000036s : 0.10% optimize.opt_a.recompute_prepare : 0.000025s : 0.07% optimize.opt_a.updatestate_depend_eliminate : 0.000012s : 0.03% optimize.opt_a.updatestate_assign_eliminate : 0.000010s : 0.03% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.03% optimize.opt_a.parameter_eliminate : 0.000004s : 0.01% optimize.opt_a.a_2 : 0.000322s : 0.89% optimize.opt_a.accelerated_algorithm : 0.000023s : 0.06% optimize.opt_a.shard : 0.000004s : 0.01% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.01% optimize.opt_a.shard_inline : 0.000023s : 0.06% optimize.opt_a.merge_send_recv : 0.000039s : 0.11% optimize.opt_a.auto_parallel : 0.000019s : 0.05% optimize.opt_a.parallel : 0.000047s : 0.13% optimize.opt_a.flash_sp : 0.000023s : 0.06% optimize.opt_a.merge_comm : 0.000012s : 0.03% optimize.opt_a.allreduce_fusion : 0.000011s : 0.03% optimize.opt_a.matmul_add_comm_reduction : 0.000021s : 0.06% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000027s : 0.07% optimize.opt_a.virtual_dataset : 0.000022s : 0.06% optimize.opt_a.get_grad_eliminate_ : 0.000021s : 0.06% optimize.opt_a.virtual_output : 0.000022s : 0.06% optimize.opt_a.merge_forward : 0.000011s : 0.03% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.01% optimize.opt_a.offload_activation : 0.000023s : 0.06% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000040s : 0.11% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.01% optimize.opt_a.before_grad : 0.000037s : 0.10% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000011s : 0.03% optimize.opt_a.meta_fg_expand : 0.000007s : 0.02% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.01% optimize.opt_a.receive_attached : 0.000012s : 0.03% optimize.opt_a.after_resolve : 0.000040s : 0.11% optimize.opt_a.a_after_grad : 0.000036s : 0.10% optimize.opt_a.renormalize : 0.000783s : 2.16% optimize.opt_a.add_forward_monad_depend : 0.000008s : 0.02% optimize.opt_a.auto_monad_grad : 0.000004s : 0.01% optimize.opt_a.auto_monad_eliminator : 0.000037s : 0.10% optimize.opt_a.cse : 0.000082s : 0.23% optimize.opt_a.a_3 : 0.000211s : 0.58% optimize.py_interpret_to_execute_after_opt_a : 0.000016s : 0.04% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.01% optimize.rewriter_after_opt_a : 0.000161s : 0.44% optimize.convert_after_rewriter : 0.000024s : 0.07% optimize.order_py_execute_after_rewriter : 0.000008s : 0.02% optimize.mutable_eliminate : 0.000691s : 1.90% optimize.opt_b.b_1 : 0.000249s : 0.69% optimize.opt_b.b_2 : 0.000012s : 0.03% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.03% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000031s : 0.09% optimize.optimize_parallel_all_gather_comm : 0.000022s : 0.06% optimize.overlap_param_gather : 0.000002s : 0.01% optimize.cconv : 0.000034s : 0.09% optimize.loop_unroll : 0.000454s : 1.25% optimize.opt_after_cconv.c_1 : 0.000070s : 0.19% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000008s : 0.02% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.01% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.01% optimize.opt_after_cconv.cse : 0.000027s : 0.08% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000015s : 0.04% optimize.tuple_transform.d_1 : 0.000080s : 0.22% 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 : 0.03% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000076s : 0.21% optimize.cse_after_recomputation.cse : 0.000019s : 0.05% optimize.environ_conv : 0.000019s : 0.05% optimize.swap_dp_allreduce_reducescatter : 0.000007s : 0.02% optimize.bias_add_comm_swap : 0.000003s : 0.01% optimize.label_micro_interleaved_index : 0.000004s : 0.01% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.01% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.01% optimize.micro_interleaved_order_control : 0.000003s : 0.01% 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 : 0.01% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.01% 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 : 0.000023s : 0.06% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000018s : 0.05% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000006s : 0.02% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 0.02% 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 : 0.01% optimize.overlap_grad_ring_attention : 0.000006s : 0.02% optimize.overlap_grad_flash_sp : 0.000038s : 0.11% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.01% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000006s : 0.02% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000015s : 0.04% optimize.symbol_engine_optimizer.elim_not_effective : 0.000019s : 0.05% optimize.symbol_engine_optimizer.opt_reshape : 0.000012s : 0.03% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000018s : 0.05% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.01% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000037s : 0.10% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.02% opt_after_jit_grad : 0.000618s : 1.70% validate : 0.000073s : 0.20% Time group info: ------[substitution.] 0.000190 60 4.83% : 0.000009s : 2: substitution.depend_value_elim 1.34% : 0.000003s : 4: substitution.elim_not_effective 1.12% : 0.000002s : 4: substitution.fold_const_symbol 4.55% : 0.000009s : 9: substitution.graph_param_transform 58.94% : 0.000112s : 1: substitution.inline 4.38% : 0.000008s : 8: substitution.j_node_and_user_rematch 4.21% : 0.000008s : 8: substitution.remove_not_recompute_node 4.86% : 0.000009s : 10: substitution.replace_old_param 8.50% : 0.000016s : 6: substitution.updatestate_pure_node_eliminater 7.27% : 0.000014s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.029230 2 98.43% : 0.028772s : 1: type_inference.infer 1.57% : 0.000458s : 1: type_inference.specialize ------[replace.] 0.000018 1 100.00% : 0.000018s : 1: replace.inline ------[match.] 0.000111 1 100.00% : 0.000111s : 1: match.inline ------[predicate.] 0.000318 2105 0.91% : 0.000003s : 19: predicate.accumulaten_eliminater 0.67% : 0.000002s : 9: predicate.ad_related_special_op_eliminate 0.78% : 0.000002s : 18: predicate.addn_check_dump 0.82% : 0.000003s : 19: predicate.addn_zero_filter 0.76% : 0.000002s : 19: predicate.adjust_all_reduce_mul_add 1.79% : 0.000006s : 37: predicate.arithmetic_simplify 0.82% : 0.000003s : 19: predicate.cast_eliminate 0.83% : 0.000003s : 18: predicate.check_bprop_eliminate 0.79% : 0.000002s : 18: predicate.compare_switch_simplify 0.27% : 0.000001s : 9: predicate.const_output_eliminate 0.92% : 0.000003s : 18: predicate.depend_value_elim 0.83% : 0.000003s : 19: predicate.dict_get_item_const_eliminator 0.88% : 0.000003s : 19: predicate.dict_get_item_eliminator 0.79% : 0.000003s : 19: predicate.dict_set_item_eliminator 1.12% : 0.000004s : 18: predicate.dumpgradient_eliminate 0.30% : 0.000001s : 9: predicate.elim_not_effective 0.54% : 0.000002s : 9: predicate.elim_shapecalc_of_broadcastargs 1.20% : 0.000004s : 28: predicate.environ_add_const_eliminate 1.20% : 0.000004s : 28: predicate.environ_get_add_eliminate 1.15% : 0.000004s : 28: predicate.environ_get_depend_swap 2.02% : 0.000006s : 46: predicate.environ_get_eliminate 1.14% : 0.000004s : 28: predicate.environ_get_set_eliminate 0.97% : 0.000003s : 20: predicate.exchange_switch_depend_value 1.44% : 0.000005s : 20: predicate.float_depend_g_call 0.78% : 0.000002s : 18: predicate.float_environ_get_switch 1.18% : 0.000004s : 27: predicate.float_tuple_getitem_switch 0.28% : 0.000001s : 9: predicate.fold_const_symbol 0.88% : 0.000003s : 18: predicate.get_grad_eliminate 0.31% : 0.000001s : 9: predicate.graph_param_transform 0.78% : 0.000002s : 18: predicate.incorporate_call 0.74% : 0.000002s : 18: predicate.incorporate_call_switch 5.59% : 0.000018s : 93: predicate.inline 1.07% : 0.000003s : 18: predicate.inline_without_move 0.53% : 0.000002s : 18: predicate.j_node_and_user_rematch 0.99% : 0.000003s : 18: predicate.less_batch_normalization 1.77% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.43% : 0.000008s : 56: predicate.load_eliminater 0.81% : 0.000003s : 9: predicate.loop_unroll_after_grad 1.23% : 0.000004s : 27: predicate.loop_unroll_before_grad 1.88% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.87% : 0.000003s : 18: predicate.merge_addn 1.03% : 0.000003s : 18: predicate.micro_step_allgather_replace 0.81% : 0.000003s : 18: predicate.mini_step_allgather_replace 0.81% : 0.000003s : 19: predicate.minmaximum_grad 1.02% : 0.000003s : 9: predicate.mutable_eliminate 0.50% : 0.000002s : 9: predicate.opt_reshape 0.46% : 0.000001s : 9: predicate.parallel_virtual_node 0.98% : 0.000003s : 20: predicate.partial_defer_inline 1.35% : 0.000004s : 28: predicate.partial_eliminate 0.87% : 0.000003s : 19: predicate.print_const_string_wrapper 0.83% : 0.000003s : 18: predicate.reduce_all_const_elim 0.94% : 0.000003s : 19: predicate.reduce_eliminate 2.37% : 0.000008s : 56: predicate.redundant_stop_gradient_eliminater 0.64% : 0.000002s : 18: predicate.remove_not_recompute_node 1.30% : 0.000004s : 37: predicate.replace_applicator 0.70% : 0.000002s : 18: predicate.replace_old_param 0.32% : 0.000001s : 9: predicate.reset_defer_inline 0.83% : 0.000003s : 19: predicate.reshape_eliminate 0.87% : 0.000003s : 18: predicate.row_tensor_add_zeros_like 0.48% : 0.000002s : 9: predicate.row_tensor_eliminate 0.91% : 0.000003s : 18: predicate.same_eliminate 0.72% : 0.000002s : 18: predicate.set_cell_output_no_recompute 1.25% : 0.000004s : 18: predicate.shard_identity_eliminate 0.91% : 0.000003s : 18: predicate.special_op_eliminate 1.04% : 0.000003s : 18: predicate.specialize_transform 1.12% : 0.000004s : 18: predicate.split_environ_get_set_with_tuple_value 1.00% : 0.000003s : 18: predicate.stack_unstack_eliminate 0.47% : 0.000001s : 9: predicate.switch_call_monad_eliminater 0.89% : 0.000003s : 20: predicate.switch_defer_inline 1.70% : 0.000005s : 38: predicate.switch_layer_defer_inline 3.70% : 0.000012s : 74: predicate.switch_simplify 0.78% : 0.000002s : 19: predicate.tile_eliminate 0.82% : 0.000003s : 19: predicate.transpose_eliminate 1.56% : 0.000005s : 37: predicate.tuple_list_convert_item_index_to_positive 1.66% : 0.000005s : 37: predicate.tuple_list_get_item_const_eliminator 1.54% : 0.000005s : 37: predicate.tuple_list_get_item_depend_reorder 2.87% : 0.000009s : 55: predicate.tuple_list_get_item_eliminator 1.56% : 0.000005s : 37: predicate.tuple_list_get_set_item_eliminator 2.52% : 0.000008s : 55: predicate.tuple_list_set_item_eliminator 1.68% : 0.000005s : 37: predicate.tuple_to_list_eliminator_ 2.47% : 0.000008s : 56: predicate.updatestate_pure_node_eliminater 3.49% : 0.000011s : 74: predicate.updatestate_useless_node_eliminater 0.44% : 0.000001s : 9: predicate.value_based_eliminate 0.88% : 0.000003s : 18: predicate.virtual_dataset_eliminate 0.91% : 0.000003s : 18: predicate.virtual_output_eliminate 0.41% : 0.000001s : 9: predicate.virtual_view_grad_eliminate 0.50% : 0.000002s : 9: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000254 4 8.29% : 0.000021s : 1: func_graph_cloner_run.FuncGraphClonerGraph 91.71% : 0.000233s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.265941 192 0.00% : 0.000004s : 1: ForceFp32Comm 41.30% : 0.109824s : 1: add_attr 41.29% : 0.109808s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.03% : 0.000080s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.05% : 0.000140s : 1: auto_monad 0.02% : 0.000042s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.24% : 0.000648s : 1: bootstrap 0.01% : 0.000038s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000021s : 1: control_data_broadcast_order 0.01% : 0.000029s : 1: convert_after_rewriter 0.01% : 0.000032s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000022s : 1: environ_conv 0.01% : 0.000020s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000009s : 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% : 0.000006s : 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% : 0.000007s : 1: label_micro_interleaved_index 0.17% : 0.000462s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.26% : 0.000702s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.01% : 0.000019s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000024s : 1: opt.transform.mutable_eliminate 0.62% : 0.001656s : 78: opt.transform.opt_a 0.03% : 0.000069s : 1: opt.transform.opt_after_cconv 0.02% : 0.000040s : 1: opt.transform.opt_after_jit_grad 0.09% : 0.000231s : 28: opt.transform.opt_b 0.03% : 0.000090s : 2: opt.transform.opt_trans_graph 0.02% : 0.000060s : 4: opt.transform.symbol_engine_opt 1.30% : 0.003469s : 1: opt_a 0.06% : 0.000163s : 1: opt_after_cconv 0.24% : 0.000629s : 1: opt_after_jit_grad 0.14% : 0.000362s : 1: opt_b 2.35% : 0.006237s : 1: optimize 0.01% : 0.000026s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.02% : 0.000042s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000009s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.01% : 0.000027s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 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 0.02% : 0.000051s : 1: pre_auto_parallel 0.01% : 0.000029s : 1: py_interpret_to_execute 0.01% : 0.000019s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000018s : 1: remove_dup_value 0.17% : 0.000460s : 1: renormalize.infer 0.12% : 0.000313s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.06% : 0.000167s : 1: rewriter_after_opt_a 0.03% : 0.000073s : 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% : 0.000010s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000105s : 1: symbol_engine_optimizer 0.04% : 0.000119s : 1: tuple_transform 11.03% : 0.029330s : 1: type_inference . [hook] pytest_runtest_teardown:test_reshape_and_cache_net[0-float16] tests/st/infer/ops/test_internal_ops/test_reshape_and_cache.py::test_reshape_and_cache_net[0-float16],max_mem:374.0M [WARNING] ME(161324:281473315311408,MainProcess):2026-01-29-17:39:11.220.914 [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 = 0.171427, [21] [bootstrap]: 0.00080524 [type_inference]: 0.155208 [event_method]: 1.344e-05 [auto_monad]: 0.0002679 [graph_reusing]: 6.36998e-06 [inline]: 2.66e-06 [add_attr]: 0.00560231, [1] [add_attr_with_inline]: 0.0055848, [1] [Cycle 1]: 8.19e-05, [2] [tag_attr]: 2.038e-05 [meta_addattr_fg_expand]: 4.13001e-06 [parallel-infer-symbol]: 4.69998e-06 [pre_auto_parallel]: 6.378e-05 [insert-virtual-dataset]: 2.89001e-06 [parallel-infer-symbol-second]: 9.10019e-07 [dataset_repeat_opt]: 2.83e-06 [pipeline_split]: 2.29999e-06 [optimize]: 0.0083016, [53] [py_interpret_to_execute]: 4.228e-05 [rewriter_before_opt_a]: 8.389e-05 [opt_a]: 0.00477787, [2] [Cycle 1]: 0.00347087, [45] [expand_dump_flag]: 3.97e-06 [switch_simplify]: 3.653e-05 [loop_unroll]: 2.904e-05 [a_1]: 0.00059604 [with_stream_mark]: 2.675e-05 [recompute_prepare]: 1.538e-05 [updatestate_depend_eliminate]: 7.71999e-06 [updatestate_assign_eliminate]: 6.36e-06 [updatestate_loads_eliminate]: 6.49999e-06 [parameter_eliminate]: 2.46e-06 [a_2]: 0.00017776 [accelerated_algorithm]: 1.576e-05 [shard]: 3.41001e-06 [meta_shard_fg_expand]: 2.54001e-06 [shard_inline]: 1.265e-05 [merge_send_recv]: 1.121e-05 [auto_parallel]: 1.212e-05 [parallel]: 4.609e-05 [flash_sp]: 1.265e-05 [merge_comm]: 6.46e-06 [allreduce_fusion]: 5.65001e-06 [matmul_add_comm_reduction]: 1.412e-05 [allreduce_slice_to_reducescatter]: 9.09989e-07 [virtual_shard_identity]: 1.674e-05 [virtual_dataset]: 1.411e-05 [get_grad_eliminate_]: 1.479e-05 [virtual_output]: 1.132e-05 [merge_forward]: 5.66e-06 [cell_reuse_recompute_pass]: 1.50001e-06 [offload_activation]: 1.623e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.29e-05 [merge_recompute_call_nodes]: 1.70001e-06 [before_grad]: 2.777e-05 [set_forward_comm_id_for_comm_node_pass]: 7.1e-06 [meta_fg_expand]: 4.52998e-06 [flash_sp_send_recv_attached]: 3.01999e-06 [receive_attached]: 3.49001e-06 [after_resolve]: 2.332e-05 [a_after_grad]: 1.978e-05 [renormalize]: 0.0014956 [add_forward_monad_depend]: 1.013e-05 [auto_monad_grad]: 3.13e-06 [auto_monad_eliminator]: 3.11e-05 [cse]: 5.966e-05 [a_3]: 9.508e-05 [Cycle 2]: 0.00128681, [45] [expand_dump_flag]: 3.13e-06 [switch_simplify]: 1.608e-05 [loop_unroll]: 1.205e-05 [a_1]: 0.00032253 [with_stream_mark]: 3.026e-05 [recompute_prepare]: 1.352e-05 [updatestate_depend_eliminate]: 7.86001e-06 [updatestate_assign_eliminate]: 6.31e-06 [updatestate_loads_eliminate]: 1.174e-05 [parameter_eliminate]: 2.22999e-06 [a_2]: 0.000164 [accelerated_algorithm]: 1.329e-05 [shard]: 3.41999e-06 [meta_shard_fg_expand]: 2.94999e-06 [shard_inline]: 1.234e-05 [merge_send_recv]: 1.171e-05 [auto_parallel]: 1.189e-05 [parallel]: 1.066e-05 [flash_sp]: 4.35999e-06 [merge_comm]: 6.09999e-06 [allreduce_fusion]: 5.42001e-06 [matmul_add_comm_reduction]: 1.356e-05 [allreduce_slice_to_reducescatter]: 7.50006e-07 [virtual_shard_identity]: 1.338e-05 [virtual_dataset]: 1.14e-05 [get_grad_eliminate_]: 1.201e-05 [virtual_output]: 1.119e-05 [merge_forward]: 6.89999e-06 [cell_reuse_recompute_pass]: 3.45003e-06 [offload_activation]: 1.419e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.226e-05 [merge_recompute_call_nodes]: 1.45001e-06 [before_grad]: 1.865e-05 [set_forward_comm_id_for_comm_node_pass]: 5.97999e-06 [meta_fg_expand]: 4.32e-06 [flash_sp_send_recv_attached]: 1.59e-06 [receive_attached]: 2.29999e-06 [after_resolve]: 2.356e-05 [a_after_grad]: 1.906e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 2.54999e-06 [auto_monad_grad]: 1.81e-06 [auto_monad_eliminator]: 1.806e-05 [cse]: 5.165e-05 [a_3]: 7.424e-05 [py_interpret_to_execute_after_opt_a]: 2.283e-05 [slice_cell_reuse_recomputed_activation]: 2.99999e-06 [rewriter_after_opt_a]: 0.00017022 [convert_after_rewriter]: 1.438e-05 [order_py_execute_after_rewriter]: 7.56001e-06 [mutable_eliminate]: 0.00089337 [opt_b]: 0.00043005, [1] [Cycle 1]: 0.00042002, [7] [b_1]: 0.00026664 [b_2]: 1.47e-05 [updatestate_depend_eliminate]: 1.48e-05 [updatestate_assign_eliminate]: 5.21002e-06 [updatestate_loads_eliminate]: 6.26e-06 [renormalize]: 6.39993e-07 [cse]: 5.247e-05 [optimize_parallel_all_gather_comm]: 3.078e-05 [overlap_param_gather]: 2.17001e-06 [cconv]: 4.1e-05 [loop_unroll]: 0.0005862 [opt_after_cconv]: 0.00020374, [1] [Cycle 1]: 0.00019413, [7] [c_1]: 7.901e-05 [parameter_eliminate]: 6.54001e-06 [updatestate_depend_eliminate]: 1.048e-05 [updatestate_assign_eliminate]: 4.63999e-06 [updatestate_loads_eliminate]: 4.23001e-06 [cse]: 4.006e-05 [renormalize]: 7.10017e-07 [remove_dup_value]: 2.229e-05 [tuple_transform]: 0.00014213, [1] [Cycle 1]: 0.0001362, [4] [d_1]: 9.157e-05 [none_parameter_eliminate]: 2.37001e-06 [renormalize]: 3.09985e-07 [switch_simplify]: 1.351e-05 [partial_unused_args_eliminate]: 2.40002e-06 [add_recomputation]: 9.547e-05 [cse_after_recomputation]: 4.271e-05, [1] [Cycle 1]: 3.309e-05, [1] [cse]: 2.604e-05 [environ_conv]: 1.496e-05 [swap_dp_allreduce_reducescatter]: 1.01e-05 [bias_add_comm_swap]: 3.66001e-06 [label_micro_interleaved_index]: 7.14001e-06 [label_fine_grained_interleaved_index]: 3.31001e-06 [merge_cast_opt]: 1.37999e-06 [slice_recompute_activation]: 2.93e-06 [micro_interleaved_order_control]: 2.82002e-06 [assign_add_opt]: 1.71e-06 [ForceFp32Comm]: 1.35999e-06 [remove_cast_before_assign_add]: 1.34998e-06 [full_micro_interleaved_order_control]: 2.96999e-06 [reorder_send_recv_between_fp_bp]: 3.65998e-06 [comm_op_add_attrs]: 1.50999e-06 [add_comm_op_reuse_tag]: 1.06002e-06 [interleave_split_concat_branches]: 1.54e-06 [interleave_parallel_branches]: 1.47001e-06 [overlap_opt_shard_in_pipeline]: 2.62001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.77999e-06 [control_data_broadcast_order]: 2.345e-05 [grouped_pairwise_exchange_alltoall]: 2.08002e-06 [offloading_packed_experts]: 5.45001e-06 [overlap_recompute_and_grad_model_parallel]: 7.21001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.89e-06 [overlap_recompute_allgather_and_fa_grad]: 1.79e-06 [overlap_recompute_comm]: 2.74999e-06 [overlap_grad_ring_attention]: 6.58e-06 [overlap_grad_flash_sp]: 3.19e-05 [begin_end_overlap_inline]: 1.20001e-06 [split_matmul_comm_elemetwise]: 2.56998e-06 [split_layernorm_comm]: 2.06998e-06 [handle_group_info]: 1.00001e-06 [symbol_engine_optimizer]: 0.00015975, [1] [Cycle 1]: 0.00015237, [6] [build]: 6.37001e-06 [elim_shapecalc]: 2.265e-05 [elim_not_effective]: 2.349e-05 [opt_reshape]: 1.711e-05 [fold_const_symbol]: 2.174e-05 [renormalize]: 2.69996e-07 [detach_backward]: 2.81999e-06 [pipeline_parallel_scheduler]: 1.89e-06 [auto_monad_reorder]: 4.945e-05 [get_jit_bprop_graph]: 2.54001e-06 [rewriter_after_jit_bprop_graph]: 7.18998e-06 [opt_after_jit_grad]: 0.00075284 [validate]: 8.431e-05 Sums bootstrap : 0.000805s : 0.49% type_inference : 0.155208s : 94.55% event_method : 0.000013s : 0.01% auto_monad : 0.000268s : 0.16% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000020s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000064s : 0.04% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000042s : 0.03% optimize.rewriter_before_opt_a : 0.000084s : 0.05% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000053s : 0.03% optimize.opt_a.loop_unroll : 0.000041s : 0.03% optimize.opt_a.a_1 : 0.000919s : 0.56% optimize.opt_a.with_stream_mark : 0.000057s : 0.03% optimize.opt_a.recompute_prepare : 0.000029s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000016s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000013s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000018s : 0.01% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000342s : 0.21% optimize.opt_a.accelerated_algorithm : 0.000029s : 0.02% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000025s : 0.02% optimize.opt_a.merge_send_recv : 0.000023s : 0.01% optimize.opt_a.auto_parallel : 0.000024s : 0.01% optimize.opt_a.parallel : 0.000057s : 0.03% optimize.opt_a.flash_sp : 0.000017s : 0.01% optimize.opt_a.merge_comm : 0.000013s : 0.01% optimize.opt_a.allreduce_fusion : 0.000011s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000028s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000030s : 0.02% optimize.opt_a.virtual_dataset : 0.000026s : 0.02% optimize.opt_a.get_grad_eliminate_ : 0.000027s : 0.02% optimize.opt_a.virtual_output : 0.000023s : 0.01% optimize.opt_a.merge_forward : 0.000013s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000030s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000045s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000046s : 0.03% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000013s : 0.01% optimize.opt_a.meta_fg_expand : 0.000009s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000047s : 0.03% optimize.opt_a.a_after_grad : 0.000039s : 0.02% optimize.opt_a.renormalize : 0.001496s : 0.91% optimize.opt_a.add_forward_monad_depend : 0.000013s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000049s : 0.03% optimize.opt_a.cse : 0.000111s : 0.07% optimize.opt_a.a_3 : 0.000169s : 0.10% optimize.py_interpret_to_execute_after_opt_a : 0.000023s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000170s : 0.10% optimize.convert_after_rewriter : 0.000014s : 0.01% optimize.order_py_execute_after_rewriter : 0.000008s : 0.00% optimize.mutable_eliminate : 0.000893s : 0.54% optimize.opt_b.b_1 : 0.000267s : 0.16% optimize.opt_b.b_2 : 0.000015s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000015s : 0.01% 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 : 0.000052s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000031s : 0.02% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000041s : 0.02% optimize.loop_unroll : 0.000586s : 0.36% optimize.opt_after_cconv.c_1 : 0.000079s : 0.05% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.cse : 0.000040s : 0.02% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000022s : 0.01% optimize.tuple_transform.d_1 : 0.000092s : 0.06% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000014s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000095s : 0.06% optimize.cse_after_recomputation.cse : 0.000026s : 0.02% optimize.environ_conv : 0.000015s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 0.01% optimize.bias_add_comm_swap : 0.000004s : 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 : 0.000003s : 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 : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000004s : 0.00% optimize.comm_op_add_attrs : 0.000002s : 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 : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000023s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000005s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 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 : 0.000007s : 0.00% optimize.overlap_grad_flash_sp : 0.000032s : 0.02% 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 : 0.000006s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000023s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000023s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000017s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000022s : 0.01% 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 : 0.000049s : 0.03% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000753s : 0.46% validate : 0.000084s : 0.05% Time group info: ------[substitution.] 0.000265 60 4.02% : 0.000011s : 2: substitution.depend_value_elim 1.04% : 0.000003s : 4: substitution.elim_not_effective 0.98% : 0.000003s : 4: substitution.fold_const_symbol 3.81% : 0.000010s : 9: substitution.graph_param_transform 67.18% : 0.000178s : 1: substitution.inline 2.54% : 0.000007s : 8: substitution.j_node_and_user_rematch 2.92% : 0.000008s : 8: substitution.remove_not_recompute_node 4.09% : 0.000011s : 10: substitution.replace_old_param 7.37% : 0.000019s : 6: substitution.updatestate_pure_node_eliminater 6.06% : 0.000016s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.155116 2 99.58% : 0.154468s : 1: type_inference.infer 0.42% : 0.000648s : 1: type_inference.specialize ------[replace.] 0.000021 1 100.00% : 0.000021s : 1: replace.inline ------[match.] 0.000177 1 100.00% : 0.000177s : 1: match.inline ------[predicate.] 0.000337 2105 0.90% : 0.000003s : 19: predicate.accumulaten_eliminater 1.06% : 0.000004s : 9: predicate.ad_related_special_op_eliminate 0.74% : 0.000002s : 18: predicate.addn_check_dump 0.78% : 0.000003s : 19: predicate.addn_zero_filter 0.76% : 0.000003s : 19: predicate.adjust_all_reduce_mul_add 1.91% : 0.000006s : 37: predicate.arithmetic_simplify 0.83% : 0.000003s : 19: predicate.cast_eliminate 0.84% : 0.000003s : 18: predicate.check_bprop_eliminate 0.75% : 0.000003s : 18: predicate.compare_switch_simplify 0.25% : 0.000001s : 9: predicate.const_output_eliminate 0.85% : 0.000003s : 18: predicate.depend_value_elim 0.78% : 0.000003s : 19: predicate.dict_get_item_const_eliminator 0.86% : 0.000003s : 19: predicate.dict_get_item_eliminator 0.80% : 0.000003s : 19: predicate.dict_set_item_eliminator 1.45% : 0.000005s : 18: predicate.dumpgradient_eliminate 0.34% : 0.000001s : 9: predicate.elim_not_effective 0.61% : 0.000002s : 9: predicate.elim_shapecalc_of_broadcastargs 1.13% : 0.000004s : 28: predicate.environ_add_const_eliminate 1.09% : 0.000004s : 28: predicate.environ_get_add_eliminate 1.09% : 0.000004s : 28: predicate.environ_get_depend_swap 1.94% : 0.000007s : 46: predicate.environ_get_eliminate 1.17% : 0.000004s : 28: predicate.environ_get_set_eliminate 0.81% : 0.000003s : 20: predicate.exchange_switch_depend_value 1.45% : 0.000005s : 20: predicate.float_depend_g_call 0.80% : 0.000003s : 18: predicate.float_environ_get_switch 1.18% : 0.000004s : 27: predicate.float_tuple_getitem_switch 0.27% : 0.000001s : 9: predicate.fold_const_symbol 0.86% : 0.000003s : 18: predicate.get_grad_eliminate 0.36% : 0.000001s : 9: predicate.graph_param_transform 0.78% : 0.000003s : 18: predicate.incorporate_call 0.70% : 0.000002s : 18: predicate.incorporate_call_switch 5.53% : 0.000019s : 93: predicate.inline 1.33% : 0.000004s : 18: predicate.inline_without_move 0.49% : 0.000002s : 18: predicate.j_node_and_user_rematch 0.98% : 0.000003s : 18: predicate.less_batch_normalization 1.75% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.38% : 0.000008s : 56: predicate.load_eliminater 1.35% : 0.000005s : 9: predicate.loop_unroll_after_grad 1.23% : 0.000004s : 27: predicate.loop_unroll_before_grad 1.71% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.88% : 0.000003s : 18: predicate.merge_addn 0.79% : 0.000003s : 18: predicate.micro_step_allgather_replace 0.84% : 0.000003s : 18: predicate.mini_step_allgather_replace 0.70% : 0.000002s : 19: predicate.minmaximum_grad 1.46% : 0.000005s : 9: predicate.mutable_eliminate 0.55% : 0.000002s : 9: predicate.opt_reshape 0.46% : 0.000002s : 9: predicate.parallel_virtual_node 0.95% : 0.000003s : 20: predicate.partial_defer_inline 1.27% : 0.000004s : 28: predicate.partial_eliminate 0.84% : 0.000003s : 19: predicate.print_const_string_wrapper 0.81% : 0.000003s : 18: predicate.reduce_all_const_elim 0.94% : 0.000003s : 19: predicate.reduce_eliminate 2.18% : 0.000007s : 56: predicate.redundant_stop_gradient_eliminater 0.64% : 0.000002s : 18: predicate.remove_not_recompute_node 1.34% : 0.000005s : 37: predicate.replace_applicator 0.75% : 0.000003s : 18: predicate.replace_old_param 0.33% : 0.000001s : 9: predicate.reset_defer_inline 0.79% : 0.000003s : 19: predicate.reshape_eliminate 0.79% : 0.000003s : 18: predicate.row_tensor_add_zeros_like 0.53% : 0.000002s : 9: predicate.row_tensor_eliminate 0.95% : 0.000003s : 18: predicate.same_eliminate 0.58% : 0.000002s : 18: predicate.set_cell_output_no_recompute 1.35% : 0.000005s : 18: predicate.shard_identity_eliminate 0.90% : 0.000003s : 18: predicate.special_op_eliminate 1.08% : 0.000004s : 18: predicate.specialize_transform 1.15% : 0.000004s : 18: predicate.split_environ_get_set_with_tuple_value 1.03% : 0.000003s : 18: predicate.stack_unstack_eliminate 0.44% : 0.000001s : 9: predicate.switch_call_monad_eliminater 0.86% : 0.000003s : 20: predicate.switch_defer_inline 1.67% : 0.000006s : 38: predicate.switch_layer_defer_inline 3.86% : 0.000013s : 74: predicate.switch_simplify 0.77% : 0.000003s : 19: predicate.tile_eliminate 0.75% : 0.000003s : 19: predicate.transpose_eliminate 1.68% : 0.000006s : 37: predicate.tuple_list_convert_item_index_to_positive 1.61% : 0.000005s : 37: predicate.tuple_list_get_item_const_eliminator 1.49% : 0.000005s : 37: predicate.tuple_list_get_item_depend_reorder 2.90% : 0.000010s : 55: predicate.tuple_list_get_item_eliminator 1.47% : 0.000005s : 37: predicate.tuple_list_get_set_item_eliminator 2.39% : 0.000008s : 55: predicate.tuple_list_set_item_eliminator 1.61% : 0.000005s : 37: predicate.tuple_to_list_eliminator_ 2.27% : 0.000008s : 56: predicate.updatestate_pure_node_eliminater 3.21% : 0.000011s : 74: predicate.updatestate_useless_node_eliminater 0.46% : 0.000002s : 9: predicate.value_based_eliminate 0.85% : 0.000003s : 18: predicate.virtual_dataset_eliminate 0.90% : 0.000003s : 18: predicate.virtual_output_eliminate 0.38% : 0.000001s : 9: predicate.virtual_view_grad_eliminate 0.68% : 0.000002s : 9: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000486 4 5.28% : 0.000026s : 1: func_graph_cloner_run.FuncGraphClonerGraph 94.72% : 0.000460s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.189020 192 0.00% : 0.000005s : 1: ForceFp32Comm 2.97% : 0.005611s : 1: add_attr 2.96% : 0.005590s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.05% : 0.000101s : 1: add_recomputation 0.00% : 0.000007s : 1: assign_add_opt 0.15% : 0.000276s : 1: auto_monad 0.03% : 0.000057s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.45% : 0.000848s : 1: bootstrap 0.02% : 0.000046s : 1: cconv 0.00% : 0.000007s : 1: comm_op_add_attrs 0.02% : 0.000031s : 1: control_data_broadcast_order 0.01% : 0.000019s : 1: convert_after_rewriter 0.03% : 0.000049s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.01% : 0.000020s : 1: environ_conv 0.01% : 0.000027s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.01% : 0.000011s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.01% : 0.000010s : 1: inline 0.01% : 0.000011s : 1: insert-virtual-dataset 0.00% : 0.000008s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.01% : 0.000011s : 1: label_fine_grained_interleaved_index 0.01% : 0.000010s : 1: label_micro_interleaved_index 0.32% : 0.000599s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.48% : 0.000911s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.01% : 0.000024s : 1: opt.transform.loop_unroll_optimizer 0.02% : 0.000031s : 1: opt.transform.mutable_eliminate 0.94% : 0.001777s : 78: opt.transform.opt_a 0.04% : 0.000077s : 1: opt.transform.opt_after_cconv 0.04% : 0.000074s : 1: opt.transform.opt_after_jit_grad 0.13% : 0.000247s : 28: opt.transform.opt_b 0.05% : 0.000103s : 2: opt.transform.opt_trans_graph 0.04% : 0.000080s : 4: opt.transform.symbol_engine_opt 2.55% : 0.004817s : 1: opt_a 0.11% : 0.000208s : 1: opt_after_cconv 0.41% : 0.000773s : 1: opt_after_jit_grad 0.23% : 0.000434s : 1: opt_b 4.40% : 0.008310s : 1: optimize 0.02% : 0.000035s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000011s : 1: order_py_execute_after_rewriter 0.02% : 0.000039s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 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% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000014s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000008s : 1: overlap_recompute_comm 0.01% : 0.000012s : 1: parallel-infer-symbol 0.00% : 0.000008s : 1: parallel-infer-symbol-second 0.01% : 0.000010s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.04% : 0.000072s : 1: pre_auto_parallel 0.03% : 0.000051s : 1: py_interpret_to_execute 0.01% : 0.000027s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000008s : 1: remove_cast_before_assign_add 0.01% : 0.000027s : 1: remove_dup_value 0.47% : 0.000880s : 1: renormalize.infer 0.32% : 0.000601s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.09% : 0.000179s : 1: rewriter_after_opt_a 0.05% : 0.000089s : 1: rewriter_before_opt_a 0.00% : 0.000007s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000008s : 1: split_matmul_comm_elemetwise 0.01% : 0.000014s : 1: swap_dp_allreduce_reducescatter 0.09% : 0.000163s : 1: symbol_engine_optimizer 0.08% : 0.000145s : 1: tuple_transform 82.12% : 0.155232s : 1: type_inference . [hook] pytest_runtest_teardown:test_reshape_and_cache_net[0-bfloat16] tests/st/infer/ops/test_internal_ops/test_reshape_and_cache.py::test_reshape_and_cache_net[0-bfloat16],max_mem:624.0M [WARNING] ME(161324:281473315311408,MainProcess):2026-01-29-17:40:05.235.674 [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 = 0.173499, [21] [bootstrap]: 0.00064736 [type_inference]: 0.0422716 [event_method]: 2.047e-05 [auto_monad]: 0.00020894 [graph_reusing]: 5.62001e-06 [inline]: 3.13e-06 [add_attr]: 0.00593646, [1] [add_attr_with_inline]: 0.00591496, [1] [Cycle 1]: 8.447e-05, [2] [tag_attr]: 2.342e-05 [meta_addattr_fg_expand]: 4.82998e-06 [parallel-infer-symbol]: 5.00999e-06 [pre_auto_parallel]: 4.929e-05 [insert-virtual-dataset]: 2.88e-06 [parallel-infer-symbol-second]: 7.2e-07 [dataset_repeat_opt]: 2.39001e-06 [pipeline_split]: 1.87001e-06 [optimize]: 0.123042, [53] [py_interpret_to_execute]: 2.336e-05 [rewriter_before_opt_a]: 6.432e-05 [opt_a]: 0.118957, [2] [Cycle 1]: 0.117098, [45] [expand_dump_flag]: 3.08e-06 [switch_simplify]: 3.608e-05 [loop_unroll]: 1.981e-05 [a_1]: 0.0007022 [with_stream_mark]: 2.542e-05 [recompute_prepare]: 2.179e-05 [updatestate_depend_eliminate]: 6.92002e-06 [updatestate_assign_eliminate]: 6.16e-06 [updatestate_loads_eliminate]: 5.96998e-06 [parameter_eliminate]: 2.32001e-06 [a_2]: 0.00022619 [accelerated_algorithm]: 1.876e-05 [shard]: 3.43999e-06 [meta_shard_fg_expand]: 2.56e-06 [shard_inline]: 1.27e-05 [merge_send_recv]: 1.24e-05 [auto_parallel]: 1.452e-05 [parallel]: 4.171e-05 [flash_sp]: 1.142e-05 [merge_comm]: 6.91001e-06 [allreduce_fusion]: 8.74e-06 [matmul_add_comm_reduction]: 1.417e-05 [allreduce_slice_to_reducescatter]: 1.11002e-06 [virtual_shard_identity]: 2.808e-05 [virtual_dataset]: 1.973e-05 [get_grad_eliminate_]: 1.994e-05 [virtual_output]: 2.029e-05 [merge_forward]: 1.041e-05 [cell_reuse_recompute_pass]: 2.16003e-06 [offload_activation]: 1.54e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.522e-05 [merge_recompute_call_nodes]: 1.94999e-06 [before_grad]: 2.525e-05 [set_forward_comm_id_for_comm_node_pass]: 6.24001e-06 [meta_fg_expand]: 4.01001e-06 [flash_sp_send_recv_attached]: 3.7e-06 [receive_attached]: 3.11001e-06 [after_resolve]: 2.98e-05 [a_after_grad]: 2.85e-05 [renormalize]: 0.11503 [add_forward_monad_depend]: 1.331e-05 [auto_monad_grad]: 3.04999e-06 [auto_monad_eliminator]: 3.671e-05 [cse]: 7.045e-05 [a_3]: 0.00011772 [Cycle 2]: 0.00184187, [45] [expand_dump_flag]: 3.48e-06 [switch_simplify]: 2.615e-05 [loop_unroll]: 2.131e-05 [a_1]: 0.00049716 [with_stream_mark]: 3.234e-05 [recompute_prepare]: 2.42e-05 [updatestate_depend_eliminate]: 8.27e-06 [updatestate_assign_eliminate]: 6.31e-06 [updatestate_loads_eliminate]: 5.12e-06 [parameter_eliminate]: 3.46999e-06 [a_2]: 0.00022497 [accelerated_algorithm]: 2.481e-05 [shard]: 3.76999e-06 [meta_shard_fg_expand]: 4.17e-06 [shard_inline]: 1.298e-05 [merge_send_recv]: 1.349e-05 [auto_parallel]: 1.295e-05 [parallel]: 1.204e-05 [flash_sp]: 5.61e-06 [merge_comm]: 1.118e-05 [allreduce_fusion]: 6.02001e-06 [matmul_add_comm_reduction]: 1.602e-05 [allreduce_slice_to_reducescatter]: 9.50007e-07 [virtual_shard_identity]: 2.365e-05 [virtual_dataset]: 1.774e-05 [get_grad_eliminate_]: 2.052e-05 [virtual_output]: 2.067e-05 [merge_forward]: 7.40003e-06 [cell_reuse_recompute_pass]: 3.75e-06 [offload_activation]: 1.696e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.62e-05 [merge_recompute_call_nodes]: 1.66e-06 [before_grad]: 3.124e-05 [set_forward_comm_id_for_comm_node_pass]: 8.03999e-06 [meta_fg_expand]: 4.48001e-06 [flash_sp_send_recv_attached]: 2.12999e-06 [receive_attached]: 3.04001e-06 [after_resolve]: 3.663e-05 [a_after_grad]: 2.989e-05 [renormalize]: 2.30008e-07 [add_forward_monad_depend]: 5.10999e-06 [auto_monad_grad]: 2.99999e-06 [auto_monad_eliminator]: 2.446e-05 [cse]: 9.529e-05 [a_3]: 0.00013147 [py_interpret_to_execute_after_opt_a]: 2.76e-05 [slice_cell_reuse_recomputed_activation]: 2.40997e-06 [rewriter_after_opt_a]: 0.00018121 [convert_after_rewriter]: 1.352e-05 [order_py_execute_after_rewriter]: 8.72e-06 [mutable_eliminate]: 0.00093057 [opt_b]: 0.00071524, [1] [Cycle 1]: 0.00070398, [7] [b_1]: 0.0004919 [b_2]: 2.501e-05 [updatestate_depend_eliminate]: 1.937e-05 [updatestate_assign_eliminate]: 6.17001e-06 [updatestate_loads_eliminate]: 6.15002e-06 [renormalize]: 8.30012e-07 [cse]: 8.147e-05 [optimize_parallel_all_gather_comm]: 3.461e-05 [overlap_param_gather]: 2.71999e-06 [cconv]: 4.585e-05 [loop_unroll]: 0.00071126 [opt_after_cconv]: 0.00027466, [1] [Cycle 1]: 0.000267, [7] [c_1]: 0.00012096 [parameter_eliminate]: 6.31998e-06 [updatestate_depend_eliminate]: 1.301e-05 [updatestate_assign_eliminate]: 4.97e-06 [updatestate_loads_eliminate]: 8.01001e-06 [cse]: 5.432e-05 [renormalize]: 5.79981e-07 [remove_dup_value]: 1.892e-05 [tuple_transform]: 0.00022849, [1] [Cycle 1]: 0.00021517, [4] [d_1]: 0.00016232 [none_parameter_eliminate]: 2.48e-06 [renormalize]: 2.3999e-07 [switch_simplify]: 1.627e-05 [partial_unused_args_eliminate]: 2.56e-06 [add_recomputation]: 0.00011268 [cse_after_recomputation]: 5.473e-05, [1] [Cycle 1]: 4.845e-05, [1] [cse]: 3.547e-05 [environ_conv]: 1.628e-05 [swap_dp_allreduce_reducescatter]: 9.32001e-06 [bias_add_comm_swap]: 3.40003e-06 [label_micro_interleaved_index]: 6.59001e-06 [label_fine_grained_interleaved_index]: 3.01001e-06 [merge_cast_opt]: 1.56998e-06 [slice_recompute_activation]: 2.36998e-06 [micro_interleaved_order_control]: 2.86999e-06 [assign_add_opt]: 1.79e-06 [ForceFp32Comm]: 9.60019e-07 [remove_cast_before_assign_add]: 1.34e-06 [full_micro_interleaved_order_control]: 2.51998e-06 [reorder_send_recv_between_fp_bp]: 3.03998e-06 [comm_op_add_attrs]: 1.15001e-06 [add_comm_op_reuse_tag]: 1.04e-06 [interleave_split_concat_branches]: 1.46998e-06 [interleave_parallel_branches]: 1.31002e-06 [overlap_opt_shard_in_pipeline]: 3.65998e-06 [overlap_opt_shard_grad_in_pipeline]: 2.27999e-06 [control_data_broadcast_order]: 2.44e-05 [grouped_pairwise_exchange_alltoall]: 1.76003e-06 [offloading_packed_experts]: 6.32001e-06 [overlap_recompute_and_grad_model_parallel]: 1.307e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.44e-06 [overlap_recompute_allgather_and_fa_grad]: 1.75001e-06 [overlap_recompute_comm]: 2.58e-06 [overlap_grad_ring_attention]: 9.44e-06 [overlap_grad_flash_sp]: 3.154e-05 [begin_end_overlap_inline]: 6.59988e-07 [split_matmul_comm_elemetwise]: 2.49999e-06 [split_layernorm_comm]: 1.86e-06 [handle_group_info]: 9.79984e-07 [symbol_engine_optimizer]: 0.00017101, [1] [Cycle 1]: 0.00016564, [6] [build]: 6.00002e-06 [elim_shapecalc]: 3.238e-05 [elim_not_effective]: 2.837e-05 [opt_reshape]: 1.767e-05 [fold_const_symbol]: 2.409e-05 [renormalize]: 2.69996e-07 [detach_backward]: 2.43e-06 [pipeline_parallel_scheduler]: 1.55001e-06 [auto_monad_reorder]: 7.157e-05 [get_jit_bprop_graph]: 2.29999e-06 [rewriter_after_jit_bprop_graph]: 7.31999e-06 [opt_after_jit_grad]: 0.00090081 [validate]: 7.054e-05 Sums bootstrap : 0.000647s : 0.39% type_inference : 0.042272s : 25.46% event_method : 0.000020s : 0.01% auto_monad : 0.000209s : 0.13% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000023s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000049s : 0.03% 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 : 0.000023s : 0.01% optimize.rewriter_before_opt_a : 0.000064s : 0.04% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000062s : 0.04% optimize.opt_a.loop_unroll : 0.000041s : 0.02% optimize.opt_a.a_1 : 0.001199s : 0.72% optimize.opt_a.with_stream_mark : 0.000058s : 0.03% optimize.opt_a.recompute_prepare : 0.000046s : 0.03% optimize.opt_a.updatestate_depend_eliminate : 0.000015s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.01% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000451s : 0.27% optimize.opt_a.accelerated_algorithm : 0.000044s : 0.03% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.00% optimize.opt_a.shard_inline : 0.000026s : 0.02% optimize.opt_a.merge_send_recv : 0.000026s : 0.02% optimize.opt_a.auto_parallel : 0.000027s : 0.02% optimize.opt_a.parallel : 0.000054s : 0.03% optimize.opt_a.flash_sp : 0.000017s : 0.01% optimize.opt_a.merge_comm : 0.000018s : 0.01% optimize.opt_a.allreduce_fusion : 0.000015s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000030s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000052s : 0.03% optimize.opt_a.virtual_dataset : 0.000037s : 0.02% optimize.opt_a.get_grad_eliminate_ : 0.000040s : 0.02% optimize.opt_a.virtual_output : 0.000041s : 0.02% optimize.opt_a.merge_forward : 0.000018s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000032s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000071s : 0.04% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000056s : 0.03% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.01% optimize.opt_a.meta_fg_expand : 0.000008s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000066s : 0.04% optimize.opt_a.a_after_grad : 0.000058s : 0.04% optimize.opt_a.renormalize : 0.115030s : 69.28% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.01% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000061s : 0.04% optimize.opt_a.cse : 0.000166s : 0.10% optimize.opt_a.a_3 : 0.000249s : 0.15% optimize.py_interpret_to_execute_after_opt_a : 0.000028s : 0.02% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000181s : 0.11% optimize.convert_after_rewriter : 0.000014s : 0.01% optimize.order_py_execute_after_rewriter : 0.000009s : 0.01% optimize.mutable_eliminate : 0.000931s : 0.56% optimize.opt_b.b_1 : 0.000492s : 0.30% optimize.opt_b.b_2 : 0.000025s : 0.02% optimize.opt_b.updatestate_depend_eliminate : 0.000019s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000081s : 0.05% optimize.optimize_parallel_all_gather_comm : 0.000035s : 0.02% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000046s : 0.03% optimize.loop_unroll : 0.000711s : 0.43% optimize.opt_after_cconv.c_1 : 0.000121s : 0.07% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.cse : 0.000054s : 0.03% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000019s : 0.01% optimize.tuple_transform.d_1 : 0.000162s : 0.10% 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 : 0.01% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000113s : 0.07% optimize.cse_after_recomputation.cse : 0.000035s : 0.02% optimize.environ_conv : 0.000016s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 0.01% 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 : 0.000003s : 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 : 0.000004s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000024s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000013s : 0.01% 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 : 0.000009s : 0.01% optimize.overlap_grad_flash_sp : 0.000032s : 0.02% 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 : 0.000006s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000032s : 0.02% optimize.symbol_engine_optimizer.elim_not_effective : 0.000028s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000018s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000024s : 0.01% 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 : 0.000072s : 0.04% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000901s : 0.54% validate : 0.000071s : 0.04% Time group info: ------[substitution.] 0.000303 60 3.91% : 0.000012s : 2: substitution.depend_value_elim 1.02% : 0.000003s : 4: substitution.elim_not_effective 0.72% : 0.000002s : 4: substitution.fold_const_symbol 3.29% : 0.000010s : 9: substitution.graph_param_transform 66.24% : 0.000200s : 1: substitution.inline 2.24% : 0.000007s : 8: substitution.j_node_and_user_rematch 2.69% : 0.000008s : 8: substitution.remove_not_recompute_node 4.13% : 0.000012s : 10: substitution.replace_old_param 7.52% : 0.000023s : 6: substitution.updatestate_pure_node_eliminater 8.26% : 0.000025s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.042167 2 97.25% : 0.041006s : 1: type_inference.infer 2.75% : 0.001161s : 1: type_inference.specialize ------[replace.] 0.000021 1 100.00% : 0.000021s : 1: replace.inline ------[match.] 0.000199 1 100.00% : 0.000199s : 1: match.inline ------[predicate.] 0.000354 2105 0.91% : 0.000003s : 19: predicate.accumulaten_eliminater 0.92% : 0.000003s : 9: predicate.ad_related_special_op_eliminate 0.72% : 0.000003s : 18: predicate.addn_check_dump 0.87% : 0.000003s : 19: predicate.addn_zero_filter 0.72% : 0.000003s : 19: predicate.adjust_all_reduce_mul_add 2.02% : 0.000007s : 37: predicate.arithmetic_simplify 0.83% : 0.000003s : 19: predicate.cast_eliminate 0.82% : 0.000003s : 18: predicate.check_bprop_eliminate 0.73% : 0.000003s : 18: predicate.compare_switch_simplify 0.25% : 0.000001s : 9: predicate.const_output_eliminate 0.97% : 0.000003s : 18: predicate.depend_value_elim 0.79% : 0.000003s : 19: predicate.dict_get_item_const_eliminator 0.89% : 0.000003s : 19: predicate.dict_get_item_eliminator 0.76% : 0.000003s : 19: predicate.dict_set_item_eliminator 1.20% : 0.000004s : 18: predicate.dumpgradient_eliminate 0.29% : 0.000001s : 9: predicate.elim_not_effective 0.45% : 0.000002s : 9: predicate.elim_shapecalc_of_broadcastargs 1.31% : 0.000005s : 28: predicate.environ_add_const_eliminate 1.09% : 0.000004s : 28: predicate.environ_get_add_eliminate 1.16% : 0.000004s : 28: predicate.environ_get_depend_swap 2.12% : 0.000007s : 46: predicate.environ_get_eliminate 1.10% : 0.000004s : 28: predicate.environ_get_set_eliminate 0.77% : 0.000003s : 20: predicate.exchange_switch_depend_value 1.41% : 0.000005s : 20: predicate.float_depend_g_call 0.73% : 0.000003s : 18: predicate.float_environ_get_switch 1.13% : 0.000004s : 27: predicate.float_tuple_getitem_switch 0.25% : 0.000001s : 9: predicate.fold_const_symbol 1.03% : 0.000004s : 18: predicate.get_grad_eliminate 0.38% : 0.000001s : 9: predicate.graph_param_transform 0.85% : 0.000003s : 18: predicate.incorporate_call 0.67% : 0.000002s : 18: predicate.incorporate_call_switch 5.73% : 0.000020s : 93: predicate.inline 1.49% : 0.000005s : 18: predicate.inline_without_move 0.45% : 0.000002s : 18: predicate.j_node_and_user_rematch 1.13% : 0.000004s : 18: predicate.less_batch_normalization 1.75% : 0.000006s : 37: predicate.list_to_tuple_eliminator_ 2.21% : 0.000008s : 56: predicate.load_eliminater 0.98% : 0.000003s : 9: predicate.loop_unroll_after_grad 1.19% : 0.000004s : 27: predicate.loop_unroll_before_grad 1.78% : 0.000006s : 37: predicate.make_slice_get_slice_eliminator 0.77% : 0.000003s : 18: predicate.merge_addn 0.77% : 0.000003s : 18: predicate.micro_step_allgather_replace 0.83% : 0.000003s : 18: predicate.mini_step_allgather_replace 0.70% : 0.000002s : 19: predicate.minmaximum_grad 1.20% : 0.000004s : 9: predicate.mutable_eliminate 0.46% : 0.000002s : 9: predicate.opt_reshape 0.41% : 0.000001s : 9: predicate.parallel_virtual_node 1.08% : 0.000004s : 20: predicate.partial_defer_inline 1.23% : 0.000004s : 28: predicate.partial_eliminate 0.89% : 0.000003s : 19: predicate.print_const_string_wrapper 0.85% : 0.000003s : 18: predicate.reduce_all_const_elim 1.01% : 0.000004s : 19: predicate.reduce_eliminate 2.33% : 0.000008s : 56: predicate.redundant_stop_gradient_eliminater 0.63% : 0.000002s : 18: predicate.remove_not_recompute_node 1.44% : 0.000005s : 37: predicate.replace_applicator 0.71% : 0.000003s : 18: predicate.replace_old_param 0.41% : 0.000001s : 9: predicate.reset_defer_inline 0.84% : 0.000003s : 19: predicate.reshape_eliminate 0.87% : 0.000003s : 18: predicate.row_tensor_add_zeros_like 0.45% : 0.000002s : 9: predicate.row_tensor_eliminate 1.05% : 0.000004s : 18: predicate.same_eliminate 0.62% : 0.000002s : 18: predicate.set_cell_output_no_recompute 1.02% : 0.000004s : 18: predicate.shard_identity_eliminate 0.84% : 0.000003s : 18: predicate.special_op_eliminate 0.91% : 0.000003s : 18: predicate.specialize_transform 1.39% : 0.000005s : 18: predicate.split_environ_get_set_with_tuple_value 0.91% : 0.000003s : 18: predicate.stack_unstack_eliminate 0.47% : 0.000002s : 9: predicate.switch_call_monad_eliminater 0.79% : 0.000003s : 20: predicate.switch_defer_inline 1.57% : 0.000006s : 38: predicate.switch_layer_defer_inline 3.56% : 0.000013s : 74: predicate.switch_simplify 0.85% : 0.000003s : 19: predicate.tile_eliminate 0.84% : 0.000003s : 19: predicate.transpose_eliminate 1.54% : 0.000005s : 37: predicate.tuple_list_convert_item_index_to_positive 1.72% : 0.000006s : 37: predicate.tuple_list_get_item_const_eliminator 1.49% : 0.000005s : 37: predicate.tuple_list_get_item_depend_reorder 2.97% : 0.000011s : 55: predicate.tuple_list_get_item_eliminator 1.78% : 0.000006s : 37: predicate.tuple_list_get_set_item_eliminator 2.35% : 0.000008s : 55: predicate.tuple_list_set_item_eliminator 1.76% : 0.000006s : 37: predicate.tuple_to_list_eliminator_ 2.25% : 0.000008s : 56: predicate.updatestate_pure_node_eliminater 3.55% : 0.000013s : 74: predicate.updatestate_useless_node_eliminater 0.40% : 0.000001s : 9: predicate.value_based_eliminate 0.84% : 0.000003s : 18: predicate.virtual_dataset_eliminate 0.87% : 0.000003s : 18: predicate.virtual_output_eliminate 0.36% : 0.000001s : 9: predicate.virtual_view_grad_eliminate 0.54% : 0.000002s : 9: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000684 4 3.93% : 0.000027s : 1: func_graph_cloner_run.FuncGraphClonerGraph 96.07% : 0.000657s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.420720 192 0.00% : 0.000004s : 1: ForceFp32Comm 1.41% : 0.005944s : 1: add_attr 1.41% : 0.005919s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.03% : 0.000117s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.05% : 0.000223s : 1: auto_monad 0.02% : 0.000077s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.16% : 0.000694s : 1: bootstrap 0.01% : 0.000050s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000028s : 1: control_data_broadcast_order 0.00% : 0.000018s : 1: convert_after_rewriter 0.01% : 0.000058s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000020s : 1: environ_conv 0.01% : 0.000030s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000012s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000017s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000010s : 1: label_fine_grained_interleaved_index 0.00% : 0.000013s : 1: label_micro_interleaved_index 0.17% : 0.000723s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.22% : 0.000945s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.01% : 0.000035s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000032s : 1: opt.transform.mutable_eliminate 0.57% : 0.002413s : 78: opt.transform.opt_a 0.03% : 0.000119s : 1: opt.transform.opt_after_cconv 0.03% : 0.000132s : 1: opt.transform.opt_after_jit_grad 0.10% : 0.000419s : 28: opt.transform.opt_b 0.04% : 0.000176s : 2: opt.transform.opt_trans_graph 0.02% : 0.000098s : 4: opt.transform.symbol_engine_opt 28.28% : 0.118961s : 1: opt_a 0.07% : 0.000279s : 1: opt_after_cconv 0.22% : 0.000920s : 1: opt_after_jit_grad 0.17% : 0.000720s : 1: opt_b 29.25% : 0.123048s : 1: optimize 0.01% : 0.000039s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.01% : 0.000036s : 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% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000010s : 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% : 0.000017s : 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% : 0.000009s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000055s : 1: pre_auto_parallel 0.01% : 0.000027s : 1: py_interpret_to_execute 0.01% : 0.000032s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000009s : 1: remove_cast_before_assign_add 0.01% : 0.000023s : 1: remove_dup_value 27.16% : 0.114285s : 1: renormalize.infer 0.17% : 0.000718s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000015s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000187s : 1: rewriter_after_opt_a 0.02% : 0.000070s : 1: rewriter_before_opt_a 0.00% : 0.000010s : 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% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000174s : 1: symbol_engine_optimizer 0.06% : 0.000232s : 1: tuple_transform 10.06% : 0.042309s : 1: type_inference . [hook] pytest_runtest_teardown:test_reshape_and_cache_net[0-int8] tests/st/infer/ops/test_internal_ops/test_reshape_and_cache.py::test_reshape_and_cache_net[0-int8],max_mem:624.0M [WARNING] ME(161324:281473315311408,MainProcess):2026-01-29-17:40:30.416.817 [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. . [hook] pytest_runtest_teardown:test_reshape_and_cache_net[1-float16] tests/st/infer/ops/test_internal_ops/test_reshape_and_cache.py::test_reshape_and_cache_net[1-float16],max_mem:490.0M [WARNING] ME(161324:281473315311408,MainProcess):2026-01-29-17:41:40.915.577 [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. . [hook] pytest_runtest_teardown:test_reshape_and_cache_net[1-bfloat16] tests/st/infer/ops/test_internal_ops/test_reshape_and_cache.py::test_reshape_and_cache_net[1-bfloat16],max_mem:990.0M [WARNING] ME(161324:281473315311408,MainProcess):2026-01-29-17:42:50.740.482 [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. . [hook] pytest_runtest_teardown:test_reshape_and_cache_net[1-int8] tests/st/infer/ops/test_internal_ops/test_reshape_and_cache.py::test_reshape_and_cache_net[1-int8],max_mem:990.0M =============================== 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 ================== 6 passed, 25 warnings in 392.32s (0:06:32) ==================