==================================================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_007/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 4 items test_qbmm_split.py [WARNING] ME(171828:281473644855088,MainProcess):2026-01-29-17:37:51.447.52 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 3.62326, [21] [bootstrap]: 0.00059534 [type_inference]: 3.04906 [event_method]: 0.00021427 [auto_monad]: 0.207738 [graph_reusing]: 7.503e-05 [inline]: 3.64002e-06 [add_attr]: 0.00878799, [1] [add_attr_with_inline]: 0.00876708, [1] [Cycle 1]: 0.00034019, [2] [tag_attr]: 0.00019946 [meta_addattr_fg_expand]: 5.424e-05 [parallel-infer-symbol]: 4.11001e-06 [pre_auto_parallel]: 0.00026189 [insert-virtual-dataset]: 2.74999e-06 [parallel-infer-symbol-second]: 1.44e-06 [dataset_repeat_opt]: 2.36998e-06 [pipeline_split]: 1.62999e-06 [optimize]: 0.355123, [53] [py_interpret_to_execute]: 0.00019456 [rewriter_before_opt_a]: 0.00076806 [opt_a]: 0.214377, [2] [Cycle 1]: 0.211827, [45] [expand_dump_flag]: 1.791e-05 [switch_simplify]: 0.00068811 [loop_unroll]: 0.00025692 [a_1]: 0.0966386 [with_stream_mark]: 0.00010774 [recompute_prepare]: 5.038e-05 [updatestate_depend_eliminate]: 2.557e-05 [updatestate_assign_eliminate]: 1.955e-05 [updatestate_loads_eliminate]: 2.764e-05 [parameter_eliminate]: 2.79999e-06 [a_2]: 0.00100446 [accelerated_algorithm]: 6.302e-05 [shard]: 2.55002e-06 [meta_shard_fg_expand]: 2.422e-05 [shard_inline]: 2.946e-05 [merge_send_recv]: 2.386e-05 [auto_parallel]: 2.332e-05 [parallel]: 6.595e-05 [flash_sp]: 1.794e-05 [merge_comm]: 1.789e-05 [allreduce_fusion]: 1.673e-05 [matmul_add_comm_reduction]: 2.639e-05 [allreduce_slice_to_reducescatter]: 8.99978e-07 [virtual_shard_identity]: 3.755e-05 [virtual_dataset]: 2.659e-05 [get_grad_eliminate_]: 2.653e-05 [virtual_output]: 2.895e-05 [merge_forward]: 1.753e-05 [cell_reuse_recompute_pass]: 3.35e-06 [offload_activation]: 2.909e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.538e-05 [merge_recompute_call_nodes]: 1.65001e-06 [before_grad]: 4.543e-05 [set_forward_comm_id_for_comm_node_pass]: 1.89e-05 [meta_fg_expand]: 2.174e-05 [flash_sp_send_recv_attached]: 5.67001e-06 [receive_attached]: 2.43e-06 [after_resolve]: 3.859e-05 [a_after_grad]: 5.05e-05 [renormalize]: 0.111108 [add_forward_monad_depend]: 2.009e-05 [auto_monad_grad]: 3.41001e-06 [auto_monad_eliminator]: 9.858e-05 [cse]: 0.00041259 [a_3]: 0.00020639 [Cycle 2]: 0.00253234, [45] [expand_dump_flag]: 3.28e-06 [switch_simplify]: 2.923e-05 [loop_unroll]: 2.523e-05 [a_1]: 0.00080356 [with_stream_mark]: 3.385e-05 [recompute_prepare]: 2.829e-05 [updatestate_depend_eliminate]: 1.723e-05 [updatestate_assign_eliminate]: 1.54e-05 [updatestate_loads_eliminate]: 2.122e-05 [parameter_eliminate]: 2.94001e-06 [a_2]: 0.00041889 [accelerated_algorithm]: 3.629e-05 [shard]: 2.88998e-06 [meta_shard_fg_expand]: 9.51e-06 [shard_inline]: 2.71e-05 [merge_send_recv]: 2.312e-05 [auto_parallel]: 2.285e-05 [parallel]: 9.99999e-06 [flash_sp]: 4.44002e-06 [merge_comm]: 1.681e-05 [allreduce_fusion]: 1.457e-05 [matmul_add_comm_reduction]: 2.489e-05 [allreduce_slice_to_reducescatter]: 1.39e-06 [virtual_shard_identity]: 2.796e-05 [virtual_dataset]: 2.597e-05 [get_grad_eliminate_]: 2.413e-05 [virtual_output]: 2.398e-05 [merge_forward]: 1.515e-05 [cell_reuse_recompute_pass]: 2.76999e-06 [offload_activation]: 2.594e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.979e-05 [merge_recompute_call_nodes]: 1.81e-06 [before_grad]: 4.476e-05 [set_forward_comm_id_for_comm_node_pass]: 1.731e-05 [meta_fg_expand]: 1.117e-05 [flash_sp_send_recv_attached]: 1.75001e-06 [receive_attached]: 3.11001e-06 [after_resolve]: 3.864e-05 [a_after_grad]: 4.125e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 3.09001e-06 [auto_monad_grad]: 2.48e-06 [auto_monad_eliminator]: 6.651e-05 [cse]: 9.762e-05 [a_3]: 0.00017483 [py_interpret_to_execute_after_opt_a]: 3.838e-05 [slice_cell_reuse_recomputed_activation]: 2.04999e-06 [rewriter_after_opt_a]: 0.00089658 [convert_after_rewriter]: 2.986e-05 [order_py_execute_after_rewriter]: 1.504e-05 [mutable_eliminate]: 0.00079013 [opt_b]: 0.00095101, [1] [Cycle 1]: 0.00094171, [7] [b_1]: 0.00066424 [b_2]: 2.95e-05 [updatestate_depend_eliminate]: 2.209e-05 [updatestate_assign_eliminate]: 1.47e-05 [updatestate_loads_eliminate]: 2.185e-05 [renormalize]: 7.59988e-07 [cse]: 0.00012812 [optimize_parallel_all_gather_comm]: 4.641e-05 [overlap_param_gather]: 2.04999e-06 [cconv]: 4.213e-05 [loop_unroll]: 0.00057483 [opt_after_cconv]: 0.0003963, [1] [Cycle 1]: 0.00038876, [7] [c_1]: 0.00017003 [parameter_eliminate]: 5.54e-06 [updatestate_depend_eliminate]: 2.507e-05 [updatestate_assign_eliminate]: 1.854e-05 [updatestate_loads_eliminate]: 2.162e-05 [cse]: 0.00010187 [renormalize]: 9.70002e-07 [remove_dup_value]: 0.00012723 [tuple_transform]: 0.00030762, [1] [Cycle 1]: 0.00030174, [4] [d_1]: 0.00024309 [none_parameter_eliminate]: 2.29001e-06 [renormalize]: 3.89991e-07 [switch_simplify]: 2.971e-05 [partial_unused_args_eliminate]: 2.58e-06 [add_recomputation]: 0.00018839 [cse_after_recomputation]: 8.793e-05, [1] [Cycle 1]: 8.158e-05, [1] [cse]: 7.221e-05 [environ_conv]: 4.153e-05 [swap_dp_allreduce_reducescatter]: 2.253e-05 [bias_add_comm_swap]: 4.32e-06 [label_micro_interleaved_index]: 6.56e-06 [label_fine_grained_interleaved_index]: 3.31999e-06 [merge_cast_opt]: 1.40999e-06 [slice_recompute_activation]: 2.39999e-06 [micro_interleaved_order_control]: 2.61999e-06 [assign_add_opt]: 1.47999e-06 [ForceFp32Comm]: 1.04e-06 [remove_cast_before_assign_add]: 1.43002e-06 [full_micro_interleaved_order_control]: 2.09999e-06 [reorder_send_recv_between_fp_bp]: 2.68e-06 [comm_op_add_attrs]: 1.21997e-06 [add_comm_op_reuse_tag]: 1.30001e-06 [interleave_split_concat_branches]: 1.22e-06 [interleave_parallel_branches]: 1.07998e-06 [overlap_opt_shard_in_pipeline]: 2.779e-05 [overlap_opt_shard_grad_in_pipeline]: 2.22001e-06 [control_data_broadcast_order]: 4.707e-05 [grouped_pairwise_exchange_alltoall]: 2.04999e-06 [offloading_packed_experts]: 0.133965 [overlap_recompute_and_grad_model_parallel]: 2.502e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.73002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.48002e-06 [overlap_recompute_comm]: 2.68e-06 [overlap_grad_ring_attention]: 1.23e-05 [overlap_grad_flash_sp]: 9.31e-05 [begin_end_overlap_inline]: 9.30013e-07 [split_matmul_comm_elemetwise]: 2.53e-06 [split_layernorm_comm]: 1.64e-06 [handle_group_info]: 9.89996e-07 [symbol_engine_optimizer]: 0.00064794, [1] [Cycle 1]: 0.00063552, [6] [build]: 0.00034549 [elim_shapecalc]: 5.512e-05 [elim_not_effective]: 7.21e-05 [opt_reshape]: 3.941e-05 [fold_const_symbol]: 6.915e-05 [renormalize]: 4.39992e-07 [detach_backward]: 3.09001e-06 [pipeline_parallel_scheduler]: 1.67999e-06 [auto_monad_reorder]: 0.00010456 [get_jit_bprop_graph]: 1.97001e-06 [rewriter_after_jit_bprop_graph]: 6.09999e-06 [opt_after_jit_grad]: 0.00088028 [validate]: 0.00013279 Sums bootstrap : 0.000595s : 0.02% type_inference : 3.049061s : 84.39% event_method : 0.000214s : 0.01% auto_monad : 0.207738s : 5.75% graph_reusing : 0.000075s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000199s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000054s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000262s : 0.01% 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 : 0.000195s : 0.01% optimize.rewriter_before_opt_a : 0.000768s : 0.02% optimize.opt_a.expand_dump_flag : 0.000021s : 0.00% optimize.opt_a.switch_simplify : 0.000717s : 0.02% optimize.opt_a.loop_unroll : 0.000282s : 0.01% optimize.opt_a.a_1 : 0.097442s : 2.70% optimize.opt_a.with_stream_mark : 0.000142s : 0.00% optimize.opt_a.recompute_prepare : 0.000079s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000043s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000035s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000049s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001423s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000099s : 0.00% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000034s : 0.00% optimize.opt_a.shard_inline : 0.000057s : 0.00% optimize.opt_a.merge_send_recv : 0.000047s : 0.00% optimize.opt_a.auto_parallel : 0.000046s : 0.00% optimize.opt_a.parallel : 0.000076s : 0.00% optimize.opt_a.flash_sp : 0.000022s : 0.00% optimize.opt_a.merge_comm : 0.000035s : 0.00% optimize.opt_a.allreduce_fusion : 0.000031s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000051s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000066s : 0.00% optimize.opt_a.virtual_dataset : 0.000053s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000051s : 0.00% optimize.opt_a.virtual_output : 0.000053s : 0.00% optimize.opt_a.merge_forward : 0.000033s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000055s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000105s : 0.00% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000090s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000036s : 0.00% optimize.opt_a.meta_fg_expand : 0.000033s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000077s : 0.00% optimize.opt_a.a_after_grad : 0.000092s : 0.00% optimize.opt_a.renormalize : 0.111108s : 3.08% optimize.opt_a.add_forward_monad_depend : 0.000023s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000165s : 0.00% optimize.opt_a.cse : 0.000510s : 0.01% optimize.opt_a.a_3 : 0.000381s : 0.01% optimize.py_interpret_to_execute_after_opt_a : 0.000038s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000897s : 0.02% optimize.convert_after_rewriter : 0.000030s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000790s : 0.02% optimize.opt_b.b_1 : 0.000664s : 0.02% optimize.opt_b.b_2 : 0.000030s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000022s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000022s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000128s : 0.00% optimize.optimize_parallel_all_gather_comm : 0.000046s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000042s : 0.00% optimize.loop_unroll : 0.000575s : 0.02% optimize.opt_after_cconv.c_1 : 0.000170s : 0.00% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000025s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000019s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000022s : 0.00% optimize.opt_after_cconv.cse : 0.000102s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000127s : 0.00% optimize.tuple_transform.d_1 : 0.000243s : 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 : 0.000030s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000188s : 0.01% optimize.cse_after_recomputation.cse : 0.000072s : 0.00% optimize.environ_conv : 0.000042s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000023s : 0.00% 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 : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000028s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000047s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.133965s : 3.71% optimize.overlap_recompute_and_grad_model_parallel : 0.000025s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 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 : 0.000012s : 0.00% optimize.overlap_grad_flash_sp : 0.000093s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000345s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000055s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000072s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000039s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000069s : 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 : 0.000105s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000880s : 0.02% validate : 0.000133s : 0.00% Time group info: ------[substitution.] 0.091695 608 0.02% : 0.000018s : 8: substitution.depend_value_elim 0.02% : 0.000022s : 17: substitution.elim_not_effective 0.02% : 0.000017s : 12: substitution.float_tuple_getitem_switch 0.03% : 0.000031s : 17: substitution.fold_const_symbol 0.02% : 0.000019s : 22: substitution.graph_param_transform 98.80% : 0.090593s : 71: substitution.inline 0.02% : 0.000015s : 35: substitution.j_node_and_user_rematch 0.03% : 0.000031s : 6: substitution.less_batch_normalization 0.06% : 0.000059s : 2: substitution.list_to_tuple_eliminator_ 0.01% : 0.000011s : 18: substitution.load_eliminater 0.03% : 0.000032s : 21: substitution.minmaximum_grad 0.01% : 0.000007s : 2: substitution.opt_reshape 0.03% : 0.000024s : 35: substitution.remove_not_recompute_node 0.01% : 0.000011s : 8: substitution.replace_old_param 0.06% : 0.000054s : 18: substitution.reshape_eliminate 0.05% : 0.000046s : 24: substitution.switch_simplify 0.14% : 0.000129s : 51: substitution.tuple_list_convert_item_index_to_positive 0.08% : 0.000078s : 51: substitution.tuple_list_get_item_const_eliminator 0.10% : 0.000090s : 51: substitution.tuple_list_get_item_depend_reorder 0.19% : 0.000179s : 73: substitution.tuple_list_get_item_eliminator 0.10% : 0.000087s : 51: substitution.tuple_list_get_set_item_eliminator 0.01% : 0.000011s : 6: substitution.updatestate_pure_node_eliminater 0.14% : 0.000132s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 3.048691 2 99.47% : 3.032616s : 1: type_inference.infer 0.53% : 0.016074s : 1: type_inference.specialize ------[replace.] 0.001090 115 4.66% : 0.000051s : 5: replace.depend_value_elim 58.81% : 0.000641s : 71: replace.inline 3.99% : 0.000044s : 2: replace.list_to_tuple_eliminator_ 23.80% : 0.000259s : 24: replace.switch_simplify 8.74% : 0.000095s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.090673 115 0.00% : 0.000002s : 5: match.depend_value_elim 99.87% : 0.090552s : 71: match.inline 0.06% : 0.000056s : 2: match.list_to_tuple_eliminator_ 0.04% : 0.000035s : 24: match.switch_simplify 0.03% : 0.000027s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001756 10915 1.06% : 0.000019s : 133: predicate.accumulaten_eliminater 0.37% : 0.000007s : 22: predicate.ad_related_special_op_eliminate 0.54% : 0.000009s : 73: predicate.addn_check_dump 1.08% : 0.000019s : 133: predicate.addn_zero_filter 1.04% : 0.000018s : 133: predicate.adjust_all_reduce_mul_add 2.28% : 0.000040s : 206: predicate.arithmetic_simplify 1.08% : 0.000019s : 133: predicate.cast_eliminate 0.34% : 0.000006s : 44: predicate.check_bprop_eliminate 0.58% : 0.000010s : 73: predicate.compare_switch_simplify 0.10% : 0.000002s : 22: predicate.const_output_eliminate 0.65% : 0.000011s : 76: predicate.depend_value_elim 1.15% : 0.000020s : 133: predicate.dict_get_item_const_eliminator 1.18% : 0.000021s : 133: predicate.dict_get_item_eliminator 1.05% : 0.000018s : 133: predicate.dict_set_item_eliminator 0.45% : 0.000008s : 44: predicate.dumpgradient_eliminate 0.13% : 0.000002s : 22: predicate.elim_not_effective 0.24% : 0.000004s : 22: predicate.elim_shapecalc_of_broadcastargs 1.24% : 0.000022s : 155: predicate.environ_add_const_eliminate 1.21% : 0.000021s : 155: predicate.environ_get_add_eliminate 1.19% : 0.000021s : 155: predicate.environ_get_depend_swap 1.84% : 0.000032s : 228: predicate.environ_get_eliminate 1.21% : 0.000021s : 155: predicate.environ_get_set_eliminate 3.38% : 0.000059s : 219: predicate.exchange_switch_depend_value 2.57% : 0.000045s : 219: predicate.float_depend_g_call 0.56% : 0.000010s : 73: predicate.float_environ_get_switch 0.80% : 0.000014s : 95: predicate.float_tuple_getitem_switch 0.09% : 0.000002s : 22: predicate.fold_const_symbol 0.38% : 0.000007s : 45: predicate.get_grad_eliminate 0.13% : 0.000002s : 22: predicate.graph_param_transform 0.56% : 0.000010s : 73: predicate.incorporate_call 0.54% : 0.000009s : 73: predicate.incorporate_call_switch 5.84% : 0.000103s : 514: predicate.inline 0.53% : 0.000009s : 45: predicate.inline_without_move 0.19% : 0.000003s : 45: predicate.j_node_and_user_rematch 0.48% : 0.000008s : 45: predicate.less_batch_normalization 1.64% : 0.000029s : 192: predicate.list_to_tuple_eliminator_ 2.86% : 0.000050s : 325: predicate.load_eliminater 0.37% : 0.000006s : 22: predicate.loop_unroll_after_grad 2.81% : 0.000049s : 324: predicate.loop_unroll_before_grad 1.59% : 0.000028s : 177: predicate.make_slice_get_slice_eliminator 0.58% : 0.000010s : 73: predicate.merge_addn 0.33% : 0.000006s : 44: predicate.micro_step_allgather_replace 0.35% : 0.000006s : 44: predicate.mini_step_allgather_replace 1.08% : 0.000019s : 133: predicate.minmaximum_grad 0.43% : 0.000008s : 22: predicate.mutable_eliminate 0.22% : 0.000004s : 22: predicate.opt_reshape 0.20% : 0.000003s : 22: predicate.parallel_virtual_node 3.46% : 0.000061s : 219: predicate.partial_defer_inline 1.50% : 0.000026s : 170: predicate.partial_eliminate 1.08% : 0.000019s : 133: predicate.print_const_string_wrapper 0.52% : 0.000009s : 68: predicate.reduce_all_const_elim 1.39% : 0.000024s : 133: predicate.reduce_eliminate 2.57% : 0.000045s : 325: predicate.redundant_stop_gradient_eliminater 0.21% : 0.000004s : 45: predicate.remove_not_recompute_node 1.10% : 0.000019s : 192: predicate.replace_applicator 0.24% : 0.000004s : 45: predicate.replace_old_param 0.13% : 0.000002s : 22: predicate.reset_defer_inline 1.23% : 0.000022s : 133: predicate.reshape_eliminate 0.35% : 0.000006s : 44: predicate.row_tensor_add_zeros_like 0.21% : 0.000004s : 22: predicate.row_tensor_eliminate 0.46% : 0.000008s : 44: predicate.same_eliminate 0.25% : 0.000004s : 50: predicate.set_cell_output_no_recompute 0.47% : 0.000008s : 45: predicate.shard_identity_eliminate 0.39% : 0.000007s : 44: predicate.special_op_eliminate 0.70% : 0.000012s : 73: predicate.specialize_transform 0.47% : 0.000008s : 44: predicate.split_environ_get_set_with_tuple_value 0.50% : 0.000009s : 45: predicate.stack_unstack_eliminate 0.20% : 0.000004s : 22: predicate.switch_call_monad_eliminater 1.98% : 0.000035s : 219: predicate.switch_defer_inline 2.37% : 0.000042s : 263: predicate.switch_layer_defer_inline 6.25% : 0.000110s : 686: predicate.switch_simplify 1.05% : 0.000018s : 133: predicate.tile_eliminate 1.05% : 0.000018s : 133: predicate.transpose_eliminate 1.68% : 0.000029s : 177: predicate.tuple_list_convert_item_index_to_positive 1.85% : 0.000032s : 177: predicate.tuple_list_get_item_const_eliminator 1.66% : 0.000029s : 177: predicate.tuple_list_get_item_depend_reorder 3.26% : 0.000057s : 263: predicate.tuple_list_get_item_eliminator 1.80% : 0.000032s : 177: predicate.tuple_list_get_set_item_eliminator 2.48% : 0.000043s : 250: predicate.tuple_list_set_item_eliminator 1.50% : 0.000026s : 190: predicate.tuple_to_list_eliminator_ 2.48% : 0.000044s : 325: predicate.updatestate_pure_node_eliminater 3.25% : 0.000057s : 398: predicate.updatestate_useless_node_eliminater 0.19% : 0.000003s : 22: predicate.value_based_eliminate 0.40% : 0.000007s : 45: predicate.virtual_dataset_eliminate 0.42% : 0.000007s : 45: predicate.virtual_output_eliminate 0.17% : 0.000003s : 22: predicate.virtual_view_grad_eliminate 0.20% : 0.000004s : 22: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.012664 135 63.51% : 0.008043s : 55: func_graph_cloner_run.FuncGraphClonerGraph 36.49% : 0.004621s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 4.200396 209 0.00% : 0.000004s : 1: ForceFp32Comm 0.21% : 0.008794s : 1: add_attr 0.21% : 0.008772s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.00% : 0.000194s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 4.95% : 0.207774s : 1: auto_monad 0.00% : 0.000111s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.02% : 0.000631s : 1: bootstrap 0.00% : 0.000046s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000052s : 1: control_data_broadcast_order 0.00% : 0.000036s : 1: convert_after_rewriter 0.00% : 0.000091s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000046s : 1: environ_conv 0.01% : 0.000227s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000084s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.01% : 0.000585s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.02% : 0.000801s : 1: mutable_eliminate 3.19% : 0.134003s : 1: offloading_packed_experts 0.00% : 0.000042s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000047s : 1: opt.transform.mutable_eliminate 2.40% : 0.100917s : 95: opt.transform.opt_a 0.00% : 0.000168s : 1: opt.transform.opt_after_cconv 0.00% : 0.000094s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000659s : 28: opt.transform.opt_b 0.01% : 0.000269s : 2: opt.transform.opt_trans_graph 0.01% : 0.000227s : 4: opt.transform.symbol_engine_opt 5.10% : 0.214382s : 1: opt_a 0.01% : 0.000400s : 1: opt_after_cconv 0.02% : 0.000893s : 1: opt_after_jit_grad 0.02% : 0.000955s : 1: opt_b 8.45% : 0.355130s : 1: optimize 0.00% : 0.000051s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000020s : 1: order_py_execute_after_rewriter 0.00% : 0.000098s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000016s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000032s : 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% : 0.000033s : 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% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000271s : 1: pre_auto_parallel 0.00% : 0.000202s : 1: py_interpret_to_execute 0.00% : 0.000043s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000134s : 1: remove_dup_value 2.52% : 0.105902s : 1: renormalize.infer 0.12% : 0.005183s : 1: renormalize.specialize 0.00% : 0.000005s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000908s : 1: rewriter_after_opt_a 0.02% : 0.000780s : 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% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000026s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000651s : 1: symbol_engine_optimizer 0.01% : 0.000311s : 1: tuple_transform 72.59% : 3.049101s : 1: type_inference . [hook] pytest_runtest_teardown:test_qbmm_qkv_1[True-k_n_shape0-256] tests/st/infer/ops/test_internal_ops/test_qbmm_split.py::test_qbmm_qkv_1[True-k_n_shape0-256],max_mem:154.0M [WARNING] ME(171828:281473644855088,MainProcess):2026-01-29-17:39:38.804.18 [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 = 1.69157, [21] [bootstrap]: 0.00080069 [type_inference]: 1.52588 [event_method]: 0.00024381 [auto_monad]: 0.00085569 [graph_reusing]: 5.09e-05 [inline]: 3.12002e-06 [add_attr]: 0.00579694, [1] [add_attr_with_inline]: 0.0057795, [1] [Cycle 1]: 0.00033462, [2] [tag_attr]: 0.00022109 [meta_addattr_fg_expand]: 5.882e-05 [parallel-infer-symbol]: 4.02e-06 [pre_auto_parallel]: 0.00025109 [insert-virtual-dataset]: 3.85998e-06 [parallel-infer-symbol-second]: 1.05001e-06 [dataset_repeat_opt]: 2.07999e-06 [pipeline_split]: 2.85998e-06 [optimize]: 0.124137, [53] [py_interpret_to_execute]: 0.00026531 [rewriter_before_opt_a]: 0.0250275 [opt_a]: 0.093235, [2] [Cycle 1]: 0.0906107, [45] [expand_dump_flag]: 5.256e-05 [switch_simplify]: 0.00089481 [loop_unroll]: 0.00030252 [a_1]: 0.00810397 [with_stream_mark]: 0.00013556 [recompute_prepare]: 4.696e-05 [updatestate_depend_eliminate]: 2.776e-05 [updatestate_assign_eliminate]: 2.021e-05 [updatestate_loads_eliminate]: 2.6e-05 [parameter_eliminate]: 2.94999e-06 [a_2]: 0.00096902 [accelerated_algorithm]: 6.443e-05 [shard]: 1.89e-06 [meta_shard_fg_expand]: 2.347e-05 [shard_inline]: 2.866e-05 [merge_send_recv]: 2.333e-05 [auto_parallel]: 2.5e-05 [parallel]: 3.967e-05 [flash_sp]: 1.701e-05 [merge_comm]: 1.717e-05 [allreduce_fusion]: 1.707e-05 [matmul_add_comm_reduction]: 2.634e-05 [allreduce_slice_to_reducescatter]: 9.00007e-07 [virtual_shard_identity]: 3.705e-05 [virtual_dataset]: 3.225e-05 [get_grad_eliminate_]: 3.079e-05 [virtual_output]: 3.012e-05 [merge_forward]: 1.587e-05 [cell_reuse_recompute_pass]: 1.86e-06 [offload_activation]: 3.951e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.799e-05 [merge_recompute_call_nodes]: 1.42999e-06 [before_grad]: 7.545e-05 [set_forward_comm_id_for_comm_node_pass]: 2.127e-05 [meta_fg_expand]: 2.235e-05 [flash_sp_send_recv_attached]: 6.07001e-06 [receive_attached]: 2.59001e-06 [after_resolve]: 4.222e-05 [a_after_grad]: 5.004e-05 [renormalize]: 0.0776719 [add_forward_monad_depend]: 1.893e-05 [auto_monad_grad]: 3.98999e-06 [auto_monad_eliminator]: 0.00010779 [cse]: 0.00083055 [a_3]: 0.00021608 [Cycle 2]: 0.00260244, [45] [expand_dump_flag]: 3.23e-06 [switch_simplify]: 2.955e-05 [loop_unroll]: 2.77e-05 [a_1]: 0.00087604 [with_stream_mark]: 3.643e-05 [recompute_prepare]: 2.862e-05 [updatestate_depend_eliminate]: 1.791e-05 [updatestate_assign_eliminate]: 1.513e-05 [updatestate_loads_eliminate]: 2.076e-05 [parameter_eliminate]: 2.73e-06 [a_2]: 0.00040084 [accelerated_algorithm]: 3.783e-05 [shard]: 2.21e-06 [meta_shard_fg_expand]: 9.69999e-06 [shard_inline]: 2.662e-05 [merge_send_recv]: 2.27e-05 [auto_parallel]: 2.135e-05 [parallel]: 1.153e-05 [flash_sp]: 4.72998e-06 [merge_comm]: 1.536e-05 [allreduce_fusion]: 1.605e-05 [matmul_add_comm_reduction]: 2.367e-05 [allreduce_slice_to_reducescatter]: 1.43002e-06 [virtual_shard_identity]: 2.928e-05 [virtual_dataset]: 2.517e-05 [get_grad_eliminate_]: 2.63e-05 [virtual_output]: 2.495e-05 [merge_forward]: 1.514e-05 [cell_reuse_recompute_pass]: 3.66999e-06 [offload_activation]: 2.548e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.028e-05 [merge_recompute_call_nodes]: 1.74e-06 [before_grad]: 4.623e-05 [set_forward_comm_id_for_comm_node_pass]: 1.683e-05 [meta_fg_expand]: 1.166e-05 [flash_sp_send_recv_attached]: 2.12999e-06 [receive_attached]: 2.34999e-06 [after_resolve]: 3.471e-05 [a_after_grad]: 4.521e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 3.12002e-06 [auto_monad_grad]: 2.54999e-06 [auto_monad_eliminator]: 6.78e-05 [cse]: 9.929e-05 [a_3]: 0.00017653 [py_interpret_to_execute_after_opt_a]: 3.639e-05 [slice_cell_reuse_recomputed_activation]: 1.99999e-06 [rewriter_after_opt_a]: 0.00088444 [convert_after_rewriter]: 2.742e-05 [order_py_execute_after_rewriter]: 1.514e-05 [mutable_eliminate]: 0.00080022 [opt_b]: 0.00095389, [1] [Cycle 1]: 0.00094536, [7] [b_1]: 0.00070213 [b_2]: 2.966e-05 [updatestate_depend_eliminate]: 2.357e-05 [updatestate_assign_eliminate]: 1.455e-05 [updatestate_loads_eliminate]: 2.146e-05 [renormalize]: 7.50006e-07 [cse]: 0.00010728 [optimize_parallel_all_gather_comm]: 5.095e-05 [overlap_param_gather]: 2.86999e-06 [cconv]: 4.336e-05 [loop_unroll]: 0.0005784 [opt_after_cconv]: 0.00036938, [1] [Cycle 1]: 0.00036254, [7] [c_1]: 0.00017063 [parameter_eliminate]: 5.56e-06 [updatestate_depend_eliminate]: 2.004e-05 [updatestate_assign_eliminate]: 1.413e-05 [updatestate_loads_eliminate]: 1.754e-05 [cse]: 9.388e-05 [renormalize]: 4.50003e-07 [remove_dup_value]: 0.00012604 [tuple_transform]: 0.0002998, [1] [Cycle 1]: 0.00029361, [4] [d_1]: 0.00023937 [none_parameter_eliminate]: 2.58e-06 [renormalize]: 3.59985e-07 [switch_simplify]: 2.774e-05 [partial_unused_args_eliminate]: 2.02999e-06 [add_recomputation]: 0.0001809 [cse_after_recomputation]: 8.241e-05, [1] [Cycle 1]: 7.732e-05, [1] [cse]: 6.903e-05 [environ_conv]: 3.061e-05 [swap_dp_allreduce_reducescatter]: 2.074e-05 [bias_add_comm_swap]: 2.80997e-06 [label_micro_interleaved_index]: 6.24001e-06 [label_fine_grained_interleaved_index]: 2.53003e-06 [merge_cast_opt]: 1.39e-06 [slice_recompute_activation]: 2.41e-06 [micro_interleaved_order_control]: 2.81e-06 [assign_add_opt]: 1.30999e-06 [ForceFp32Comm]: 7.30011e-07 [remove_cast_before_assign_add]: 1.05001e-06 [full_micro_interleaved_order_control]: 2.11e-06 [reorder_send_recv_between_fp_bp]: 2.68e-06 [comm_op_add_attrs]: 1.25999e-06 [add_comm_op_reuse_tag]: 9.20001e-07 [interleave_split_concat_branches]: 1.12e-06 [interleave_parallel_branches]: 1.02e-06 [overlap_opt_shard_in_pipeline]: 2.73e-06 [overlap_opt_shard_grad_in_pipeline]: 1.81e-06 [control_data_broadcast_order]: 4.525e-05 [grouped_pairwise_exchange_alltoall]: 1.80001e-06 [offloading_packed_experts]: 1.34e-05 [overlap_recompute_and_grad_model_parallel]: 1.269e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.25999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.43002e-06 [overlap_recompute_comm]: 2.67001e-06 [overlap_grad_ring_attention]: 1.081e-05 [overlap_grad_flash_sp]: 6.403e-05 [begin_end_overlap_inline]: 6.60017e-07 [split_matmul_comm_elemetwise]: 2.39999e-06 [split_layernorm_comm]: 1.92001e-06 [handle_group_info]: 8.89995e-07 [symbol_engine_optimizer]: 0.00057688, [1] [Cycle 1]: 0.00056981, [6] [build]: 0.00030107 [elim_shapecalc]: 4.308e-05 [elim_not_effective]: 6.084e-05 [opt_reshape]: 4.256e-05 [fold_const_symbol]: 7.295e-05 [renormalize]: 3.00002e-07 [detach_backward]: 2.43e-06 [pipeline_parallel_scheduler]: 2.31e-06 [auto_monad_reorder]: 8.22e-05 [get_jit_bprop_graph]: 1.87001e-06 [rewriter_after_jit_bprop_graph]: 6.04001e-06 [opt_after_jit_grad]: 0.0329904 [validate]: 0.00014795 Sums bootstrap : 0.000801s : 0.05% type_inference : 1.525879s : 90.58% event_method : 0.000244s : 0.01% auto_monad : 0.000856s : 0.05% graph_reusing : 0.000051s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000221s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000059s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000251s : 0.01% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000265s : 0.02% optimize.rewriter_before_opt_a : 0.025028s : 1.49% optimize.opt_a.expand_dump_flag : 0.000056s : 0.00% optimize.opt_a.switch_simplify : 0.000924s : 0.05% optimize.opt_a.loop_unroll : 0.000330s : 0.02% optimize.opt_a.a_1 : 0.008980s : 0.53% optimize.opt_a.with_stream_mark : 0.000172s : 0.01% optimize.opt_a.recompute_prepare : 0.000076s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000046s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000035s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000047s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.001370s : 0.08% optimize.opt_a.accelerated_algorithm : 0.000102s : 0.01% optimize.opt_a.shard : 0.000004s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000033s : 0.00% optimize.opt_a.shard_inline : 0.000055s : 0.00% optimize.opt_a.merge_send_recv : 0.000046s : 0.00% optimize.opt_a.auto_parallel : 0.000046s : 0.00% optimize.opt_a.parallel : 0.000051s : 0.00% optimize.opt_a.flash_sp : 0.000022s : 0.00% optimize.opt_a.merge_comm : 0.000033s : 0.00% optimize.opt_a.allreduce_fusion : 0.000033s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000050s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000066s : 0.00% optimize.opt_a.virtual_dataset : 0.000057s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000057s : 0.00% optimize.opt_a.virtual_output : 0.000055s : 0.00% optimize.opt_a.merge_forward : 0.000031s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000065s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000108s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000122s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000038s : 0.00% optimize.opt_a.meta_fg_expand : 0.000034s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000077s : 0.00% optimize.opt_a.a_after_grad : 0.000095s : 0.01% optimize.opt_a.renormalize : 0.077672s : 4.61% optimize.opt_a.add_forward_monad_depend : 0.000022s : 0.00% optimize.opt_a.auto_monad_grad : 0.000007s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000176s : 0.01% optimize.opt_a.cse : 0.000930s : 0.06% optimize.opt_a.a_3 : 0.000393s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000036s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000884s : 0.05% optimize.convert_after_rewriter : 0.000027s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000800s : 0.05% optimize.opt_b.b_1 : 0.000702s : 0.04% optimize.opt_b.b_2 : 0.000030s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000024s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000021s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000107s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000051s : 0.00% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000043s : 0.00% optimize.loop_unroll : 0.000578s : 0.03% optimize.opt_after_cconv.c_1 : 0.000171s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000018s : 0.00% optimize.opt_after_cconv.cse : 0.000094s : 0.01% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000126s : 0.01% optimize.tuple_transform.d_1 : 0.000239s : 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 : 0.000028s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000181s : 0.01% optimize.cse_after_recomputation.cse : 0.000069s : 0.00% optimize.environ_conv : 0.000031s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000021s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000045s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000013s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000013s : 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 : 0.000011s : 0.00% optimize.overlap_grad_flash_sp : 0.000064s : 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 : 0.000301s : 0.02% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000043s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000061s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000043s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000073s : 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 : 0.000082s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.032990s : 1.96% validate : 0.000148s : 0.01% Time group info: ------[substitution.] 0.003147 608 0.50% : 0.000016s : 8: substitution.depend_value_elim 0.54% : 0.000017s : 17: substitution.elim_not_effective 0.55% : 0.000017s : 12: substitution.float_tuple_getitem_switch 0.97% : 0.000031s : 17: substitution.fold_const_symbol 0.57% : 0.000018s : 22: substitution.graph_param_transform 63.24% : 0.001990s : 71: substitution.inline 0.55% : 0.000017s : 35: substitution.j_node_and_user_rematch 0.92% : 0.000029s : 6: substitution.less_batch_normalization 1.70% : 0.000054s : 2: substitution.list_to_tuple_eliminator_ 0.36% : 0.000011s : 18: substitution.load_eliminater 1.00% : 0.000031s : 21: substitution.minmaximum_grad 0.23% : 0.000007s : 2: substitution.opt_reshape 0.69% : 0.000022s : 35: substitution.remove_not_recompute_node 0.33% : 0.000010s : 8: substitution.replace_old_param 1.71% : 0.000054s : 18: substitution.reshape_eliminate 1.66% : 0.000052s : 24: substitution.switch_simplify 5.07% : 0.000160s : 51: substitution.tuple_list_convert_item_index_to_positive 2.12% : 0.000067s : 51: substitution.tuple_list_get_item_const_eliminator 3.34% : 0.000105s : 51: substitution.tuple_list_get_item_depend_reorder 6.53% : 0.000205s : 73: substitution.tuple_list_get_item_eliminator 3.20% : 0.000101s : 51: substitution.tuple_list_get_set_item_eliminator 0.35% : 0.000011s : 6: substitution.updatestate_pure_node_eliminater 3.86% : 0.000121s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 1.525436 2 90.71% : 1.383677s : 1: type_inference.infer 9.29% : 0.141760s : 1: type_inference.specialize ------[replace.] 0.001118 115 3.92% : 0.000044s : 5: replace.depend_value_elim 54.17% : 0.000606s : 71: replace.inline 3.50% : 0.000039s : 2: replace.list_to_tuple_eliminator_ 29.28% : 0.000327s : 24: replace.switch_simplify 9.13% : 0.000102s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002080 115 0.10% : 0.000002s : 5: match.depend_value_elim 93.76% : 0.001951s : 71: match.inline 2.44% : 0.000051s : 2: match.list_to_tuple_eliminator_ 2.00% : 0.000042s : 24: match.switch_simplify 1.69% : 0.000035s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001825 10915 1.01% : 0.000018s : 133: predicate.accumulaten_eliminater 0.70% : 0.000013s : 22: predicate.ad_related_special_op_eliminate 0.53% : 0.000010s : 73: predicate.addn_check_dump 1.08% : 0.000020s : 133: predicate.addn_zero_filter 0.99% : 0.000018s : 133: predicate.adjust_all_reduce_mul_add 2.50% : 0.000046s : 206: predicate.arithmetic_simplify 1.05% : 0.000019s : 133: predicate.cast_eliminate 0.36% : 0.000007s : 44: predicate.check_bprop_eliminate 0.54% : 0.000010s : 73: predicate.compare_switch_simplify 0.09% : 0.000002s : 22: predicate.const_output_eliminate 0.62% : 0.000011s : 76: predicate.depend_value_elim 1.10% : 0.000020s : 133: predicate.dict_get_item_const_eliminator 1.22% : 0.000022s : 133: predicate.dict_get_item_eliminator 0.99% : 0.000018s : 133: predicate.dict_set_item_eliminator 0.50% : 0.000009s : 44: predicate.dumpgradient_eliminate 0.12% : 0.000002s : 22: predicate.elim_not_effective 0.23% : 0.000004s : 22: predicate.elim_shapecalc_of_broadcastargs 1.14% : 0.000021s : 155: predicate.environ_add_const_eliminate 1.13% : 0.000021s : 155: predicate.environ_get_add_eliminate 1.18% : 0.000022s : 155: predicate.environ_get_depend_swap 1.81% : 0.000033s : 228: predicate.environ_get_eliminate 1.13% : 0.000021s : 155: predicate.environ_get_set_eliminate 1.66% : 0.000030s : 219: predicate.exchange_switch_depend_value 2.63% : 0.000048s : 219: predicate.float_depend_g_call 0.57% : 0.000010s : 73: predicate.float_environ_get_switch 0.80% : 0.000015s : 95: predicate.float_tuple_getitem_switch 0.10% : 0.000002s : 22: predicate.fold_const_symbol 0.42% : 0.000008s : 45: predicate.get_grad_eliminate 0.11% : 0.000002s : 22: predicate.graph_param_transform 0.65% : 0.000012s : 73: predicate.incorporate_call 0.60% : 0.000011s : 73: predicate.incorporate_call_switch 5.99% : 0.000109s : 514: predicate.inline 0.53% : 0.000010s : 45: predicate.inline_without_move 1.19% : 0.000022s : 45: predicate.j_node_and_user_rematch 0.56% : 0.000010s : 45: predicate.less_batch_normalization 1.56% : 0.000029s : 192: predicate.list_to_tuple_eliminator_ 2.77% : 0.000050s : 325: predicate.load_eliminater 0.37% : 0.000007s : 22: predicate.loop_unroll_after_grad 3.05% : 0.000056s : 324: predicate.loop_unroll_before_grad 1.51% : 0.000028s : 177: predicate.make_slice_get_slice_eliminator 0.57% : 0.000010s : 73: predicate.merge_addn 0.34% : 0.000006s : 44: predicate.micro_step_allgather_replace 0.36% : 0.000007s : 44: predicate.mini_step_allgather_replace 1.05% : 0.000019s : 133: predicate.minmaximum_grad 0.43% : 0.000008s : 22: predicate.mutable_eliminate 0.23% : 0.000004s : 22: predicate.opt_reshape 0.21% : 0.000004s : 22: predicate.parallel_virtual_node 2.85% : 0.000052s : 219: predicate.partial_defer_inline 1.62% : 0.000030s : 170: predicate.partial_eliminate 1.05% : 0.000019s : 133: predicate.print_const_string_wrapper 0.53% : 0.000010s : 68: predicate.reduce_all_const_elim 1.59% : 0.000029s : 133: predicate.reduce_eliminate 2.63% : 0.000048s : 325: predicate.redundant_stop_gradient_eliminater 0.20% : 0.000004s : 45: predicate.remove_not_recompute_node 1.11% : 0.000020s : 192: predicate.replace_applicator 0.20% : 0.000004s : 45: predicate.replace_old_param 0.11% : 0.000002s : 22: predicate.reset_defer_inline 1.19% : 0.000022s : 133: predicate.reshape_eliminate 0.36% : 0.000007s : 44: predicate.row_tensor_add_zeros_like 0.24% : 0.000004s : 22: predicate.row_tensor_eliminate 0.47% : 0.000009s : 44: predicate.same_eliminate 0.24% : 0.000004s : 50: predicate.set_cell_output_no_recompute 0.46% : 0.000008s : 45: predicate.shard_identity_eliminate 0.42% : 0.000008s : 44: predicate.special_op_eliminate 0.71% : 0.000013s : 73: predicate.specialize_transform 0.44% : 0.000008s : 44: predicate.split_environ_get_set_with_tuple_value 0.46% : 0.000008s : 45: predicate.stack_unstack_eliminate 0.22% : 0.000004s : 22: predicate.switch_call_monad_eliminater 1.94% : 0.000035s : 219: predicate.switch_defer_inline 2.12% : 0.000039s : 263: predicate.switch_layer_defer_inline 7.65% : 0.000140s : 686: predicate.switch_simplify 1.10% : 0.000020s : 133: predicate.tile_eliminate 1.07% : 0.000020s : 133: predicate.transpose_eliminate 1.70% : 0.000031s : 177: predicate.tuple_list_convert_item_index_to_positive 1.81% : 0.000033s : 177: predicate.tuple_list_get_item_const_eliminator 1.63% : 0.000030s : 177: predicate.tuple_list_get_item_depend_reorder 3.09% : 0.000056s : 263: predicate.tuple_list_get_item_eliminator 1.59% : 0.000029s : 177: predicate.tuple_list_get_set_item_eliminator 2.31% : 0.000042s : 250: predicate.tuple_list_set_item_eliminator 1.56% : 0.000028s : 190: predicate.tuple_to_list_eliminator_ 2.41% : 0.000044s : 325: predicate.updatestate_pure_node_eliminater 3.32% : 0.000061s : 398: predicate.updatestate_useless_node_eliminater 0.19% : 0.000003s : 22: predicate.value_based_eliminate 0.38% : 0.000007s : 45: predicate.virtual_dataset_eliminate 0.39% : 0.000007s : 45: predicate.virtual_output_eliminate 0.17% : 0.000003s : 22: predicate.virtual_view_grad_eliminate 0.20% : 0.000004s : 22: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.254747 135 97.40% : 0.248127s : 55: func_graph_cloner_run.FuncGraphClonerGraph 2.60% : 0.006620s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.913101 209 0.00% : 0.000003s : 1: ForceFp32Comm 0.30% : 0.005804s : 1: add_attr 0.30% : 0.005784s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000187s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.05% : 0.000870s : 1: auto_monad 0.00% : 0.000089s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.04% : 0.000861s : 1: bootstrap 0.00% : 0.000048s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000049s : 1: control_data_broadcast_order 0.00% : 0.000033s : 1: convert_after_rewriter 0.00% : 0.000086s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000036s : 1: environ_conv 0.01% : 0.000259s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000058s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000003s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.03% : 0.000588s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.04% : 0.000810s : 1: mutable_eliminate 0.00% : 0.000017s : 1: offloading_packed_experts 0.00% : 0.000042s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000046s : 1: opt.transform.mutable_eliminate 0.66% : 0.012718s : 95: opt.transform.opt_a 0.01% : 0.000169s : 1: opt.transform.opt_after_cconv 0.01% : 0.000130s : 1: opt.transform.opt_after_jit_grad 0.04% : 0.000693s : 28: opt.transform.opt_b 0.01% : 0.000263s : 2: opt.transform.opt_trans_graph 0.01% : 0.000214s : 4: opt.transform.symbol_engine_opt 4.87% : 0.093243s : 1: opt_a 0.02% : 0.000374s : 1: opt_after_cconv 1.73% : 0.033013s : 1: opt_after_jit_grad 0.05% : 0.000958s : 1: opt_b 6.49% : 0.124145s : 1: optimize 0.00% : 0.000056s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.00% : 0.000068s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000014s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000016s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.01% : 0.000260s : 1: pre_auto_parallel 0.01% : 0.000274s : 1: py_interpret_to_execute 0.00% : 0.000041s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000132s : 1: remove_dup_value 0.33% : 0.006232s : 1: renormalize.infer 3.73% : 0.071419s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.05% : 0.000898s : 1: rewriter_after_opt_a 1.31% : 0.025063s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000024s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000580s : 1: symbol_engine_optimizer 0.02% : 0.000303s : 1: tuple_transform 79.76% : 1.525913s : 1: type_inference . [hook] pytest_runtest_teardown:test_qbmm_qkv_1[True-k_n_shape0-1024] tests/st/infer/ops/test_internal_ops/test_qbmm_split.py::test_qbmm_qkv_1[True-k_n_shape0-1024],max_mem:176.0M [WARNING] ME(171828:281473644855088,MainProcess):2026-01-29-17:43:45.122.214 [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 = 1.04909, [21] [bootstrap]: 0.00068748 [type_inference]: 0.890624 [event_method]: 0.00026452 [auto_monad]: 0.00090484 [graph_reusing]: 4.971e-05 [inline]: 3.06999e-06 [add_attr]: 0.00679491, [1] [add_attr_with_inline]: 0.00677025, [1] [Cycle 1]: 0.00045463, [2] [tag_attr]: 0.00029558 [meta_addattr_fg_expand]: 7.754e-05 [parallel-infer-symbol]: 4.85999e-06 [pre_auto_parallel]: 0.00030993 [insert-virtual-dataset]: 4.70001e-06 [parallel-infer-symbol-second]: 1.75001e-06 [dataset_repeat_opt]: 3.63e-06 [pipeline_split]: 3.31999e-06 [optimize]: 0.148309, [53] [py_interpret_to_execute]: 0.00034063 [rewriter_before_opt_a]: 0.00090935 [opt_a]: 0.141565, [2] [Cycle 1]: 0.138814, [45] [expand_dump_flag]: 5.287e-05 [switch_simplify]: 0.00110634 [loop_unroll]: 0.00038352 [a_1]: 0.0674932 [with_stream_mark]: 0.0006463 [recompute_prepare]: 5.869e-05 [updatestate_depend_eliminate]: 3.172e-05 [updatestate_assign_eliminate]: 2.072e-05 [updatestate_loads_eliminate]: 2.864e-05 [parameter_eliminate]: 2.77002e-06 [a_2]: 0.00103618 [accelerated_algorithm]: 7.249e-05 [shard]: 2.63e-06 [meta_shard_fg_expand]: 2.711e-05 [shard_inline]: 2.973e-05 [merge_send_recv]: 2.435e-05 [auto_parallel]: 2.472e-05 [parallel]: 4.271e-05 [flash_sp]: 1.832e-05 [merge_comm]: 1.684e-05 [allreduce_fusion]: 1.65e-05 [matmul_add_comm_reduction]: 2.827e-05 [allreduce_slice_to_reducescatter]: 9.09989e-07 [virtual_shard_identity]: 3.441e-05 [virtual_dataset]: 2.878e-05 [get_grad_eliminate_]: 2.831e-05 [virtual_output]: 2.854e-05 [merge_forward]: 1.849e-05 [cell_reuse_recompute_pass]: 2.41998e-06 [offload_activation]: 2.848e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.964e-05 [merge_recompute_call_nodes]: 1.96998e-06 [before_grad]: 4.965e-05 [set_forward_comm_id_for_comm_node_pass]: 1.76e-05 [meta_fg_expand]: 1.798e-05 [flash_sp_send_recv_attached]: 5.96e-06 [receive_attached]: 2.56998e-06 [after_resolve]: 3.896e-05 [a_after_grad]: 4.932e-05 [renormalize]: 0.0154208 [add_forward_monad_depend]: 2.308e-05 [auto_monad_grad]: 3.32002e-06 [auto_monad_eliminator]: 0.00010067 [cse]: 0.00073345 [a_3]: 0.0504344 [Cycle 2]: 0.0027273, [45] [expand_dump_flag]: 4.95999e-06 [switch_simplify]: 3.786e-05 [loop_unroll]: 2.904e-05 [a_1]: 0.00086606 [with_stream_mark]: 4.209e-05 [recompute_prepare]: 2.678e-05 [updatestate_depend_eliminate]: 1.778e-05 [updatestate_assign_eliminate]: 1.531e-05 [updatestate_loads_eliminate]: 2.192e-05 [parameter_eliminate]: 2.46e-06 [a_2]: 0.00039802 [accelerated_algorithm]: 3.751e-05 [shard]: 2.57001e-06 [meta_shard_fg_expand]: 1.349e-05 [shard_inline]: 3.874e-05 [merge_send_recv]: 2.442e-05 [auto_parallel]: 2.229e-05 [parallel]: 1.113e-05 [flash_sp]: 5.50001e-06 [merge_comm]: 2.369e-05 [allreduce_fusion]: 1.52e-05 [matmul_add_comm_reduction]: 2.882e-05 [allreduce_slice_to_reducescatter]: 1.05001e-06 [virtual_shard_identity]: 3.344e-05 [virtual_dataset]: 2.724e-05 [get_grad_eliminate_]: 2.501e-05 [virtual_output]: 2.536e-05 [merge_forward]: 1.559e-05 [cell_reuse_recompute_pass]: 3.43e-06 [offload_activation]: 2.657e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.993e-05 [merge_recompute_call_nodes]: 1.50999e-06 [before_grad]: 4.391e-05 [set_forward_comm_id_for_comm_node_pass]: 3.376e-05 [meta_fg_expand]: 1.229e-05 [flash_sp_send_recv_attached]: 1.71998e-06 [receive_attached]: 2.17001e-06 [after_resolve]: 3.771e-05 [a_after_grad]: 4.273e-05 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 4.63999e-06 [auto_monad_grad]: 2.93998e-06 [auto_monad_eliminator]: 7.943e-05 [cse]: 0.00012409 [a_3]: 0.00017723 [py_interpret_to_execute_after_opt_a]: 4.012e-05 [slice_cell_reuse_recomputed_activation]: 2.49001e-06 [rewriter_after_opt_a]: 0.0008799 [convert_after_rewriter]: 2.755e-05 [order_py_execute_after_rewriter]: 1.522e-05 [mutable_eliminate]: 0.00083272 [opt_b]: 0.00090443, [1] [Cycle 1]: 0.00089579, [7] [b_1]: 0.0006656 [b_2]: 2.898e-05 [updatestate_depend_eliminate]: 2.007e-05 [updatestate_assign_eliminate]: 1.502e-05 [updatestate_loads_eliminate]: 2.083e-05 [renormalize]: 1.21002e-06 [cse]: 0.00010095 [optimize_parallel_all_gather_comm]: 4.33e-05 [overlap_param_gather]: 2.19999e-06 [cconv]: 4.332e-05 [loop_unroll]: 0.00058347 [opt_after_cconv]: 0.0003624, [1] [Cycle 1]: 0.00035461, [7] [c_1]: 0.00016978 [parameter_eliminate]: 4.22998e-06 [updatestate_depend_eliminate]: 1.904e-05 [updatestate_assign_eliminate]: 1.381e-05 [updatestate_loads_eliminate]: 1.845e-05 [cse]: 8.982e-05 [renormalize]: 6.00005e-07 [remove_dup_value]: 0.00013234 [tuple_transform]: 0.00029699, [1] [Cycle 1]: 0.0002906, [4] [d_1]: 0.00023636 [none_parameter_eliminate]: 3.08e-06 [renormalize]: 2.29978e-07 [switch_simplify]: 2.671e-05 [partial_unused_args_eliminate]: 1.86e-06 [add_recomputation]: 0.00016893 [cse_after_recomputation]: 7.843e-05, [1] [Cycle 1]: 7.334e-05, [1] [cse]: 6.625e-05 [environ_conv]: 2.671e-05 [swap_dp_allreduce_reducescatter]: 2.112e-05 [bias_add_comm_swap]: 3.21001e-06 [label_micro_interleaved_index]: 5.32001e-06 [label_fine_grained_interleaved_index]: 2.67001e-06 [merge_cast_opt]: 1.42e-06 [slice_recompute_activation]: 2.41e-06 [micro_interleaved_order_control]: 2.71999e-06 [assign_add_opt]: 1.30001e-06 [ForceFp32Comm]: 8.10018e-07 [remove_cast_before_assign_add]: 1.29e-06 [full_micro_interleaved_order_control]: 2.07999e-06 [reorder_send_recv_between_fp_bp]: 2.66e-06 [comm_op_add_attrs]: 1.00001e-06 [add_comm_op_reuse_tag]: 1.04e-06 [interleave_split_concat_branches]: 1.44e-06 [interleave_parallel_branches]: 1.04e-06 [overlap_opt_shard_in_pipeline]: 1.26997e-06 [overlap_opt_shard_grad_in_pipeline]: 1.67001e-06 [control_data_broadcast_order]: 4.392e-05 [grouped_pairwise_exchange_alltoall]: 1.60999e-06 [offloading_packed_experts]: 1.282e-05 [overlap_recompute_and_grad_model_parallel]: 1.172e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.22e-06 [overlap_recompute_allgather_and_fa_grad]: 1.38002e-06 [overlap_recompute_comm]: 2.16e-06 [overlap_grad_ring_attention]: 1.092e-05 [overlap_grad_flash_sp]: 5.688e-05 [begin_end_overlap_inline]: 5.19998e-07 [split_matmul_comm_elemetwise]: 2.69999e-06 [split_layernorm_comm]: 1.93002e-06 [handle_group_info]: 1.11997e-06 [symbol_engine_optimizer]: 0.00052375, [1] [Cycle 1]: 0.00051693, [6] [build]: 0.00027359 [elim_shapecalc]: 3.777e-05 [elim_not_effective]: 5.857e-05 [opt_reshape]: 3.775e-05 [fold_const_symbol]: 6.326e-05 [renormalize]: 3.59985e-07 [detach_backward]: 2.57001e-06 [pipeline_parallel_scheduler]: 2.48e-06 [auto_monad_reorder]: 8.141e-05 [get_jit_bprop_graph]: 2.00002e-06 [rewriter_after_jit_bprop_graph]: 4.79e-06 [opt_after_jit_grad]: 0.00066854 [validate]: 0.00010753 Sums bootstrap : 0.000687s : 0.07% type_inference : 0.890624s : 85.55% event_method : 0.000265s : 0.03% auto_monad : 0.000905s : 0.09% graph_reusing : 0.000050s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000296s : 0.03% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000078s : 0.01% parallel-infer-symbol : 0.000005s : 0.00% pre_auto_parallel : 0.000310s : 0.03% insert-virtual-dataset : 0.000005s : 0.00% parallel-infer-symbol-second : 0.000002s : 0.00% dataset_repeat_opt : 0.000004s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000341s : 0.03% optimize.rewriter_before_opt_a : 0.000909s : 0.09% optimize.opt_a.expand_dump_flag : 0.000058s : 0.01% optimize.opt_a.switch_simplify : 0.001144s : 0.11% optimize.opt_a.loop_unroll : 0.000413s : 0.04% optimize.opt_a.a_1 : 0.068359s : 6.57% optimize.opt_a.with_stream_mark : 0.000688s : 0.07% optimize.opt_a.recompute_prepare : 0.000085s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000049s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000036s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000051s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.001434s : 0.14% optimize.opt_a.accelerated_algorithm : 0.000110s : 0.01% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000041s : 0.00% optimize.opt_a.shard_inline : 0.000068s : 0.01% optimize.opt_a.merge_send_recv : 0.000049s : 0.00% optimize.opt_a.auto_parallel : 0.000047s : 0.00% optimize.opt_a.parallel : 0.000054s : 0.01% optimize.opt_a.flash_sp : 0.000024s : 0.00% optimize.opt_a.merge_comm : 0.000041s : 0.00% optimize.opt_a.allreduce_fusion : 0.000032s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000057s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000068s : 0.01% optimize.opt_a.virtual_dataset : 0.000056s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000053s : 0.01% optimize.opt_a.virtual_output : 0.000054s : 0.01% optimize.opt_a.merge_forward : 0.000034s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000055s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000110s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000094s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000051s : 0.00% optimize.opt_a.meta_fg_expand : 0.000030s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000077s : 0.01% optimize.opt_a.a_after_grad : 0.000092s : 0.01% optimize.opt_a.renormalize : 0.015421s : 1.48% optimize.opt_a.add_forward_monad_depend : 0.000028s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000180s : 0.02% optimize.opt_a.cse : 0.000858s : 0.08% optimize.opt_a.a_3 : 0.050612s : 4.86% optimize.py_interpret_to_execute_after_opt_a : 0.000040s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000880s : 0.08% optimize.convert_after_rewriter : 0.000028s : 0.00% optimize.order_py_execute_after_rewriter : 0.000015s : 0.00% optimize.mutable_eliminate : 0.000833s : 0.08% optimize.opt_b.b_1 : 0.000666s : 0.06% optimize.opt_b.b_2 : 0.000029s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000021s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000101s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000043s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000043s : 0.00% optimize.loop_unroll : 0.000583s : 0.06% optimize.opt_after_cconv.c_1 : 0.000170s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000018s : 0.00% optimize.opt_after_cconv.cse : 0.000090s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000132s : 0.01% optimize.tuple_transform.d_1 : 0.000236s : 0.02% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000027s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000169s : 0.02% optimize.cse_after_recomputation.cse : 0.000066s : 0.01% optimize.environ_conv : 0.000027s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000021s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000044s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000013s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000012s : 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 : 0.000011s : 0.00% optimize.overlap_grad_flash_sp : 0.000057s : 0.01% 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 : 0.000274s : 0.03% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000038s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000059s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000038s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000063s : 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 : 0.000081s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000669s : 0.06% validate : 0.000108s : 0.01% Time group info: ------[substitution.] 0.004647 608 0.38% : 0.000018s : 8: substitution.depend_value_elim 0.32% : 0.000015s : 17: substitution.elim_not_effective 0.40% : 0.000019s : 12: substitution.float_tuple_getitem_switch 0.57% : 0.000027s : 17: substitution.fold_const_symbol 0.40% : 0.000018s : 22: substitution.graph_param_transform 67.97% : 0.003159s : 71: substitution.inline 0.34% : 0.000016s : 35: substitution.j_node_and_user_rematch 0.76% : 0.000035s : 6: substitution.less_batch_normalization 1.41% : 0.000065s : 2: substitution.list_to_tuple_eliminator_ 0.24% : 0.000011s : 18: substitution.load_eliminater 0.89% : 0.000042s : 21: substitution.minmaximum_grad 0.15% : 0.000007s : 2: substitution.opt_reshape 0.49% : 0.000023s : 35: substitution.remove_not_recompute_node 0.25% : 0.000012s : 8: substitution.replace_old_param 1.71% : 0.000079s : 18: substitution.reshape_eliminate 1.44% : 0.000067s : 24: substitution.switch_simplify 4.08% : 0.000189s : 51: substitution.tuple_list_convert_item_index_to_positive 2.30% : 0.000107s : 51: substitution.tuple_list_get_item_const_eliminator 3.03% : 0.000141s : 51: substitution.tuple_list_get_item_depend_reorder 5.82% : 0.000270s : 73: substitution.tuple_list_get_item_eliminator 3.88% : 0.000180s : 51: substitution.tuple_list_get_set_item_eliminator 0.25% : 0.000011s : 6: substitution.updatestate_pure_node_eliminater 2.93% : 0.000136s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.890095 2 92.76% : 0.825653s : 1: type_inference.infer 7.24% : 0.064441s : 1: type_inference.specialize ------[replace.] 0.001465 115 3.63% : 0.000053s : 5: replace.depend_value_elim 54.42% : 0.000797s : 71: replace.inline 3.32% : 0.000049s : 2: replace.list_to_tuple_eliminator_ 29.29% : 0.000429s : 24: replace.switch_simplify 9.34% : 0.000137s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.003268 115 0.06% : 0.000002s : 5: match.depend_value_elim 94.95% : 0.003103s : 71: match.inline 1.89% : 0.000062s : 2: match.list_to_tuple_eliminator_ 1.59% : 0.000052s : 24: match.switch_simplify 1.50% : 0.000049s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001944 10915 1.05% : 0.000020s : 133: predicate.accumulaten_eliminater 0.35% : 0.000007s : 22: predicate.ad_related_special_op_eliminate 0.51% : 0.000010s : 73: predicate.addn_check_dump 1.16% : 0.000022s : 133: predicate.addn_zero_filter 1.03% : 0.000020s : 133: predicate.adjust_all_reduce_mul_add 2.47% : 0.000048s : 206: predicate.arithmetic_simplify 1.06% : 0.000021s : 133: predicate.cast_eliminate 0.34% : 0.000007s : 44: predicate.check_bprop_eliminate 0.51% : 0.000010s : 73: predicate.compare_switch_simplify 0.09% : 0.000002s : 22: predicate.const_output_eliminate 0.60% : 0.000012s : 76: predicate.depend_value_elim 1.13% : 0.000022s : 133: predicate.dict_get_item_const_eliminator 1.23% : 0.000024s : 133: predicate.dict_get_item_eliminator 1.00% : 0.000019s : 133: predicate.dict_set_item_eliminator 0.38% : 0.000007s : 44: predicate.dumpgradient_eliminate 0.11% : 0.000002s : 22: predicate.elim_not_effective 0.19% : 0.000004s : 22: predicate.elim_shapecalc_of_broadcastargs 1.15% : 0.000022s : 155: predicate.environ_add_const_eliminate 1.15% : 0.000022s : 155: predicate.environ_get_add_eliminate 1.15% : 0.000022s : 155: predicate.environ_get_depend_swap 1.73% : 0.000034s : 228: predicate.environ_get_eliminate 1.14% : 0.000022s : 155: predicate.environ_get_set_eliminate 1.69% : 0.000033s : 219: predicate.exchange_switch_depend_value 2.84% : 0.000055s : 219: predicate.float_depend_g_call 0.55% : 0.000011s : 73: predicate.float_environ_get_switch 0.74% : 0.000014s : 95: predicate.float_tuple_getitem_switch 0.09% : 0.000002s : 22: predicate.fold_const_symbol 0.37% : 0.000007s : 45: predicate.get_grad_eliminate 0.10% : 0.000002s : 22: predicate.graph_param_transform 0.52% : 0.000010s : 73: predicate.incorporate_call 0.51% : 0.000010s : 73: predicate.incorporate_call_switch 5.89% : 0.000115s : 514: predicate.inline 0.48% : 0.000009s : 45: predicate.inline_without_move 0.17% : 0.000003s : 45: predicate.j_node_and_user_rematch 0.51% : 0.000010s : 45: predicate.less_batch_normalization 1.79% : 0.000035s : 192: predicate.list_to_tuple_eliminator_ 2.42% : 0.000047s : 325: predicate.load_eliminater 0.31% : 0.000006s : 22: predicate.loop_unroll_after_grad 3.92% : 0.000076s : 324: predicate.loop_unroll_before_grad 1.40% : 0.000027s : 177: predicate.make_slice_get_slice_eliminator 0.55% : 0.000011s : 73: predicate.merge_addn 0.31% : 0.000006s : 44: predicate.micro_step_allgather_replace 0.30% : 0.000006s : 44: predicate.mini_step_allgather_replace 1.02% : 0.000020s : 133: predicate.minmaximum_grad 0.39% : 0.000008s : 22: predicate.mutable_eliminate 0.20% : 0.000004s : 22: predicate.opt_reshape 0.17% : 0.000003s : 22: predicate.parallel_virtual_node 3.35% : 0.000065s : 219: predicate.partial_defer_inline 1.43% : 0.000028s : 170: predicate.partial_eliminate 1.07% : 0.000021s : 133: predicate.print_const_string_wrapper 0.48% : 0.000009s : 68: predicate.reduce_all_const_elim 1.62% : 0.000032s : 133: predicate.reduce_eliminate 2.44% : 0.000047s : 325: predicate.redundant_stop_gradient_eliminater 0.19% : 0.000004s : 45: predicate.remove_not_recompute_node 1.00% : 0.000019s : 192: predicate.replace_applicator 0.21% : 0.000004s : 45: predicate.replace_old_param 0.11% : 0.000002s : 22: predicate.reset_defer_inline 1.29% : 0.000025s : 133: predicate.reshape_eliminate 0.37% : 0.000007s : 44: predicate.row_tensor_add_zeros_like 0.19% : 0.000004s : 22: predicate.row_tensor_eliminate 0.44% : 0.000008s : 44: predicate.same_eliminate 0.28% : 0.000005s : 50: predicate.set_cell_output_no_recompute 0.45% : 0.000009s : 45: predicate.shard_identity_eliminate 0.38% : 0.000007s : 44: predicate.special_op_eliminate 0.74% : 0.000014s : 73: predicate.specialize_transform 0.45% : 0.000009s : 44: predicate.split_environ_get_set_with_tuple_value 0.44% : 0.000009s : 45: predicate.stack_unstack_eliminate 0.17% : 0.000003s : 22: predicate.switch_call_monad_eliminater 2.08% : 0.000040s : 219: predicate.switch_defer_inline 2.45% : 0.000048s : 263: predicate.switch_layer_defer_inline 9.66% : 0.000188s : 686: predicate.switch_simplify 1.05% : 0.000020s : 133: predicate.tile_eliminate 0.99% : 0.000019s : 133: predicate.transpose_eliminate 1.58% : 0.000031s : 177: predicate.tuple_list_convert_item_index_to_positive 1.57% : 0.000031s : 177: predicate.tuple_list_get_item_const_eliminator 1.50% : 0.000029s : 177: predicate.tuple_list_get_item_depend_reorder 3.13% : 0.000061s : 263: predicate.tuple_list_get_item_eliminator 1.53% : 0.000030s : 177: predicate.tuple_list_get_set_item_eliminator 2.13% : 0.000041s : 250: predicate.tuple_list_set_item_eliminator 1.51% : 0.000029s : 190: predicate.tuple_to_list_eliminator_ 2.56% : 0.000050s : 325: predicate.updatestate_pure_node_eliminater 3.08% : 0.000060s : 398: predicate.updatestate_useless_node_eliminater 0.19% : 0.000004s : 22: predicate.value_based_eliminate 0.37% : 0.000007s : 45: predicate.virtual_dataset_eliminate 0.36% : 0.000007s : 45: predicate.virtual_output_eliminate 0.16% : 0.000003s : 22: predicate.virtual_view_grad_eliminate 0.20% : 0.000004s : 22: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.048013 135 20.12% : 0.009662s : 55: func_graph_cloner_run.FuncGraphClonerGraph 79.88% : 0.038351s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.343427 209 0.00% : 0.000003s : 1: ForceFp32Comm 0.51% : 0.006804s : 1: add_attr 0.50% : 0.006776s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000174s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.07% : 0.000929s : 1: auto_monad 0.01% : 0.000087s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.05% : 0.000722s : 1: bootstrap 0.00% : 0.000047s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000047s : 1: control_data_broadcast_order 0.00% : 0.000033s : 1: convert_after_rewriter 0.01% : 0.000082s : 1: cse_after_recomputation 0.00% : 0.000007s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000031s : 1: environ_conv 0.02% : 0.000281s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000057s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000009s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.04% : 0.000592s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.06% : 0.000843s : 1: mutable_eliminate 0.00% : 0.000016s : 1: offloading_packed_experts 0.00% : 0.000039s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000046s : 1: opt.transform.mutable_eliminate 9.13% : 0.122651s : 95: opt.transform.opt_a 0.01% : 0.000168s : 1: opt.transform.opt_after_cconv 0.01% : 0.000089s : 1: opt.transform.opt_after_jit_grad 0.05% : 0.000657s : 28: opt.transform.opt_b 0.02% : 0.000259s : 2: opt.transform.opt_trans_graph 0.01% : 0.000192s : 4: opt.transform.symbol_engine_opt 10.54% : 0.141570s : 1: opt_a 0.03% : 0.000366s : 1: opt_after_cconv 0.05% : 0.000680s : 1: opt_after_jit_grad 0.07% : 0.000909s : 1: opt_b 11.04% : 0.148316s : 1: optimize 0.00% : 0.000048s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000019s : 1: order_py_execute_after_rewriter 0.00% : 0.000060s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000014s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000015s : 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% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000007s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.02% : 0.000324s : 1: pre_auto_parallel 0.03% : 0.000357s : 1: py_interpret_to_execute 0.00% : 0.000044s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000139s : 1: remove_dup_value 0.51% : 0.006868s : 1: renormalize.infer 0.63% : 0.008529s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.07% : 0.000891s : 1: rewriter_after_opt_a 0.07% : 0.000932s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000025s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000527s : 1: symbol_engine_optimizer 0.02% : 0.000300s : 1: tuple_transform 66.30% : 0.890664s : 1: type_inference . [hook] pytest_runtest_teardown:test_qbmm_qkv_1[True-k_n_shape1-256] tests/st/infer/ops/test_internal_ops/test_qbmm_split.py::test_qbmm_qkv_1[True-k_n_shape1-256],max_mem:176.0M [WARNING] ME(171828:281473644855088,MainProcess):2026-01-29-17:44:27.339.758 [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 = 0.375778, [21] [bootstrap]: 0.00062255 [type_inference]: 0.333129 [event_method]: 0.00020745 [auto_monad]: 0.00073275 [graph_reusing]: 4.36e-05 [inline]: 2.36998e-06 [add_attr]: 0.00484325, [1] [add_attr_with_inline]: 0.00482721, [1] [Cycle 1]: 0.00030897, [2] [tag_attr]: 0.00019816 [meta_addattr_fg_expand]: 5.44e-05 [parallel-infer-symbol]: 3.45998e-06 [pre_auto_parallel]: 0.00028258 [insert-virtual-dataset]: 3.88001e-06 [parallel-infer-symbol-second]: 1.20999e-06 [dataset_repeat_opt]: 2.61e-06 [pipeline_split]: 2.59001e-06 [optimize]: 0.034797, [53] [py_interpret_to_execute]: 0.00026311 [rewriter_before_opt_a]: 0.00076855 [opt_a]: 0.028197, [2] [Cycle 1]: 0.0254573, [45] [expand_dump_flag]: 2.757e-05 [switch_simplify]: 0.00087823 [loop_unroll]: 0.00031772 [a_1]: 0.00909647 [with_stream_mark]: 0.00034377 [recompute_prepare]: 6.17e-05 [updatestate_depend_eliminate]: 2.922e-05 [updatestate_assign_eliminate]: 2.049e-05 [updatestate_loads_eliminate]: 2.748e-05 [parameter_eliminate]: 2.73e-06 [a_2]: 0.00098897 [accelerated_algorithm]: 6.485e-05 [shard]: 2.49001e-06 [meta_shard_fg_expand]: 1.927e-05 [shard_inline]: 2.836e-05 [merge_send_recv]: 2.29e-05 [auto_parallel]: 2.328e-05 [parallel]: 4.191e-05 [flash_sp]: 1.559e-05 [merge_comm]: 1.656e-05 [allreduce_fusion]: 1.582e-05 [matmul_add_comm_reduction]: 2.687e-05 [allreduce_slice_to_reducescatter]: 7.49977e-07 [virtual_shard_identity]: 3.137e-05 [virtual_dataset]: 2.832e-05 [get_grad_eliminate_]: 2.825e-05 [virtual_output]: 2.692e-05 [merge_forward]: 1.605e-05 [cell_reuse_recompute_pass]: 1.67001e-06 [offload_activation]: 2.721e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.585e-05 [merge_recompute_call_nodes]: 1.66998e-06 [before_grad]: 4.783e-05 [set_forward_comm_id_for_comm_node_pass]: 1.74e-05 [meta_fg_expand]: 1.893e-05 [flash_sp_send_recv_attached]: 5.60001e-06 [receive_attached]: 2.09e-06 [after_resolve]: 3.693e-05 [a_after_grad]: 4.677e-05 [renormalize]: 0.0118063 [add_forward_monad_depend]: 1.557e-05 [auto_monad_grad]: 2.86e-06 [auto_monad_eliminator]: 9.171e-05 [cse]: 0.00044891 [a_3]: 0.00020774 [Cycle 2]: 0.00272241, [45] [expand_dump_flag]: 2.63e-06 [switch_simplify]: 2.996e-05 [loop_unroll]: 2.618e-05 [a_1]: 0.00081256 [with_stream_mark]: 3.17e-05 [recompute_prepare]: 2.861e-05 [updatestate_depend_eliminate]: 1.681e-05 [updatestate_assign_eliminate]: 1.544e-05 [updatestate_loads_eliminate]: 2.077e-05 [parameter_eliminate]: 2.39001e-06 [a_2]: 0.00061273 [accelerated_algorithm]: 3.768e-05 [shard]: 2.54001e-06 [meta_shard_fg_expand]: 7.60998e-06 [shard_inline]: 2.705e-05 [merge_send_recv]: 2.529e-05 [auto_parallel]: 2.233e-05 [parallel]: 9.41e-06 [flash_sp]: 4.4e-06 [merge_comm]: 1.637e-05 [allreduce_fusion]: 1.437e-05 [matmul_add_comm_reduction]: 2.386e-05 [allreduce_slice_to_reducescatter]: 6.69999e-07 [virtual_shard_identity]: 2.801e-05 [virtual_dataset]: 2.655e-05 [get_grad_eliminate_]: 2.449e-05 [virtual_output]: 2.512e-05 [merge_forward]: 1.519e-05 [cell_reuse_recompute_pass]: 2.31e-06 [offload_activation]: 2.624e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.943e-05 [merge_recompute_call_nodes]: 1.44e-06 [before_grad]: 4.306e-05 [set_forward_comm_id_for_comm_node_pass]: 1.784e-05 [meta_fg_expand]: 1.161e-05 [flash_sp_send_recv_attached]: 1.82001e-06 [receive_attached]: 2.46e-06 [after_resolve]: 3.517e-05 [a_after_grad]: 4.109e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 3.20998e-06 [auto_monad_grad]: 2.43e-06 [auto_monad_eliminator]: 6.235e-05 [cse]: 9.846e-05 [a_3]: 0.00017535 [py_interpret_to_execute_after_opt_a]: 3.678e-05 [slice_cell_reuse_recomputed_activation]: 2.27999e-06 [rewriter_after_opt_a]: 0.00092344 [convert_after_rewriter]: 2.881e-05 [order_py_execute_after_rewriter]: 1.735e-05 [mutable_eliminate]: 0.00086107 [opt_b]: 0.00093148, [1] [Cycle 1]: 0.00092297, [7] [b_1]: 0.00066658 [b_2]: 4.391e-05 [updatestate_depend_eliminate]: 2.312e-05 [updatestate_assign_eliminate]: 1.499e-05 [updatestate_loads_eliminate]: 2.239e-05 [renormalize]: 8.70001e-07 [cse]: 0.00010407 [optimize_parallel_all_gather_comm]: 4.552e-05 [overlap_param_gather]: 4.22998e-06 [cconv]: 4.181e-05 [loop_unroll]: 0.00053445 [opt_after_cconv]: 0.00035239, [1] [Cycle 1]: 0.00034536, [7] [c_1]: 0.00016956 [parameter_eliminate]: 4.33001e-06 [updatestate_depend_eliminate]: 1.848e-05 [updatestate_assign_eliminate]: 1.355e-05 [updatestate_loads_eliminate]: 1.751e-05 [cse]: 8.372e-05 [renormalize]: 4.2998e-07 [remove_dup_value]: 0.00012286 [tuple_transform]: 0.00028793, [1] [Cycle 1]: 0.0002823, [4] [d_1]: 0.00022961 [none_parameter_eliminate]: 2.28002e-06 [renormalize]: 2.50002e-07 [switch_simplify]: 2.688e-05 [partial_unused_args_eliminate]: 1.91e-06 [add_recomputation]: 0.00017654 [cse_after_recomputation]: 8.792e-05, [1] [Cycle 1]: 8.275e-05, [1] [cse]: 7.404e-05 [environ_conv]: 3.058e-05 [swap_dp_allreduce_reducescatter]: 2.065e-05 [bias_add_comm_swap]: 2.94001e-06 [label_micro_interleaved_index]: 5.04003e-06 [label_fine_grained_interleaved_index]: 2.50002e-06 [merge_cast_opt]: 1.55001e-06 [slice_recompute_activation]: 2.07999e-06 [micro_interleaved_order_control]: 2.29001e-06 [assign_add_opt]: 1.51002e-06 [ForceFp32Comm]: 7.30011e-07 [remove_cast_before_assign_add]: 1.02998e-06 [full_micro_interleaved_order_control]: 2.19001e-06 [reorder_send_recv_between_fp_bp]: 2.98998e-06 [comm_op_add_attrs]: 1.30001e-06 [add_comm_op_reuse_tag]: 9.5999e-07 [interleave_split_concat_branches]: 1.10001e-06 [interleave_parallel_branches]: 1.01002e-06 [overlap_opt_shard_in_pipeline]: 2.94001e-06 [overlap_opt_shard_grad_in_pipeline]: 2.17999e-06 [control_data_broadcast_order]: 4.425e-05 [grouped_pairwise_exchange_alltoall]: 1.84e-06 [offloading_packed_experts]: 1.38e-05 [overlap_recompute_and_grad_model_parallel]: 1.298e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.40001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.36002e-06 [overlap_recompute_comm]: 2.06e-06 [overlap_grad_ring_attention]: 1.152e-05 [overlap_grad_flash_sp]: 6.201e-05 [begin_end_overlap_inline]: 5.60016e-07 [split_matmul_comm_elemetwise]: 2.28002e-06 [split_layernorm_comm]: 1.89e-06 [handle_group_info]: 1.14998e-06 [symbol_engine_optimizer]: 0.00056069, [1] [Cycle 1]: 0.00055343, [6] [build]: 0.0002986 [elim_shapecalc]: 4.103e-05 [elim_not_effective]: 6.122e-05 [opt_reshape]: 3.979e-05 [fold_const_symbol]: 6.333e-05 [renormalize]: 2.60014e-07 [detach_backward]: 2.96999e-06 [pipeline_parallel_scheduler]: 2.79999e-06 [auto_monad_reorder]: 8.629e-05 [get_jit_bprop_graph]: 2.12999e-06 [rewriter_after_jit_bprop_graph]: 7.05e-06 [opt_after_jit_grad]: 0.00066584 [validate]: 0.00011969 Sums bootstrap : 0.000623s : 0.17% type_inference : 0.333129s : 90.09% event_method : 0.000207s : 0.06% auto_monad : 0.000733s : 0.20% graph_reusing : 0.000044s : 0.01% inline : 0.000002s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000198s : 0.05% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000054s : 0.01% parallel-infer-symbol : 0.000003s : 0.00% pre_auto_parallel : 0.000283s : 0.08% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000263s : 0.07% optimize.rewriter_before_opt_a : 0.000769s : 0.21% optimize.opt_a.expand_dump_flag : 0.000030s : 0.01% optimize.opt_a.switch_simplify : 0.000908s : 0.25% optimize.opt_a.loop_unroll : 0.000344s : 0.09% optimize.opt_a.a_1 : 0.009909s : 2.68% optimize.opt_a.with_stream_mark : 0.000375s : 0.10% optimize.opt_a.recompute_prepare : 0.000090s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000046s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000036s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000048s : 0.01% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.001602s : 0.43% optimize.opt_a.accelerated_algorithm : 0.000103s : 0.03% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000027s : 0.01% optimize.opt_a.shard_inline : 0.000055s : 0.01% optimize.opt_a.merge_send_recv : 0.000048s : 0.01% optimize.opt_a.auto_parallel : 0.000046s : 0.01% optimize.opt_a.parallel : 0.000051s : 0.01% optimize.opt_a.flash_sp : 0.000020s : 0.01% optimize.opt_a.merge_comm : 0.000033s : 0.01% optimize.opt_a.allreduce_fusion : 0.000030s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000051s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000059s : 0.02% optimize.opt_a.virtual_dataset : 0.000055s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000053s : 0.01% optimize.opt_a.virtual_output : 0.000052s : 0.01% optimize.opt_a.merge_forward : 0.000031s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000053s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000105s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000091s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000035s : 0.01% optimize.opt_a.meta_fg_expand : 0.000031s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000072s : 0.02% optimize.opt_a.a_after_grad : 0.000088s : 0.02% optimize.opt_a.renormalize : 0.011806s : 3.19% optimize.opt_a.add_forward_monad_depend : 0.000019s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000154s : 0.04% optimize.opt_a.cse : 0.000547s : 0.15% optimize.opt_a.a_3 : 0.000383s : 0.10% optimize.py_interpret_to_execute_after_opt_a : 0.000037s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000923s : 0.25% optimize.convert_after_rewriter : 0.000029s : 0.01% optimize.order_py_execute_after_rewriter : 0.000017s : 0.00% optimize.mutable_eliminate : 0.000861s : 0.23% optimize.opt_b.b_1 : 0.000667s : 0.18% optimize.opt_b.b_2 : 0.000044s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000023s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000015s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000022s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000104s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000046s : 0.01% optimize.overlap_param_gather : 0.000004s : 0.00% optimize.cconv : 0.000042s : 0.01% optimize.loop_unroll : 0.000534s : 0.14% optimize.opt_after_cconv.c_1 : 0.000170s : 0.05% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000018s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000014s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000018s : 0.00% optimize.opt_after_cconv.cse : 0.000084s : 0.02% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000123s : 0.03% optimize.tuple_transform.d_1 : 0.000230s : 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 : 0.000027s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000177s : 0.05% optimize.cse_after_recomputation.cse : 0.000074s : 0.02% optimize.environ_conv : 0.000031s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000021s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000044s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000014s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000013s : 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 : 0.000012s : 0.00% optimize.overlap_grad_flash_sp : 0.000062s : 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 : 0.000299s : 0.08% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000041s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000061s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000040s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000063s : 0.02% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000003s : 0.00% auto_monad_reorder : 0.000086s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000666s : 0.18% validate : 0.000120s : 0.03% Time group info: ------[substitution.] 0.003376 608 0.49% : 0.000017s : 8: substitution.depend_value_elim 0.50% : 0.000017s : 17: substitution.elim_not_effective 0.53% : 0.000018s : 12: substitution.float_tuple_getitem_switch 0.79% : 0.000027s : 17: substitution.fold_const_symbol 0.52% : 0.000017s : 22: substitution.graph_param_transform 66.63% : 0.002249s : 71: substitution.inline 0.45% : 0.000015s : 35: substitution.j_node_and_user_rematch 0.91% : 0.000031s : 6: substitution.less_batch_normalization 1.61% : 0.000055s : 2: substitution.list_to_tuple_eliminator_ 0.31% : 0.000011s : 18: substitution.load_eliminater 0.97% : 0.000033s : 21: substitution.minmaximum_grad 0.22% : 0.000007s : 2: substitution.opt_reshape 0.66% : 0.000022s : 35: substitution.remove_not_recompute_node 0.30% : 0.000010s : 8: substitution.replace_old_param 2.02% : 0.000068s : 18: substitution.reshape_eliminate 1.35% : 0.000045s : 24: substitution.switch_simplify 4.24% : 0.000143s : 51: substitution.tuple_list_convert_item_index_to_positive 2.31% : 0.000078s : 51: substitution.tuple_list_get_item_const_eliminator 3.00% : 0.000101s : 51: substitution.tuple_list_get_item_depend_reorder 5.67% : 0.000191s : 73: substitution.tuple_list_get_item_eliminator 2.92% : 0.000098s : 51: substitution.tuple_list_get_set_item_eliminator 0.32% : 0.000011s : 6: substitution.updatestate_pure_node_eliminater 3.30% : 0.000111s : 9: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.332788 2 87.28% : 0.290454s : 1: type_inference.infer 12.72% : 0.042334s : 1: type_inference.specialize ------[replace.] 0.001080 115 4.30% : 0.000046s : 5: replace.depend_value_elim 55.62% : 0.000600s : 71: replace.inline 3.33% : 0.000036s : 2: replace.list_to_tuple_eliminator_ 27.45% : 0.000296s : 24: replace.switch_simplify 9.30% : 0.000100s : 13: replace.tuple_list_get_item_eliminator ------[match.] 0.002329 115 0.10% : 0.000002s : 5: match.depend_value_elim 94.81% : 0.002208s : 71: match.inline 2.26% : 0.000053s : 2: match.list_to_tuple_eliminator_ 1.45% : 0.000034s : 24: match.switch_simplify 1.38% : 0.000032s : 13: match.tuple_list_get_item_eliminator ------[predicate.] 0.001764 10915 1.11% : 0.000020s : 133: predicate.accumulaten_eliminater 0.35% : 0.000006s : 22: predicate.ad_related_special_op_eliminate 0.56% : 0.000010s : 73: predicate.addn_check_dump 1.14% : 0.000020s : 133: predicate.addn_zero_filter 1.09% : 0.000019s : 133: predicate.adjust_all_reduce_mul_add 2.50% : 0.000044s : 206: predicate.arithmetic_simplify 1.10% : 0.000019s : 133: predicate.cast_eliminate 0.36% : 0.000006s : 44: predicate.check_bprop_eliminate 0.57% : 0.000010s : 73: predicate.compare_switch_simplify 0.10% : 0.000002s : 22: predicate.const_output_eliminate 0.68% : 0.000012s : 76: predicate.depend_value_elim 1.22% : 0.000021s : 133: predicate.dict_get_item_const_eliminator 1.31% : 0.000023s : 133: predicate.dict_get_item_eliminator 1.09% : 0.000019s : 133: predicate.dict_set_item_eliminator 0.44% : 0.000008s : 44: predicate.dumpgradient_eliminate 0.11% : 0.000002s : 22: predicate.elim_not_effective 0.22% : 0.000004s : 22: predicate.elim_shapecalc_of_broadcastargs 1.28% : 0.000023s : 155: predicate.environ_add_const_eliminate 1.21% : 0.000021s : 155: predicate.environ_get_add_eliminate 1.22% : 0.000022s : 155: predicate.environ_get_depend_swap 1.89% : 0.000033s : 228: predicate.environ_get_eliminate 1.22% : 0.000022s : 155: predicate.environ_get_set_eliminate 1.90% : 0.000034s : 219: predicate.exchange_switch_depend_value 2.67% : 0.000047s : 219: predicate.float_depend_g_call 0.59% : 0.000010s : 73: predicate.float_environ_get_switch 0.81% : 0.000014s : 95: predicate.float_tuple_getitem_switch 0.10% : 0.000002s : 22: predicate.fold_const_symbol 0.39% : 0.000007s : 45: predicate.get_grad_eliminate 0.11% : 0.000002s : 22: predicate.graph_param_transform 0.62% : 0.000011s : 73: predicate.incorporate_call 0.61% : 0.000011s : 73: predicate.incorporate_call_switch 5.95% : 0.000105s : 514: predicate.inline 0.47% : 0.000008s : 45: predicate.inline_without_move 0.20% : 0.000003s : 45: predicate.j_node_and_user_rematch 0.50% : 0.000009s : 45: predicate.less_batch_normalization 1.72% : 0.000030s : 192: predicate.list_to_tuple_eliminator_ 2.64% : 0.000047s : 325: predicate.load_eliminater 0.39% : 0.000007s : 22: predicate.loop_unroll_after_grad 3.17% : 0.000056s : 324: predicate.loop_unroll_before_grad 1.50% : 0.000027s : 177: predicate.make_slice_get_slice_eliminator 0.59% : 0.000010s : 73: predicate.merge_addn 0.34% : 0.000006s : 44: predicate.micro_step_allgather_replace 0.35% : 0.000006s : 44: predicate.mini_step_allgather_replace 1.09% : 0.000019s : 133: predicate.minmaximum_grad 0.45% : 0.000008s : 22: predicate.mutable_eliminate 0.21% : 0.000004s : 22: predicate.opt_reshape 0.20% : 0.000004s : 22: predicate.parallel_virtual_node 2.84% : 0.000050s : 219: predicate.partial_defer_inline 1.53% : 0.000027s : 170: predicate.partial_eliminate 1.15% : 0.000020s : 133: predicate.print_const_string_wrapper 0.53% : 0.000009s : 68: predicate.reduce_all_const_elim 1.49% : 0.000026s : 133: predicate.reduce_eliminate 2.60% : 0.000046s : 325: predicate.redundant_stop_gradient_eliminater 0.21% : 0.000004s : 45: predicate.remove_not_recompute_node 1.08% : 0.000019s : 192: predicate.replace_applicator 0.22% : 0.000004s : 45: predicate.replace_old_param 0.10% : 0.000002s : 22: predicate.reset_defer_inline 1.23% : 0.000022s : 133: predicate.reshape_eliminate 0.37% : 0.000006s : 44: predicate.row_tensor_add_zeros_like 0.24% : 0.000004s : 22: predicate.row_tensor_eliminate 0.48% : 0.000008s : 44: predicate.same_eliminate 0.87% : 0.000015s : 50: predicate.set_cell_output_no_recompute 0.42% : 0.000007s : 45: predicate.shard_identity_eliminate 0.38% : 0.000007s : 44: predicate.special_op_eliminate 0.69% : 0.000012s : 73: predicate.specialize_transform 0.45% : 0.000008s : 44: predicate.split_environ_get_set_with_tuple_value 0.43% : 0.000008s : 45: predicate.stack_unstack_eliminate 0.20% : 0.000003s : 22: predicate.switch_call_monad_eliminater 2.01% : 0.000036s : 219: predicate.switch_defer_inline 2.26% : 0.000040s : 263: predicate.switch_layer_defer_inline 6.58% : 0.000116s : 686: predicate.switch_simplify 1.11% : 0.000020s : 133: predicate.tile_eliminate 1.06% : 0.000019s : 133: predicate.transpose_eliminate 1.67% : 0.000030s : 177: predicate.tuple_list_convert_item_index_to_positive 1.70% : 0.000030s : 177: predicate.tuple_list_get_item_const_eliminator 1.67% : 0.000029s : 177: predicate.tuple_list_get_item_depend_reorder 3.01% : 0.000053s : 263: predicate.tuple_list_get_item_eliminator 1.62% : 0.000029s : 177: predicate.tuple_list_get_set_item_eliminator 2.39% : 0.000042s : 250: predicate.tuple_list_set_item_eliminator 1.73% : 0.000030s : 190: predicate.tuple_to_list_eliminator_ 2.59% : 0.000046s : 325: predicate.updatestate_pure_node_eliminater 3.30% : 0.000058s : 398: predicate.updatestate_useless_node_eliminater 0.22% : 0.000004s : 22: predicate.value_based_eliminate 0.41% : 0.000007s : 45: predicate.virtual_dataset_eliminate 0.39% : 0.000007s : 45: predicate.virtual_output_eliminate 0.18% : 0.000003s : 22: predicate.virtual_view_grad_eliminate 0.23% : 0.000004s : 22: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.015354 135 61.26% : 0.009405s : 55: func_graph_cloner_run.FuncGraphClonerGraph 38.74% : 0.005949s : 80: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.442252 209 0.00% : 0.000003s : 1: ForceFp32Comm 1.10% : 0.004850s : 1: add_attr 1.09% : 0.004832s : 1: add_attr_with_inline 0.00% : 0.000003s : 1: add_comm_op_reuse_tag 0.04% : 0.000183s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.17% : 0.000749s : 1: auto_monad 0.02% : 0.000092s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.15% : 0.000659s : 1: bootstrap 0.01% : 0.000046s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.01% : 0.000049s : 1: control_data_broadcast_order 0.01% : 0.000035s : 1: convert_after_rewriter 0.02% : 0.000091s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000036s : 1: environ_conv 0.05% : 0.000219s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.01% : 0.000050s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000005s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.12% : 0.000544s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.20% : 0.000872s : 1: mutable_eliminate 0.00% : 0.000017s : 1: offloading_packed_experts 0.01% : 0.000042s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000051s : 1: opt.transform.mutable_eliminate 3.13% : 0.013824s : 95: opt.transform.opt_a 0.04% : 0.000168s : 1: opt.transform.opt_after_cconv 0.02% : 0.000090s : 1: opt.transform.opt_after_jit_grad 0.15% : 0.000674s : 28: opt.transform.opt_b 0.06% : 0.000252s : 2: opt.transform.opt_trans_graph 0.04% : 0.000199s : 4: opt.transform.symbol_engine_opt 6.38% : 0.028202s : 1: opt_a 0.08% : 0.000356s : 1: opt_after_cconv 0.15% : 0.000677s : 1: opt_after_jit_grad 0.21% : 0.000936s : 1: opt_b 7.87% : 0.034804s : 1: optimize 0.01% : 0.000050s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000021s : 1: order_py_execute_after_rewriter 0.02% : 0.000067s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000015s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000008s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000016s : 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% : 0.000007s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.07% : 0.000292s : 1: pre_auto_parallel 0.06% : 0.000271s : 1: py_interpret_to_execute 0.01% : 0.000042s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.03% : 0.000129s : 1: remove_dup_value 1.37% : 0.006058s : 1: renormalize.infer 1.30% : 0.005730s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.21% : 0.000936s : 1: rewriter_after_opt_a 0.18% : 0.000781s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.01% : 0.000025s : 1: swap_dp_allreduce_reducescatter 0.13% : 0.000564s : 1: symbol_engine_optimizer 0.07% : 0.000291s : 1: tuple_transform 75.33% : 0.333160s : 1: type_inference . [hook] pytest_runtest_teardown:test_qbmm_qkv_1[True-k_n_shape1-1024] tests/st/infer/ops/test_internal_ops/test_qbmm_split.py::test_qbmm_qkv_1[True-k_n_shape1-1024],max_mem:174.0M =============================== 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") test_qbmm_split.py::test_qbmm_qkv_1[True-k_n_shape0-256] test_qbmm_split.py::test_qbmm_qkv_1[True-k_n_shape0-1024] test_qbmm_split.py::test_qbmm_qkv_1[True-k_n_shape1-256] test_qbmm_split.py::test_qbmm_qkv_1[True-k_n_shape1-1024] /home/jenkins/mindspore/testcases/testcases/tests/st/infer/ops/test_internal_ops/st_utils.py:39: RuntimeWarning: invalid value encountered in divide err_cnt = np.sum(np.abs(out_flatten - expect_flatten) / -- Docs: https://docs.pytest.org/en/stable/warnings.html ================== 4 passed, 29 warnings in 504.45s (0:08:24) ==================