==================================================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 8 items test_quant_bmm.py [WARNING] ME(169497:281473358380848,MainProcess):2026-01-29-17:37:40.434.505 [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 = 0.15481, [21] [bootstrap]: 0.00061739 [type_inference]: 0.0387999 [event_method]: 1.601e-05 [auto_monad]: 0.00023173 [graph_reusing]: 6.07999e-06 [inline]: 2.84999e-06 [add_attr]: 0.106718, [1] [add_attr_with_inline]: 0.106698, [1] [Cycle 1]: 0.00010469, [2] [tag_attr]: 2.467e-05 [meta_addattr_fg_expand]: 4.49002e-06 [parallel-infer-symbol]: 3.51001e-06 [pre_auto_parallel]: 5.029e-05 [insert-virtual-dataset]: 2.37001e-06 [parallel-infer-symbol-second]: 6.59988e-07 [dataset_repeat_opt]: 1.93002e-06 [pipeline_split]: 1.52999e-06 [optimize]: 0.0074709, [53] [py_interpret_to_execute]: 3.165e-05 [rewriter_before_opt_a]: 8.41e-05 [opt_a]: 0.00428309, [2] [Cycle 1]: 0.00292275, [45] [expand_dump_flag]: 2.66e-06 [switch_simplify]: 3.3e-05 [loop_unroll]: 1.843e-05 [a_1]: 0.00059483 [with_stream_mark]: 3.067e-05 [recompute_prepare]: 1.567e-05 [updatestate_depend_eliminate]: 9.56e-06 [updatestate_assign_eliminate]: 1.166e-05 [updatestate_loads_eliminate]: 1.477e-05 [parameter_eliminate]: 2.06e-06 [a_2]: 0.00023053 [accelerated_algorithm]: 3.896e-05 [shard]: 2.21e-06 [meta_shard_fg_expand]: 3.21001e-06 [shard_inline]: 1.399e-05 [merge_send_recv]: 2.231e-05 [auto_parallel]: 1.156e-05 [parallel]: 5.236e-05 [flash_sp]: 2.023e-05 [merge_comm]: 9.04e-06 [allreduce_fusion]: 8.22e-06 [matmul_add_comm_reduction]: 1.76e-05 [allreduce_slice_to_reducescatter]: 9.00007e-07 [virtual_shard_identity]: 1.629e-05 [virtual_dataset]: 1.363e-05 [get_grad_eliminate_]: 1.332e-05 [virtual_output]: 1.358e-05 [merge_forward]: 8.90001e-06 [cell_reuse_recompute_pass]: 1.62999e-06 [offload_activation]: 1.75e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.606e-05 [merge_recompute_call_nodes]: 1.53002e-06 [before_grad]: 2.632e-05 [set_forward_comm_id_for_comm_node_pass]: 8.90001e-06 [meta_fg_expand]: 5.59e-06 [flash_sp_send_recv_attached]: 4.99e-06 [receive_attached]: 2.98998e-06 [after_resolve]: 2.142e-05 [a_after_grad]: 2.155e-05 [renormalize]: 0.0010441 [add_forward_monad_depend]: 6.38e-06 [auto_monad_grad]: 3.06999e-06 [auto_monad_eliminator]: 4.618e-05 [cse]: 9.938e-05 [a_3]: 0.00010244 [Cycle 2]: 0.0013488, [45] [expand_dump_flag]: 1.62999e-06 [switch_simplify]: 1.631e-05 [loop_unroll]: 1.374e-05 [a_1]: 0.00037829 [with_stream_mark]: 1.63e-05 [recompute_prepare]: 1.414e-05 [updatestate_depend_eliminate]: 8.57998e-06 [updatestate_assign_eliminate]: 8.45001e-06 [updatestate_loads_eliminate]: 1.203e-05 [parameter_eliminate]: 1.84998e-06 [a_2]: 0.0002073 [accelerated_algorithm]: 1.85e-05 [shard]: 1.32999e-06 [meta_shard_fg_expand]: 2.76999e-06 [shard_inline]: 1.385e-05 [merge_send_recv]: 1.241e-05 [auto_parallel]: 1.182e-05 [parallel]: 7.25e-06 [flash_sp]: 3.78999e-06 [merge_comm]: 9.27001e-06 [allreduce_fusion]: 8.75001e-06 [matmul_add_comm_reduction]: 1.55e-05 [allreduce_slice_to_reducescatter]: 3.50003e-07 [virtual_shard_identity]: 1.495e-05 [virtual_dataset]: 1.337e-05 [get_grad_eliminate_]: 1.296e-05 [virtual_output]: 1.286e-05 [merge_forward]: 8.12998e-06 [cell_reuse_recompute_pass]: 2.27001e-06 [offload_activation]: 1.563e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.544e-05 [merge_recompute_call_nodes]: 9.79984e-07 [before_grad]: 2.259e-05 [set_forward_comm_id_for_comm_node_pass]: 9.22001e-06 [meta_fg_expand]: 5.37001e-06 [flash_sp_send_recv_attached]: 1.19e-06 [receive_attached]: 1.75001e-06 [after_resolve]: 2.016e-05 [a_after_grad]: 2.208e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 1.50001e-06 [auto_monad_grad]: 1.09e-06 [auto_monad_eliminator]: 3.055e-05 [cse]: 4.578e-05 [a_3]: 9.019e-05 [py_interpret_to_execute_after_opt_a]: 1.961e-05 [slice_cell_reuse_recomputed_activation]: 2.43e-06 [rewriter_after_opt_a]: 0.00020843 [convert_after_rewriter]: 1.57e-05 [order_py_execute_after_rewriter]: 1.02e-05 [mutable_eliminate]: 0.00066935 [opt_b]: 0.0004656, [1] [Cycle 1]: 0.00045778, [7] [b_1]: 0.00032022 [b_2]: 1.616e-05 [updatestate_depend_eliminate]: 1.288e-05 [updatestate_assign_eliminate]: 8.37998e-06 [updatestate_loads_eliminate]: 1.161e-05 [renormalize]: 6.00005e-07 [cse]: 5.206e-05 [optimize_parallel_all_gather_comm]: 2.747e-05 [overlap_param_gather]: 4.42998e-06 [cconv]: 3.346e-05 [loop_unroll]: 0.00045338 [opt_after_cconv]: 0.0002263, [1] [Cycle 1]: 0.00021997, [7] [c_1]: 9.886e-05 [parameter_eliminate]: 4.39998e-06 [updatestate_depend_eliminate]: 1.163e-05 [updatestate_assign_eliminate]: 8.55999e-06 [updatestate_loads_eliminate]: 1.08e-05 [cse]: 4.891e-05 [renormalize]: 4.90021e-07 [remove_dup_value]: 6.548e-05 [tuple_transform]: 0.00013251, [1] [Cycle 1]: 0.00012751, [4] [d_1]: 9.234e-05 [none_parameter_eliminate]: 1.72999e-06 [renormalize]: 2.80008e-07 [switch_simplify]: 1.475e-05 [partial_unused_args_eliminate]: 1.74998e-06 [add_recomputation]: 0.00010164 [cse_after_recomputation]: 4.544e-05, [1] [Cycle 1]: 4.018e-05, [1] [cse]: 3.346e-05 [environ_conv]: 2.359e-05 [swap_dp_allreduce_reducescatter]: 1.143e-05 [bias_add_comm_swap]: 3.48999e-06 [label_micro_interleaved_index]: 4.58999e-06 [label_fine_grained_interleaved_index]: 2.74999e-06 [merge_cast_opt]: 1.52001e-06 [slice_recompute_activation]: 2.74999e-06 [micro_interleaved_order_control]: 2.33998e-06 [assign_add_opt]: 1.22e-06 [ForceFp32Comm]: 8.2e-07 [remove_cast_before_assign_add]: 1.22e-06 [full_micro_interleaved_order_control]: 2.02001e-06 [reorder_send_recv_between_fp_bp]: 3.23e-06 [comm_op_add_attrs]: 9.90025e-07 [add_comm_op_reuse_tag]: 9.89996e-07 [interleave_split_concat_branches]: 1.27e-06 [interleave_parallel_branches]: 1.28002e-06 [overlap_opt_shard_in_pipeline]: 2.408e-05 [overlap_opt_shard_grad_in_pipeline]: 1.92999e-06 [control_data_broadcast_order]: 2.796e-05 [grouped_pairwise_exchange_alltoall]: 1.52001e-06 [offloading_packed_experts]: 8.25999e-06 [overlap_recompute_and_grad_model_parallel]: 8.72998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.20999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.44e-06 [overlap_recompute_comm]: 2.32999e-06 [overlap_grad_ring_attention]: 7.43e-06 [overlap_grad_flash_sp]: 3.904e-05 [begin_end_overlap_inline]: 6.29982e-07 [split_matmul_comm_elemetwise]: 2.53e-06 [split_layernorm_comm]: 1.72999e-06 [handle_group_info]: 1.25999e-06 [symbol_engine_optimizer]: 0.00015115, [1] [Cycle 1]: 0.00014578, [6] [build]: 2.475e-05 [elim_shapecalc]: 2.03e-05 [elim_not_effective]: 2.8e-05 [opt_reshape]: 1.576e-05 [fold_const_symbol]: 2.392e-05 [renormalize]: 2.89991e-07 [detach_backward]: 2.31998e-06 [pipeline_parallel_scheduler]: 1.54998e-06 [auto_monad_reorder]: 5.896e-05 [get_jit_bprop_graph]: 1.69e-06 [rewriter_after_jit_bprop_graph]: 5.51e-06 [opt_after_jit_grad]: 0.00055797 [validate]: 8.015e-05 Sums bootstrap : 0.000617s : 1.31% type_inference : 0.038800s : 82.41% event_method : 0.000016s : 0.03% auto_monad : 0.000232s : 0.49% graph_reusing : 0.000006s : 0.01% inline : 0.000003s : 0.01% add_attr.add_attr_with_inline.tag_attr : 0.000025s : 0.05% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.01% parallel-infer-symbol : 0.000004s : 0.01% pre_auto_parallel : 0.000050s : 0.11% insert-virtual-dataset : 0.000002s : 0.01% 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 : 0.000032s : 0.07% optimize.rewriter_before_opt_a : 0.000084s : 0.18% optimize.opt_a.expand_dump_flag : 0.000004s : 0.01% optimize.opt_a.switch_simplify : 0.000049s : 0.10% optimize.opt_a.loop_unroll : 0.000032s : 0.07% optimize.opt_a.a_1 : 0.000973s : 2.07% optimize.opt_a.with_stream_mark : 0.000047s : 0.10% optimize.opt_a.recompute_prepare : 0.000030s : 0.06% optimize.opt_a.updatestate_depend_eliminate : 0.000018s : 0.04% optimize.opt_a.updatestate_assign_eliminate : 0.000020s : 0.04% optimize.opt_a.updatestate_loads_eliminate : 0.000027s : 0.06% optimize.opt_a.parameter_eliminate : 0.000004s : 0.01% optimize.opt_a.a_2 : 0.000438s : 0.93% optimize.opt_a.accelerated_algorithm : 0.000057s : 0.12% optimize.opt_a.shard : 0.000004s : 0.01% optimize.opt_a.meta_shard_fg_expand : 0.000006s : 0.01% optimize.opt_a.shard_inline : 0.000028s : 0.06% optimize.opt_a.merge_send_recv : 0.000035s : 0.07% optimize.opt_a.auto_parallel : 0.000023s : 0.05% optimize.opt_a.parallel : 0.000060s : 0.13% optimize.opt_a.flash_sp : 0.000024s : 0.05% optimize.opt_a.merge_comm : 0.000018s : 0.04% optimize.opt_a.allreduce_fusion : 0.000017s : 0.04% optimize.opt_a.matmul_add_comm_reduction : 0.000033s : 0.07% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000031s : 0.07% optimize.opt_a.virtual_dataset : 0.000027s : 0.06% optimize.opt_a.get_grad_eliminate_ : 0.000026s : 0.06% optimize.opt_a.virtual_output : 0.000026s : 0.06% optimize.opt_a.merge_forward : 0.000017s : 0.04% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.01% optimize.opt_a.offload_activation : 0.000033s : 0.07% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000062s : 0.13% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.01% optimize.opt_a.before_grad : 0.000049s : 0.10% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000018s : 0.04% optimize.opt_a.meta_fg_expand : 0.000011s : 0.02% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.01% optimize.opt_a.receive_attached : 0.000005s : 0.01% optimize.opt_a.after_resolve : 0.000042s : 0.09% optimize.opt_a.a_after_grad : 0.000044s : 0.09% optimize.opt_a.renormalize : 0.001044s : 2.22% optimize.opt_a.add_forward_monad_depend : 0.000008s : 0.02% optimize.opt_a.auto_monad_grad : 0.000004s : 0.01% optimize.opt_a.auto_monad_eliminator : 0.000077s : 0.16% optimize.opt_a.cse : 0.000145s : 0.31% optimize.opt_a.a_3 : 0.000193s : 0.41% optimize.py_interpret_to_execute_after_opt_a : 0.000020s : 0.04% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.01% optimize.rewriter_after_opt_a : 0.000208s : 0.44% optimize.convert_after_rewriter : 0.000016s : 0.03% optimize.order_py_execute_after_rewriter : 0.000010s : 0.02% optimize.mutable_eliminate : 0.000669s : 1.42% optimize.opt_b.b_1 : 0.000320s : 0.68% optimize.opt_b.b_2 : 0.000016s : 0.03% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.03% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.02% optimize.opt_b.updatestate_loads_eliminate : 0.000012s : 0.02% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000052s : 0.11% optimize.optimize_parallel_all_gather_comm : 0.000027s : 0.06% optimize.overlap_param_gather : 0.000004s : 0.01% optimize.cconv : 0.000033s : 0.07% optimize.loop_unroll : 0.000453s : 0.96% optimize.opt_after_cconv.c_1 : 0.000099s : 0.21% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.02% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000009s : 0.02% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000011s : 0.02% optimize.opt_after_cconv.cse : 0.000049s : 0.10% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000065s : 0.14% optimize.tuple_transform.d_1 : 0.000092s : 0.20% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000015s : 0.03% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000102s : 0.22% optimize.cse_after_recomputation.cse : 0.000033s : 0.07% optimize.environ_conv : 0.000024s : 0.05% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 0.02% optimize.bias_add_comm_swap : 0.000003s : 0.01% optimize.label_micro_interleaved_index : 0.000005s : 0.01% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.01% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.01% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.01% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000024s : 0.05% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000028s : 0.06% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.02% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 0.02% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000007s : 0.02% optimize.overlap_grad_flash_sp : 0.000039s : 0.08% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.01% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000025s : 0.05% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000020s : 0.04% optimize.symbol_engine_optimizer.elim_not_effective : 0.000028s : 0.06% optimize.symbol_engine_optimizer.opt_reshape : 0.000016s : 0.03% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000024s : 0.05% 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 : 0.000059s : 0.13% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.01% opt_after_jit_grad : 0.000558s : 1.19% validate : 0.000080s : 0.17% Time group info: ------[substitution.] 0.000373 102 22.51% : 0.000084s : 4: substitution.arithmetic_simplify 2.55% : 0.000009s : 2: substitution.depend_value_elim 1.07% : 0.000004s : 8: substitution.elim_not_effective 0.87% : 0.000003s : 8: substitution.fold_const_symbol 2.77% : 0.000010s : 11: substitution.graph_param_transform 29.75% : 0.000111s : 1: substitution.inline 2.24% : 0.000008s : 16: substitution.j_node_and_user_rematch 6.12% : 0.000023s : 4: substitution.less_batch_normalization 2.12% : 0.000008s : 12: substitution.load_eliminater 5.64% : 0.000021s : 16: substitution.remove_not_recompute_node 2.01% : 0.000007s : 6: substitution.replace_old_param 2.11% : 0.000008s : 6: substitution.updatestate_pure_node_eliminater 20.25% : 0.000076s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.038732 2 98.71% : 0.038235s : 1: type_inference.infer 1.29% : 0.000498s : 1: type_inference.specialize ------[replace.] 0.000017 1 100.00% : 0.000017s : 1: replace.inline ------[match.] 0.000110 1 100.00% : 0.000110s : 1: match.inline ------[predicate.] 0.000363 2549 0.83% : 0.000003s : 23: predicate.accumulaten_eliminater 1.00% : 0.000004s : 11: predicate.ad_related_special_op_eliminate 0.78% : 0.000003s : 22: predicate.addn_check_dump 0.86% : 0.000003s : 23: predicate.addn_zero_filter 0.78% : 0.000003s : 23: predicate.adjust_all_reduce_mul_add 2.31% : 0.000008s : 45: predicate.arithmetic_simplify 0.81% : 0.000003s : 23: predicate.cast_eliminate 0.82% : 0.000003s : 22: predicate.check_bprop_eliminate 0.82% : 0.000003s : 22: predicate.compare_switch_simplify 0.24% : 0.000001s : 11: predicate.const_output_eliminate 0.87% : 0.000003s : 22: predicate.depend_value_elim 0.87% : 0.000003s : 23: predicate.dict_get_item_const_eliminator 0.93% : 0.000003s : 23: predicate.dict_get_item_eliminator 0.81% : 0.000003s : 23: predicate.dict_set_item_eliminator 1.12% : 0.000004s : 22: predicate.dumpgradient_eliminate 0.27% : 0.000001s : 11: predicate.elim_not_effective 0.62% : 0.000002s : 11: predicate.elim_shapecalc_of_broadcastargs 1.19% : 0.000004s : 34: predicate.environ_add_const_eliminate 1.17% : 0.000004s : 34: predicate.environ_get_add_eliminate 1.14% : 0.000004s : 34: predicate.environ_get_depend_swap 1.95% : 0.000007s : 56: predicate.environ_get_eliminate 1.15% : 0.000004s : 34: predicate.environ_get_set_eliminate 0.82% : 0.000003s : 24: predicate.exchange_switch_depend_value 1.30% : 0.000005s : 24: predicate.float_depend_g_call 0.79% : 0.000003s : 22: predicate.float_environ_get_switch 1.17% : 0.000004s : 33: predicate.float_tuple_getitem_switch 0.26% : 0.000001s : 11: predicate.fold_const_symbol 0.94% : 0.000003s : 22: predicate.get_grad_eliminate 0.28% : 0.000001s : 11: predicate.graph_param_transform 0.83% : 0.000003s : 22: predicate.incorporate_call 0.75% : 0.000003s : 22: predicate.incorporate_call_switch 5.72% : 0.000021s : 113: predicate.inline 1.20% : 0.000004s : 22: predicate.inline_without_move 0.44% : 0.000002s : 22: predicate.j_node_and_user_rematch 1.08% : 0.000004s : 22: predicate.less_batch_normalization 1.67% : 0.000006s : 45: predicate.list_to_tuple_eliminator_ 2.50% : 0.000009s : 68: predicate.load_eliminater 0.74% : 0.000003s : 11: predicate.loop_unroll_after_grad 1.03% : 0.000004s : 27: predicate.loop_unroll_before_grad 1.81% : 0.000007s : 45: predicate.make_slice_get_slice_eliminator 0.78% : 0.000003s : 22: predicate.merge_addn 0.77% : 0.000003s : 22: predicate.micro_step_allgather_replace 0.83% : 0.000003s : 22: predicate.mini_step_allgather_replace 0.76% : 0.000003s : 23: predicate.minmaximum_grad 1.00% : 0.000004s : 11: predicate.mutable_eliminate 0.52% : 0.000002s : 11: predicate.opt_reshape 0.48% : 0.000002s : 11: predicate.parallel_virtual_node 0.98% : 0.000004s : 24: predicate.partial_defer_inline 1.38% : 0.000005s : 34: predicate.partial_eliminate 0.79% : 0.000003s : 23: predicate.print_const_string_wrapper 0.85% : 0.000003s : 22: predicate.reduce_all_const_elim 1.01% : 0.000004s : 23: predicate.reduce_eliminate 2.52% : 0.000009s : 68: predicate.redundant_stop_gradient_eliminater 0.58% : 0.000002s : 22: predicate.remove_not_recompute_node 1.27% : 0.000005s : 45: predicate.replace_applicator 0.57% : 0.000002s : 22: predicate.replace_old_param 0.34% : 0.000001s : 11: predicate.reset_defer_inline 0.85% : 0.000003s : 23: predicate.reshape_eliminate 0.85% : 0.000003s : 22: predicate.row_tensor_add_zeros_like 0.50% : 0.000002s : 11: predicate.row_tensor_eliminate 0.92% : 0.000003s : 22: predicate.same_eliminate 0.57% : 0.000002s : 22: predicate.set_cell_output_no_recompute 0.92% : 0.000003s : 22: predicate.shard_identity_eliminate 0.98% : 0.000004s : 22: predicate.special_op_eliminate 0.94% : 0.000003s : 22: predicate.specialize_transform 1.03% : 0.000004s : 22: predicate.split_environ_get_set_with_tuple_value 0.96% : 0.000003s : 22: predicate.stack_unstack_eliminate 0.49% : 0.000002s : 11: predicate.switch_call_monad_eliminater 0.88% : 0.000003s : 24: predicate.switch_defer_inline 1.69% : 0.000006s : 46: predicate.switch_layer_defer_inline 3.40% : 0.000012s : 84: predicate.switch_simplify 0.82% : 0.000003s : 23: predicate.tile_eliminate 0.78% : 0.000003s : 23: predicate.transpose_eliminate 1.75% : 0.000006s : 45: predicate.tuple_list_convert_item_index_to_positive 1.73% : 0.000006s : 45: predicate.tuple_list_get_item_const_eliminator 1.61% : 0.000006s : 45: predicate.tuple_list_get_item_depend_reorder 3.10% : 0.000011s : 67: predicate.tuple_list_get_item_eliminator 1.62% : 0.000006s : 45: predicate.tuple_list_get_set_item_eliminator 2.65% : 0.000010s : 67: predicate.tuple_list_set_item_eliminator 1.71% : 0.000006s : 45: predicate.tuple_to_list_eliminator_ 2.56% : 0.000009s : 68: predicate.updatestate_pure_node_eliminater 3.44% : 0.000012s : 90: predicate.updatestate_useless_node_eliminater 0.45% : 0.000002s : 11: predicate.value_based_eliminate 0.90% : 0.000003s : 22: predicate.virtual_dataset_eliminate 0.93% : 0.000003s : 22: predicate.virtual_output_eliminate 0.48% : 0.000002s : 11: predicate.virtual_view_grad_eliminate 0.46% : 0.000002s : 11: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000274 4 8.36% : 0.000023s : 1: func_graph_cloner_run.FuncGraphClonerGraph 91.64% : 0.000251s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.272558 192 0.00% : 0.000004s : 1: ForceFp32Comm 39.16% : 0.106725s : 1: add_attr 39.15% : 0.106702s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.04% : 0.000106s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.09% : 0.000240s : 1: auto_monad 0.02% : 0.000064s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.24% : 0.000652s : 1: bootstrap 0.01% : 0.000037s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000031s : 1: control_data_broadcast_order 0.01% : 0.000020s : 1: convert_after_rewriter 0.02% : 0.000049s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000027s : 1: environ_conv 0.01% : 0.000023s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.17% : 0.000461s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.25% : 0.000678s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.01% : 0.000024s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000026s : 1: opt.transform.mutable_eliminate 0.74% : 0.002014s : 78: opt.transform.opt_a 0.04% : 0.000097s : 1: opt.transform.opt_after_cconv 0.02% : 0.000053s : 1: opt.transform.opt_after_jit_grad 0.11% : 0.000309s : 28: opt.transform.opt_b 0.04% : 0.000105s : 2: opt.transform.opt_trans_graph 0.03% : 0.000084s : 4: opt.transform.symbol_engine_opt 1.57% : 0.004287s : 1: opt_a 0.08% : 0.000230s : 1: opt_after_cconv 0.21% : 0.000569s : 1: opt_after_jit_grad 0.17% : 0.000469s : 1: opt_b 2.74% : 0.007477s : 1: optimize 0.01% : 0.000032s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.02% : 0.000043s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.01% : 0.000028s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000008s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.02% : 0.000055s : 1: pre_auto_parallel 0.01% : 0.000036s : 1: py_interpret_to_execute 0.01% : 0.000024s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.03% : 0.000070s : 1: remove_dup_value 0.23% : 0.000613s : 1: renormalize.infer 0.15% : 0.000420s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.08% : 0.000216s : 1: rewriter_after_opt_a 0.03% : 0.000088s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.01% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.06% : 0.000154s : 1: symbol_engine_optimizer 0.05% : 0.000136s : 1: tuple_transform 14.24% : 0.038821s : 1: type_inference . [hook] pytest_runtest_teardown:test_qbmm_add[False-False-input_shape0] tests/st/infer/ops/test_internal_ops/test_quant_bmm.py::test_qbmm_add[False-False-input_shape0],max_mem:20.0M [WARNING] ME(169497:281473358380848,MainProcess):2026-01-29-17:38:15.941.621 [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 = 0.314165, [21] [bootstrap]: 0.00095554 [type_inference]: 0.297059 [event_method]: 2.21e-05 [auto_monad]: 0.00030412 [graph_reusing]: 7.5e-06 [inline]: 3.39001e-06 [add_attr]: 0.00554948, [1] [add_attr_with_inline]: 0.00553029, [1] [Cycle 1]: 8.278e-05, [2] [tag_attr]: 2.667e-05 [meta_addattr_fg_expand]: 4.44002e-06 [parallel-infer-symbol]: 4.27e-06 [pre_auto_parallel]: 4.684e-05 [insert-virtual-dataset]: 3.25e-06 [parallel-infer-symbol-second]: 7.89994e-07 [dataset_repeat_opt]: 1.99e-06 [pipeline_split]: 2.61999e-06 [optimize]: 0.0092393, [53] [py_interpret_to_execute]: 3.89e-05 [rewriter_before_opt_a]: 8.484e-05 [opt_a]: 0.00560857, [2] [Cycle 1]: 0.00412439, [45] [expand_dump_flag]: 3.48999e-06 [switch_simplify]: 3.505e-05 [loop_unroll]: 1.824e-05 [a_1]: 0.00071779 [with_stream_mark]: 2.597e-05 [recompute_prepare]: 1.643e-05 [updatestate_depend_eliminate]: 1.003e-05 [updatestate_assign_eliminate]: 1.103e-05 [updatestate_loads_eliminate]: 1.943e-05 [parameter_eliminate]: 2.14999e-06 [a_2]: 0.00027917 [accelerated_algorithm]: 4.267e-05 [shard]: 2.65997e-06 [meta_shard_fg_expand]: 3.56001e-06 [shard_inline]: 1.62e-05 [merge_send_recv]: 2.14e-05 [auto_parallel]: 1.286e-05 [parallel]: 4.662e-05 [flash_sp]: 1.518e-05 [merge_comm]: 9.91e-06 [allreduce_fusion]: 8.70001e-06 [matmul_add_comm_reduction]: 1.85e-05 [allreduce_slice_to_reducescatter]: 9.20001e-07 [virtual_shard_identity]: 2.158e-05 [virtual_dataset]: 1.411e-05 [get_grad_eliminate_]: 1.368e-05 [virtual_output]: 1.828e-05 [merge_forward]: 1.956e-05 [cell_reuse_recompute_pass]: 1.54e-06 [offload_activation]: 2.469e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.834e-05 [merge_recompute_call_nodes]: 1.91e-06 [before_grad]: 2.936e-05 [set_forward_comm_id_for_comm_node_pass]: 1.02e-05 [meta_fg_expand]: 6.73e-06 [flash_sp_send_recv_attached]: 0.00043312 [receive_attached]: 4.38001e-06 [after_resolve]: 4.641e-05 [a_after_grad]: 2.643e-05 [renormalize]: 0.00144881 [add_forward_monad_depend]: 1.098e-05 [auto_monad_grad]: 3.06001e-06 [auto_monad_eliminator]: 4.916e-05 [cse]: 0.0001476 [a_3]: 0.00011267 [Cycle 2]: 0.00147113, [45] [expand_dump_flag]: 1.86e-06 [switch_simplify]: 1.689e-05 [loop_unroll]: 1.365e-05 [a_1]: 0.00041056 [with_stream_mark]: 1.956e-05 [recompute_prepare]: 1.468e-05 [updatestate_depend_eliminate]: 9.91e-06 [updatestate_assign_eliminate]: 9.24e-06 [updatestate_loads_eliminate]: 1.222e-05 [parameter_eliminate]: 1.27e-06 [a_2]: 0.00022503 [accelerated_algorithm]: 1.977e-05 [shard]: 2.12999e-06 [meta_shard_fg_expand]: 3.56001e-06 [shard_inline]: 1.376e-05 [merge_send_recv]: 1.258e-05 [auto_parallel]: 1.265e-05 [parallel]: 7.15e-06 [flash_sp]: 4.43999e-06 [merge_comm]: 1.165e-05 [allreduce_fusion]: 8.01001e-06 [matmul_add_comm_reduction]: 1.426e-05 [allreduce_slice_to_reducescatter]: 6.59988e-07 [virtual_shard_identity]: 1.589e-05 [virtual_dataset]: 1.829e-05 [get_grad_eliminate_]: 1.395e-05 [virtual_output]: 2.348e-05 [merge_forward]: 9.24e-06 [cell_reuse_recompute_pass]: 1.77001e-06 [offload_activation]: 1.867e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.706e-05 [merge_recompute_call_nodes]: 1.04e-06 [before_grad]: 2.336e-05 [set_forward_comm_id_for_comm_node_pass]: 9.17001e-06 [meta_fg_expand]: 5.97001e-06 [flash_sp_send_recv_attached]: 1.36998e-06 [receive_attached]: 1.39e-06 [after_resolve]: 2.37e-05 [a_after_grad]: 2.192e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 1.97001e-06 [auto_monad_grad]: 1.30001e-06 [auto_monad_eliminator]: 3.325e-05 [cse]: 4.992e-05 [a_3]: 9.748e-05 [py_interpret_to_execute_after_opt_a]: 2.103e-05 [slice_cell_reuse_recomputed_activation]: 2.02001e-06 [rewriter_after_opt_a]: 0.00018407 [convert_after_rewriter]: 1.511e-05 [order_py_execute_after_rewriter]: 9.81e-06 [mutable_eliminate]: 0.0007691 [opt_b]: 0.00051848, [1] [Cycle 1]: 0.00050995, [7] [b_1]: 0.00035252 [b_2]: 1.785e-05 [updatestate_depend_eliminate]: 1.335e-05 [updatestate_assign_eliminate]: 9.66998e-06 [updatestate_loads_eliminate]: 1.172e-05 [renormalize]: 1.08001e-06 [cse]: 6.118e-05 [optimize_parallel_all_gather_comm]: 3.582e-05 [overlap_param_gather]: 2.44001e-06 [cconv]: 4.032e-05 [loop_unroll]: 0.00059658 [opt_after_cconv]: 0.00023387, [1] [Cycle 1]: 0.00022699, [7] [c_1]: 9.692e-05 [parameter_eliminate]: 4.90001e-06 [updatestate_depend_eliminate]: 1.558e-05 [updatestate_assign_eliminate]: 8.74e-06 [updatestate_loads_eliminate]: 1.125e-05 [cse]: 5.264e-05 [renormalize]: 4.69998e-07 [remove_dup_value]: 8.596e-05 [tuple_transform]: 0.00016193, [1] [Cycle 1]: 0.00015612, [4] [d_1]: 0.00011286 [none_parameter_eliminate]: 2.13002e-06 [renormalize]: 4.09986e-07 [switch_simplify]: 1.493e-05 [partial_unused_args_eliminate]: 2.35002e-06 [add_recomputation]: 0.00010695 [cse_after_recomputation]: 4.733e-05, [1] [Cycle 1]: 4.221e-05, [1] [cse]: 3.563e-05 [environ_conv]: 1.502e-05 [swap_dp_allreduce_reducescatter]: 1.151e-05 [bias_add_comm_swap]: 4.02e-06 [label_micro_interleaved_index]: 4.97e-06 [label_fine_grained_interleaved_index]: 2.98e-06 [merge_cast_opt]: 1.58002e-06 [slice_recompute_activation]: 2.22001e-06 [micro_interleaved_order_control]: 3.13e-06 [assign_add_opt]: 1.55999e-06 [ForceFp32Comm]: 9.70002e-07 [remove_cast_before_assign_add]: 1.19e-06 [full_micro_interleaved_order_control]: 2.37999e-06 [reorder_send_recv_between_fp_bp]: 3.03e-06 [comm_op_add_attrs]: 1.33002e-06 [add_comm_op_reuse_tag]: 1.17e-06 [interleave_split_concat_branches]: 1.22e-06 [interleave_parallel_branches]: 1.75001e-06 [overlap_opt_shard_in_pipeline]: 1.29e-06 [overlap_opt_shard_grad_in_pipeline]: 2.09e-06 [control_data_broadcast_order]: 3.167e-05 [grouped_pairwise_exchange_alltoall]: 1.49998e-06 [offloading_packed_experts]: 7.37002e-06 [overlap_recompute_and_grad_model_parallel]: 8.24002e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.39e-06 [overlap_recompute_allgather_and_fa_grad]: 1.74e-06 [overlap_recompute_comm]: 2.74999e-06 [overlap_grad_ring_attention]: 7.56001e-06 [overlap_grad_flash_sp]: 3.891e-05 [begin_end_overlap_inline]: 6.69999e-07 [split_matmul_comm_elemetwise]: 3.71001e-06 [split_layernorm_comm]: 2.13998e-06 [handle_group_info]: 1.30001e-06 [symbol_engine_optimizer]: 0.00020428, [1] [Cycle 1]: 0.00019932, [6] [build]: 2.104e-05 [elim_shapecalc]: 4.297e-05 [elim_not_effective]: 3.257e-05 [opt_reshape]: 3.411e-05 [fold_const_symbol]: 3.032e-05 [renormalize]: 2.00002e-07 [detach_backward]: 2.15002e-06 [pipeline_parallel_scheduler]: 1.79e-06 [auto_monad_reorder]: 7.37e-05 [get_jit_bprop_graph]: 5.91e-06 [rewriter_after_jit_bprop_graph]: 6.09001e-06 [opt_after_jit_grad]: 0.00059819 [validate]: 8.604e-05 Sums bootstrap : 0.000956s : 0.31% type_inference : 0.297059s : 96.63% event_method : 0.000022s : 0.01% auto_monad : 0.000304s : 0.10% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000027s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000047s : 0.02% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000003s : 0.00% optimize.py_interpret_to_execute : 0.000039s : 0.01% optimize.rewriter_before_opt_a : 0.000085s : 0.03% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000052s : 0.02% optimize.opt_a.loop_unroll : 0.000032s : 0.01% optimize.opt_a.a_1 : 0.001128s : 0.37% optimize.opt_a.with_stream_mark : 0.000046s : 0.01% optimize.opt_a.recompute_prepare : 0.000031s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000020s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000020s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000032s : 0.01% optimize.opt_a.parameter_eliminate : 0.000003s : 0.00% optimize.opt_a.a_2 : 0.000504s : 0.16% optimize.opt_a.accelerated_algorithm : 0.000062s : 0.02% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.00% optimize.opt_a.shard_inline : 0.000030s : 0.01% optimize.opt_a.merge_send_recv : 0.000034s : 0.01% optimize.opt_a.auto_parallel : 0.000026s : 0.01% optimize.opt_a.parallel : 0.000054s : 0.02% optimize.opt_a.flash_sp : 0.000020s : 0.01% optimize.opt_a.merge_comm : 0.000022s : 0.01% optimize.opt_a.allreduce_fusion : 0.000017s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000033s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000037s : 0.01% optimize.opt_a.virtual_dataset : 0.000032s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000028s : 0.01% optimize.opt_a.virtual_output : 0.000042s : 0.01% optimize.opt_a.merge_forward : 0.000029s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.00% optimize.opt_a.offload_activation : 0.000043s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000055s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000053s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000019s : 0.01% optimize.opt_a.meta_fg_expand : 0.000013s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000434s : 0.14% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000070s : 0.02% optimize.opt_a.a_after_grad : 0.000048s : 0.02% optimize.opt_a.renormalize : 0.001449s : 0.47% optimize.opt_a.add_forward_monad_depend : 0.000013s : 0.00% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000082s : 0.03% optimize.opt_a.cse : 0.000198s : 0.06% optimize.opt_a.a_3 : 0.000210s : 0.07% optimize.py_interpret_to_execute_after_opt_a : 0.000021s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000184s : 0.06% optimize.convert_after_rewriter : 0.000015s : 0.00% optimize.order_py_execute_after_rewriter : 0.000010s : 0.00% optimize.mutable_eliminate : 0.000769s : 0.25% optimize.opt_b.b_1 : 0.000353s : 0.11% optimize.opt_b.b_2 : 0.000018s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000061s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000036s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000040s : 0.01% optimize.loop_unroll : 0.000597s : 0.19% optimize.opt_after_cconv.c_1 : 0.000097s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000016s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_after_cconv.cse : 0.000053s : 0.02% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000086s : 0.03% optimize.tuple_transform.d_1 : 0.000113s : 0.04% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000015s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000107s : 0.03% optimize.cse_after_recomputation.cse : 0.000036s : 0.01% optimize.environ_conv : 0.000015s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000012s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 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 : 0.000002s : 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 : 0.000032s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000001s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000039s : 0.01% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000004s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000021s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000043s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000033s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000034s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000030s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000074s : 0.02% get_jit_bprop_graph : 0.000006s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000598s : 0.19% validate : 0.000086s : 0.03% Time group info: ------[substitution.] 0.000463 102 19.88% : 0.000092s : 4: substitution.arithmetic_simplify 7.75% : 0.000036s : 2: substitution.depend_value_elim 0.84% : 0.000004s : 8: substitution.elim_not_effective 2.19% : 0.000010s : 8: substitution.fold_const_symbol 2.15% : 0.000010s : 11: substitution.graph_param_transform 26.47% : 0.000123s : 1: substitution.inline 1.81% : 0.000008s : 16: substitution.j_node_and_user_rematch 5.48% : 0.000025s : 4: substitution.less_batch_normalization 1.64% : 0.000008s : 12: substitution.load_eliminater 2.61% : 0.000012s : 16: substitution.remove_not_recompute_node 2.25% : 0.000010s : 6: substitution.replace_old_param 1.94% : 0.000009s : 6: substitution.updatestate_pure_node_eliminater 24.99% : 0.000116s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.296965 2 2.24% : 0.006642s : 1: type_inference.infer 97.76% : 0.290323s : 1: type_inference.specialize ------[replace.] 0.000020 1 100.00% : 0.000020s : 1: replace.inline ------[match.] 0.000121 1 100.00% : 0.000121s : 1: match.inline ------[predicate.] 0.000391 2549 0.92% : 0.000004s : 23: predicate.accumulaten_eliminater 0.94% : 0.000004s : 11: predicate.ad_related_special_op_eliminate 0.71% : 0.000003s : 22: predicate.addn_check_dump 0.87% : 0.000003s : 23: predicate.addn_zero_filter 0.73% : 0.000003s : 23: predicate.adjust_all_reduce_mul_add 2.43% : 0.000010s : 45: predicate.arithmetic_simplify 0.87% : 0.000003s : 23: predicate.cast_eliminate 0.81% : 0.000003s : 22: predicate.check_bprop_eliminate 0.79% : 0.000003s : 22: predicate.compare_switch_simplify 0.23% : 0.000001s : 11: predicate.const_output_eliminate 0.85% : 0.000003s : 22: predicate.depend_value_elim 0.86% : 0.000003s : 23: predicate.dict_get_item_const_eliminator 0.91% : 0.000004s : 23: predicate.dict_get_item_eliminator 0.83% : 0.000003s : 23: predicate.dict_set_item_eliminator 1.12% : 0.000004s : 22: predicate.dumpgradient_eliminate 0.26% : 0.000001s : 11: predicate.elim_not_effective 0.48% : 0.000002s : 11: predicate.elim_shapecalc_of_broadcastargs 1.12% : 0.000004s : 34: predicate.environ_add_const_eliminate 1.09% : 0.000004s : 34: predicate.environ_get_add_eliminate 1.09% : 0.000004s : 34: predicate.environ_get_depend_swap 2.01% : 0.000008s : 56: predicate.environ_get_eliminate 1.17% : 0.000005s : 34: predicate.environ_get_set_eliminate 0.79% : 0.000003s : 24: predicate.exchange_switch_depend_value 1.30% : 0.000005s : 24: predicate.float_depend_g_call 0.74% : 0.000003s : 22: predicate.float_environ_get_switch 1.06% : 0.000004s : 33: predicate.float_tuple_getitem_switch 0.22% : 0.000001s : 11: predicate.fold_const_symbol 0.79% : 0.000003s : 22: predicate.get_grad_eliminate 0.25% : 0.000001s : 11: predicate.graph_param_transform 0.79% : 0.000003s : 22: predicate.incorporate_call 0.71% : 0.000003s : 22: predicate.incorporate_call_switch 5.51% : 0.000022s : 113: predicate.inline 1.29% : 0.000005s : 22: predicate.inline_without_move 0.39% : 0.000002s : 22: predicate.j_node_and_user_rematch 1.14% : 0.000004s : 22: predicate.less_batch_normalization 1.70% : 0.000007s : 45: predicate.list_to_tuple_eliminator_ 2.37% : 0.000009s : 68: predicate.load_eliminater 0.93% : 0.000004s : 11: predicate.loop_unroll_after_grad 0.98% : 0.000004s : 27: predicate.loop_unroll_before_grad 1.64% : 0.000006s : 45: predicate.make_slice_get_slice_eliminator 0.80% : 0.000003s : 22: predicate.merge_addn 0.79% : 0.000003s : 22: predicate.micro_step_allgather_replace 0.78% : 0.000003s : 22: predicate.mini_step_allgather_replace 0.74% : 0.000003s : 23: predicate.minmaximum_grad 1.07% : 0.000004s : 11: predicate.mutable_eliminate 0.44% : 0.000002s : 11: predicate.opt_reshape 0.52% : 0.000002s : 11: predicate.parallel_virtual_node 1.02% : 0.000004s : 24: predicate.partial_defer_inline 1.31% : 0.000005s : 34: predicate.partial_eliminate 0.80% : 0.000003s : 23: predicate.print_const_string_wrapper 0.77% : 0.000003s : 22: predicate.reduce_all_const_elim 1.03% : 0.000004s : 23: predicate.reduce_eliminate 2.31% : 0.000009s : 68: predicate.redundant_stop_gradient_eliminater 0.52% : 0.000002s : 22: predicate.remove_not_recompute_node 1.19% : 0.000005s : 45: predicate.replace_applicator 0.56% : 0.000002s : 22: predicate.replace_old_param 0.29% : 0.000001s : 11: predicate.reset_defer_inline 0.86% : 0.000003s : 23: predicate.reshape_eliminate 0.81% : 0.000003s : 22: predicate.row_tensor_add_zeros_like 0.61% : 0.000002s : 11: predicate.row_tensor_eliminate 0.98% : 0.000004s : 22: predicate.same_eliminate 0.51% : 0.000002s : 22: predicate.set_cell_output_no_recompute 0.99% : 0.000004s : 22: predicate.shard_identity_eliminate 0.90% : 0.000004s : 22: predicate.special_op_eliminate 1.03% : 0.000004s : 22: predicate.specialize_transform 1.02% : 0.000004s : 22: predicate.split_environ_get_set_with_tuple_value 1.17% : 0.000005s : 22: predicate.stack_unstack_eliminate 0.46% : 0.000002s : 11: predicate.switch_call_monad_eliminater 0.84% : 0.000003s : 24: predicate.switch_defer_inline 1.57% : 0.000006s : 46: predicate.switch_layer_defer_inline 3.29% : 0.000013s : 84: predicate.switch_simplify 0.79% : 0.000003s : 23: predicate.tile_eliminate 0.89% : 0.000003s : 23: predicate.transpose_eliminate 1.70% : 0.000007s : 45: predicate.tuple_list_convert_item_index_to_positive 1.67% : 0.000007s : 45: predicate.tuple_list_get_item_const_eliminator 1.48% : 0.000006s : 45: predicate.tuple_list_get_item_depend_reorder 2.96% : 0.000012s : 67: predicate.tuple_list_get_item_eliminator 1.51% : 0.000006s : 45: predicate.tuple_list_get_set_item_eliminator 2.46% : 0.000010s : 67: predicate.tuple_list_set_item_eliminator 1.54% : 0.000006s : 45: predicate.tuple_to_list_eliminator_ 2.32% : 0.000009s : 68: predicate.updatestate_pure_node_eliminater 3.40% : 0.000013s : 90: predicate.updatestate_useless_node_eliminater 0.49% : 0.000002s : 11: predicate.value_based_eliminate 0.80% : 0.000003s : 22: predicate.virtual_dataset_eliminate 3.42% : 0.000013s : 22: predicate.virtual_output_eliminate 0.40% : 0.000002s : 11: predicate.virtual_view_grad_eliminate 0.50% : 0.000002s : 11: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000465 4 5.79% : 0.000027s : 1: func_graph_cloner_run.FuncGraphClonerGraph 94.21% : 0.000438s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.333274 192 0.00% : 0.000004s : 1: ForceFp32Comm 1.67% : 0.005556s : 1: add_attr 1.66% : 0.005537s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.03% : 0.000111s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.09% : 0.000311s : 1: auto_monad 0.02% : 0.000080s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.30% : 0.000987s : 1: bootstrap 0.01% : 0.000044s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000036s : 1: control_data_broadcast_order 0.01% : 0.000019s : 1: convert_after_rewriter 0.02% : 0.000053s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000019s : 1: environ_conv 0.01% : 0.000032s : 1: event_method 0.00% : 0.000009s : 1: full_micro_interleaved_order_control 0.00% : 0.000010s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000009s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.18% : 0.000606s : 1: loop_unroll 0.00% : 0.000008s : 1: merge_cast_opt 0.00% : 0.000009s : 1: micro_interleaved_order_control 0.23% : 0.000780s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.01% : 0.000027s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000029s : 1: opt.transform.mutable_eliminate 0.69% : 0.002310s : 78: opt.transform.opt_a 0.03% : 0.000096s : 1: opt.transform.opt_after_cconv 0.02% : 0.000051s : 1: opt.transform.opt_after_jit_grad 0.10% : 0.000340s : 28: opt.transform.opt_b 0.04% : 0.000125s : 2: opt.transform.opt_trans_graph 0.04% : 0.000127s : 4: opt.transform.symbol_engine_opt 1.68% : 0.005613s : 1: opt_a 0.07% : 0.000238s : 1: opt_after_cconv 0.18% : 0.000607s : 1: opt_after_jit_grad 0.16% : 0.000523s : 1: opt_b 2.77% : 0.009245s : 1: optimize 0.01% : 0.000041s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.01% : 0.000043s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000009s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000006s : 1: pipeline_split 0.02% : 0.000052s : 1: pre_auto_parallel 0.01% : 0.000043s : 1: py_interpret_to_execute 0.01% : 0.000025s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.03% : 0.000091s : 1: remove_dup_value 0.22% : 0.000749s : 1: renormalize.infer 0.21% : 0.000689s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.06% : 0.000190s : 1: rewriter_after_opt_a 0.03% : 0.000089s : 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% : 0.000010s : 1: split_layernorm_comm 0.00% : 0.000007s : 1: split_matmul_comm_elemetwise 0.00% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.06% : 0.000207s : 1: symbol_engine_optimizer 0.05% : 0.000165s : 1: tuple_transform 89.14% : 0.297088s : 1: type_inference . [hook] pytest_runtest_teardown:test_qbmm_add[False-False-input_shape1] tests/st/infer/ops/test_internal_ops/test_quant_bmm.py::test_qbmm_add[False-False-input_shape1],max_mem:24.0M [WARNING] ME(169497:281473358380848,MainProcess):2026-01-29-17:38:22.872.535 [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 = 0.244998, [21] [bootstrap]: 0.00059311 [type_inference]: 0.19566 [event_method]: 1.274e-05 [auto_monad]: 0.00022068 [graph_reusing]: 6.09001e-06 [inline]: 2.39001e-06 [add_attr]: 0.0386624, [1] [add_attr_with_inline]: 0.0386393, [1] [Cycle 1]: 0.0337752, [2] [tag_attr]: 0.00016207 [meta_addattr_fg_expand]: 1.884e-05 [parallel-infer-symbol]: 7.3e-06 [pre_auto_parallel]: 6.316e-05 [insert-virtual-dataset]: 2.98e-06 [parallel-infer-symbol-second]: 9.40025e-07 [dataset_repeat_opt]: 2.78e-06 [pipeline_split]: 1.69e-06 [optimize]: 0.00878804, [53] [py_interpret_to_execute]: 5.957e-05 [rewriter_before_opt_a]: 9.925e-05 [opt_a]: 0.00507875, [2] [Cycle 1]: 0.00363492, [45] [expand_dump_flag]: 2.92002e-06 [switch_simplify]: 3.79e-05 [loop_unroll]: 2.02e-05 [a_1]: 0.00076543 [with_stream_mark]: 2.782e-05 [recompute_prepare]: 2.188e-05 [updatestate_depend_eliminate]: 1.149e-05 [updatestate_assign_eliminate]: 1.031e-05 [updatestate_loads_eliminate]: 1.914e-05 [parameter_eliminate]: 2.39999e-06 [a_2]: 0.00029313 [accelerated_algorithm]: 5.165e-05 [shard]: 2.21e-06 [meta_shard_fg_expand]: 4.23999e-06 [shard_inline]: 1.581e-05 [merge_send_recv]: 2.201e-05 [auto_parallel]: 1.559e-05 [parallel]: 4.311e-05 [flash_sp]: 1.733e-05 [merge_comm]: 9.90002e-06 [allreduce_fusion]: 9.47999e-06 [matmul_add_comm_reduction]: 2.116e-05 [allreduce_slice_to_reducescatter]: 2.37999e-06 [virtual_shard_identity]: 2.032e-05 [virtual_dataset]: 1.517e-05 [get_grad_eliminate_]: 1.378e-05 [virtual_output]: 1.887e-05 [merge_forward]: 1.065e-05 [cell_reuse_recompute_pass]: 1.92999e-06 [offload_activation]: 2.195e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.243e-05 [merge_recompute_call_nodes]: 1.85001e-06 [before_grad]: 2.617e-05 [set_forward_comm_id_for_comm_node_pass]: 1.029e-05 [meta_fg_expand]: 8.35001e-06 [flash_sp_send_recv_attached]: 7.42002e-06 [receive_attached]: 3.21999e-06 [after_resolve]: 2.894e-05 [a_after_grad]: 2.334e-05 [renormalize]: 0.0013886 [add_forward_monad_depend]: 7.66999e-06 [auto_monad_grad]: 2.81e-06 [auto_monad_eliminator]: 5.347e-05 [cse]: 9.124e-05 [a_3]: 0.00010908 [Cycle 2]: 0.0014237, [45] [expand_dump_flag]: 1.86e-06 [switch_simplify]: 1.714e-05 [loop_unroll]: 1.406e-05 [a_1]: 0.00040617 [with_stream_mark]: 1.816e-05 [recompute_prepare]: 1.569e-05 [updatestate_depend_eliminate]: 8.95999e-06 [updatestate_assign_eliminate]: 9.04e-06 [updatestate_loads_eliminate]: 1.198e-05 [parameter_eliminate]: 1.77001e-06 [a_2]: 0.0002207 [accelerated_algorithm]: 2.037e-05 [shard]: 2.05002e-06 [meta_shard_fg_expand]: 3.61999e-06 [shard_inline]: 1.382e-05 [merge_send_recv]: 1.358e-05 [auto_parallel]: 1.324e-05 [parallel]: 7.77e-06 [flash_sp]: 3.8e-06 [merge_comm]: 9.07999e-06 [allreduce_fusion]: 8.28001e-06 [matmul_add_comm_reduction]: 1.464e-05 [allreduce_slice_to_reducescatter]: 3.80009e-07 [virtual_shard_identity]: 2.229e-05 [virtual_dataset]: 1.443e-05 [get_grad_eliminate_]: 1.322e-05 [virtual_output]: 1.335e-05 [merge_forward]: 8.32e-06 [cell_reuse_recompute_pass]: 2.22999e-06 [offload_activation]: 1.549e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.704e-05 [merge_recompute_call_nodes]: 9.80013e-07 [before_grad]: 2.264e-05 [set_forward_comm_id_for_comm_node_pass]: 9.31e-06 [meta_fg_expand]: 5.64e-06 [flash_sp_send_recv_attached]: 1.27999e-06 [receive_attached]: 1.64e-06 [after_resolve]: 2.026e-05 [a_after_grad]: 2.151e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 2.33002e-06 [auto_monad_grad]: 1.30999e-06 [auto_monad_eliminator]: 3.299e-05 [cse]: 4.82e-05 [a_3]: 9.281e-05 [py_interpret_to_execute_after_opt_a]: 2.257e-05 [slice_cell_reuse_recomputed_activation]: 2.24001e-06 [rewriter_after_opt_a]: 0.00017937 [convert_after_rewriter]: 1.485e-05 [order_py_execute_after_rewriter]: 1.432e-05 [mutable_eliminate]: 0.00093429 [opt_b]: 0.00050374, [1] [Cycle 1]: 0.00049489, [7] [b_1]: 0.0003361 [b_2]: 1.844e-05 [updatestate_depend_eliminate]: 1.342e-05 [updatestate_assign_eliminate]: 8.94e-06 [updatestate_loads_eliminate]: 1.278e-05 [renormalize]: 1.05999e-06 [cse]: 6.37e-05 [optimize_parallel_all_gather_comm]: 3.237e-05 [overlap_param_gather]: 2.63e-06 [cconv]: 3.923e-05 [loop_unroll]: 0.00056732 [opt_after_cconv]: 0.00024655, [1] [Cycle 1]: 0.00023867, [7] [c_1]: 0.00010439 [parameter_eliminate]: 3.78001e-06 [updatestate_depend_eliminate]: 1.403e-05 [updatestate_assign_eliminate]: 9.57999e-06 [updatestate_loads_eliminate]: 1.159e-05 [cse]: 5.579e-05 [renormalize]: 7.80012e-07 [remove_dup_value]: 7.664e-05 [tuple_transform]: 0.00014924, [1] [Cycle 1]: 0.00014386, [4] [d_1]: 0.00010287 [none_parameter_eliminate]: 2.27001e-06 [renormalize]: 2.09984e-07 [switch_simplify]: 1.621e-05 [partial_unused_args_eliminate]: 2.05002e-06 [add_recomputation]: 0.00011294 [cse_after_recomputation]: 5.074e-05, [1] [Cycle 1]: 4.483e-05, [1] [cse]: 3.832e-05 [environ_conv]: 1.802e-05 [swap_dp_allreduce_reducescatter]: 1.16e-05 [bias_add_comm_swap]: 3.2e-06 [label_micro_interleaved_index]: 5.79999e-06 [label_fine_grained_interleaved_index]: 2.59001e-06 [merge_cast_opt]: 1.27e-06 [slice_recompute_activation]: 2.39001e-06 [micro_interleaved_order_control]: 2.69999e-06 [assign_add_opt]: 1.50001e-06 [ForceFp32Comm]: 1.29e-06 [remove_cast_before_assign_add]: 1.12e-06 [full_micro_interleaved_order_control]: 2.92002e-06 [reorder_send_recv_between_fp_bp]: 3.08998e-06 [comm_op_add_attrs]: 1.35001e-06 [add_comm_op_reuse_tag]: 1.04003e-06 [interleave_split_concat_branches]: 1.20001e-06 [interleave_parallel_branches]: 1.75001e-06 [overlap_opt_shard_in_pipeline]: 1.41998e-06 [overlap_opt_shard_grad_in_pipeline]: 2.61e-06 [control_data_broadcast_order]: 2.926e-05 [grouped_pairwise_exchange_alltoall]: 1.47999e-06 [offloading_packed_experts]: 8.05e-06 [overlap_recompute_and_grad_model_parallel]: 8.12e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.15001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.30999e-06 [overlap_recompute_comm]: 2.54999e-06 [overlap_grad_ring_attention]: 1.11e-05 [overlap_grad_flash_sp]: 3.884e-05 [begin_end_overlap_inline]: 5.09986e-07 [split_matmul_comm_elemetwise]: 2.13002e-06 [split_layernorm_comm]: 1.87001e-06 [handle_group_info]: 1.79998e-06 [symbol_engine_optimizer]: 0.00016786, [1] [Cycle 1]: 0.00016235, [6] [build]: 1.593e-05 [elim_shapecalc]: 2.726e-05 [elim_not_effective]: 3.118e-05 [opt_reshape]: 2.312e-05 [fold_const_symbol]: 2.542e-05 [renormalize]: 2.00002e-07 [detach_backward]: 2.54001e-06 [pipeline_parallel_scheduler]: 1.69998e-06 [auto_monad_reorder]: 6.2e-05 [get_jit_bprop_graph]: 2.94999e-06 [rewriter_after_jit_bprop_graph]: 7.77998e-06 [opt_after_jit_grad]: 0.00063053 [validate]: 7.423e-05 Sums bootstrap : 0.000593s : 0.29% type_inference : 0.195660s : 95.28% event_method : 0.000013s : 0.01% auto_monad : 0.000221s : 0.11% graph_reusing : 0.000006s : 0.00% inline : 0.000002s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000162s : 0.08% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000019s : 0.01% parallel-infer-symbol : 0.000007s : 0.00% pre_auto_parallel : 0.000063s : 0.03% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000060s : 0.03% optimize.rewriter_before_opt_a : 0.000099s : 0.05% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000055s : 0.03% optimize.opt_a.loop_unroll : 0.000034s : 0.02% optimize.opt_a.a_1 : 0.001172s : 0.57% optimize.opt_a.with_stream_mark : 0.000046s : 0.02% optimize.opt_a.recompute_prepare : 0.000038s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000020s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000019s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000031s : 0.02% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000514s : 0.25% optimize.opt_a.accelerated_algorithm : 0.000072s : 0.04% optimize.opt_a.shard : 0.000004s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000008s : 0.00% optimize.opt_a.shard_inline : 0.000030s : 0.01% optimize.opt_a.merge_send_recv : 0.000036s : 0.02% optimize.opt_a.auto_parallel : 0.000029s : 0.01% optimize.opt_a.parallel : 0.000051s : 0.02% optimize.opt_a.flash_sp : 0.000021s : 0.01% optimize.opt_a.merge_comm : 0.000019s : 0.01% optimize.opt_a.allreduce_fusion : 0.000018s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000036s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000043s : 0.02% optimize.opt_a.virtual_dataset : 0.000030s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000027s : 0.01% optimize.opt_a.virtual_output : 0.000032s : 0.02% optimize.opt_a.merge_forward : 0.000019s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000037s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000059s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000049s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000020s : 0.01% optimize.opt_a.meta_fg_expand : 0.000014s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000049s : 0.02% optimize.opt_a.a_after_grad : 0.000045s : 0.02% optimize.opt_a.renormalize : 0.001389s : 0.68% optimize.opt_a.add_forward_monad_depend : 0.000010s : 0.00% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000086s : 0.04% optimize.opt_a.cse : 0.000139s : 0.07% optimize.opt_a.a_3 : 0.000202s : 0.10% optimize.py_interpret_to_execute_after_opt_a : 0.000023s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000179s : 0.09% optimize.convert_after_rewriter : 0.000015s : 0.01% optimize.order_py_execute_after_rewriter : 0.000014s : 0.01% optimize.mutable_eliminate : 0.000934s : 0.45% optimize.opt_b.b_1 : 0.000336s : 0.16% optimize.opt_b.b_2 : 0.000018s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000013s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000064s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000032s : 0.02% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000039s : 0.02% optimize.loop_unroll : 0.000567s : 0.28% optimize.opt_after_cconv.c_1 : 0.000104s : 0.05% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000014s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000012s : 0.01% optimize.opt_after_cconv.cse : 0.000056s : 0.03% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000077s : 0.04% optimize.tuple_transform.d_1 : 0.000103s : 0.05% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000016s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000113s : 0.05% optimize.cse_after_recomputation.cse : 0.000038s : 0.02% optimize.environ_conv : 0.000018s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000012s : 0.01% 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 : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000002s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000003s : 0.00% optimize.control_data_broadcast_order : 0.000029s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000001s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000011s : 0.01% optimize.overlap_grad_flash_sp : 0.000039s : 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 : 0.000002s : 0.00% optimize.symbol_engine_optimizer.build : 0.000016s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000027s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000031s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000023s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000025s : 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 : 0.000062s : 0.03% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.00% opt_after_jit_grad : 0.000631s : 0.31% validate : 0.000074s : 0.04% Time group info: ------[substitution.] 0.000466 102 21.60% : 0.000101s : 4: substitution.arithmetic_simplify 2.90% : 0.000014s : 2: substitution.depend_value_elim 0.81% : 0.000004s : 8: substitution.elim_not_effective 0.77% : 0.000004s : 8: substitution.fold_const_symbol 2.27% : 0.000011s : 11: substitution.graph_param_transform 32.52% : 0.000152s : 1: substitution.inline 1.88% : 0.000009s : 16: substitution.j_node_and_user_rematch 6.16% : 0.000029s : 4: substitution.less_batch_normalization 1.77% : 0.000008s : 12: substitution.load_eliminater 2.87% : 0.000013s : 16: substitution.remove_not_recompute_node 1.89% : 0.000009s : 6: substitution.replace_old_param 1.95% : 0.000009s : 6: substitution.updatestate_pure_node_eliminater 22.61% : 0.000105s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.195595 2 99.64% : 0.194888s : 1: type_inference.infer 0.36% : 0.000707s : 1: type_inference.specialize ------[replace.] 0.000019 1 100.00% : 0.000019s : 1: replace.inline ------[match.] 0.000150 1 100.00% : 0.000150s : 1: match.inline ------[predicate.] 0.000400 2549 0.89% : 0.000004s : 23: predicate.accumulaten_eliminater 0.99% : 0.000004s : 11: predicate.ad_related_special_op_eliminate 0.75% : 0.000003s : 22: predicate.addn_check_dump 0.89% : 0.000004s : 23: predicate.addn_zero_filter 0.77% : 0.000003s : 23: predicate.adjust_all_reduce_mul_add 2.64% : 0.000011s : 45: predicate.arithmetic_simplify 0.89% : 0.000004s : 23: predicate.cast_eliminate 0.76% : 0.000003s : 22: predicate.check_bprop_eliminate 0.79% : 0.000003s : 22: predicate.compare_switch_simplify 0.22% : 0.000001s : 11: predicate.const_output_eliminate 0.84% : 0.000003s : 22: predicate.depend_value_elim 0.83% : 0.000003s : 23: predicate.dict_get_item_const_eliminator 0.88% : 0.000004s : 23: predicate.dict_get_item_eliminator 0.90% : 0.000004s : 23: predicate.dict_set_item_eliminator 1.01% : 0.000004s : 22: predicate.dumpgradient_eliminate 0.26% : 0.000001s : 11: predicate.elim_not_effective 0.63% : 0.000003s : 11: predicate.elim_shapecalc_of_broadcastargs 1.21% : 0.000005s : 34: predicate.environ_add_const_eliminate 1.16% : 0.000005s : 34: predicate.environ_get_add_eliminate 1.13% : 0.000005s : 34: predicate.environ_get_depend_swap 1.95% : 0.000008s : 56: predicate.environ_get_eliminate 1.08% : 0.000004s : 34: predicate.environ_get_set_eliminate 0.82% : 0.000003s : 24: predicate.exchange_switch_depend_value 1.35% : 0.000005s : 24: predicate.float_depend_g_call 0.77% : 0.000003s : 22: predicate.float_environ_get_switch 1.12% : 0.000004s : 33: predicate.float_tuple_getitem_switch 0.27% : 0.000001s : 11: predicate.fold_const_symbol 0.81% : 0.000003s : 22: predicate.get_grad_eliminate 0.25% : 0.000001s : 11: predicate.graph_param_transform 0.76% : 0.000003s : 22: predicate.incorporate_call 0.72% : 0.000003s : 22: predicate.incorporate_call_switch 5.57% : 0.000022s : 113: predicate.inline 0.98% : 0.000004s : 22: predicate.inline_without_move 0.51% : 0.000002s : 22: predicate.j_node_and_user_rematch 1.15% : 0.000005s : 22: predicate.less_batch_normalization 1.71% : 0.000007s : 45: predicate.list_to_tuple_eliminator_ 2.40% : 0.000010s : 68: predicate.load_eliminater 0.94% : 0.000004s : 11: predicate.loop_unroll_after_grad 1.07% : 0.000004s : 27: predicate.loop_unroll_before_grad 1.78% : 0.000007s : 45: predicate.make_slice_get_slice_eliminator 0.81% : 0.000003s : 22: predicate.merge_addn 0.75% : 0.000003s : 22: predicate.micro_step_allgather_replace 0.85% : 0.000003s : 22: predicate.mini_step_allgather_replace 0.75% : 0.000003s : 23: predicate.minmaximum_grad 1.48% : 0.000006s : 11: predicate.mutable_eliminate 0.47% : 0.000002s : 11: predicate.opt_reshape 0.45% : 0.000002s : 11: predicate.parallel_virtual_node 1.04% : 0.000004s : 24: predicate.partial_defer_inline 1.30% : 0.000005s : 34: predicate.partial_eliminate 0.80% : 0.000003s : 23: predicate.print_const_string_wrapper 0.78% : 0.000003s : 22: predicate.reduce_all_const_elim 1.26% : 0.000005s : 23: predicate.reduce_eliminate 2.42% : 0.000010s : 68: predicate.redundant_stop_gradient_eliminater 0.54% : 0.000002s : 22: predicate.remove_not_recompute_node 1.10% : 0.000004s : 45: predicate.replace_applicator 0.52% : 0.000002s : 22: predicate.replace_old_param 0.27% : 0.000001s : 11: predicate.reset_defer_inline 0.83% : 0.000003s : 23: predicate.reshape_eliminate 0.83% : 0.000003s : 22: predicate.row_tensor_add_zeros_like 0.49% : 0.000002s : 11: predicate.row_tensor_eliminate 0.96% : 0.000004s : 22: predicate.same_eliminate 0.50% : 0.000002s : 22: predicate.set_cell_output_no_recompute 1.05% : 0.000004s : 22: predicate.shard_identity_eliminate 0.98% : 0.000004s : 22: predicate.special_op_eliminate 0.92% : 0.000004s : 22: predicate.specialize_transform 1.19% : 0.000005s : 22: predicate.split_environ_get_set_with_tuple_value 0.98% : 0.000004s : 22: predicate.stack_unstack_eliminate 0.50% : 0.000002s : 11: predicate.switch_call_monad_eliminater 0.89% : 0.000004s : 24: predicate.switch_defer_inline 1.61% : 0.000006s : 46: predicate.switch_layer_defer_inline 3.54% : 0.000014s : 84: predicate.switch_simplify 0.82% : 0.000003s : 23: predicate.tile_eliminate 0.86% : 0.000003s : 23: predicate.transpose_eliminate 1.81% : 0.000007s : 45: predicate.tuple_list_convert_item_index_to_positive 1.70% : 0.000007s : 45: predicate.tuple_list_get_item_const_eliminator 1.53% : 0.000006s : 45: predicate.tuple_list_get_item_depend_reorder 3.23% : 0.000013s : 67: predicate.tuple_list_get_item_eliminator 1.69% : 0.000007s : 45: predicate.tuple_list_get_set_item_eliminator 2.62% : 0.000010s : 67: predicate.tuple_list_set_item_eliminator 1.56% : 0.000006s : 45: predicate.tuple_to_list_eliminator_ 2.38% : 0.000010s : 68: predicate.updatestate_pure_node_eliminater 3.48% : 0.000014s : 90: predicate.updatestate_useless_node_eliminater 0.43% : 0.000002s : 11: predicate.value_based_eliminate 0.79% : 0.000003s : 22: predicate.virtual_dataset_eliminate 0.80% : 0.000003s : 22: predicate.virtual_output_eliminate 0.44% : 0.000002s : 11: predicate.virtual_view_grad_eliminate 0.49% : 0.000002s : 11: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000423 4 6.15% : 0.000026s : 1: func_graph_cloner_run.FuncGraphClonerGraph 93.85% : 0.000397s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.296741 192 0.00% : 0.000004s : 1: ForceFp32Comm 13.03% : 0.038672s : 1: add_attr 13.02% : 0.038645s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.04% : 0.000118s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.08% : 0.000228s : 1: auto_monad 0.02% : 0.000067s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.21% : 0.000631s : 1: bootstrap 0.01% : 0.000043s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000033s : 1: control_data_broadcast_order 0.01% : 0.000019s : 1: convert_after_rewriter 0.02% : 0.000054s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000022s : 1: environ_conv 0.01% : 0.000020s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000005s : 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 0.19% : 0.000577s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.32% : 0.000944s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.01% : 0.000028s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000035s : 1: opt.transform.mutable_eliminate 0.79% : 0.002343s : 78: opt.transform.opt_a 0.03% : 0.000103s : 1: opt.transform.opt_after_cconv 0.02% : 0.000061s : 1: opt.transform.opt_after_jit_grad 0.11% : 0.000322s : 28: opt.transform.opt_b 0.04% : 0.000116s : 2: opt.transform.opt_trans_graph 0.03% : 0.000102s : 4: opt.transform.symbol_engine_opt 1.71% : 0.005083s : 1: opt_a 0.08% : 0.000250s : 1: opt_after_cconv 0.22% : 0.000641s : 1: opt_after_jit_grad 0.17% : 0.000508s : 1: opt_b 2.96% : 0.008794s : 1: optimize 0.01% : 0.000036s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000018s : 1: order_py_execute_after_rewriter 0.01% : 0.000042s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000015s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000012s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000069s : 1: pre_auto_parallel 0.02% : 0.000064s : 1: py_interpret_to_execute 0.01% : 0.000026s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.03% : 0.000081s : 1: remove_dup_value 0.26% : 0.000771s : 1: renormalize.infer 0.20% : 0.000605s : 1: renormalize.specialize 0.00% : 0.000010s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.06% : 0.000185s : 1: rewriter_after_opt_a 0.04% : 0.000104s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.06% : 0.000171s : 1: symbol_engine_optimizer 0.05% : 0.000152s : 1: tuple_transform 65.94% : 0.195680s : 1: type_inference . [hook] pytest_runtest_teardown:test_qbmm_add[False-True-input_shape0] tests/st/infer/ops/test_internal_ops/test_quant_bmm.py::test_qbmm_add[False-True-input_shape0],max_mem:24.0M [WARNING] ME(169497:281473358380848,MainProcess):2026-01-29-17:38:27.757.340 [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 = 0.165788, [21] [bootstrap]: 0.00064231 [type_inference]: 0.149586 [event_method]: 2.006e-05 [auto_monad]: 0.00026842 [graph_reusing]: 7.03998e-06 [inline]: 2.81e-06 [add_attr]: 0.00584734, [1] [add_attr_with_inline]: 0.00583033, [1] [Cycle 1]: 7.57e-05, [2] [tag_attr]: 2.347e-05 [meta_addattr_fg_expand]: 4.63999e-06 [parallel-infer-symbol]: 3.92002e-06 [pre_auto_parallel]: 3.965e-05 [insert-virtual-dataset]: 2.79999e-06 [parallel-infer-symbol-second]: 8.60018e-07 [dataset_repeat_opt]: 2.29999e-06 [pipeline_split]: 2.02999e-06 [optimize]: 0.00836563, [53] [py_interpret_to_execute]: 4.243e-05 [rewriter_before_opt_a]: 8.655e-05 [opt_a]: 0.00493387, [2] [Cycle 1]: 0.00336892, [45] [expand_dump_flag]: 3.09999e-06 [switch_simplify]: 3.492e-05 [loop_unroll]: 2.073e-05 [a_1]: 0.00075034 [with_stream_mark]: 2.735e-05 [recompute_prepare]: 1.945e-05 [updatestate_depend_eliminate]: 1.087e-05 [updatestate_assign_eliminate]: 1.337e-05 [updatestate_loads_eliminate]: 1.624e-05 [parameter_eliminate]: 2.39999e-06 [a_2]: 0.00026167 [accelerated_algorithm]: 4.38e-05 [shard]: 2.19999e-06 [meta_shard_fg_expand]: 4.52998e-06 [shard_inline]: 1.602e-05 [merge_send_recv]: 1.625e-05 [auto_parallel]: 1.681e-05 [parallel]: 3.83e-05 [flash_sp]: 1.259e-05 [merge_comm]: 9.79999e-06 [allreduce_fusion]: 9.62999e-06 [matmul_add_comm_reduction]: 2.03e-05 [allreduce_slice_to_reducescatter]: 6.39993e-07 [virtual_shard_identity]: 2.005e-05 [virtual_dataset]: 1.629e-05 [get_grad_eliminate_]: 1.539e-05 [virtual_output]: 1.617e-05 [merge_forward]: 9.98002e-06 [cell_reuse_recompute_pass]: 2.54001e-06 [offload_activation]: 1.986e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.133e-05 [merge_recompute_call_nodes]: 1.54e-06 [before_grad]: 2.806e-05 [set_forward_comm_id_for_comm_node_pass]: 1.073e-05 [meta_fg_expand]: 6.54999e-06 [flash_sp_send_recv_attached]: 5.23002e-06 [receive_attached]: 2.56e-06 [after_resolve]: 2.663e-05 [a_after_grad]: 2.734e-05 [renormalize]: 0.00120254 [add_forward_monad_depend]: 7.47002e-06 [auto_monad_grad]: 2.43e-06 [auto_monad_eliminator]: 4.716e-05 [cse]: 9.16e-05 [a_3]: 0.00011165 [Cycle 2]: 0.0015512, [45] [expand_dump_flag]: 3.06001e-06 [switch_simplify]: 1.85e-05 [loop_unroll]: 1.415e-05 [a_1]: 0.00040677 [with_stream_mark]: 1.934e-05 [recompute_prepare]: 1.464e-05 [updatestate_depend_eliminate]: 9.79e-06 [updatestate_assign_eliminate]: 1.041e-05 [updatestate_loads_eliminate]: 1.385e-05 [parameter_eliminate]: 1.99999e-06 [a_2]: 0.00021678 [accelerated_algorithm]: 2.131e-05 [shard]: 2.39999e-06 [meta_shard_fg_expand]: 3.98001e-06 [shard_inline]: 1.44e-05 [merge_send_recv]: 1.961e-05 [auto_parallel]: 1.542e-05 [parallel]: 7.95e-06 [flash_sp]: 3.7e-06 [merge_comm]: 8.68001e-06 [allreduce_fusion]: 2.431e-05 [matmul_add_comm_reduction]: 1.629e-05 [allreduce_slice_to_reducescatter]: 7.00005e-07 [virtual_shard_identity]: 1.837e-05 [virtual_dataset]: 1.384e-05 [get_grad_eliminate_]: 1.397e-05 [virtual_output]: 1.439e-05 [merge_forward]: 1.006e-05 [cell_reuse_recompute_pass]: 2.51e-06 [offload_activation]: 2.031e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.823e-05 [merge_recompute_call_nodes]: 1.67999e-06 [before_grad]: 2.312e-05 [set_forward_comm_id_for_comm_node_pass]: 1.251e-05 [meta_fg_expand]: 6.23002e-06 [flash_sp_send_recv_attached]: 1.50999e-06 [receive_attached]: 2.76999e-06 [after_resolve]: 2.161e-05 [a_after_grad]: 2.097e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 3.48999e-06 [auto_monad_grad]: 2.32001e-06 [auto_monad_eliminator]: 3.784e-05 [cse]: 8.525e-05 [a_3]: 9.671e-05 [py_interpret_to_execute_after_opt_a]: 2.251e-05 [slice_cell_reuse_recomputed_activation]: 2.07999e-06 [rewriter_after_opt_a]: 0.00020227 [convert_after_rewriter]: 1.426e-05 [order_py_execute_after_rewriter]: 1.004e-05 [mutable_eliminate]: 0.00076146 [opt_b]: 0.00051976, [1] [Cycle 1]: 0.00051119, [7] [b_1]: 0.00035022 [b_2]: 1.78e-05 [updatestate_depend_eliminate]: 1.359e-05 [updatestate_assign_eliminate]: 9.57001e-06 [updatestate_loads_eliminate]: 1.361e-05 [renormalize]: 9.00007e-07 [cse]: 6.399e-05 [optimize_parallel_all_gather_comm]: 3.191e-05 [overlap_param_gather]: 2.01e-06 [cconv]: 4.032e-05 [loop_unroll]: 0.0005244 [opt_after_cconv]: 0.00023785, [1] [Cycle 1]: 0.00023069, [7] [c_1]: 0.00010073 [parameter_eliminate]: 4.15999e-06 [updatestate_depend_eliminate]: 1.183e-05 [updatestate_assign_eliminate]: 9.27001e-06 [updatestate_loads_eliminate]: 1.102e-05 [cse]: 5.389e-05 [renormalize]: 6.69999e-07 [remove_dup_value]: 6.852e-05 [tuple_transform]: 0.00014635, [1] [Cycle 1]: 0.00014101, [4] [d_1]: 0.00010479 [none_parameter_eliminate]: 1.66e-06 [renormalize]: 1.80007e-07 [switch_simplify]: 1.542e-05 [partial_unused_args_eliminate]: 2.30002e-06 [add_recomputation]: 0.00010174 [cse_after_recomputation]: 4.677e-05, [1] [Cycle 1]: 4.151e-05, [1] [cse]: 3.531e-05 [environ_conv]: 1.361e-05 [swap_dp_allreduce_reducescatter]: 1.086e-05 [bias_add_comm_swap]: 3.02002e-06 [label_micro_interleaved_index]: 5.22e-06 [label_fine_grained_interleaved_index]: 3.04999e-06 [merge_cast_opt]: 1.40999e-06 [slice_recompute_activation]: 2.31e-06 [micro_interleaved_order_control]: 2.50002e-06 [assign_add_opt]: 1.51998e-06 [ForceFp32Comm]: 1.40001e-06 [remove_cast_before_assign_add]: 1.10001e-06 [full_micro_interleaved_order_control]: 2.11e-06 [reorder_send_recv_between_fp_bp]: 3.44001e-06 [comm_op_add_attrs]: 1.05001e-06 [add_comm_op_reuse_tag]: 9.99979e-07 [interleave_split_concat_branches]: 1.17999e-06 [interleave_parallel_branches]: 1.17e-06 [overlap_opt_shard_in_pipeline]: 1.32e-06 [overlap_opt_shard_grad_in_pipeline]: 1.99999e-06 [control_data_broadcast_order]: 2.902e-05 [grouped_pairwise_exchange_alltoall]: 1.62001e-06 [offloading_packed_experts]: 7.91001e-06 [overlap_recompute_and_grad_model_parallel]: 7.89002e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.54e-06 [overlap_recompute_allgather_and_fa_grad]: 1.22e-06 [overlap_recompute_comm]: 2.87002e-06 [overlap_grad_ring_attention]: 7.73001e-06 [overlap_grad_flash_sp]: 4.191e-05 [begin_end_overlap_inline]: 5.09986e-07 [split_matmul_comm_elemetwise]: 1.87999e-06 [split_layernorm_comm]: 2.00002e-06 [handle_group_info]: 1.35001e-06 [symbol_engine_optimizer]: 0.00014308, [1] [Cycle 1]: 0.00013797, [6] [build]: 1.494e-05 [elim_shapecalc]: 2.182e-05 [elim_not_effective]: 2.762e-05 [opt_reshape]: 1.67e-05 [fold_const_symbol]: 2.282e-05 [renormalize]: 2.3999e-07 [detach_backward]: 2.72001e-06 [pipeline_parallel_scheduler]: 1.47001e-06 [auto_monad_reorder]: 5.529e-05 [get_jit_bprop_graph]: 2.34001e-06 [rewriter_after_jit_bprop_graph]: 4.32e-06 [opt_after_jit_grad]: 0.00065727 [validate]: 7.155e-05 Sums bootstrap : 0.000642s : 0.40% type_inference : 0.149586s : 94.22% event_method : 0.000020s : 0.01% auto_monad : 0.000268s : 0.17% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000023s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000040s : 0.02% 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 : 0.000042s : 0.03% optimize.rewriter_before_opt_a : 0.000087s : 0.05% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000053s : 0.03% optimize.opt_a.loop_unroll : 0.000035s : 0.02% optimize.opt_a.a_1 : 0.001157s : 0.73% optimize.opt_a.with_stream_mark : 0.000047s : 0.03% optimize.opt_a.recompute_prepare : 0.000034s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000024s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000030s : 0.02% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000478s : 0.30% optimize.opt_a.accelerated_algorithm : 0.000065s : 0.04% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.01% optimize.opt_a.shard_inline : 0.000030s : 0.02% optimize.opt_a.merge_send_recv : 0.000036s : 0.02% optimize.opt_a.auto_parallel : 0.000032s : 0.02% optimize.opt_a.parallel : 0.000046s : 0.03% optimize.opt_a.flash_sp : 0.000016s : 0.01% optimize.opt_a.merge_comm : 0.000018s : 0.01% optimize.opt_a.allreduce_fusion : 0.000034s : 0.02% optimize.opt_a.matmul_add_comm_reduction : 0.000037s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000038s : 0.02% optimize.opt_a.virtual_dataset : 0.000030s : 0.02% optimize.opt_a.get_grad_eliminate_ : 0.000029s : 0.02% optimize.opt_a.virtual_output : 0.000031s : 0.02% optimize.opt_a.merge_forward : 0.000020s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000040s : 0.03% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000060s : 0.04% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000051s : 0.03% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000023s : 0.01% optimize.opt_a.meta_fg_expand : 0.000013s : 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 : 0.000048s : 0.03% optimize.opt_a.a_after_grad : 0.000048s : 0.03% optimize.opt_a.renormalize : 0.001203s : 0.76% optimize.opt_a.add_forward_monad_depend : 0.000011s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000085s : 0.05% optimize.opt_a.cse : 0.000177s : 0.11% optimize.opt_a.a_3 : 0.000208s : 0.13% optimize.py_interpret_to_execute_after_opt_a : 0.000023s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000202s : 0.13% optimize.convert_after_rewriter : 0.000014s : 0.01% optimize.order_py_execute_after_rewriter : 0.000010s : 0.01% optimize.mutable_eliminate : 0.000761s : 0.48% optimize.opt_b.b_1 : 0.000350s : 0.22% optimize.opt_b.b_2 : 0.000018s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000010s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000014s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000064s : 0.04% optimize.optimize_parallel_all_gather_comm : 0.000032s : 0.02% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000040s : 0.03% optimize.loop_unroll : 0.000524s : 0.33% optimize.opt_after_cconv.c_1 : 0.000101s : 0.06% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000009s : 0.01% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000011s : 0.01% optimize.opt_after_cconv.cse : 0.000054s : 0.03% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000069s : 0.04% optimize.tuple_transform.d_1 : 0.000105s : 0.07% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000015s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000102s : 0.06% optimize.cse_after_recomputation.cse : 0.000035s : 0.02% optimize.environ_conv : 0.000014s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 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 : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000029s : 0.02% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 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 : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000042s : 0.03% 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 : 0.000015s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000022s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000028s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000017s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000023s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000055s : 0.03% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000004s : 0.00% opt_after_jit_grad : 0.000657s : 0.41% validate : 0.000072s : 0.05% Time group info: ------[substitution.] 0.000425 102 22.14% : 0.000094s : 4: substitution.arithmetic_simplify 2.55% : 0.000011s : 2: substitution.depend_value_elim 0.96% : 0.000004s : 8: substitution.elim_not_effective 0.74% : 0.000003s : 8: substitution.fold_const_symbol 2.44% : 0.000010s : 11: substitution.graph_param_transform 31.39% : 0.000133s : 1: substitution.inline 2.15% : 0.000009s : 16: substitution.j_node_and_user_rematch 6.21% : 0.000026s : 4: substitution.less_batch_normalization 1.85% : 0.000008s : 12: substitution.load_eliminater 3.17% : 0.000013s : 16: substitution.remove_not_recompute_node 1.69% : 0.000007s : 6: substitution.replace_old_param 2.27% : 0.000010s : 6: substitution.updatestate_pure_node_eliminater 22.44% : 0.000095s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.149500 2 99.34% : 0.148510s : 1: type_inference.infer 0.66% : 0.000990s : 1: type_inference.specialize ------[replace.] 0.000023 1 100.00% : 0.000023s : 1: replace.inline ------[match.] 0.000132 1 100.00% : 0.000132s : 1: match.inline ------[predicate.] 0.000387 2549 0.84% : 0.000003s : 23: predicate.accumulaten_eliminater 0.81% : 0.000003s : 11: predicate.ad_related_special_op_eliminate 0.75% : 0.000003s : 22: predicate.addn_check_dump 1.04% : 0.000004s : 23: predicate.addn_zero_filter 0.74% : 0.000003s : 23: predicate.adjust_all_reduce_mul_add 2.41% : 0.000009s : 45: predicate.arithmetic_simplify 0.81% : 0.000003s : 23: predicate.cast_eliminate 0.83% : 0.000003s : 22: predicate.check_bprop_eliminate 0.73% : 0.000003s : 22: predicate.compare_switch_simplify 0.22% : 0.000001s : 11: predicate.const_output_eliminate 0.89% : 0.000003s : 22: predicate.depend_value_elim 0.82% : 0.000003s : 23: predicate.dict_get_item_const_eliminator 0.90% : 0.000003s : 23: predicate.dict_get_item_eliminator 0.79% : 0.000003s : 23: predicate.dict_set_item_eliminator 1.06% : 0.000004s : 22: predicate.dumpgradient_eliminate 0.26% : 0.000001s : 11: predicate.elim_not_effective 0.47% : 0.000002s : 11: predicate.elim_shapecalc_of_broadcastargs 1.14% : 0.000004s : 34: predicate.environ_add_const_eliminate 1.10% : 0.000004s : 34: predicate.environ_get_add_eliminate 1.11% : 0.000004s : 34: predicate.environ_get_depend_swap 2.04% : 0.000008s : 56: predicate.environ_get_eliminate 1.12% : 0.000004s : 34: predicate.environ_get_set_eliminate 0.83% : 0.000003s : 24: predicate.exchange_switch_depend_value 1.38% : 0.000005s : 24: predicate.float_depend_g_call 0.74% : 0.000003s : 22: predicate.float_environ_get_switch 1.18% : 0.000005s : 33: predicate.float_tuple_getitem_switch 0.22% : 0.000001s : 11: predicate.fold_const_symbol 1.00% : 0.000004s : 22: predicate.get_grad_eliminate 0.32% : 0.000001s : 11: predicate.graph_param_transform 0.82% : 0.000003s : 22: predicate.incorporate_call 0.74% : 0.000003s : 22: predicate.incorporate_call_switch 5.47% : 0.000021s : 113: predicate.inline 0.94% : 0.000004s : 22: predicate.inline_without_move 0.42% : 0.000002s : 22: predicate.j_node_and_user_rematch 1.24% : 0.000005s : 22: predicate.less_batch_normalization 1.65% : 0.000006s : 45: predicate.list_to_tuple_eliminator_ 2.43% : 0.000009s : 68: predicate.load_eliminater 1.10% : 0.000004s : 11: predicate.loop_unroll_after_grad 1.18% : 0.000005s : 27: predicate.loop_unroll_before_grad 1.84% : 0.000007s : 45: predicate.make_slice_get_slice_eliminator 0.76% : 0.000003s : 22: predicate.merge_addn 0.76% : 0.000003s : 22: predicate.micro_step_allgather_replace 0.76% : 0.000003s : 22: predicate.mini_step_allgather_replace 0.71% : 0.000003s : 23: predicate.minmaximum_grad 1.27% : 0.000005s : 11: predicate.mutable_eliminate 0.52% : 0.000002s : 11: predicate.opt_reshape 0.46% : 0.000002s : 11: predicate.parallel_virtual_node 1.05% : 0.000004s : 24: predicate.partial_defer_inline 1.27% : 0.000005s : 34: predicate.partial_eliminate 0.78% : 0.000003s : 23: predicate.print_const_string_wrapper 0.87% : 0.000003s : 22: predicate.reduce_all_const_elim 1.10% : 0.000004s : 23: predicate.reduce_eliminate 2.36% : 0.000009s : 68: predicate.redundant_stop_gradient_eliminater 0.58% : 0.000002s : 22: predicate.remove_not_recompute_node 1.18% : 0.000005s : 45: predicate.replace_applicator 0.58% : 0.000002s : 22: predicate.replace_old_param 0.31% : 0.000001s : 11: predicate.reset_defer_inline 0.78% : 0.000003s : 23: predicate.reshape_eliminate 0.80% : 0.000003s : 22: predicate.row_tensor_add_zeros_like 0.55% : 0.000002s : 11: predicate.row_tensor_eliminate 1.03% : 0.000004s : 22: predicate.same_eliminate 0.55% : 0.000002s : 22: predicate.set_cell_output_no_recompute 1.08% : 0.000004s : 22: predicate.shard_identity_eliminate 0.91% : 0.000004s : 22: predicate.special_op_eliminate 1.01% : 0.000004s : 22: predicate.specialize_transform 1.23% : 0.000005s : 22: predicate.split_environ_get_set_with_tuple_value 1.03% : 0.000004s : 22: predicate.stack_unstack_eliminate 0.50% : 0.000002s : 11: predicate.switch_call_monad_eliminater 0.94% : 0.000004s : 24: predicate.switch_defer_inline 1.61% : 0.000006s : 46: predicate.switch_layer_defer_inline 3.55% : 0.000014s : 84: predicate.switch_simplify 0.82% : 0.000003s : 23: predicate.tile_eliminate 0.80% : 0.000003s : 23: predicate.transpose_eliminate 1.59% : 0.000006s : 45: predicate.tuple_list_convert_item_index_to_positive 1.73% : 0.000007s : 45: predicate.tuple_list_get_item_const_eliminator 1.57% : 0.000006s : 45: predicate.tuple_list_get_item_depend_reorder 2.95% : 0.000011s : 67: predicate.tuple_list_get_item_eliminator 1.60% : 0.000006s : 45: predicate.tuple_list_get_set_item_eliminator 2.66% : 0.000010s : 67: predicate.tuple_list_set_item_eliminator 1.61% : 0.000006s : 45: predicate.tuple_to_list_eliminator_ 2.33% : 0.000009s : 68: predicate.updatestate_pure_node_eliminater 3.34% : 0.000013s : 90: predicate.updatestate_useless_node_eliminater 0.95% : 0.000004s : 11: predicate.value_based_eliminate 0.93% : 0.000004s : 22: predicate.virtual_dataset_eliminate 0.89% : 0.000003s : 22: predicate.virtual_output_eliminate 0.42% : 0.000002s : 11: predicate.virtual_view_grad_eliminate 0.48% : 0.000002s : 11: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000551 4 4.32% : 0.000024s : 1: func_graph_cloner_run.FuncGraphClonerGraph 95.68% : 0.000528s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.184043 192 0.00% : 0.000004s : 1: ForceFp32Comm 3.18% : 0.005854s : 1: add_attr 3.17% : 0.005836s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.06% : 0.000106s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.15% : 0.000277s : 1: auto_monad 0.03% : 0.000061s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.37% : 0.000678s : 1: bootstrap 0.02% : 0.000045s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.02% : 0.000032s : 1: control_data_broadcast_order 0.01% : 0.000018s : 1: convert_after_rewriter 0.03% : 0.000050s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000017s : 1: environ_conv 0.01% : 0.000027s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.01% : 0.000012s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000009s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.29% : 0.000534s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.42% : 0.000772s : 1: mutable_eliminate 0.01% : 0.000011s : 1: offloading_packed_experts 0.01% : 0.000027s : 1: opt.transform.loop_unroll_optimizer 0.02% : 0.000032s : 1: opt.transform.mutable_eliminate 1.24% : 0.002288s : 78: opt.transform.opt_a 0.05% : 0.000099s : 1: opt.transform.opt_after_cconv 0.03% : 0.000054s : 1: opt.transform.opt_after_jit_grad 0.18% : 0.000334s : 28: opt.transform.opt_b 0.06% : 0.000118s : 2: opt.transform.opt_trans_graph 0.05% : 0.000085s : 4: opt.transform.symbol_engine_opt 2.68% : 0.004938s : 1: opt_a 0.13% : 0.000242s : 1: opt_after_cconv 0.36% : 0.000669s : 1: opt_after_jit_grad 0.28% : 0.000524s : 1: opt_b 4.55% : 0.008372s : 1: optimize 0.02% : 0.000036s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000013s : 1: order_py_execute_after_rewriter 0.02% : 0.000046s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.01% : 0.000014s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000044s : 1: pre_auto_parallel 0.03% : 0.000047s : 1: py_interpret_to_execute 0.01% : 0.000026s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.04% : 0.000073s : 1: remove_dup_value 0.36% : 0.000657s : 1: renormalize.infer 0.29% : 0.000534s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.11% : 0.000209s : 1: rewriter_after_opt_a 0.05% : 0.000091s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.01% : 0.000014s : 1: swap_dp_allreduce_reducescatter 0.08% : 0.000146s : 1: symbol_engine_optimizer 0.08% : 0.000149s : 1: tuple_transform 81.29% : 0.149614s : 1: type_inference . [hook] pytest_runtest_teardown:test_qbmm_add[False-True-input_shape1] tests/st/infer/ops/test_internal_ops/test_quant_bmm.py::test_qbmm_add[False-True-input_shape1],max_mem:24.0M [WARNING] ME(169497:281473358380848,MainProcess):2026-01-29-17:38:34.613.925 [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 = 0.213823, [21] [bootstrap]: 0.00053502 [type_inference]: 0.00734132 [event_method]: 1.684e-05 [auto_monad]: 0.00024138 [graph_reusing]: 5.18002e-06 [inline]: 2.43e-06 [add_attr]: 0.00530933, [1] [add_attr_with_inline]: 0.00529141, [1] [Cycle 1]: 7.347e-05, [2] [tag_attr]: 2.374e-05 [meta_addattr_fg_expand]: 4.3e-06 [parallel-infer-symbol]: 3.71001e-06 [pre_auto_parallel]: 4.833e-05 [insert-virtual-dataset]: 9.79e-06 [parallel-infer-symbol-second]: 8.29983e-07 [dataset_repeat_opt]: 2.05002e-06 [pipeline_split]: 1.77001e-06 [optimize]: 0.199377, [53] [py_interpret_to_execute]: 3.567e-05 [rewriter_before_opt_a]: 7.62e-05 [opt_a]: 0.195667, [2] [Cycle 1]: 0.194124, [45] [expand_dump_flag]: 2.99999e-06 [switch_simplify]: 3.399e-05 [loop_unroll]: 2.01e-05 [a_1]: 0.00067779 [with_stream_mark]: 2.949e-05 [recompute_prepare]: 1.955e-05 [updatestate_depend_eliminate]: 0.190537 [updatestate_assign_eliminate]: 2.732e-05 [updatestate_loads_eliminate]: 1.802e-05 [parameter_eliminate]: 7.78999e-06 [a_2]: 0.00036352 [accelerated_algorithm]: 5.509e-05 [shard]: 3.68e-06 [meta_shard_fg_expand]: 7.53999e-06 [shard_inline]: 1.543e-05 [merge_send_recv]: 1.901e-05 [auto_parallel]: 2.112e-05 [parallel]: 3.52e-05 [flash_sp]: 1.443e-05 [merge_comm]: 1.201e-05 [allreduce_fusion]: 1.124e-05 [matmul_add_comm_reduction]: 2.537e-05 [allreduce_slice_to_reducescatter]: 1.52001e-06 [virtual_shard_identity]: 1.93e-05 [virtual_dataset]: 1.519e-05 [get_grad_eliminate_]: 1.812e-05 [virtual_output]: 1.805e-05 [merge_forward]: 1.183e-05 [cell_reuse_recompute_pass]: 3.18998e-06 [offload_activation]: 2.236e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.972e-05 [merge_recompute_call_nodes]: 1.45999e-06 [before_grad]: 2.83e-05 [set_forward_comm_id_for_comm_node_pass]: 1.178e-05 [meta_fg_expand]: 6.40002e-06 [flash_sp_send_recv_attached]: 4.98001e-06 [receive_attached]: 2.39001e-06 [after_resolve]: 2.568e-05 [a_after_grad]: 2.356e-05 [renormalize]: 0.00130613 [add_forward_monad_depend]: 8.25999e-06 [auto_monad_grad]: 2.34999e-06 [auto_monad_eliminator]: 5.045e-05 [cse]: 9.265e-05 [a_3]: 0.00011212 [Cycle 2]: 0.00152923, [45] [expand_dump_flag]: 2.21e-06 [switch_simplify]: 1.753e-05 [loop_unroll]: 1.482e-05 [a_1]: 0.0004201 [with_stream_mark]: 2.35e-05 [recompute_prepare]: 1.56e-05 [updatestate_depend_eliminate]: 9.43997e-06 [updatestate_assign_eliminate]: 8.92e-06 [updatestate_loads_eliminate]: 1.231e-05 [parameter_eliminate]: 1.35999e-06 [a_2]: 0.00024863 [accelerated_algorithm]: 2.15e-05 [shard]: 1.51002e-06 [meta_shard_fg_expand]: 3.85998e-06 [shard_inline]: 1.886e-05 [merge_send_recv]: 1.33e-05 [auto_parallel]: 1.525e-05 [parallel]: 6.69999e-06 [flash_sp]: 5.44e-06 [merge_comm]: 9.41e-06 [allreduce_fusion]: 8.05999e-06 [matmul_add_comm_reduction]: 1.529e-05 [allreduce_slice_to_reducescatter]: 5.19998e-07 [virtual_shard_identity]: 1.678e-05 [virtual_dataset]: 1.502e-05 [get_grad_eliminate_]: 1.392e-05 [virtual_output]: 1.674e-05 [merge_forward]: 8.20999e-06 [cell_reuse_recompute_pass]: 2.59999e-06 [offload_activation]: 1.638e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.735e-05 [merge_recompute_call_nodes]: 1.01002e-06 [before_grad]: 2.349e-05 [set_forward_comm_id_for_comm_node_pass]: 9.46e-06 [meta_fg_expand]: 6.55002e-06 [flash_sp_send_recv_attached]: 1.67001e-06 [receive_attached]: 1.66e-06 [after_resolve]: 2.172e-05 [a_after_grad]: 2.217e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 2.51e-06 [auto_monad_grad]: 1.35999e-06 [auto_monad_eliminator]: 4.084e-05 [cse]: 6.322e-05 [a_3]: 9.804e-05 [py_interpret_to_execute_after_opt_a]: 2.497e-05 [slice_cell_reuse_recomputed_activation]: 1.92999e-06 [rewriter_after_opt_a]: 0.0001952 [convert_after_rewriter]: 1.678e-05 [order_py_execute_after_rewriter]: 1.024e-05 [mutable_eliminate]: 0.00077979 [opt_b]: 0.00053104, [1] [Cycle 1]: 0.00052092, [7] [b_1]: 0.0003509 [b_2]: 2.021e-05 [updatestate_depend_eliminate]: 1.346e-05 [updatestate_assign_eliminate]: 9.10999e-06 [updatestate_loads_eliminate]: 1.24e-05 [renormalize]: 6.09987e-07 [cse]: 7.47e-05 [optimize_parallel_all_gather_comm]: 3.287e-05 [overlap_param_gather]: 2.26e-06 [cconv]: 3.618e-05 [loop_unroll]: 0.0005395 [opt_after_cconv]: 0.00024334, [1] [Cycle 1]: 0.00023611, [7] [c_1]: 0.00010122 [parameter_eliminate]: 4.58999e-06 [updatestate_depend_eliminate]: 1.275e-05 [updatestate_assign_eliminate]: 8.23001e-06 [updatestate_loads_eliminate]: 1.069e-05 [cse]: 6.082e-05 [renormalize]: 4.50003e-07 [remove_dup_value]: 7.548e-05 [tuple_transform]: 0.0001447, [1] [Cycle 1]: 0.00013877, [4] [d_1]: 0.00010244 [none_parameter_eliminate]: 2.27001e-06 [renormalize]: 1.8999e-07 [switch_simplify]: 1.528e-05 [partial_unused_args_eliminate]: 2.40002e-06 [add_recomputation]: 0.00010252 [cse_after_recomputation]: 4.719e-05, [1] [Cycle 1]: 4.226e-05, [1] [cse]: 3.614e-05 [environ_conv]: 1.428e-05 [swap_dp_allreduce_reducescatter]: 1.085e-05 [bias_add_comm_swap]: 2.66e-06 [label_micro_interleaved_index]: 5.20001e-06 [label_fine_grained_interleaved_index]: 2.91999e-06 [merge_cast_opt]: 1.47999e-06 [slice_recompute_activation]: 2.42001e-06 [micro_interleaved_order_control]: 2.71e-06 [assign_add_opt]: 1.18001e-06 [ForceFp32Comm]: 9.20001e-07 [remove_cast_before_assign_add]: 1.39e-06 [full_micro_interleaved_order_control]: 2.36998e-06 [reorder_send_recv_between_fp_bp]: 2.83e-06 [comm_op_add_attrs]: 1.25999e-06 [add_comm_op_reuse_tag]: 9.99979e-07 [interleave_split_concat_branches]: 1.12e-06 [interleave_parallel_branches]: 1.10999e-06 [overlap_opt_shard_in_pipeline]: 1.27e-06 [overlap_opt_shard_grad_in_pipeline]: 1.82999e-06 [control_data_broadcast_order]: 2.667e-05 [grouped_pairwise_exchange_alltoall]: 1.32999e-06 [offloading_packed_experts]: 1.096e-05 [overlap_recompute_and_grad_model_parallel]: 7.85998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.28002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.25999e-06 [overlap_recompute_comm]: 2.21998e-06 [overlap_grad_ring_attention]: 7.62002e-06 [overlap_grad_flash_sp]: 4.115e-05 [begin_end_overlap_inline]: 7.09988e-07 [split_matmul_comm_elemetwise]: 2.24001e-06 [split_layernorm_comm]: 1.94e-06 [handle_group_info]: 1.27e-06 [symbol_engine_optimizer]: 0.00037661, [1] [Cycle 1]: 0.00036836, [6] [build]: 0.00019745 [elim_shapecalc]: 2.871e-05 [elim_not_effective]: 4.394e-05 [opt_reshape]: 1.757e-05 [fold_const_symbol]: 3.45e-05 [renormalize]: 2.10013e-07 [detach_backward]: 5.07e-06 [pipeline_parallel_scheduler]: 1.55001e-06 [auto_monad_reorder]: 5.935e-05 [get_jit_bprop_graph]: 2.12999e-06 [rewriter_after_jit_bprop_graph]: 5.63997e-06 [opt_after_jit_grad]: 0.0006009 [validate]: 6.764e-05 Sums bootstrap : 0.000535s : 0.26% type_inference : 0.007341s : 3.54% event_method : 0.000017s : 0.01% auto_monad : 0.000241s : 0.12% graph_reusing : 0.000005s : 0.00% inline : 0.000002s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000024s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000048s : 0.02% insert-virtual-dataset : 0.000010s : 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 : 0.000036s : 0.02% optimize.rewriter_before_opt_a : 0.000076s : 0.04% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000052s : 0.02% optimize.opt_a.loop_unroll : 0.000035s : 0.02% optimize.opt_a.a_1 : 0.001098s : 0.53% optimize.opt_a.with_stream_mark : 0.000053s : 0.03% optimize.opt_a.recompute_prepare : 0.000035s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.190547s : 91.91% optimize.opt_a.updatestate_assign_eliminate : 0.000036s : 0.02% optimize.opt_a.updatestate_loads_eliminate : 0.000030s : 0.01% optimize.opt_a.parameter_eliminate : 0.000009s : 0.00% optimize.opt_a.a_2 : 0.000612s : 0.30% optimize.opt_a.accelerated_algorithm : 0.000077s : 0.04% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000011s : 0.01% optimize.opt_a.shard_inline : 0.000034s : 0.02% optimize.opt_a.merge_send_recv : 0.000032s : 0.02% optimize.opt_a.auto_parallel : 0.000036s : 0.02% optimize.opt_a.parallel : 0.000042s : 0.02% optimize.opt_a.flash_sp : 0.000020s : 0.01% optimize.opt_a.merge_comm : 0.000021s : 0.01% optimize.opt_a.allreduce_fusion : 0.000019s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000041s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000036s : 0.02% optimize.opt_a.virtual_dataset : 0.000030s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000032s : 0.02% optimize.opt_a.virtual_output : 0.000035s : 0.02% optimize.opt_a.merge_forward : 0.000020s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000039s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000057s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000002s : 0.00% optimize.opt_a.before_grad : 0.000052s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000021s : 0.01% optimize.opt_a.meta_fg_expand : 0.000013s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000047s : 0.02% optimize.opt_a.a_after_grad : 0.000046s : 0.02% optimize.opt_a.renormalize : 0.001306s : 0.63% optimize.opt_a.add_forward_monad_depend : 0.000011s : 0.01% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000091s : 0.04% optimize.opt_a.cse : 0.000156s : 0.08% optimize.opt_a.a_3 : 0.000210s : 0.10% optimize.py_interpret_to_execute_after_opt_a : 0.000025s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000195s : 0.09% optimize.convert_after_rewriter : 0.000017s : 0.01% optimize.order_py_execute_after_rewriter : 0.000010s : 0.00% optimize.mutable_eliminate : 0.000780s : 0.38% optimize.opt_b.b_1 : 0.000351s : 0.17% optimize.opt_b.b_2 : 0.000020s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000009s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000012s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000075s : 0.04% optimize.optimize_parallel_all_gather_comm : 0.000033s : 0.02% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000036s : 0.02% optimize.loop_unroll : 0.000539s : 0.26% optimize.opt_after_cconv.c_1 : 0.000101s : 0.05% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000011s : 0.01% optimize.opt_after_cconv.cse : 0.000061s : 0.03% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000075s : 0.04% optimize.tuple_transform.d_1 : 0.000102s : 0.05% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000015s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000103s : 0.05% optimize.cse_after_recomputation.cse : 0.000036s : 0.02% optimize.environ_conv : 0.000014s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 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 : 0.000001s : 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 : 0.000027s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000001s : 0.00% optimize.offloading_packed_experts : 0.000011s : 0.01% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000041s : 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 : 0.000197s : 0.10% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000029s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000044s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000018s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000035s : 0.02% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000005s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000059s : 0.03% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000601s : 0.29% validate : 0.000068s : 0.03% Time group info: ------[substitution.] 0.000508 102 24.97% : 0.000127s : 4: substitution.arithmetic_simplify 2.66% : 0.000014s : 2: substitution.depend_value_elim 3.41% : 0.000017s : 8: substitution.elim_not_effective 2.70% : 0.000014s : 8: substitution.fold_const_symbol 2.09% : 0.000011s : 11: substitution.graph_param_transform 24.15% : 0.000123s : 1: substitution.inline 1.75% : 0.000009s : 16: substitution.j_node_and_user_rematch 6.28% : 0.000032s : 4: substitution.less_batch_normalization 1.70% : 0.000009s : 12: substitution.load_eliminater 2.61% : 0.000013s : 16: substitution.remove_not_recompute_node 1.66% : 0.000008s : 6: substitution.replace_old_param 1.82% : 0.000009s : 6: substitution.updatestate_pure_node_eliminater 24.20% : 0.000123s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.007275 2 90.46% : 0.006581s : 1: type_inference.infer 9.54% : 0.000694s : 1: type_inference.specialize ------[replace.] 0.000019 1 100.00% : 0.000019s : 1: replace.inline ------[match.] 0.000121 1 100.00% : 0.000121s : 1: match.inline ------[predicate.] 0.000390 2549 0.86% : 0.000003s : 23: predicate.accumulaten_eliminater 1.02% : 0.000004s : 11: predicate.ad_related_special_op_eliminate 0.73% : 0.000003s : 22: predicate.addn_check_dump 1.05% : 0.000004s : 23: predicate.addn_zero_filter 0.73% : 0.000003s : 23: predicate.adjust_all_reduce_mul_add 2.87% : 0.000011s : 45: predicate.arithmetic_simplify 0.90% : 0.000004s : 23: predicate.cast_eliminate 0.84% : 0.000003s : 22: predicate.check_bprop_eliminate 0.76% : 0.000003s : 22: predicate.compare_switch_simplify 0.23% : 0.000001s : 11: predicate.const_output_eliminate 1.00% : 0.000004s : 22: predicate.depend_value_elim 0.91% : 0.000004s : 23: predicate.dict_get_item_const_eliminator 0.86% : 0.000003s : 23: predicate.dict_get_item_eliminator 0.79% : 0.000003s : 23: predicate.dict_set_item_eliminator 1.06% : 0.000004s : 22: predicate.dumpgradient_eliminate 0.35% : 0.000001s : 11: predicate.elim_not_effective 0.47% : 0.000002s : 11: predicate.elim_shapecalc_of_broadcastargs 1.24% : 0.000005s : 34: predicate.environ_add_const_eliminate 1.11% : 0.000004s : 34: predicate.environ_get_add_eliminate 1.12% : 0.000004s : 34: predicate.environ_get_depend_swap 1.89% : 0.000007s : 56: predicate.environ_get_eliminate 1.13% : 0.000004s : 34: predicate.environ_get_set_eliminate 0.78% : 0.000003s : 24: predicate.exchange_switch_depend_value 1.29% : 0.000005s : 24: predicate.float_depend_g_call 0.76% : 0.000003s : 22: predicate.float_environ_get_switch 1.13% : 0.000004s : 33: predicate.float_tuple_getitem_switch 0.22% : 0.000001s : 11: predicate.fold_const_symbol 0.85% : 0.000003s : 22: predicate.get_grad_eliminate 0.31% : 0.000001s : 11: predicate.graph_param_transform 0.85% : 0.000003s : 22: predicate.incorporate_call 0.71% : 0.000003s : 22: predicate.incorporate_call_switch 5.63% : 0.000022s : 113: predicate.inline 1.03% : 0.000004s : 22: predicate.inline_without_move 0.40% : 0.000002s : 22: predicate.j_node_and_user_rematch 1.18% : 0.000005s : 22: predicate.less_batch_normalization 1.69% : 0.000007s : 45: predicate.list_to_tuple_eliminator_ 2.37% : 0.000009s : 68: predicate.load_eliminater 0.98% : 0.000004s : 11: predicate.loop_unroll_after_grad 1.02% : 0.000004s : 27: predicate.loop_unroll_before_grad 1.77% : 0.000007s : 45: predicate.make_slice_get_slice_eliminator 0.84% : 0.000003s : 22: predicate.merge_addn 0.82% : 0.000003s : 22: predicate.micro_step_allgather_replace 0.78% : 0.000003s : 22: predicate.mini_step_allgather_replace 0.73% : 0.000003s : 23: predicate.minmaximum_grad 1.12% : 0.000004s : 11: predicate.mutable_eliminate 0.48% : 0.000002s : 11: predicate.opt_reshape 0.47% : 0.000002s : 11: predicate.parallel_virtual_node 1.01% : 0.000004s : 24: predicate.partial_defer_inline 1.25% : 0.000005s : 34: predicate.partial_eliminate 0.80% : 0.000003s : 23: predicate.print_const_string_wrapper 0.83% : 0.000003s : 22: predicate.reduce_all_const_elim 1.08% : 0.000004s : 23: predicate.reduce_eliminate 2.48% : 0.000010s : 68: predicate.redundant_stop_gradient_eliminater 0.55% : 0.000002s : 22: predicate.remove_not_recompute_node 1.22% : 0.000005s : 45: predicate.replace_applicator 0.59% : 0.000002s : 22: predicate.replace_old_param 0.32% : 0.000001s : 11: predicate.reset_defer_inline 0.81% : 0.000003s : 23: predicate.reshape_eliminate 0.83% : 0.000003s : 22: predicate.row_tensor_add_zeros_like 0.48% : 0.000002s : 11: predicate.row_tensor_eliminate 0.93% : 0.000004s : 22: predicate.same_eliminate 0.50% : 0.000002s : 22: predicate.set_cell_output_no_recompute 0.94% : 0.000004s : 22: predicate.shard_identity_eliminate 0.90% : 0.000004s : 22: predicate.special_op_eliminate 1.22% : 0.000005s : 22: predicate.specialize_transform 1.20% : 0.000005s : 22: predicate.split_environ_get_set_with_tuple_value 0.98% : 0.000004s : 22: predicate.stack_unstack_eliminate 0.54% : 0.000002s : 11: predicate.switch_call_monad_eliminater 0.82% : 0.000003s : 24: predicate.switch_defer_inline 1.57% : 0.000006s : 46: predicate.switch_layer_defer_inline 3.44% : 0.000013s : 84: predicate.switch_simplify 0.78% : 0.000003s : 23: predicate.tile_eliminate 0.80% : 0.000003s : 23: predicate.transpose_eliminate 1.83% : 0.000007s : 45: predicate.tuple_list_convert_item_index_to_positive 1.67% : 0.000007s : 45: predicate.tuple_list_get_item_const_eliminator 1.69% : 0.000007s : 45: predicate.tuple_list_get_item_depend_reorder 3.13% : 0.000012s : 67: predicate.tuple_list_get_item_eliminator 1.71% : 0.000007s : 45: predicate.tuple_list_get_set_item_eliminator 2.63% : 0.000010s : 67: predicate.tuple_list_set_item_eliminator 1.59% : 0.000006s : 45: predicate.tuple_to_list_eliminator_ 2.27% : 0.000009s : 68: predicate.updatestate_pure_node_eliminater 3.44% : 0.000013s : 90: predicate.updatestate_useless_node_eliminater 0.46% : 0.000002s : 11: predicate.value_based_eliminate 0.86% : 0.000003s : 22: predicate.virtual_dataset_eliminate 0.82% : 0.000003s : 22: predicate.virtual_output_eliminate 0.42% : 0.000002s : 11: predicate.virtual_view_grad_eliminate 0.50% : 0.000002s : 11: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000430 4 5.56% : 0.000024s : 1: func_graph_cloner_run.FuncGraphClonerGraph 94.44% : 0.000406s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.422754 192 0.00% : 0.000004s : 1: ForceFp32Comm 1.26% : 0.005316s : 1: add_attr 1.25% : 0.005296s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.03% : 0.000107s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.06% : 0.000250s : 1: auto_monad 0.02% : 0.000064s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.14% : 0.000571s : 1: bootstrap 0.01% : 0.000040s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000030s : 1: control_data_broadcast_order 0.01% : 0.000022s : 1: convert_after_rewriter 0.01% : 0.000050s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000009s : 1: detach_backward 0.00% : 0.000018s : 1: environ_conv 0.01% : 0.000023s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 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% : 0.000013s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000006s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.13% : 0.000548s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.19% : 0.000789s : 1: mutable_eliminate 0.00% : 0.000014s : 1: offloading_packed_experts 0.01% : 0.000028s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000030s : 1: opt.transform.mutable_eliminate 0.56% : 0.002365s : 78: opt.transform.opt_a 0.02% : 0.000100s : 1: opt.transform.opt_after_cconv 0.01% : 0.000053s : 1: opt.transform.opt_after_jit_grad 0.08% : 0.000334s : 28: opt.transform.opt_b 0.03% : 0.000115s : 2: opt.transform.opt_trans_graph 0.03% : 0.000120s : 4: opt.transform.symbol_engine_opt 46.28% : 0.195671s : 1: opt_a 0.06% : 0.000247s : 1: opt_after_cconv 0.14% : 0.000612s : 1: opt_after_jit_grad 0.13% : 0.000535s : 1: opt_b 47.16% : 0.199383s : 1: optimize 0.01% : 0.000037s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000014s : 1: order_py_execute_after_rewriter 0.01% : 0.000045s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000008s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000053s : 1: pre_auto_parallel 0.01% : 0.000043s : 1: py_interpret_to_execute 0.01% : 0.000029s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000080s : 1: remove_dup_value 0.17% : 0.000700s : 1: renormalize.infer 0.14% : 0.000592s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.05% : 0.000201s : 1: rewriter_after_opt_a 0.02% : 0.000081s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000008s : 1: split_matmul_comm_elemetwise 0.00% : 0.000014s : 1: swap_dp_allreduce_reducescatter 0.09% : 0.000380s : 1: symbol_engine_optimizer 0.03% : 0.000148s : 1: tuple_transform 1.74% : 0.007361s : 1: type_inference . [hook] pytest_runtest_teardown:test_qbmm_add[True-False-input_shape0] tests/st/infer/ops/test_internal_ops/test_quant_bmm.py::test_qbmm_add[True-False-input_shape0],max_mem:24.0M [WARNING] ME(169497:281473358380848,MainProcess):2026-01-29-17:38:42.242.265 [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 = 0.175278, [21] [bootstrap]: 0.00066946 [type_inference]: 0.159927 [event_method]: 1.972e-05 [auto_monad]: 0.00023001 [graph_reusing]: 5.57001e-06 [inline]: 1.66e-06 [add_attr]: 0.00523426, [1] [add_attr_with_inline]: 0.00521937, [1] [Cycle 1]: 6.785e-05, [2] [tag_attr]: 2.414e-05 [meta_addattr_fg_expand]: 4.63001e-06 [parallel-infer-symbol]: 3.54002e-06 [pre_auto_parallel]: 4.239e-05 [insert-virtual-dataset]: 2.81e-06 [parallel-infer-symbol-second]: 6.80011e-07 [dataset_repeat_opt]: 1.73002e-06 [pipeline_split]: 1.70001e-06 [optimize]: 0.00823155, [53] [py_interpret_to_execute]: 3.658e-05 [rewriter_before_opt_a]: 7.737e-05 [opt_a]: 0.00480301, [2] [Cycle 1]: 0.00337416, [45] [expand_dump_flag]: 2.76e-06 [switch_simplify]: 3.758e-05 [loop_unroll]: 1.857e-05 [a_1]: 0.00067343 [with_stream_mark]: 2.554e-05 [recompute_prepare]: 1.71e-05 [updatestate_depend_eliminate]: 1.027e-05 [updatestate_assign_eliminate]: 1.023e-05 [updatestate_loads_eliminate]: 1.526e-05 [parameter_eliminate]: 2.28002e-06 [a_2]: 0.00023329 [accelerated_algorithm]: 4.185e-05 [shard]: 2.11998e-06 [meta_shard_fg_expand]: 4.50001e-06 [shard_inline]: 1.546e-05 [merge_send_recv]: 1.563e-05 [auto_parallel]: 1.722e-05 [parallel]: 3.352e-05 [flash_sp]: 1.34e-05 [merge_comm]: 9.49e-06 [allreduce_fusion]: 9.17999e-06 [matmul_add_comm_reduction]: 2.208e-05 [allreduce_slice_to_reducescatter]: 7.50006e-07 [virtual_shard_identity]: 2.12e-05 [virtual_dataset]: 1.466e-05 [get_grad_eliminate_]: 1.394e-05 [virtual_output]: 1.66e-05 [merge_forward]: 1.026e-05 [cell_reuse_recompute_pass]: 1.94e-06 [offload_activation]: 2.246e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.8e-05 [merge_recompute_call_nodes]: 1.44e-06 [before_grad]: 2.415e-05 [set_forward_comm_id_for_comm_node_pass]: 9.86e-06 [meta_fg_expand]: 6.61e-06 [flash_sp_send_recv_attached]: 4.48001e-06 [receive_attached]: 2.21998e-06 [after_resolve]: 2.17e-05 [a_after_grad]: 2.554e-05 [renormalize]: 0.00138655 [add_forward_monad_depend]: 6.94001e-06 [auto_monad_grad]: 2.59999e-06 [auto_monad_eliminator]: 5.034e-05 [cse]: 9.232e-05 [a_3]: 0.00010901 [Cycle 2]: 0.001417, [45] [expand_dump_flag]: 2.22999e-06 [switch_simplify]: 1.751e-05 [loop_unroll]: 1.463e-05 [a_1]: 0.00040164 [with_stream_mark]: 1.823e-05 [recompute_prepare]: 1.495e-05 [updatestate_depend_eliminate]: 9.99999e-06 [updatestate_assign_eliminate]: 9.44998e-06 [updatestate_loads_eliminate]: 1.175e-05 [parameter_eliminate]: 1.24e-06 [a_2]: 0.00021399 [accelerated_algorithm]: 2.056e-05 [shard]: 1.30001e-06 [meta_shard_fg_expand]: 3.88001e-06 [shard_inline]: 1.404e-05 [merge_send_recv]: 1.265e-05 [auto_parallel]: 1.312e-05 [parallel]: 7.18e-06 [flash_sp]: 3.71999e-06 [merge_comm]: 9.00001e-06 [allreduce_fusion]: 8.21002e-06 [matmul_add_comm_reduction]: 1.529e-05 [allreduce_slice_to_reducescatter]: 5.10016e-07 [virtual_shard_identity]: 1.565e-05 [virtual_dataset]: 1.43e-05 [get_grad_eliminate_]: 1.317e-05 [virtual_output]: 1.347e-05 [merge_forward]: 8.87e-06 [cell_reuse_recompute_pass]: 2.02001e-06 [offload_activation]: 1.511e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.585e-05 [merge_recompute_call_nodes]: 1.07e-06 [before_grad]: 2.369e-05 [set_forward_comm_id_for_comm_node_pass]: 8.79998e-06 [meta_fg_expand]: 6.23998e-06 [flash_sp_send_recv_attached]: 1.69e-06 [receive_attached]: 2.26e-06 [after_resolve]: 2.046e-05 [a_after_grad]: 2.163e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.07001e-06 [auto_monad_grad]: 1.79e-06 [auto_monad_eliminator]: 3.245e-05 [cse]: 4.735e-05 [a_3]: 9.311e-05 [py_interpret_to_execute_after_opt_a]: 2.482e-05 [slice_cell_reuse_recomputed_activation]: 2.39999e-06 [rewriter_after_opt_a]: 0.00017997 [convert_after_rewriter]: 1.471e-05 [order_py_execute_after_rewriter]: 9.81998e-06 [mutable_eliminate]: 0.00070988 [opt_b]: 0.00050457, [1] [Cycle 1]: 0.00049611, [7] [b_1]: 0.00035239 [b_2]: 1.732e-05 [updatestate_depend_eliminate]: 1.236e-05 [updatestate_assign_eliminate]: 8.70001e-06 [updatestate_loads_eliminate]: 1.112e-05 [renormalize]: 6.39993e-07 [cse]: 5.505e-05 [optimize_parallel_all_gather_comm]: 2.918e-05 [overlap_param_gather]: 2.31e-06 [cconv]: 3.698e-05 [loop_unroll]: 0.0004945 [opt_after_cconv]: 0.00023262, [1] [Cycle 1]: 0.00022569, [7] [c_1]: 9.564e-05 [parameter_eliminate]: 3.41001e-06 [updatestate_depend_eliminate]: 1.22e-05 [updatestate_assign_eliminate]: 8.64e-06 [updatestate_loads_eliminate]: 1.008e-05 [cse]: 5.877e-05 [renormalize]: 5.59987e-07 [remove_dup_value]: 7.173e-05 [tuple_transform]: 0.0001385, [1] [Cycle 1]: 0.00013343, [4] [d_1]: 9.728e-05 [none_parameter_eliminate]: 2.15002e-06 [renormalize]: 1.80007e-07 [switch_simplify]: 1.513e-05 [partial_unused_args_eliminate]: 2.17999e-06 [add_recomputation]: 0.00010096 [cse_after_recomputation]: 5.013e-05, [1] [Cycle 1]: 4.478e-05, [1] [cse]: 3.906e-05 [environ_conv]: 1.333e-05 [swap_dp_allreduce_reducescatter]: 1.14e-05 [bias_add_comm_swap]: 3.15998e-06 [label_micro_interleaved_index]: 4.87e-06 [label_fine_grained_interleaved_index]: 3.34001e-06 [merge_cast_opt]: 1.67001e-06 [slice_recompute_activation]: 2.02001e-06 [micro_interleaved_order_control]: 2.61e-06 [assign_add_opt]: 1.19e-06 [ForceFp32Comm]: 1.29e-06 [remove_cast_before_assign_add]: 1.04998e-06 [full_micro_interleaved_order_control]: 2.51998e-06 [reorder_send_recv_between_fp_bp]: 2.87002e-06 [comm_op_add_attrs]: 1.32999e-06 [add_comm_op_reuse_tag]: 1.05001e-06 [interleave_split_concat_branches]: 1.15999e-06 [interleave_parallel_branches]: 1.00999e-06 [overlap_opt_shard_in_pipeline]: 1.27e-06 [overlap_opt_shard_grad_in_pipeline]: 1.72001e-06 [control_data_broadcast_order]: 2.657e-05 [grouped_pairwise_exchange_alltoall]: 1.44998e-06 [offloading_packed_experts]: 7.68001e-06 [overlap_recompute_and_grad_model_parallel]: 8.40001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.15001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.29e-06 [overlap_recompute_comm]: 2.71e-06 [overlap_grad_ring_attention]: 7.7e-06 [overlap_grad_flash_sp]: 3.612e-05 [begin_end_overlap_inline]: 4.80009e-07 [split_matmul_comm_elemetwise]: 2.16e-06 [split_layernorm_comm]: 1.97001e-06 [handle_group_info]: 1.05001e-06 [symbol_engine_optimizer]: 0.00029958, [1] [Cycle 1]: 0.00029451, [6] [build]: 0.0001459 [elim_shapecalc]: 2.628e-05 [elim_not_effective]: 2.952e-05 [opt_reshape]: 1.914e-05 [fold_const_symbol]: 3.27e-05 [renormalize]: 2.50002e-07 [detach_backward]: 3.05002e-06 [pipeline_parallel_scheduler]: 1.74998e-06 [auto_monad_reorder]: 5.487e-05 [get_jit_bprop_graph]: 2.42001e-06 [rewriter_after_jit_bprop_graph]: 6.82002e-06 [opt_after_jit_grad]: 0.00058251 [validate]: 6.532e-05 Sums bootstrap : 0.000669s : 0.40% type_inference : 0.159927s : 94.66% event_method : 0.000020s : 0.01% auto_monad : 0.000230s : 0.14% graph_reusing : 0.000006s : 0.00% inline : 0.000002s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000024s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000042s : 0.03% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000037s : 0.02% optimize.rewriter_before_opt_a : 0.000077s : 0.05% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000055s : 0.03% optimize.opt_a.loop_unroll : 0.000033s : 0.02% optimize.opt_a.a_1 : 0.001075s : 0.64% optimize.opt_a.with_stream_mark : 0.000044s : 0.03% optimize.opt_a.recompute_prepare : 0.000032s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000020s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000020s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000027s : 0.02% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000447s : 0.26% optimize.opt_a.accelerated_algorithm : 0.000062s : 0.04% optimize.opt_a.shard : 0.000003s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000008s : 0.00% optimize.opt_a.shard_inline : 0.000030s : 0.02% optimize.opt_a.merge_send_recv : 0.000028s : 0.02% optimize.opt_a.auto_parallel : 0.000030s : 0.02% optimize.opt_a.parallel : 0.000041s : 0.02% optimize.opt_a.flash_sp : 0.000017s : 0.01% optimize.opt_a.merge_comm : 0.000018s : 0.01% optimize.opt_a.allreduce_fusion : 0.000017s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000037s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000037s : 0.02% optimize.opt_a.virtual_dataset : 0.000029s : 0.02% optimize.opt_a.get_grad_eliminate_ : 0.000027s : 0.02% optimize.opt_a.virtual_output : 0.000030s : 0.02% optimize.opt_a.merge_forward : 0.000019s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000038s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000054s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000048s : 0.03% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000019s : 0.01% optimize.opt_a.meta_fg_expand : 0.000013s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.00% optimize.opt_a.receive_attached : 0.000004s : 0.00% optimize.opt_a.after_resolve : 0.000042s : 0.02% optimize.opt_a.a_after_grad : 0.000047s : 0.03% optimize.opt_a.renormalize : 0.001387s : 0.82% optimize.opt_a.add_forward_monad_depend : 0.000009s : 0.01% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000083s : 0.05% optimize.opt_a.cse : 0.000140s : 0.08% optimize.opt_a.a_3 : 0.000202s : 0.12% optimize.py_interpret_to_execute_after_opt_a : 0.000025s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000180s : 0.11% optimize.convert_after_rewriter : 0.000015s : 0.01% optimize.order_py_execute_after_rewriter : 0.000010s : 0.01% optimize.mutable_eliminate : 0.000710s : 0.42% optimize.opt_b.b_1 : 0.000352s : 0.21% optimize.opt_b.b_2 : 0.000017s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000009s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000011s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000055s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000029s : 0.02% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000037s : 0.02% optimize.loop_unroll : 0.000494s : 0.29% optimize.opt_after_cconv.c_1 : 0.000096s : 0.06% optimize.opt_after_cconv.parameter_eliminate : 0.000003s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000009s : 0.01% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000010s : 0.01% optimize.opt_after_cconv.cse : 0.000059s : 0.03% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000072s : 0.04% optimize.tuple_transform.d_1 : 0.000097s : 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 : 0.000015s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000101s : 0.06% optimize.cse_after_recomputation.cse : 0.000039s : 0.02% optimize.environ_conv : 0.000013s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 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 : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000027s : 0.02% optimize.grouped_pairwise_exchange_alltoall : 0.000001s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000036s : 0.02% optimize.begin_end_overlap_inline : 0.000000s : 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 : 0.000146s : 0.09% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000026s : 0.02% optimize.symbol_engine_optimizer.elim_not_effective : 0.000030s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000019s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000033s : 0.02% 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 : 0.000055s : 0.03% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000583s : 0.34% validate : 0.000065s : 0.04% Time group info: ------[substitution.] 0.000404 102 23.19% : 0.000094s : 4: substitution.arithmetic_simplify 2.99% : 0.000012s : 2: substitution.depend_value_elim 1.50% : 0.000006s : 8: substitution.elim_not_effective 3.07% : 0.000012s : 8: substitution.fold_const_symbol 2.54% : 0.000010s : 11: substitution.graph_param_transform 28.28% : 0.000114s : 1: substitution.inline 2.01% : 0.000008s : 16: substitution.j_node_and_user_rematch 6.14% : 0.000025s : 4: substitution.less_batch_normalization 1.83% : 0.000007s : 12: substitution.load_eliminater 2.98% : 0.000012s : 16: substitution.remove_not_recompute_node 1.90% : 0.000008s : 6: substitution.replace_old_param 1.90% : 0.000008s : 6: substitution.updatestate_pure_node_eliminater 21.66% : 0.000088s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.159857 2 99.48% : 0.159028s : 1: type_inference.infer 0.52% : 0.000828s : 1: type_inference.specialize ------[replace.] 0.000016 1 100.00% : 0.000016s : 1: replace.inline ------[match.] 0.000113 1 100.00% : 0.000113s : 1: match.inline ------[predicate.] 0.000373 2549 0.82% : 0.000003s : 23: predicate.accumulaten_eliminater 0.89% : 0.000003s : 11: predicate.ad_related_special_op_eliminate 0.75% : 0.000003s : 22: predicate.addn_check_dump 0.89% : 0.000003s : 23: predicate.addn_zero_filter 0.78% : 0.000003s : 23: predicate.adjust_all_reduce_mul_add 2.38% : 0.000009s : 45: predicate.arithmetic_simplify 0.85% : 0.000003s : 23: predicate.cast_eliminate 0.80% : 0.000003s : 22: predicate.check_bprop_eliminate 0.75% : 0.000003s : 22: predicate.compare_switch_simplify 0.24% : 0.000001s : 11: predicate.const_output_eliminate 0.88% : 0.000003s : 22: predicate.depend_value_elim 0.83% : 0.000003s : 23: predicate.dict_get_item_const_eliminator 0.89% : 0.000003s : 23: predicate.dict_get_item_eliminator 0.85% : 0.000003s : 23: predicate.dict_set_item_eliminator 1.12% : 0.000004s : 22: predicate.dumpgradient_eliminate 0.35% : 0.000001s : 11: predicate.elim_not_effective 0.50% : 0.000002s : 11: predicate.elim_shapecalc_of_broadcastargs 1.16% : 0.000004s : 34: predicate.environ_add_const_eliminate 1.13% : 0.000004s : 34: predicate.environ_get_add_eliminate 1.21% : 0.000005s : 34: predicate.environ_get_depend_swap 1.94% : 0.000007s : 56: predicate.environ_get_eliminate 1.15% : 0.000004s : 34: predicate.environ_get_set_eliminate 0.83% : 0.000003s : 24: predicate.exchange_switch_depend_value 1.49% : 0.000006s : 24: predicate.float_depend_g_call 0.76% : 0.000003s : 22: predicate.float_environ_get_switch 1.14% : 0.000004s : 33: predicate.float_tuple_getitem_switch 0.24% : 0.000001s : 11: predicate.fold_const_symbol 0.84% : 0.000003s : 22: predicate.get_grad_eliminate 0.26% : 0.000001s : 11: predicate.graph_param_transform 0.80% : 0.000003s : 22: predicate.incorporate_call 0.74% : 0.000003s : 22: predicate.incorporate_call_switch 5.58% : 0.000021s : 113: predicate.inline 1.28% : 0.000005s : 22: predicate.inline_without_move 0.44% : 0.000002s : 22: predicate.j_node_and_user_rematch 1.26% : 0.000005s : 22: predicate.less_batch_normalization 1.67% : 0.000006s : 45: predicate.list_to_tuple_eliminator_ 2.41% : 0.000009s : 68: predicate.load_eliminater 0.98% : 0.000004s : 11: predicate.loop_unroll_after_grad 1.05% : 0.000004s : 27: predicate.loop_unroll_before_grad 1.71% : 0.000006s : 45: predicate.make_slice_get_slice_eliminator 0.79% : 0.000003s : 22: predicate.merge_addn 0.89% : 0.000003s : 22: predicate.micro_step_allgather_replace 0.79% : 0.000003s : 22: predicate.mini_step_allgather_replace 0.75% : 0.000003s : 23: predicate.minmaximum_grad 1.44% : 0.000005s : 11: predicate.mutable_eliminate 0.48% : 0.000002s : 11: predicate.opt_reshape 0.49% : 0.000002s : 11: predicate.parallel_virtual_node 1.06% : 0.000004s : 24: predicate.partial_defer_inline 1.30% : 0.000005s : 34: predicate.partial_eliminate 0.75% : 0.000003s : 23: predicate.print_const_string_wrapper 0.81% : 0.000003s : 22: predicate.reduce_all_const_elim 1.10% : 0.000004s : 23: predicate.reduce_eliminate 2.33% : 0.000009s : 68: predicate.redundant_stop_gradient_eliminater 0.58% : 0.000002s : 22: predicate.remove_not_recompute_node 1.21% : 0.000005s : 45: predicate.replace_applicator 0.54% : 0.000002s : 22: predicate.replace_old_param 0.37% : 0.000001s : 11: predicate.reset_defer_inline 0.82% : 0.000003s : 23: predicate.reshape_eliminate 0.85% : 0.000003s : 22: predicate.row_tensor_add_zeros_like 0.48% : 0.000002s : 11: predicate.row_tensor_eliminate 0.97% : 0.000004s : 22: predicate.same_eliminate 0.51% : 0.000002s : 22: predicate.set_cell_output_no_recompute 1.17% : 0.000004s : 22: predicate.shard_identity_eliminate 0.99% : 0.000004s : 22: predicate.special_op_eliminate 0.92% : 0.000003s : 22: predicate.specialize_transform 1.16% : 0.000004s : 22: predicate.split_environ_get_set_with_tuple_value 1.02% : 0.000004s : 22: predicate.stack_unstack_eliminate 0.48% : 0.000002s : 11: predicate.switch_call_monad_eliminater 0.87% : 0.000003s : 24: predicate.switch_defer_inline 1.68% : 0.000006s : 46: predicate.switch_layer_defer_inline 3.65% : 0.000014s : 84: predicate.switch_simplify 0.81% : 0.000003s : 23: predicate.tile_eliminate 0.74% : 0.000003s : 23: predicate.transpose_eliminate 1.76% : 0.000007s : 45: predicate.tuple_list_convert_item_index_to_positive 1.72% : 0.000006s : 45: predicate.tuple_list_get_item_const_eliminator 1.64% : 0.000006s : 45: predicate.tuple_list_get_item_depend_reorder 2.86% : 0.000011s : 67: predicate.tuple_list_get_item_eliminator 1.68% : 0.000006s : 45: predicate.tuple_list_get_set_item_eliminator 2.55% : 0.000010s : 67: predicate.tuple_list_set_item_eliminator 1.64% : 0.000006s : 45: predicate.tuple_to_list_eliminator_ 2.35% : 0.000009s : 68: predicate.updatestate_pure_node_eliminater 3.25% : 0.000012s : 90: predicate.updatestate_useless_node_eliminater 0.45% : 0.000002s : 11: predicate.value_based_eliminate 0.90% : 0.000003s : 22: predicate.virtual_dataset_eliminate 0.83% : 0.000003s : 22: predicate.virtual_output_eliminate 0.40% : 0.000001s : 11: predicate.virtual_view_grad_eliminate 0.53% : 0.000002s : 11: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000498 4 4.75% : 0.000024s : 1: func_graph_cloner_run.FuncGraphClonerGraph 95.25% : 0.000474s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.192843 192 0.00% : 0.000004s : 1: ForceFp32Comm 2.72% : 0.005242s : 1: add_attr 2.71% : 0.005224s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.05% : 0.000105s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.12% : 0.000238s : 1: auto_monad 0.03% : 0.000059s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.36% : 0.000702s : 1: bootstrap 0.02% : 0.000041s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.02% : 0.000030s : 1: control_data_broadcast_order 0.01% : 0.000019s : 1: convert_after_rewriter 0.03% : 0.000053s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000017s : 1: environ_conv 0.01% : 0.000027s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.01% : 0.000010s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000005s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.26% : 0.000503s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.37% : 0.000719s : 1: mutable_eliminate 0.01% : 0.000011s : 1: offloading_packed_experts 0.01% : 0.000025s : 1: opt.transform.loop_unroll_optimizer 0.02% : 0.000031s : 1: opt.transform.mutable_eliminate 1.12% : 0.002152s : 78: opt.transform.opt_a 0.05% : 0.000094s : 1: opt.transform.opt_after_cconv 0.03% : 0.000051s : 1: opt.transform.opt_after_jit_grad 0.18% : 0.000338s : 28: opt.transform.opt_b 0.06% : 0.000110s : 2: opt.transform.opt_trans_graph 0.05% : 0.000103s : 4: opt.transform.symbol_engine_opt 2.49% : 0.004807s : 1: opt_a 0.12% : 0.000236s : 1: opt_after_cconv 0.31% : 0.000594s : 1: opt_after_jit_grad 0.26% : 0.000509s : 1: opt_b 4.27% : 0.008237s : 1: optimize 0.02% : 0.000033s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000013s : 1: order_py_execute_after_rewriter 0.02% : 0.000039s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000012s : 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% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.01% : 0.000010s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000047s : 1: pre_auto_parallel 0.02% : 0.000043s : 1: py_interpret_to_execute 0.01% : 0.000029s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.04% : 0.000076s : 1: remove_dup_value 0.42% : 0.000802s : 1: renormalize.infer 0.30% : 0.000572s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.10% : 0.000187s : 1: rewriter_after_opt_a 0.04% : 0.000082s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000008s : 1: split_matmul_comm_elemetwise 0.01% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.16% : 0.000303s : 1: symbol_engine_optimizer 0.07% : 0.000142s : 1: tuple_transform 82.94% : 0.159951s : 1: type_inference . [hook] pytest_runtest_teardown:test_qbmm_add[True-False-input_shape1] tests/st/infer/ops/test_internal_ops/test_quant_bmm.py::test_qbmm_add[True-False-input_shape1],max_mem:24.0M [WARNING] ME(169497:281473358380848,MainProcess):2026-01-29-17:38:50.396.876 [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 = 0.328503, [21] [bootstrap]: 0.00060195 [type_inference]: 0.00731967 [event_method]: 2.173e-05 [auto_monad]: 0.00023268 [graph_reusing]: 6.10002e-06 [inline]: 2.49001e-06 [add_attr]: 0.309894, [1] [add_attr_with_inline]: 0.309875, [1] [Cycle 1]: 7.476e-05, [2] [tag_attr]: 2.44e-05 [meta_addattr_fg_expand]: 4.65001e-06 [parallel-infer-symbol]: 4.11001e-06 [pre_auto_parallel]: 4.262e-05 [insert-virtual-dataset]: 3.23998e-06 [parallel-infer-symbol-second]: 1.25999e-06 [dataset_repeat_opt]: 1.86e-06 [pipeline_split]: 1.69e-06 [optimize]: 0.00923803, [53] [py_interpret_to_execute]: 4.341e-05 [rewriter_before_opt_a]: 7.945e-05 [opt_a]: 0.00501228, [2] [Cycle 1]: 0.00344349, [45] [expand_dump_flag]: 2.73998e-06 [switch_simplify]: 3.307e-05 [loop_unroll]: 1.889e-05 [a_1]: 0.00068837 [with_stream_mark]: 3.121e-05 [recompute_prepare]: 1.942e-05 [updatestate_depend_eliminate]: 1.134e-05 [updatestate_assign_eliminate]: 1.09e-05 [updatestate_loads_eliminate]: 1.516e-05 [parameter_eliminate]: 2.17999e-06 [a_2]: 0.00028819 [accelerated_algorithm]: 4.841e-05 [shard]: 3.14999e-06 [meta_shard_fg_expand]: 3.76001e-06 [shard_inline]: 1.562e-05 [merge_send_recv]: 1.564e-05 [auto_parallel]: 1.425e-05 [parallel]: 3.352e-05 [flash_sp]: 1.385e-05 [merge_comm]: 9.74e-06 [allreduce_fusion]: 9.17001e-06 [matmul_add_comm_reduction]: 2.239e-05 [allreduce_slice_to_reducescatter]: 6.89994e-07 [virtual_shard_identity]: 2.374e-05 [virtual_dataset]: 1.455e-05 [get_grad_eliminate_]: 1.863e-05 [virtual_output]: 1.423e-05 [merge_forward]: 1.071e-05 [cell_reuse_recompute_pass]: 2.14e-06 [offload_activation]: 2.567e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.38e-05 [merge_recompute_call_nodes]: 1.51998e-06 [before_grad]: 2.558e-05 [set_forward_comm_id_for_comm_node_pass]: 1.04e-05 [meta_fg_expand]: 7.01001e-06 [flash_sp_send_recv_attached]: 6.68e-06 [receive_attached]: 2.34001e-06 [after_resolve]: 3.157e-05 [a_after_grad]: 2.445e-05 [renormalize]: 0.00129491 [add_forward_monad_depend]: 8.3e-06 [auto_monad_grad]: 2.69001e-06 [auto_monad_eliminator]: 5.439e-05 [cse]: 0.00010136 [a_3]: 0.00011757 [Cycle 2]: 0.00155414, [45] [expand_dump_flag]: 3.01001e-06 [switch_simplify]: 1.716e-05 [loop_unroll]: 1.684e-05 [a_1]: 0.00041945 [with_stream_mark]: 2.604e-05 [recompute_prepare]: 1.662e-05 [updatestate_depend_eliminate]: 9.59999e-06 [updatestate_assign_eliminate]: 1.006e-05 [updatestate_loads_eliminate]: 1.34e-05 [parameter_eliminate]: 1.77999e-06 [a_2]: 0.00022959 [accelerated_algorithm]: 2.28e-05 [shard]: 2.16e-06 [meta_shard_fg_expand]: 3.97e-06 [shard_inline]: 1.449e-05 [merge_send_recv]: 1.435e-05 [auto_parallel]: 1.533e-05 [parallel]: 8.85999e-06 [flash_sp]: 4.65999e-06 [merge_comm]: 9.44e-06 [allreduce_fusion]: 8.35001e-06 [matmul_add_comm_reduction]: 1.705e-05 [allreduce_slice_to_reducescatter]: 6.30011e-07 [virtual_shard_identity]: 1.835e-05 [virtual_dataset]: 1.679e-05 [get_grad_eliminate_]: 1.412e-05 [virtual_output]: 1.348e-05 [merge_forward]: 8.97e-06 [cell_reuse_recompute_pass]: 2.39999e-06 [offload_activation]: 1.805e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.003e-05 [merge_recompute_call_nodes]: 1.27e-06 [before_grad]: 2.424e-05 [set_forward_comm_id_for_comm_node_pass]: 1.311e-05 [meta_fg_expand]: 6.27001e-06 [flash_sp_send_recv_attached]: 1.86e-06 [receive_attached]: 2.39001e-06 [after_resolve]: 2.242e-05 [a_after_grad]: 2.466e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 3.38e-06 [auto_monad_grad]: 2.61e-06 [auto_monad_eliminator]: 4.577e-05 [cse]: 6.338e-05 [a_3]: 9.58e-05 [py_interpret_to_execute_after_opt_a]: 2.87e-05 [slice_cell_reuse_recomputed_activation]: 2.22001e-06 [rewriter_after_opt_a]: 0.00021918 [convert_after_rewriter]: 1.732e-05 [order_py_execute_after_rewriter]: 1.017e-05 [mutable_eliminate]: 0.00085991 [opt_b]: 0.00076458, [1] [Cycle 1]: 0.00075495, [7] [b_1]: 0.00056189 [b_2]: 2.011e-05 [updatestate_depend_eliminate]: 1.763e-05 [updatestate_assign_eliminate]: 1.05e-05 [updatestate_loads_eliminate]: 1.428e-05 [renormalize]: 6.19999e-07 [cse]: 8.006e-05 [optimize_parallel_all_gather_comm]: 3.54e-05 [overlap_param_gather]: 2.07999e-06 [cconv]: 3.891e-05 [loop_unroll]: 0.00064748 [opt_after_cconv]: 0.00026275, [1] [Cycle 1]: 0.00025387, [7] [c_1]: 0.00010708 [parameter_eliminate]: 5.44998e-06 [updatestate_depend_eliminate]: 1.447e-05 [updatestate_assign_eliminate]: 9.29e-06 [updatestate_loads_eliminate]: 1.379e-05 [cse]: 6.467e-05 [renormalize]: 7.7e-07 [remove_dup_value]: 8.119e-05 [tuple_transform]: 0.0001566, [1] [Cycle 1]: 0.00015107, [4] [d_1]: 0.0001126 [none_parameter_eliminate]: 2.20002e-06 [renormalize]: 1.50001e-07 [switch_simplify]: 1.578e-05 [partial_unused_args_eliminate]: 2.11e-06 [add_recomputation]: 0.00011029 [cse_after_recomputation]: 5.546e-05, [1] [Cycle 1]: 5.004e-05, [1] [cse]: 4.391e-05 [environ_conv]: 1.782e-05 [swap_dp_allreduce_reducescatter]: 1.249e-05 [bias_add_comm_swap]: 3.96001e-06 [label_micro_interleaved_index]: 6.58e-06 [label_fine_grained_interleaved_index]: 3.04999e-06 [merge_cast_opt]: 1.50001e-06 [slice_recompute_activation]: 2.52001e-06 [micro_interleaved_order_control]: 3.01999e-06 [assign_add_opt]: 1.37e-06 [ForceFp32Comm]: 1.27e-06 [remove_cast_before_assign_add]: 1.25999e-06 [full_micro_interleaved_order_control]: 2.27001e-06 [reorder_send_recv_between_fp_bp]: 3.16001e-06 [comm_op_add_attrs]: 1.42999e-06 [add_comm_op_reuse_tag]: 9.5999e-07 [interleave_split_concat_branches]: 1.24e-06 [interleave_parallel_branches]: 1.29e-06 [overlap_opt_shard_in_pipeline]: 1.19998e-06 [overlap_opt_shard_grad_in_pipeline]: 1.77001e-06 [control_data_broadcast_order]: 3.319e-05 [grouped_pairwise_exchange_alltoall]: 1.56998e-06 [offloading_packed_experts]: 8.85001e-06 [overlap_recompute_and_grad_model_parallel]: 1.263e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.45999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.21002e-06 [overlap_recompute_comm]: 2.04e-06 [overlap_grad_ring_attention]: 1.065e-05 [overlap_grad_flash_sp]: 3.855e-05 [begin_end_overlap_inline]: 5.69999e-07 [split_matmul_comm_elemetwise]: 2.14999e-06 [split_layernorm_comm]: 2.27999e-06 [handle_group_info]: 1.17e-06 [symbol_engine_optimizer]: 0.0003385, [1] [Cycle 1]: 0.00033268, [6] [build]: 0.00016104 [elim_shapecalc]: 2.584e-05 [elim_not_effective]: 3.301e-05 [opt_reshape]: 2.219e-05 [fold_const_symbol]: 3.797e-05 [renormalize]: 2.09984e-07 [detach_backward]: 3.65e-06 [pipeline_parallel_scheduler]: 1.99e-06 [auto_monad_reorder]: 9.974e-05 [get_jit_bprop_graph]: 2.74999e-06 [rewriter_after_jit_bprop_graph]: 6.66999e-06 [opt_after_jit_grad]: 0.00074261 [validate]: 7.705e-05 Sums bootstrap : 0.000602s : 3.46% type_inference : 0.007320s : 42.07% event_method : 0.000022s : 0.12% auto_monad : 0.000233s : 1.34% graph_reusing : 0.000006s : 0.04% inline : 0.000002s : 0.01% add_attr.add_attr_with_inline.tag_attr : 0.000024s : 0.14% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.03% parallel-infer-symbol : 0.000004s : 0.02% pre_auto_parallel : 0.000043s : 0.24% insert-virtual-dataset : 0.000003s : 0.02% parallel-infer-symbol-second : 0.000001s : 0.01% dataset_repeat_opt : 0.000002s : 0.01% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000043s : 0.25% optimize.rewriter_before_opt_a : 0.000079s : 0.46% optimize.opt_a.expand_dump_flag : 0.000006s : 0.03% optimize.opt_a.switch_simplify : 0.000050s : 0.29% optimize.opt_a.loop_unroll : 0.000036s : 0.21% optimize.opt_a.a_1 : 0.001108s : 6.37% optimize.opt_a.with_stream_mark : 0.000057s : 0.33% optimize.opt_a.recompute_prepare : 0.000036s : 0.21% optimize.opt_a.updatestate_depend_eliminate : 0.000021s : 0.12% optimize.opt_a.updatestate_assign_eliminate : 0.000021s : 0.12% optimize.opt_a.updatestate_loads_eliminate : 0.000029s : 0.16% optimize.opt_a.parameter_eliminate : 0.000004s : 0.02% optimize.opt_a.a_2 : 0.000518s : 2.98% optimize.opt_a.accelerated_algorithm : 0.000071s : 0.41% optimize.opt_a.shard : 0.000005s : 0.03% optimize.opt_a.meta_shard_fg_expand : 0.000008s : 0.04% optimize.opt_a.shard_inline : 0.000030s : 0.17% optimize.opt_a.merge_send_recv : 0.000030s : 0.17% optimize.opt_a.auto_parallel : 0.000030s : 0.17% optimize.opt_a.parallel : 0.000042s : 0.24% optimize.opt_a.flash_sp : 0.000019s : 0.11% optimize.opt_a.merge_comm : 0.000019s : 0.11% optimize.opt_a.allreduce_fusion : 0.000018s : 0.10% optimize.opt_a.matmul_add_comm_reduction : 0.000039s : 0.23% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000042s : 0.24% optimize.opt_a.virtual_dataset : 0.000031s : 0.18% optimize.opt_a.get_grad_eliminate_ : 0.000033s : 0.19% optimize.opt_a.virtual_output : 0.000028s : 0.16% optimize.opt_a.merge_forward : 0.000020s : 0.11% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.03% optimize.opt_a.offload_activation : 0.000044s : 0.25% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000064s : 0.37% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.02% optimize.opt_a.before_grad : 0.000050s : 0.29% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000024s : 0.14% optimize.opt_a.meta_fg_expand : 0.000013s : 0.08% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.05% optimize.opt_a.receive_attached : 0.000005s : 0.03% optimize.opt_a.after_resolve : 0.000054s : 0.31% optimize.opt_a.a_after_grad : 0.000049s : 0.28% optimize.opt_a.renormalize : 0.001295s : 7.44% optimize.opt_a.add_forward_monad_depend : 0.000012s : 0.07% optimize.opt_a.auto_monad_grad : 0.000005s : 0.03% optimize.opt_a.auto_monad_eliminator : 0.000100s : 0.58% optimize.opt_a.cse : 0.000165s : 0.95% optimize.opt_a.a_3 : 0.000213s : 1.23% optimize.py_interpret_to_execute_after_opt_a : 0.000029s : 0.16% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.01% optimize.rewriter_after_opt_a : 0.000219s : 1.26% optimize.convert_after_rewriter : 0.000017s : 0.10% optimize.order_py_execute_after_rewriter : 0.000010s : 0.06% optimize.mutable_eliminate : 0.000860s : 4.94% optimize.opt_b.b_1 : 0.000562s : 3.23% optimize.opt_b.b_2 : 0.000020s : 0.12% optimize.opt_b.updatestate_depend_eliminate : 0.000018s : 0.10% optimize.opt_b.updatestate_assign_eliminate : 0.000010s : 0.06% optimize.opt_b.updatestate_loads_eliminate : 0.000014s : 0.08% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000080s : 0.46% optimize.optimize_parallel_all_gather_comm : 0.000035s : 0.20% optimize.overlap_param_gather : 0.000002s : 0.01% optimize.cconv : 0.000039s : 0.22% optimize.loop_unroll : 0.000647s : 3.72% optimize.opt_after_cconv.c_1 : 0.000107s : 0.62% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.03% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000014s : 0.08% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000009s : 0.05% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000014s : 0.08% optimize.opt_after_cconv.cse : 0.000065s : 0.37% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000081s : 0.47% optimize.tuple_transform.d_1 : 0.000113s : 0.65% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000016s : 0.09% optimize.partial_unused_args_eliminate : 0.000002s : 0.01% optimize.add_recomputation : 0.000110s : 0.63% optimize.cse_after_recomputation.cse : 0.000044s : 0.25% optimize.environ_conv : 0.000018s : 0.10% optimize.swap_dp_allreduce_reducescatter : 0.000012s : 0.07% optimize.bias_add_comm_swap : 0.000004s : 0.02% optimize.label_micro_interleaved_index : 0.000007s : 0.04% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.02% optimize.merge_cast_opt : 0.000002s : 0.01% optimize.slice_recompute_activation : 0.000003s : 0.01% optimize.micro_interleaved_order_control : 0.000003s : 0.02% optimize.assign_add_opt : 0.000001s : 0.01% optimize.ForceFp32Comm : 0.000001s : 0.01% optimize.remove_cast_before_assign_add : 0.000001s : 0.01% optimize.full_micro_interleaved_order_control : 0.000002s : 0.01% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.02% optimize.comm_op_add_attrs : 0.000001s : 0.01% optimize.add_comm_op_reuse_tag : 0.000001s : 0.01% optimize.interleave_split_concat_branches : 0.000001s : 0.01% optimize.interleave_parallel_branches : 0.000001s : 0.01% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000033s : 0.19% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000009s : 0.05% optimize.overlap_recompute_and_grad_model_parallel : 0.000013s : 0.07% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.01% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.01% optimize.overlap_recompute_comm : 0.000002s : 0.01% optimize.overlap_grad_ring_attention : 0.000011s : 0.06% optimize.overlap_grad_flash_sp : 0.000039s : 0.22% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.01% optimize.split_layernorm_comm : 0.000002s : 0.01% optimize.handle_group_info : 0.000001s : 0.01% optimize.symbol_engine_optimizer.build : 0.000161s : 0.93% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000026s : 0.15% optimize.symbol_engine_optimizer.elim_not_effective : 0.000033s : 0.19% optimize.symbol_engine_optimizer.opt_reshape : 0.000022s : 0.13% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000038s : 0.22% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000004s : 0.02% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000100s : 0.57% get_jit_bprop_graph : 0.000003s : 0.02% rewriter_after_jit_bprop_graph : 0.000007s : 0.04% opt_after_jit_grad : 0.000743s : 4.27% validate : 0.000077s : 0.44% Time group info: ------[substitution.] 0.000481 102 24.14% : 0.000116s : 4: substitution.arithmetic_simplify 2.04% : 0.000010s : 2: substitution.depend_value_elim 1.45% : 0.000007s : 8: substitution.elim_not_effective 3.33% : 0.000016s : 8: substitution.fold_const_symbol 2.20% : 0.000011s : 11: substitution.graph_param_transform 25.50% : 0.000123s : 1: substitution.inline 1.63% : 0.000008s : 16: substitution.j_node_and_user_rematch 5.77% : 0.000028s : 4: substitution.less_batch_normalization 1.50% : 0.000007s : 12: substitution.load_eliminater 3.26% : 0.000016s : 16: substitution.remove_not_recompute_node 2.14% : 0.000010s : 6: substitution.replace_old_param 2.29% : 0.000011s : 6: substitution.updatestate_pure_node_eliminater 24.76% : 0.000119s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.007247 2 88.88% : 0.006441s : 1: type_inference.infer 11.12% : 0.000806s : 1: type_inference.specialize ------[replace.] 0.000018 1 100.00% : 0.000018s : 1: replace.inline ------[match.] 0.000121 1 100.00% : 0.000121s : 1: match.inline ------[predicate.] 0.000392 2549 0.78% : 0.000003s : 23: predicate.accumulaten_eliminater 0.96% : 0.000004s : 11: predicate.ad_related_special_op_eliminate 0.78% : 0.000003s : 22: predicate.addn_check_dump 0.75% : 0.000003s : 23: predicate.addn_zero_filter 0.71% : 0.000003s : 23: predicate.adjust_all_reduce_mul_add 2.49% : 0.000010s : 45: predicate.arithmetic_simplify 0.79% : 0.000003s : 23: predicate.cast_eliminate 0.78% : 0.000003s : 22: predicate.check_bprop_eliminate 0.80% : 0.000003s : 22: predicate.compare_switch_simplify 0.22% : 0.000001s : 11: predicate.const_output_eliminate 0.83% : 0.000003s : 22: predicate.depend_value_elim 0.79% : 0.000003s : 23: predicate.dict_get_item_const_eliminator 0.90% : 0.000004s : 23: predicate.dict_get_item_eliminator 0.81% : 0.000003s : 23: predicate.dict_set_item_eliminator 1.05% : 0.000004s : 22: predicate.dumpgradient_eliminate 0.36% : 0.000001s : 11: predicate.elim_not_effective 0.46% : 0.000002s : 11: predicate.elim_shapecalc_of_broadcastargs 1.25% : 0.000005s : 34: predicate.environ_add_const_eliminate 1.11% : 0.000004s : 34: predicate.environ_get_add_eliminate 1.20% : 0.000005s : 34: predicate.environ_get_depend_swap 1.99% : 0.000008s : 56: predicate.environ_get_eliminate 1.21% : 0.000005s : 34: predicate.environ_get_set_eliminate 0.80% : 0.000003s : 24: predicate.exchange_switch_depend_value 1.47% : 0.000006s : 24: predicate.float_depend_g_call 0.76% : 0.000003s : 22: predicate.float_environ_get_switch 1.19% : 0.000005s : 33: predicate.float_tuple_getitem_switch 0.22% : 0.000001s : 11: predicate.fold_const_symbol 0.83% : 0.000003s : 22: predicate.get_grad_eliminate 0.30% : 0.000001s : 11: predicate.graph_param_transform 0.78% : 0.000003s : 22: predicate.incorporate_call 0.70% : 0.000003s : 22: predicate.incorporate_call_switch 5.87% : 0.000023s : 113: predicate.inline 1.47% : 0.000006s : 22: predicate.inline_without_move 0.42% : 0.000002s : 22: predicate.j_node_and_user_rematch 1.17% : 0.000005s : 22: predicate.less_batch_normalization 1.90% : 0.000007s : 45: predicate.list_to_tuple_eliminator_ 2.32% : 0.000009s : 68: predicate.load_eliminater 1.31% : 0.000005s : 11: predicate.loop_unroll_after_grad 1.00% : 0.000004s : 27: predicate.loop_unroll_before_grad 1.79% : 0.000007s : 45: predicate.make_slice_get_slice_eliminator 0.75% : 0.000003s : 22: predicate.merge_addn 0.77% : 0.000003s : 22: predicate.micro_step_allgather_replace 0.75% : 0.000003s : 22: predicate.mini_step_allgather_replace 0.70% : 0.000003s : 23: predicate.minmaximum_grad 1.28% : 0.000005s : 11: predicate.mutable_eliminate 0.49% : 0.000002s : 11: predicate.opt_reshape 0.50% : 0.000002s : 11: predicate.parallel_virtual_node 0.98% : 0.000004s : 24: predicate.partial_defer_inline 1.35% : 0.000005s : 34: predicate.partial_eliminate 0.76% : 0.000003s : 23: predicate.print_const_string_wrapper 0.80% : 0.000003s : 22: predicate.reduce_all_const_elim 1.15% : 0.000005s : 23: predicate.reduce_eliminate 2.28% : 0.000009s : 68: predicate.redundant_stop_gradient_eliminater 0.61% : 0.000002s : 22: predicate.remove_not_recompute_node 1.22% : 0.000005s : 45: predicate.replace_applicator 0.61% : 0.000002s : 22: predicate.replace_old_param 0.34% : 0.000001s : 11: predicate.reset_defer_inline 0.86% : 0.000003s : 23: predicate.reshape_eliminate 0.78% : 0.000003s : 22: predicate.row_tensor_add_zeros_like 0.48% : 0.000002s : 11: predicate.row_tensor_eliminate 0.91% : 0.000004s : 22: predicate.same_eliminate 0.48% : 0.000002s : 22: predicate.set_cell_output_no_recompute 1.19% : 0.000005s : 22: predicate.shard_identity_eliminate 0.93% : 0.000004s : 22: predicate.special_op_eliminate 0.92% : 0.000004s : 22: predicate.specialize_transform 1.32% : 0.000005s : 22: predicate.split_environ_get_set_with_tuple_value 1.01% : 0.000004s : 22: predicate.stack_unstack_eliminate 0.47% : 0.000002s : 11: predicate.switch_call_monad_eliminater 0.83% : 0.000003s : 24: predicate.switch_defer_inline 1.56% : 0.000006s : 46: predicate.switch_layer_defer_inline 3.44% : 0.000014s : 84: predicate.switch_simplify 0.84% : 0.000003s : 23: predicate.tile_eliminate 0.76% : 0.000003s : 23: predicate.transpose_eliminate 1.65% : 0.000006s : 45: predicate.tuple_list_convert_item_index_to_positive 1.69% : 0.000007s : 45: predicate.tuple_list_get_item_const_eliminator 1.63% : 0.000006s : 45: predicate.tuple_list_get_item_depend_reorder 3.20% : 0.000013s : 67: predicate.tuple_list_get_item_eliminator 1.70% : 0.000007s : 45: predicate.tuple_list_get_set_item_eliminator 2.47% : 0.000010s : 67: predicate.tuple_list_set_item_eliminator 1.66% : 0.000007s : 45: predicate.tuple_to_list_eliminator_ 2.30% : 0.000009s : 68: predicate.updatestate_pure_node_eliminater 3.19% : 0.000013s : 90: predicate.updatestate_useless_node_eliminater 0.56% : 0.000002s : 11: predicate.value_based_eliminate 0.79% : 0.000003s : 22: predicate.virtual_dataset_eliminate 0.85% : 0.000003s : 22: predicate.virtual_output_eliminate 0.40% : 0.000002s : 11: predicate.virtual_view_grad_eliminate 0.43% : 0.000002s : 11: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000432 4 6.00% : 0.000026s : 1: func_graph_cloner_run.FuncGraphClonerGraph 94.00% : 0.000406s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.652016 192 0.00% : 0.000004s : 1: ForceFp32Comm 47.53% : 0.309901s : 1: add_attr 47.53% : 0.309880s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000114s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.04% : 0.000241s : 1: auto_monad 0.02% : 0.000107s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000009s : 1: bias_add_comm_swap 0.10% : 0.000640s : 1: bootstrap 0.01% : 0.000043s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000037s : 1: control_data_broadcast_order 0.00% : 0.000022s : 1: convert_after_rewriter 0.01% : 0.000058s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000021s : 1: environ_conv 0.00% : 0.000028s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 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% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.10% : 0.000657s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.13% : 0.000872s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.01% : 0.000033s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000035s : 1: opt.transform.mutable_eliminate 0.35% : 0.002292s : 78: opt.transform.opt_a 0.02% : 0.000105s : 1: opt.transform.opt_after_cconv 0.01% : 0.000059s : 1: opt.transform.opt_after_jit_grad 0.08% : 0.000542s : 28: opt.transform.opt_b 0.02% : 0.000125s : 2: opt.transform.opt_trans_graph 0.02% : 0.000114s : 4: opt.transform.symbol_engine_opt 0.77% : 0.005016s : 1: opt_a 0.04% : 0.000267s : 1: opt_after_cconv 0.12% : 0.000754s : 1: opt_after_jit_grad 0.12% : 0.000769s : 1: opt_b 1.42% : 0.009246s : 1: optimize 0.01% : 0.000039s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000014s : 1: order_py_execute_after_rewriter 0.01% : 0.000042s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000017s : 1: overlap_grad_ring_attention 0.00% : 0.000007s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000007s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 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% : 0.000011s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000048s : 1: pre_auto_parallel 0.01% : 0.000050s : 1: py_interpret_to_execute 0.00% : 0.000032s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000086s : 1: remove_dup_value 0.11% : 0.000712s : 1: renormalize.infer 0.09% : 0.000570s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000228s : 1: rewriter_after_opt_a 0.01% : 0.000084s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000016s : 1: swap_dp_allreduce_reducescatter 0.05% : 0.000342s : 1: symbol_engine_optimizer 0.02% : 0.000160s : 1: tuple_transform 1.13% : 0.007341s : 1: type_inference . [hook] pytest_runtest_teardown:test_qbmm_add[True-True-input_shape0] tests/st/infer/ops/test_internal_ops/test_quant_bmm.py::test_qbmm_add[True-True-input_shape0],max_mem:24.0M [WARNING] ME(169497:281473358380848,MainProcess):2026-01-29-17:39:01.828.424 [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 = 0.436914, [21] [bootstrap]: 0.00061971 [type_inference]: 0.212514 [event_method]: 1.822e-05 [auto_monad]: 0.00025161 [graph_reusing]: 6.67002e-06 [inline]: 2.57001e-06 [add_attr]: 0.00611093, [1] [add_attr_with_inline]: 0.00608275, [1] [Cycle 1]: 8.03e-05, [2] [tag_attr]: 2.883e-05 [meta_addattr_fg_expand]: 4.65999e-06 [parallel-infer-symbol]: 4.27e-06 [pre_auto_parallel]: 4.334e-05 [insert-virtual-dataset]: 3.3e-06 [parallel-infer-symbol-second]: 7.2e-07 [dataset_repeat_opt]: 2.09e-06 [pipeline_split]: 1.89e-06 [optimize]: 0.216249, [53] [py_interpret_to_execute]: 3.902e-05 [rewriter_before_opt_a]: 8.127e-05 [opt_a]: 0.0052421, [2] [Cycle 1]: 0.00357346, [45] [expand_dump_flag]: 3.27997e-06 [switch_simplify]: 3.334e-05 [loop_unroll]: 1.998e-05 [a_1]: 0.00072518 [with_stream_mark]: 2.996e-05 [recompute_prepare]: 2.103e-05 [updatestate_depend_eliminate]: 1.006e-05 [updatestate_assign_eliminate]: 1.086e-05 [updatestate_loads_eliminate]: 1.533e-05 [parameter_eliminate]: 2.05002e-06 [a_2]: 0.00025532 [accelerated_algorithm]: 5.453e-05 [shard]: 2.17999e-06 [meta_shard_fg_expand]: 4.63999e-06 [shard_inline]: 1.831e-05 [merge_send_recv]: 1.689e-05 [auto_parallel]: 1.511e-05 [parallel]: 3.97e-05 [flash_sp]: 1.486e-05 [merge_comm]: 1.05e-05 [allreduce_fusion]: 1.203e-05 [matmul_add_comm_reduction]: 2.232e-05 [allreduce_slice_to_reducescatter]: 1.12999e-06 [virtual_shard_identity]: 2.703e-05 [virtual_dataset]: 1.538e-05 [get_grad_eliminate_]: 1.383e-05 [virtual_output]: 1.692e-05 [merge_forward]: 1.09e-05 [cell_reuse_recompute_pass]: 2.91999e-06 [offload_activation]: 2.08e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.667e-05 [merge_recompute_call_nodes]: 1.96e-06 [before_grad]: 2.956e-05 [set_forward_comm_id_for_comm_node_pass]: 1.615e-05 [meta_fg_expand]: 7.08e-06 [flash_sp_send_recv_attached]: 6.25997e-06 [receive_attached]: 2.24999e-06 [after_resolve]: 2.518e-05 [a_after_grad]: 2.412e-05 [renormalize]: 0.00135305 [add_forward_monad_depend]: 8.79998e-06 [auto_monad_grad]: 3.51001e-06 [auto_monad_eliminator]: 5.588e-05 [cse]: 0.00010096 [a_3]: 0.00012121 [Cycle 2]: 0.00165408, [45] [expand_dump_flag]: 3.22002e-06 [switch_simplify]: 1.966e-05 [loop_unroll]: 1.757e-05 [a_1]: 0.00045229 [with_stream_mark]: 2.834e-05 [recompute_prepare]: 2.145e-05 [updatestate_depend_eliminate]: 1.158e-05 [updatestate_assign_eliminate]: 1.041e-05 [updatestate_loads_eliminate]: 1.424e-05 [parameter_eliminate]: 2.07001e-06 [a_2]: 0.0002338 [accelerated_algorithm]: 2.229e-05 [shard]: 2.19999e-06 [meta_shard_fg_expand]: 5.59e-06 [shard_inline]: 1.609e-05 [merge_send_recv]: 1.695e-05 [auto_parallel]: 1.586e-05 [parallel]: 1.084e-05 [flash_sp]: 4.78001e-06 [merge_comm]: 1.001e-05 [allreduce_fusion]: 8.3e-06 [matmul_add_comm_reduction]: 1.677e-05 [allreduce_slice_to_reducescatter]: 9.39996e-07 [virtual_shard_identity]: 2.107e-05 [virtual_dataset]: 1.833e-05 [get_grad_eliminate_]: 1.838e-05 [virtual_output]: 1.383e-05 [merge_forward]: 1.024e-05 [cell_reuse_recompute_pass]: 2.94001e-06 [offload_activation]: 1.746e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.114e-05 [merge_recompute_call_nodes]: 1.55999e-06 [before_grad]: 2.631e-05 [set_forward_comm_id_for_comm_node_pass]: 1.006e-05 [meta_fg_expand]: 6.61e-06 [flash_sp_send_recv_attached]: 2.39001e-06 [receive_attached]: 2.31998e-06 [after_resolve]: 2.591e-05 [a_after_grad]: 2.335e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 3.56001e-06 [auto_monad_grad]: 2.53e-06 [auto_monad_eliminator]: 4.895e-05 [cse]: 6.647e-05 [a_3]: 9.97e-05 [py_interpret_to_execute_after_opt_a]: 2.858e-05 [slice_cell_reuse_recomputed_activation]: 3.17002e-06 [rewriter_after_opt_a]: 0.00020088 [convert_after_rewriter]: 1.439e-05 [order_py_execute_after_rewriter]: 1.232e-05 [mutable_eliminate]: 0.00076087 [opt_b]: 0.00053407, [1] [Cycle 1]: 0.00052507, [7] [b_1]: 0.00036518 [b_2]: 1.719e-05 [updatestate_depend_eliminate]: 1.4e-05 [updatestate_assign_eliminate]: 9.65002e-06 [updatestate_loads_eliminate]: 1.353e-05 [renormalize]: 6.39993e-07 [cse]: 6.565e-05 [optimize_parallel_all_gather_comm]: 3.24e-05 [overlap_param_gather]: 2.12999e-06 [cconv]: 3.755e-05 [loop_unroll]: 0.207748 [opt_after_cconv]: 0.00032437, [1] [Cycle 1]: 0.00031381, [7] [c_1]: 0.00012752 [parameter_eliminate]: 7.03e-06 [updatestate_depend_eliminate]: 1.988e-05 [updatestate_assign_eliminate]: 1.017e-05 [updatestate_loads_eliminate]: 1.525e-05 [cse]: 8.694e-05 [renormalize]: 1.09e-06 [remove_dup_value]: 7.705e-05 [tuple_transform]: 0.00015457, [1] [Cycle 1]: 0.00014901, [4] [d_1]: 0.00011079 [none_parameter_eliminate]: 2.55002e-06 [renormalize]: 2.10013e-07 [switch_simplify]: 1.612e-05 [partial_unused_args_eliminate]: 2.62001e-06 [add_recomputation]: 0.00011841 [cse_after_recomputation]: 4.994e-05, [1] [Cycle 1]: 4.493e-05, [1] [cse]: 3.888e-05 [environ_conv]: 1.744e-05 [swap_dp_allreduce_reducescatter]: 1.218e-05 [bias_add_comm_swap]: 3.70998e-06 [label_micro_interleaved_index]: 8.52e-06 [label_fine_grained_interleaved_index]: 2.86999e-06 [merge_cast_opt]: 1.63002e-06 [slice_recompute_activation]: 2.36998e-06 [micro_interleaved_order_control]: 2.84999e-06 [assign_add_opt]: 1.20999e-06 [ForceFp32Comm]: 9.30013e-07 [remove_cast_before_assign_add]: 1.00999e-06 [full_micro_interleaved_order_control]: 1.99e-06 [reorder_send_recv_between_fp_bp]: 2.79999e-06 [comm_op_add_attrs]: 1.04e-06 [add_comm_op_reuse_tag]: 1.02e-06 [interleave_split_concat_branches]: 1.15001e-06 [interleave_parallel_branches]: 1.09e-06 [overlap_opt_shard_in_pipeline]: 1.49e-06 [overlap_opt_shard_grad_in_pipeline]: 2.02001e-06 [control_data_broadcast_order]: 3.143e-05 [grouped_pairwise_exchange_alltoall]: 1.37e-06 [offloading_packed_experts]: 8.22998e-06 [overlap_recompute_and_grad_model_parallel]: 1.163e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.12e-06 [overlap_recompute_allgather_and_fa_grad]: 1.51002e-06 [overlap_recompute_comm]: 2.25002e-06 [overlap_grad_ring_attention]: 7.51999e-06 [overlap_grad_flash_sp]: 3.824e-05 [begin_end_overlap_inline]: 5.10016e-07 [split_matmul_comm_elemetwise]: 2.16998e-06 [split_layernorm_comm]: 1.77999e-06 [handle_group_info]: 1.49e-06 [symbol_engine_optimizer]: 0.00032968, [1] [Cycle 1]: 0.00032416, [6] [build]: 0.00016341 [elim_shapecalc]: 3.095e-05 [elim_not_effective]: 3.212e-05 [opt_reshape]: 2.641e-05 [fold_const_symbol]: 3.457e-05 [renormalize]: 1.99972e-07 [detach_backward]: 2.84001e-06 [pipeline_parallel_scheduler]: 1.90001e-06 [auto_monad_reorder]: 6.045e-05 [get_jit_bprop_graph]: 1.94999e-06 [rewriter_after_jit_bprop_graph]: 5.96e-06 [opt_after_jit_grad]: 0.0007131 [validate]: 8.146e-05 Sums bootstrap : 0.000620s : 0.14% type_inference : 0.212514s : 49.47% event_method : 0.000018s : 0.00% auto_monad : 0.000252s : 0.06% graph_reusing : 0.000007s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000029s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000043s : 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 : 0.000039s : 0.01% optimize.rewriter_before_opt_a : 0.000081s : 0.02% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000053s : 0.01% optimize.opt_a.loop_unroll : 0.000038s : 0.01% optimize.opt_a.a_1 : 0.001177s : 0.27% optimize.opt_a.with_stream_mark : 0.000058s : 0.01% optimize.opt_a.recompute_prepare : 0.000042s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000022s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000021s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000030s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000489s : 0.11% optimize.opt_a.accelerated_algorithm : 0.000077s : 0.02% optimize.opt_a.shard : 0.000004s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000010s : 0.00% optimize.opt_a.shard_inline : 0.000034s : 0.01% optimize.opt_a.merge_send_recv : 0.000034s : 0.01% optimize.opt_a.auto_parallel : 0.000031s : 0.01% optimize.opt_a.parallel : 0.000051s : 0.01% optimize.opt_a.flash_sp : 0.000020s : 0.00% optimize.opt_a.merge_comm : 0.000021s : 0.00% optimize.opt_a.allreduce_fusion : 0.000020s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000039s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000048s : 0.01% optimize.opt_a.virtual_dataset : 0.000034s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000032s : 0.01% optimize.opt_a.virtual_output : 0.000031s : 0.01% optimize.opt_a.merge_forward : 0.000021s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000038s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000068s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000056s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000026s : 0.01% optimize.opt_a.meta_fg_expand : 0.000014s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000009s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000051s : 0.01% optimize.opt_a.a_after_grad : 0.000047s : 0.01% optimize.opt_a.renormalize : 0.001353s : 0.32% optimize.opt_a.add_forward_monad_depend : 0.000012s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000105s : 0.02% optimize.opt_a.cse : 0.000167s : 0.04% optimize.opt_a.a_3 : 0.000221s : 0.05% optimize.py_interpret_to_execute_after_opt_a : 0.000029s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000201s : 0.05% optimize.convert_after_rewriter : 0.000014s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000761s : 0.18% optimize.opt_b.b_1 : 0.000365s : 0.09% optimize.opt_b.b_2 : 0.000017s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000014s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000066s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000032s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000038s : 0.01% optimize.loop_unroll : 0.207748s : 48.36% optimize.opt_after_cconv.c_1 : 0.000128s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000015s : 0.00% optimize.opt_after_cconv.cse : 0.000087s : 0.02% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000077s : 0.02% optimize.tuple_transform.d_1 : 0.000111s : 0.03% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000016s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000118s : 0.03% optimize.cse_after_recomputation.cse : 0.000039s : 0.01% optimize.environ_conv : 0.000017s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000012s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000009s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000031s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000001s : 0.00% optimize.offloading_packed_experts : 0.000008s : 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 : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.00% optimize.overlap_grad_flash_sp : 0.000038s : 0.01% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000163s : 0.04% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000031s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000032s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000026s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000035s : 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 : 0.000060s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000713s : 0.17% validate : 0.000081s : 0.02% Time group info: ------[substitution.] 0.000506 102 25.31% : 0.000128s : 4: substitution.arithmetic_simplify 2.00% : 0.000010s : 2: substitution.depend_value_elim 1.39% : 0.000007s : 8: substitution.elim_not_effective 2.68% : 0.000014s : 8: substitution.fold_const_symbol 2.08% : 0.000011s : 11: substitution.graph_param_transform 26.57% : 0.000134s : 1: substitution.inline 1.84% : 0.000009s : 16: substitution.j_node_and_user_rematch 5.85% : 0.000030s : 4: substitution.less_batch_normalization 1.78% : 0.000009s : 12: substitution.load_eliminater 2.48% : 0.000013s : 16: substitution.remove_not_recompute_node 1.89% : 0.000010s : 6: substitution.replace_old_param 2.28% : 0.000012s : 6: substitution.updatestate_pure_node_eliminater 23.85% : 0.000121s : 8: substitution.updatestate_useless_node_eliminater ------[type_inference.] 0.212438 2 99.58% : 0.211545s : 1: type_inference.infer 0.42% : 0.000893s : 1: type_inference.specialize ------[replace.] 0.000021 1 100.00% : 0.000021s : 1: replace.inline ------[match.] 0.000133 1 100.00% : 0.000133s : 1: match.inline ------[predicate.] 0.000404 2549 0.84% : 0.000003s : 23: predicate.accumulaten_eliminater 1.00% : 0.000004s : 11: predicate.ad_related_special_op_eliminate 0.85% : 0.000003s : 22: predicate.addn_check_dump 0.86% : 0.000003s : 23: predicate.addn_zero_filter 0.82% : 0.000003s : 23: predicate.adjust_all_reduce_mul_add 2.42% : 0.000010s : 45: predicate.arithmetic_simplify 0.90% : 0.000004s : 23: predicate.cast_eliminate 0.79% : 0.000003s : 22: predicate.check_bprop_eliminate 0.72% : 0.000003s : 22: predicate.compare_switch_simplify 0.22% : 0.000001s : 11: predicate.const_output_eliminate 0.89% : 0.000004s : 22: predicate.depend_value_elim 0.82% : 0.000003s : 23: predicate.dict_get_item_const_eliminator 0.87% : 0.000004s : 23: predicate.dict_get_item_eliminator 0.81% : 0.000003s : 23: predicate.dict_set_item_eliminator 1.06% : 0.000004s : 22: predicate.dumpgradient_eliminate 0.27% : 0.000001s : 11: predicate.elim_not_effective 0.48% : 0.000002s : 11: predicate.elim_shapecalc_of_broadcastargs 1.19% : 0.000005s : 34: predicate.environ_add_const_eliminate 1.06% : 0.000004s : 34: predicate.environ_get_add_eliminate 1.13% : 0.000005s : 34: predicate.environ_get_depend_swap 1.95% : 0.000008s : 56: predicate.environ_get_eliminate 1.12% : 0.000005s : 34: predicate.environ_get_set_eliminate 0.75% : 0.000003s : 24: predicate.exchange_switch_depend_value 1.35% : 0.000005s : 24: predicate.float_depend_g_call 0.76% : 0.000003s : 22: predicate.float_environ_get_switch 1.09% : 0.000004s : 33: predicate.float_tuple_getitem_switch 0.21% : 0.000001s : 11: predicate.fold_const_symbol 0.84% : 0.000003s : 22: predicate.get_grad_eliminate 0.31% : 0.000001s : 11: predicate.graph_param_transform 0.72% : 0.000003s : 22: predicate.incorporate_call 0.66% : 0.000003s : 22: predicate.incorporate_call_switch 5.72% : 0.000023s : 113: predicate.inline 1.17% : 0.000005s : 22: predicate.inline_without_move 0.40% : 0.000002s : 22: predicate.j_node_and_user_rematch 1.10% : 0.000004s : 22: predicate.less_batch_normalization 1.67% : 0.000007s : 45: predicate.list_to_tuple_eliminator_ 2.44% : 0.000010s : 68: predicate.load_eliminater 2.54% : 0.000010s : 11: predicate.loop_unroll_after_grad 1.02% : 0.000004s : 27: predicate.loop_unroll_before_grad 1.95% : 0.000008s : 45: predicate.make_slice_get_slice_eliminator 0.81% : 0.000003s : 22: predicate.merge_addn 0.76% : 0.000003s : 22: predicate.micro_step_allgather_replace 0.77% : 0.000003s : 22: predicate.mini_step_allgather_replace 0.73% : 0.000003s : 23: predicate.minmaximum_grad 1.08% : 0.000004s : 11: predicate.mutable_eliminate 0.48% : 0.000002s : 11: predicate.opt_reshape 0.47% : 0.000002s : 11: predicate.parallel_virtual_node 1.08% : 0.000004s : 24: predicate.partial_defer_inline 1.26% : 0.000005s : 34: predicate.partial_eliminate 0.81% : 0.000003s : 23: predicate.print_const_string_wrapper 0.83% : 0.000003s : 22: predicate.reduce_all_const_elim 1.20% : 0.000005s : 23: predicate.reduce_eliminate 2.27% : 0.000009s : 68: predicate.redundant_stop_gradient_eliminater 0.68% : 0.000003s : 22: predicate.remove_not_recompute_node 1.14% : 0.000005s : 45: predicate.replace_applicator 0.54% : 0.000002s : 22: predicate.replace_old_param 0.31% : 0.000001s : 11: predicate.reset_defer_inline 0.85% : 0.000003s : 23: predicate.reshape_eliminate 0.87% : 0.000004s : 22: predicate.row_tensor_add_zeros_like 0.44% : 0.000002s : 11: predicate.row_tensor_eliminate 0.92% : 0.000004s : 22: predicate.same_eliminate 0.66% : 0.000003s : 22: predicate.set_cell_output_no_recompute 0.95% : 0.000004s : 22: predicate.shard_identity_eliminate 0.95% : 0.000004s : 22: predicate.special_op_eliminate 0.87% : 0.000004s : 22: predicate.specialize_transform 1.38% : 0.000006s : 22: predicate.split_environ_get_set_with_tuple_value 1.13% : 0.000005s : 22: predicate.stack_unstack_eliminate 0.48% : 0.000002s : 11: predicate.switch_call_monad_eliminater 0.83% : 0.000003s : 24: predicate.switch_defer_inline 1.59% : 0.000006s : 46: predicate.switch_layer_defer_inline 3.28% : 0.000013s : 84: predicate.switch_simplify 0.81% : 0.000003s : 23: predicate.tile_eliminate 0.79% : 0.000003s : 23: predicate.transpose_eliminate 1.72% : 0.000007s : 45: predicate.tuple_list_convert_item_index_to_positive 1.67% : 0.000007s : 45: predicate.tuple_list_get_item_const_eliminator 1.67% : 0.000007s : 45: predicate.tuple_list_get_item_depend_reorder 2.88% : 0.000012s : 67: predicate.tuple_list_get_item_eliminator 1.64% : 0.000007s : 45: predicate.tuple_list_get_set_item_eliminator 2.46% : 0.000010s : 67: predicate.tuple_list_set_item_eliminator 1.61% : 0.000007s : 45: predicate.tuple_to_list_eliminator_ 2.19% : 0.000009s : 68: predicate.updatestate_pure_node_eliminater 3.26% : 0.000013s : 90: predicate.updatestate_useless_node_eliminater 0.51% : 0.000002s : 11: predicate.value_based_eliminate 0.93% : 0.000004s : 22: predicate.virtual_dataset_eliminate 0.80% : 0.000003s : 22: predicate.virtual_output_eliminate 0.39% : 0.000002s : 11: predicate.virtual_view_grad_eliminate 0.48% : 0.000002s : 11: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000518 4 4.75% : 0.000025s : 1: func_graph_cloner_run.FuncGraphClonerGraph 95.25% : 0.000493s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.663627 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.92% : 0.006118s : 1: add_attr 0.92% : 0.006087s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000123s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.04% : 0.000260s : 1: auto_monad 0.01% : 0.000065s : 1: auto_monad_reorder 0.00% : 0.000006s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.10% : 0.000656s : 1: bootstrap 0.01% : 0.000041s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000035s : 1: control_data_broadcast_order 0.00% : 0.000018s : 1: convert_after_rewriter 0.01% : 0.000053s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000021s : 1: environ_conv 0.00% : 0.000026s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.01% : 0.000043s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 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% : 0.000012s : 1: label_micro_interleaved_index 31.31% : 0.207767s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.12% : 0.000771s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.01% : 0.000055s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000029s : 1: opt.transform.mutable_eliminate 0.36% : 0.002371s : 78: opt.transform.opt_a 0.02% : 0.000125s : 1: opt.transform.opt_after_cconv 0.01% : 0.000057s : 1: opt.transform.opt_after_jit_grad 0.05% : 0.000349s : 28: opt.transform.opt_b 0.02% : 0.000124s : 2: opt.transform.opt_trans_graph 0.02% : 0.000119s : 4: opt.transform.symbol_engine_opt 0.79% : 0.005246s : 1: opt_a 0.05% : 0.000329s : 1: opt_after_cconv 0.11% : 0.000724s : 1: opt_after_jit_grad 0.08% : 0.000539s : 1: opt_b 32.59% : 0.216255s : 1: optimize 0.01% : 0.000036s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000016s : 1: order_py_execute_after_rewriter 0.01% : 0.000042s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000007s : 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% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000048s : 1: pre_auto_parallel 0.01% : 0.000043s : 1: py_interpret_to_execute 0.00% : 0.000032s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000081s : 1: remove_dup_value 0.11% : 0.000750s : 1: renormalize.infer 0.09% : 0.000589s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.000207s : 1: rewriter_after_opt_a 0.01% : 0.000086s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.05% : 0.000333s : 1: symbol_engine_optimizer 0.02% : 0.000158s : 1: tuple_transform 32.03% : 0.212537s : 1: type_inference . [hook] pytest_runtest_teardown:test_qbmm_add[True-True-input_shape1] tests/st/infer/ops/test_internal_ops/test_quant_bmm.py::test_qbmm_add[True-True-input_shape1],max_mem:24.0M =============================== warnings summary =============================== ../../../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/classifier/transdata/transdata_classifier.py:222 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/classifier/transdata/transdata_classifier.py:222: DeprecationWarning: invalid escape sequence \B """ ../../../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:143 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:143: DeprecationWarning: invalid escape sequence \c """ ../../../../../../../../../../usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:170 /usr/local/Ascend/cann-8.5.0/python/site-packages/tbe/dsl/unify_schedule/vector/transdata/common/graph/transdata_graph_info.py:170: DeprecationWarning: invalid escape sequence \c """ ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for type is zero. setattr(self, word, getattr(machar, word).flat[0]) ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for type is zero. setattr(self, word, getattr(machar, word).flat[0]) ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2.py:57 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2.py:57: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad.py:56 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad.py:56: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2_grad") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad_reduce.py:48 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/batchnorm_fold2_grad_reduce.py:48: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("batchnorm_fold2_grad_reduce") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul.py:51 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul.py:51: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:51 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:51: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul_grad") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:143 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/correction_mul_grad.py:143: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("correction_mul_grad_reduce") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad.py:92 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad.py:92: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer_grad_d") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad_reduce.py:49 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perlayer_grad_reduce.py:49: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perlayer_grad_d_reduce") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad.py:91 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad.py:91: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel_grad_d") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad_reduce.py:48 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_learned_scale_quant_perchannel_grad_reduce.py:48: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_learned_scale_quant_perchannel_grad_d_reduce") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel.py:52 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel.py:52: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_perchannel") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel_grad.py:81 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perchannel_grad.py:81: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_perchannel_grad") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer.py:54 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer.py:54: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_per_layer") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer_grad.py:81 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/fake_quant_perlayer_grad.py:81: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("fake_quant_per_layer_grad") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perchannel.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perchannel.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("minmax_update_perchannel") ../../../../../../../../anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perlayer.py:50 /home/jenkins/anaconda3/envs/ci39/lib/python3.9/site-packages/mindspore/ops/_op_impl/_custom_op/minmax_update_perlayer.py:50: DeprecationWarning: te_fusion.fusion_manager.fusion_manager.register is deprecated,please replace it with tbe.common.register.register_op_compute @fusion_manager.register("minmax_update_perlayer") -- Docs: https://docs.pytest.org/en/stable/warnings.html ================== 8 passed, 25 warnings in 136.12s (0:02:16) ==================