==================================================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_004/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 2 items test_matmul_qkv_silu.py [WARNING] ME(160016:281473300533040,MainProcess):2026-01-29-17:37:17.882.050 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 1.16704, [21] [bootstrap]: 0.00068245 [type_inference]: 1.0616 [event_method]: 3.031e-05 [auto_monad]: 0.00155669 [graph_reusing]: 9.61e-06 [inline]: 3.91999e-06 [add_attr]: 0.0175095, [1] [add_attr_with_inline]: 0.0174922, [1] [Cycle 1]: 0.00013869, [2] [tag_attr]: 4.324e-05 [meta_addattr_fg_expand]: 8.85999e-06 [parallel-infer-symbol]: 4.1e-06 [pre_auto_parallel]: 7.127e-05 [insert-virtual-dataset]: 2.91e-06 [parallel-infer-symbol-second]: 1.02e-06 [dataset_repeat_opt]: 2.21e-06 [pipeline_split]: 1.70001e-06 [optimize]: 0.0841983, [53] [py_interpret_to_execute]: 4.695e-05 [rewriter_before_opt_a]: 0.00016941 [opt_a]: 0.0793121, [2] [Cycle 1]: 0.0771356, [45] [expand_dump_flag]: 3.9e-06 [switch_simplify]: 6.588e-05 [loop_unroll]: 4.693e-05 [a_1]: 0.00162287 [with_stream_mark]: 4.368e-05 [recompute_prepare]: 3.832e-05 [updatestate_depend_eliminate]: 6.249e-05 [updatestate_assign_eliminate]: 1.319e-05 [updatestate_loads_eliminate]: 1.325e-05 [parameter_eliminate]: 3.25998e-06 [a_2]: 0.00034603 [accelerated_algorithm]: 5.727e-05 [shard]: 3.41001e-06 [meta_shard_fg_expand]: 6.06e-06 [shard_inline]: 2.223e-05 [merge_send_recv]: 1.813e-05 [auto_parallel]: 1.942e-05 [parallel]: 6.279e-05 [flash_sp]: 1.625e-05 [merge_comm]: 1.314e-05 [allreduce_fusion]: 1.109e-05 [matmul_add_comm_reduction]: 2.097e-05 [allreduce_slice_to_reducescatter]: 1.14998e-06 [virtual_shard_identity]: 2.761e-05 [virtual_dataset]: 2.11e-05 [get_grad_eliminate_]: 2.009e-05 [virtual_output]: 2.1e-05 [merge_forward]: 1.285e-05 [cell_reuse_recompute_pass]: 2.33998e-06 [offload_activation]: 2.177e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.596e-05 [merge_recompute_call_nodes]: 2.14999e-06 [before_grad]: 3.805e-05 [set_forward_comm_id_for_comm_node_pass]: 1.323e-05 [meta_fg_expand]: 1.024e-05 [flash_sp_send_recv_attached]: 6.19001e-06 [receive_attached]: 2.37999e-06 [after_resolve]: 3.012e-05 [a_after_grad]: 3.429e-05 [renormalize]: 0.0733589 [add_forward_monad_depend]: 3.754e-05 [auto_monad_grad]: 2.54999e-06 [auto_monad_eliminator]: 7.538e-05 [cse]: 0.0002414 [a_3]: 0.00016951 [Cycle 2]: 0.00215944, [45] [expand_dump_flag]: 3.35e-06 [switch_simplify]: 2.463e-05 [loop_unroll]: 2.091e-05 [a_1]: 0.00064003 [with_stream_mark]: 3.444e-05 [recompute_prepare]: 2.474e-05 [updatestate_depend_eliminate]: 1.251e-05 [updatestate_assign_eliminate]: 1.035e-05 [updatestate_loads_eliminate]: 1.243e-05 [parameter_eliminate]: 2.44001e-06 [a_2]: 0.00031651 [accelerated_algorithm]: 3.152e-05 [shard]: 2.88003e-06 [meta_shard_fg_expand]: 6.17999e-06 [shard_inline]: 2.214e-05 [merge_send_recv]: 1.964e-05 [auto_parallel]: 1.858e-05 [parallel]: 1.058e-05 [flash_sp]: 5.24998e-06 [merge_comm]: 1.163e-05 [allreduce_fusion]: 1.049e-05 [matmul_add_comm_reduction]: 2.212e-05 [allreduce_slice_to_reducescatter]: 8.60018e-07 [virtual_shard_identity]: 2.639e-05 [virtual_dataset]: 2.102e-05 [get_grad_eliminate_]: 2.087e-05 [virtual_output]: 1.994e-05 [merge_forward]: 1.203e-05 [cell_reuse_recompute_pass]: 4.28001e-06 [offload_activation]: 2.133e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.387e-05 [merge_recompute_call_nodes]: 1.55999e-06 [before_grad]: 3.666e-05 [set_forward_comm_id_for_comm_node_pass]: 1.388e-05 [meta_fg_expand]: 9.19998e-06 [flash_sp_send_recv_attached]: 1.89e-06 [receive_attached]: 2.96001e-06 [after_resolve]: 2.903e-05 [a_after_grad]: 3.221e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 5.54e-06 [auto_monad_grad]: 3.38e-06 [auto_monad_eliminator]: 6.743e-05 [cse]: 7.825e-05 [a_3]: 0.00013981 [py_interpret_to_execute_after_opt_a]: 3.267e-05 [slice_cell_reuse_recomputed_activation]: 3.35e-06 [rewriter_after_opt_a]: 0.00048607 [convert_after_rewriter]: 2.52e-05 [order_py_execute_after_rewriter]: 1.109e-05 [mutable_eliminate]: 0.00085431 [opt_b]: 0.00082814, [1] [Cycle 1]: 0.00081765, [7] [b_1]: 0.00056563 [b_2]: 2.997e-05 [updatestate_depend_eliminate]: 2.002e-05 [updatestate_assign_eliminate]: 1.078e-05 [updatestate_loads_eliminate]: 1.347e-05 [renormalize]: 1.59e-06 [cse]: 0.00010891 [optimize_parallel_all_gather_comm]: 4.141e-05 [overlap_param_gather]: 2.12999e-06 [cconv]: 4.404e-05 [loop_unroll]: 0.00065076 [opt_after_cconv]: 0.00031806, [1] [Cycle 1]: 0.00030861, [7] [c_1]: 0.00013543 [parameter_eliminate]: 6.74999e-06 [updatestate_depend_eliminate]: 1.792e-05 [updatestate_assign_eliminate]: 9.82999e-06 [updatestate_loads_eliminate]: 1.277e-05 [cse]: 8.004e-05 [renormalize]: 7.50006e-07 [remove_dup_value]: 8.552e-05 [tuple_transform]: 0.00026215, [1] [Cycle 1]: 0.00025456, [4] [d_1]: 0.00019438 [none_parameter_eliminate]: 2.74001e-06 [renormalize]: 2.79979e-07 [switch_simplify]: 2.519e-05 [partial_unused_args_eliminate]: 2.32001e-06 [add_recomputation]: 0.00014917 [cse_after_recomputation]: 7.671e-05, [1] [Cycle 1]: 6.898e-05, [1] [cse]: 5.623e-05 [environ_conv]: 3.963e-05 [swap_dp_allreduce_reducescatter]: 1.58e-05 [bias_add_comm_swap]: 3.14001e-06 [label_micro_interleaved_index]: 6.86001e-06 [label_fine_grained_interleaved_index]: 2.83e-06 [merge_cast_opt]: 1.40001e-06 [slice_recompute_activation]: 2.30002e-06 [micro_interleaved_order_control]: 2.26998e-06 [assign_add_opt]: 1.85001e-06 [ForceFp32Comm]: 9.10019e-07 [remove_cast_before_assign_add]: 1.32999e-06 [full_micro_interleaved_order_control]: 2.73e-06 [reorder_send_recv_between_fp_bp]: 2.84999e-06 [comm_op_add_attrs]: 1.20001e-06 [add_comm_op_reuse_tag]: 9.60019e-07 [interleave_split_concat_branches]: 1.24998e-06 [interleave_parallel_branches]: 1.00999e-06 [overlap_opt_shard_in_pipeline]: 2.369e-05 [overlap_opt_shard_grad_in_pipeline]: 2.22999e-06 [control_data_broadcast_order]: 3.958e-05 [grouped_pairwise_exchange_alltoall]: 1.50999e-06 [offloading_packed_experts]: 9.14998e-06 [overlap_recompute_and_grad_model_parallel]: 1.015e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.58002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.42e-06 [overlap_recompute_comm]: 2.34999e-06 [overlap_grad_ring_attention]: 8.65001e-06 [overlap_grad_flash_sp]: 6.672e-05 [begin_end_overlap_inline]: 8.30012e-07 [split_matmul_comm_elemetwise]: 2.43e-06 [split_layernorm_comm]: 1.69e-06 [handle_group_info]: 1.12e-06 [symbol_engine_optimizer]: 0.00021393, [1] [Cycle 1]: 0.00020513, [6] [build]: 2.35e-05 [elim_shapecalc]: 3.548e-05 [elim_not_effective]: 4.205e-05 [opt_reshape]: 2.613e-05 [fold_const_symbol]: 3.434e-05 [renormalize]: 4.69998e-07 [detach_backward]: 2.34001e-06 [pipeline_parallel_scheduler]: 2.30002e-06 [auto_monad_reorder]: 6.404e-05 [get_jit_bprop_graph]: 3.06001e-06 [rewriter_after_jit_bprop_graph]: 6.38e-06 [opt_after_jit_grad]: 0.00089638 [validate]: 0.00013508 Sums bootstrap : 0.000682s : 0.06% type_inference : 1.061595s : 92.47% event_method : 0.000030s : 0.00% auto_monad : 0.001557s : 0.14% graph_reusing : 0.000010s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000043s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000009s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000071s : 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 : 0.000047s : 0.00% optimize.rewriter_before_opt_a : 0.000169s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000091s : 0.01% optimize.opt_a.loop_unroll : 0.000068s : 0.01% optimize.opt_a.a_1 : 0.002263s : 0.20% optimize.opt_a.with_stream_mark : 0.000078s : 0.01% optimize.opt_a.recompute_prepare : 0.000063s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000075s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000024s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000026s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000663s : 0.06% optimize.opt_a.accelerated_algorithm : 0.000089s : 0.01% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000012s : 0.00% optimize.opt_a.shard_inline : 0.000044s : 0.00% optimize.opt_a.merge_send_recv : 0.000038s : 0.00% optimize.opt_a.auto_parallel : 0.000038s : 0.00% optimize.opt_a.parallel : 0.000073s : 0.01% optimize.opt_a.flash_sp : 0.000021s : 0.00% optimize.opt_a.merge_comm : 0.000025s : 0.00% optimize.opt_a.allreduce_fusion : 0.000022s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000043s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000054s : 0.00% optimize.opt_a.virtual_dataset : 0.000042s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000041s : 0.00% optimize.opt_a.virtual_output : 0.000041s : 0.00% optimize.opt_a.merge_forward : 0.000025s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000007s : 0.00% optimize.opt_a.offload_activation : 0.000043s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000090s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000075s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000027s : 0.00% optimize.opt_a.meta_fg_expand : 0.000019s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000059s : 0.01% optimize.opt_a.a_after_grad : 0.000067s : 0.01% optimize.opt_a.renormalize : 0.073359s : 6.39% optimize.opt_a.add_forward_monad_depend : 0.000043s : 0.00% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000143s : 0.01% optimize.opt_a.cse : 0.000320s : 0.03% optimize.opt_a.a_3 : 0.000309s : 0.03% optimize.py_interpret_to_execute_after_opt_a : 0.000033s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000486s : 0.04% optimize.convert_after_rewriter : 0.000025s : 0.00% optimize.order_py_execute_after_rewriter : 0.000011s : 0.00% optimize.mutable_eliminate : 0.000854s : 0.07% optimize.opt_b.b_1 : 0.000566s : 0.05% optimize.opt_b.b_2 : 0.000030s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_b.renormalize : 0.000002s : 0.00% optimize.opt_b.cse : 0.000109s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000041s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000044s : 0.00% optimize.loop_unroll : 0.000651s : 0.06% optimize.opt_after_cconv.c_1 : 0.000135s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000018s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.cse : 0.000080s : 0.01% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000086s : 0.01% optimize.tuple_transform.d_1 : 0.000194s : 0.02% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000025s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000149s : 0.01% optimize.cse_after_recomputation.cse : 0.000056s : 0.00% optimize.environ_conv : 0.000040s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000016s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000024s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000040s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000009s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000010s : 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 : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000009s : 0.00% optimize.overlap_grad_flash_sp : 0.000067s : 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 : 0.000024s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000035s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000042s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000026s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000034s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000064s : 0.01% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000896s : 0.08% validate : 0.000135s : 0.01% Time group info: ------[substitution.] 0.000747 196 1.42% : 0.000011s : 2: substitution.depend_value_elim 0.81% : 0.000006s : 12: substitution.elim_not_effective 1.89% : 0.000014s : 6: substitution.float_tuple_getitem_switch 0.63% : 0.000005s : 12: substitution.fold_const_symbol 2.13% : 0.000016s : 17: substitution.graph_param_transform 47.95% : 0.000358s : 7: substitution.inline 1.82% : 0.000014s : 24: substitution.j_node_and_user_rematch 3.46% : 0.000026s : 2: substitution.less_batch_normalization 0.91% : 0.000007s : 6: substitution.load_eliminater 1.66% : 0.000012s : 4: substitution.minmaximum_grad 0.24% : 0.000002s : 2: substitution.opt_reshape 2.49% : 0.000019s : 24: substitution.remove_not_recompute_node 1.20% : 0.000009s : 4: substitution.replace_old_param 3.35% : 0.000025s : 4: substitution.reshape_eliminate 4.70% : 0.000035s : 8: substitution.tuple_list_convert_item_index_to_positive 3.56% : 0.000027s : 8: substitution.tuple_list_get_item_const_eliminator 3.21% : 0.000024s : 8: substitution.tuple_list_get_item_depend_reorder 8.14% : 0.000061s : 12: substitution.tuple_list_get_item_eliminator 3.03% : 0.000023s : 8: substitution.tuple_list_get_set_item_eliminator 3.82% : 0.000029s : 12: substitution.updatestate_pure_node_eliminater 3.59% : 0.000027s : 14: substitution.updatestate_useless_node_eliminater ------[type_inference.] 1.061468 2 99.51% : 1.056303s : 1: type_inference.infer 0.49% : 0.005165s : 1: type_inference.specialize ------[replace.] 0.000095 7 100.00% : 0.000095s : 7: replace.inline ------[match.] 0.000353 7 100.00% : 0.000353s : 7: match.inline ------[predicate.] 0.000702 4469 0.91% : 0.000006s : 45: predicate.accumulaten_eliminater 0.88% : 0.000006s : 17: predicate.ad_related_special_op_eliminate 0.73% : 0.000005s : 34: predicate.addn_check_dump 0.90% : 0.000006s : 45: predicate.addn_zero_filter 0.84% : 0.000006s : 45: predicate.adjust_all_reduce_mul_add 1.98% : 0.000014s : 79: predicate.arithmetic_simplify 0.90% : 0.000006s : 45: predicate.cast_eliminate 0.78% : 0.000005s : 34: predicate.check_bprop_eliminate 0.70% : 0.000005s : 34: predicate.compare_switch_simplify 0.21% : 0.000001s : 17: predicate.const_output_eliminate 0.75% : 0.000005s : 34: predicate.depend_value_elim 0.94% : 0.000007s : 45: predicate.dict_get_item_const_eliminator 0.99% : 0.000007s : 45: predicate.dict_get_item_eliminator 0.88% : 0.000006s : 45: predicate.dict_set_item_eliminator 0.97% : 0.000007s : 34: predicate.dumpgradient_eliminate 0.22% : 0.000002s : 17: predicate.elim_not_effective 0.46% : 0.000003s : 17: predicate.elim_shapecalc_of_broadcastargs 1.21% : 0.000008s : 62: predicate.environ_add_const_eliminate 1.19% : 0.000008s : 62: predicate.environ_get_add_eliminate 1.16% : 0.000008s : 62: predicate.environ_get_depend_swap 1.96% : 0.000014s : 96: predicate.environ_get_eliminate 1.19% : 0.000008s : 62: predicate.environ_get_set_eliminate 1.03% : 0.000007s : 52: predicate.exchange_switch_depend_value 1.58% : 0.000011s : 52: predicate.float_depend_g_call 0.68% : 0.000005s : 34: predicate.float_environ_get_switch 1.18% : 0.000008s : 51: predicate.float_tuple_getitem_switch 0.19% : 0.000001s : 17: predicate.fold_const_symbol 0.77% : 0.000005s : 34: predicate.get_grad_eliminate 0.24% : 0.000002s : 17: predicate.graph_param_transform 0.73% : 0.000005s : 34: predicate.incorporate_call 0.64% : 0.000004s : 34: predicate.incorporate_call_switch 5.99% : 0.000042s : 199: predicate.inline 0.98% : 0.000007s : 34: predicate.inline_without_move 0.36% : 0.000003s : 34: predicate.j_node_and_user_rematch 1.09% : 0.000008s : 36: predicate.less_batch_normalization 1.64% : 0.000012s : 79: predicate.list_to_tuple_eliminator_ 2.38% : 0.000017s : 124: predicate.load_eliminater 0.95% : 0.000007s : 17: predicate.loop_unroll_after_grad 1.36% : 0.000010s : 67: predicate.loop_unroll_before_grad 1.76% : 0.000012s : 79: predicate.make_slice_get_slice_eliminator 0.70% : 0.000005s : 34: predicate.merge_addn 0.69% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.69% : 0.000005s : 34: predicate.mini_step_allgather_replace 0.86% : 0.000006s : 45: predicate.minmaximum_grad 1.06% : 0.000007s : 17: predicate.mutable_eliminate 0.44% : 0.000003s : 17: predicate.opt_reshape 0.39% : 0.000003s : 17: predicate.parallel_virtual_node 1.58% : 0.000011s : 52: predicate.partial_defer_inline 1.41% : 0.000010s : 62: predicate.partial_eliminate 0.91% : 0.000006s : 45: predicate.print_const_string_wrapper 0.69% : 0.000005s : 34: predicate.reduce_all_const_elim 1.10% : 0.000008s : 45: predicate.reduce_eliminate 2.39% : 0.000017s : 124: predicate.redundant_stop_gradient_eliminater 0.45% : 0.000003s : 34: predicate.remove_not_recompute_node 1.26% : 0.000009s : 79: predicate.replace_applicator 0.46% : 0.000003s : 34: predicate.replace_old_param 0.28% : 0.000002s : 17: predicate.reset_defer_inline 0.95% : 0.000007s : 45: predicate.reshape_eliminate 0.72% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.51% : 0.000004s : 17: predicate.row_tensor_eliminate 0.95% : 0.000007s : 34: predicate.same_eliminate 0.54% : 0.000004s : 38: predicate.set_cell_output_no_recompute 1.04% : 0.000007s : 34: predicate.shard_identity_eliminate 0.78% : 0.000005s : 34: predicate.special_op_eliminate 0.88% : 0.000006s : 34: predicate.specialize_transform 0.98% : 0.000007s : 34: predicate.split_environ_get_set_with_tuple_value 0.91% : 0.000006s : 34: predicate.stack_unstack_eliminate 0.41% : 0.000003s : 17: predicate.switch_call_monad_eliminater 1.13% : 0.000008s : 52: predicate.switch_defer_inline 1.79% : 0.000013s : 86: predicate.switch_layer_defer_inline 3.91% : 0.000027s : 170: predicate.switch_simplify 0.89% : 0.000006s : 45: predicate.tile_eliminate 0.87% : 0.000006s : 45: predicate.transpose_eliminate 1.69% : 0.000012s : 79: predicate.tuple_list_convert_item_index_to_positive 1.93% : 0.000014s : 79: predicate.tuple_list_get_item_const_eliminator 1.71% : 0.000012s : 79: predicate.tuple_list_get_item_depend_reorder 3.33% : 0.000023s : 113: predicate.tuple_list_get_item_eliminator 1.87% : 0.000013s : 79: predicate.tuple_list_get_set_item_eliminator 2.45% : 0.000017s : 113: predicate.tuple_list_set_item_eliminator 1.68% : 0.000012s : 79: predicate.tuple_to_list_eliminator_ 2.43% : 0.000017s : 124: predicate.updatestate_pure_node_eliminater 3.27% : 0.000023s : 158: predicate.updatestate_useless_node_eliminater 0.40% : 0.000003s : 17: predicate.value_based_eliminate 0.76% : 0.000005s : 34: predicate.virtual_dataset_eliminate 0.76% : 0.000005s : 34: predicate.virtual_output_eliminate 0.33% : 0.000002s : 17: predicate.virtual_view_grad_eliminate 0.48% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.011128 64 77.17% : 0.008588s : 55: func_graph_cloner_run.FuncGraphClonerGraph 22.83% : 0.002540s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.346939 192 0.00% : 0.000004s : 1: ForceFp32Comm 1.30% : 0.017516s : 1: add_attr 1.30% : 0.017497s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000159s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.12% : 0.001595s : 1: auto_monad 0.01% : 0.000073s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.05% : 0.000720s : 1: bootstrap 0.00% : 0.000049s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000044s : 1: control_data_broadcast_order 0.00% : 0.000032s : 1: convert_after_rewriter 0.01% : 0.000080s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000046s : 1: environ_conv 0.00% : 0.000040s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000016s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.05% : 0.000669s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.06% : 0.000873s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.00% : 0.000042s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000048s : 1: opt.transform.mutable_eliminate 0.29% : 0.003912s : 78: opt.transform.opt_a 0.01% : 0.000133s : 1: opt.transform.opt_after_cconv 0.01% : 0.000079s : 1: opt.transform.opt_after_jit_grad 0.04% : 0.000550s : 28: opt.transform.opt_b 0.02% : 0.000215s : 2: opt.transform.opt_trans_graph 0.01% : 0.000132s : 4: opt.transform.symbol_engine_opt 5.89% : 0.079316s : 1: opt_a 0.02% : 0.000323s : 1: opt_after_cconv 0.07% : 0.000919s : 1: opt_after_jit_grad 0.06% : 0.000832s : 1: opt_b 6.25% : 0.084204s : 1: optimize 0.00% : 0.000047s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000014s : 1: order_py_execute_after_rewriter 0.01% : 0.000074s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000028s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000014s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000007s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000007s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000077s : 1: pre_auto_parallel 0.00% : 0.000053s : 1: py_interpret_to_execute 0.00% : 0.000038s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000091s : 1: remove_dup_value 5.23% : 0.070463s : 1: renormalize.infer 0.21% : 0.002878s : 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% : 0.000501s : 1: rewriter_after_opt_a 0.01% : 0.000177s : 1: rewriter_before_opt_a 0.00% : 0.000007s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000021s : 1: swap_dp_allreduce_reducescatter 0.02% : 0.000217s : 1: symbol_engine_optimizer 0.02% : 0.000265s : 1: tuple_transform 78.82% : 1.061637s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_3584_3584[False-0-mstype0-1024-1] tests/st/infer/ops/test_internal_ops/test_matmul_qkv_silu.py::test_matmul_ffn_3584_3584[False-0-mstype0-1024-1],max_mem:114.0M [WARNING] ME(160016:281473300533040,MainProcess):2026-01-29-17:37:47.463.669 [mindspore/context.py:1334] For 'context.set_context', the parameter 'device_target' will be deprecated and removed in a future version. Please use the api mindspore.set_device() instead. TotalTime = 1.68487, [21] [bootstrap]: 0.00057459 [type_inference]: 1.49564 [event_method]: 2.901e-05 [auto_monad]: 0.00038231 [graph_reusing]: 7.79002e-06 [inline]: 3.06999e-06 [add_attr]: 0.0203713, [1] [add_attr_with_inline]: 0.0203534, [1] [Cycle 1]: 0.0001, [2] [tag_attr]: 3.985e-05 [meta_addattr_fg_expand]: 8.33001e-06 [parallel-infer-symbol]: 3.81001e-06 [pre_auto_parallel]: 6.236e-05 [insert-virtual-dataset]: 2.71e-06 [parallel-infer-symbol-second]: 1.03001e-06 [dataset_repeat_opt]: 1.95001e-06 [pipeline_split]: 1.72999e-06 [optimize]: 0.130112, [53] [py_interpret_to_execute]: 4.652e-05 [rewriter_before_opt_a]: 0.00018064 [opt_a]: 0.125346, [2] [Cycle 1]: 0.123165, [45] [expand_dump_flag]: 3.22002e-06 [switch_simplify]: 6.497e-05 [loop_unroll]: 5.038e-05 [a_1]: 0.00204308 [with_stream_mark]: 3.752e-05 [recompute_prepare]: 3.363e-05 [updatestate_depend_eliminate]: 6.015e-05 [updatestate_assign_eliminate]: 1.447e-05 [updatestate_loads_eliminate]: 1.44e-05 [parameter_eliminate]: 2.66e-06 [a_2]: 0.00037412 [accelerated_algorithm]: 5.5e-05 [shard]: 2.85002e-06 [meta_shard_fg_expand]: 5.12999e-06 [shard_inline]: 2.21e-05 [merge_send_recv]: 1.868e-05 [auto_parallel]: 1.916e-05 [parallel]: 2.838e-05 [flash_sp]: 1.317e-05 [merge_comm]: 1.246e-05 [allreduce_fusion]: 1.101e-05 [matmul_add_comm_reduction]: 1.926e-05 [allreduce_slice_to_reducescatter]: 8.2e-07 [virtual_shard_identity]: 2.796e-05 [virtual_dataset]: 2.42e-05 [get_grad_eliminate_]: 2.251e-05 [virtual_output]: 2.469e-05 [merge_forward]: 1.074e-05 [cell_reuse_recompute_pass]: 1.76e-06 [offload_activation]: 2.189e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.604e-05 [merge_recompute_call_nodes]: 1.62001e-06 [before_grad]: 4.127e-05 [set_forward_comm_id_for_comm_node_pass]: 1.226e-05 [meta_fg_expand]: 9.29998e-06 [flash_sp_send_recv_attached]: 4.81002e-06 [receive_attached]: 2.38002e-06 [after_resolve]: 2.912e-05 [a_after_grad]: 4.014e-05 [renormalize]: 0.11835 [add_forward_monad_depend]: 1.24e-05 [auto_monad_grad]: 2.32999e-06 [auto_monad_eliminator]: 7.02e-05 [cse]: 0.00095455 [a_3]: 0.00018126 [Cycle 2]: 0.00216597, [45] [expand_dump_flag]: 3.75e-06 [switch_simplify]: 2.541e-05 [loop_unroll]: 2.203e-05 [a_1]: 0.00066459 [with_stream_mark]: 3.342e-05 [recompute_prepare]: 2.362e-05 [updatestate_depend_eliminate]: 1.318e-05 [updatestate_assign_eliminate]: 1.099e-05 [updatestate_loads_eliminate]: 1.234e-05 [parameter_eliminate]: 3.36001e-06 [a_2]: 0.00033299 [accelerated_algorithm]: 2.989e-05 [shard]: 2.47001e-06 [meta_shard_fg_expand]: 6.16998e-06 [shard_inline]: 2.222e-05 [merge_send_recv]: 1.852e-05 [auto_parallel]: 1.786e-05 [parallel]: 1.086e-05 [flash_sp]: 4.32e-06 [merge_comm]: 1.176e-05 [allreduce_fusion]: 1.075e-05 [matmul_add_comm_reduction]: 2.051e-05 [allreduce_slice_to_reducescatter]: 1.12e-06 [virtual_shard_identity]: 2.769e-05 [virtual_dataset]: 2.27e-05 [get_grad_eliminate_]: 2.257e-05 [virtual_output]: 2.214e-05 [merge_forward]: 1.174e-05 [cell_reuse_recompute_pass]: 3.62002e-06 [offload_activation]: 2.163e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.213e-05 [merge_recompute_call_nodes]: 1.49998e-06 [before_grad]: 3.863e-05 [set_forward_comm_id_for_comm_node_pass]: 1.294e-05 [meta_fg_expand]: 9.83002e-06 [flash_sp_send_recv_attached]: 1.79e-06 [receive_attached]: 2.89999e-06 [after_resolve]: 3.053e-05 [a_after_grad]: 3.451e-05 [renormalize]: 9.00181e-08 [add_forward_monad_depend]: 3.38e-06 [auto_monad_grad]: 2.01e-06 [auto_monad_eliminator]: 6.313e-05 [cse]: 7.249e-05 [a_3]: 0.00014941 [py_interpret_to_execute_after_opt_a]: 3.509e-05 [slice_cell_reuse_recomputed_activation]: 2.16e-06 [rewriter_after_opt_a]: 0.00044923 [convert_after_rewriter]: 2.419e-05 [order_py_execute_after_rewriter]: 1.19e-05 [mutable_eliminate]: 0.00085321 [opt_b]: 0.00077419, [1] [Cycle 1]: 0.00076403, [7] [b_1]: 0.00054789 [b_2]: 2.803e-05 [updatestate_depend_eliminate]: 2.001e-05 [updatestate_assign_eliminate]: 1.032e-05 [updatestate_loads_eliminate]: 1.299e-05 [renormalize]: 1.64e-06 [cse]: 9.151e-05 [optimize_parallel_all_gather_comm]: 4.377e-05 [overlap_param_gather]: 2.17999e-06 [cconv]: 4.155e-05 [loop_unroll]: 0.00063949 [opt_after_cconv]: 0.00030893, [1] [Cycle 1]: 0.0003004, [7] [c_1]: 0.00013655 [parameter_eliminate]: 6.89001e-06 [updatestate_depend_eliminate]: 1.761e-05 [updatestate_assign_eliminate]: 9.76e-06 [updatestate_loads_eliminate]: 1.254e-05 [cse]: 7.538e-05 [renormalize]: 7.00005e-07 [remove_dup_value]: 8.945e-05 [tuple_transform]: 0.00026613, [1] [Cycle 1]: 0.00025874, [4] [d_1]: 0.00020311 [none_parameter_eliminate]: 2.68e-06 [renormalize]: 6.09987e-07 [switch_simplify]: 2.414e-05 [partial_unused_args_eliminate]: 2.56e-06 [add_recomputation]: 0.00015089 [cse_after_recomputation]: 8.028e-05, [1] [Cycle 1]: 7.375e-05, [1] [cse]: 6.327e-05 [environ_conv]: 2.305e-05 [swap_dp_allreduce_reducescatter]: 1.768e-05 [bias_add_comm_swap]: 3.97998e-06 [label_micro_interleaved_index]: 7.66001e-06 [label_fine_grained_interleaved_index]: 3.16001e-06 [merge_cast_opt]: 1.79e-06 [slice_recompute_activation]: 2.31e-06 [micro_interleaved_order_control]: 2.48e-06 [assign_add_opt]: 1.49998e-06 [ForceFp32Comm]: 1.30999e-06 [remove_cast_before_assign_add]: 1.37999e-06 [full_micro_interleaved_order_control]: 2.17001e-06 [reorder_send_recv_between_fp_bp]: 2.54999e-06 [comm_op_add_attrs]: 1.14e-06 [add_comm_op_reuse_tag]: 1.14e-06 [interleave_split_concat_branches]: 1.27e-06 [interleave_parallel_branches]: 1.24e-06 [overlap_opt_shard_in_pipeline]: 1.93002e-06 [overlap_opt_shard_grad_in_pipeline]: 1.69e-06 [control_data_broadcast_order]: 3.819e-05 [grouped_pairwise_exchange_alltoall]: 1.76998e-06 [offloading_packed_experts]: 1.126e-05 [overlap_recompute_and_grad_model_parallel]: 9.97999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.25999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.42e-06 [overlap_recompute_comm]: 2.37001e-06 [overlap_grad_ring_attention]: 8.42e-06 [overlap_grad_flash_sp]: 5.672e-05 [begin_end_overlap_inline]: 5.3001e-07 [split_matmul_comm_elemetwise]: 3.15002e-06 [split_layernorm_comm]: 2.37001e-06 [handle_group_info]: 1.07998e-06 [symbol_engine_optimizer]: 0.00023288, [1] [Cycle 1]: 0.00022146, [6] [build]: 2.321e-05 [elim_shapecalc]: 4.035e-05 [elim_not_effective]: 4.559e-05 [opt_reshape]: 2.919e-05 [fold_const_symbol]: 3.56e-05 [renormalize]: 6.69999e-07 [detach_backward]: 2.26e-06 [pipeline_parallel_scheduler]: 1.94e-06 [auto_monad_reorder]: 6.681e-05 [get_jit_bprop_graph]: 1.81e-06 [rewriter_after_jit_bprop_graph]: 7.13998e-06 [opt_after_jit_grad]: 0.0372391 [validate]: 0.00013614 Sums bootstrap : 0.000575s : 0.03% type_inference : 1.495644s : 89.93% event_method : 0.000029s : 0.00% auto_monad : 0.000382s : 0.02% graph_reusing : 0.000008s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000040s : 0.00% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000008s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000062s : 0.00% insert-virtual-dataset : 0.000003s : 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 : 0.000047s : 0.00% optimize.rewriter_before_opt_a : 0.000181s : 0.01% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000090s : 0.01% optimize.opt_a.loop_unroll : 0.000072s : 0.00% optimize.opt_a.a_1 : 0.002708s : 0.16% optimize.opt_a.with_stream_mark : 0.000071s : 0.00% optimize.opt_a.recompute_prepare : 0.000057s : 0.00% optimize.opt_a.updatestate_depend_eliminate : 0.000073s : 0.00% optimize.opt_a.updatestate_assign_eliminate : 0.000025s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000027s : 0.00% optimize.opt_a.parameter_eliminate : 0.000006s : 0.00% optimize.opt_a.a_2 : 0.000707s : 0.04% optimize.opt_a.accelerated_algorithm : 0.000085s : 0.01% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000011s : 0.00% optimize.opt_a.shard_inline : 0.000044s : 0.00% optimize.opt_a.merge_send_recv : 0.000037s : 0.00% optimize.opt_a.auto_parallel : 0.000037s : 0.00% optimize.opt_a.parallel : 0.000039s : 0.00% optimize.opt_a.flash_sp : 0.000017s : 0.00% optimize.opt_a.merge_comm : 0.000024s : 0.00% optimize.opt_a.allreduce_fusion : 0.000022s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000040s : 0.00% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000056s : 0.00% optimize.opt_a.virtual_dataset : 0.000047s : 0.00% optimize.opt_a.get_grad_eliminate_ : 0.000045s : 0.00% optimize.opt_a.virtual_output : 0.000047s : 0.00% optimize.opt_a.merge_forward : 0.000022s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000044s : 0.00% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000088s : 0.01% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000080s : 0.00% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000025s : 0.00% optimize.opt_a.meta_fg_expand : 0.000019s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000060s : 0.00% optimize.opt_a.a_after_grad : 0.000075s : 0.00% optimize.opt_a.renormalize : 0.118350s : 7.12% optimize.opt_a.add_forward_monad_depend : 0.000016s : 0.00% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000133s : 0.01% optimize.opt_a.cse : 0.001027s : 0.06% optimize.opt_a.a_3 : 0.000331s : 0.02% optimize.py_interpret_to_execute_after_opt_a : 0.000035s : 0.00% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000449s : 0.03% optimize.convert_after_rewriter : 0.000024s : 0.00% optimize.order_py_execute_after_rewriter : 0.000012s : 0.00% optimize.mutable_eliminate : 0.000853s : 0.05% optimize.opt_b.b_1 : 0.000548s : 0.03% optimize.opt_b.b_2 : 0.000028s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000020s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_b.renormalize : 0.000002s : 0.00% optimize.opt_b.cse : 0.000092s : 0.01% optimize.optimize_parallel_all_gather_comm : 0.000044s : 0.00% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000042s : 0.00% optimize.loop_unroll : 0.000639s : 0.04% optimize.opt_after_cconv.c_1 : 0.000137s : 0.01% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000018s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000013s : 0.00% optimize.opt_after_cconv.cse : 0.000075s : 0.00% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000089s : 0.01% optimize.tuple_transform.d_1 : 0.000203s : 0.01% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000001s : 0.00% optimize.tuple_transform.switch_simplify : 0.000024s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000151s : 0.01% optimize.cse_after_recomputation.cse : 0.000063s : 0.00% optimize.environ_conv : 0.000023s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000018s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000008s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000038s : 0.00% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000011s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000010s : 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 : 0.000057s : 0.00% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000023s : 0.00% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000040s : 0.00% optimize.symbol_engine_optimizer.elim_not_effective : 0.000046s : 0.00% optimize.symbol_engine_optimizer.opt_reshape : 0.000029s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000036s : 0.00% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000067s : 0.00% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.037239s : 2.24% validate : 0.000136s : 0.01% Time group info: ------[substitution.] 0.000759 196 1.41% : 0.000011s : 2: substitution.depend_value_elim 0.70% : 0.000005s : 12: substitution.elim_not_effective 1.78% : 0.000014s : 6: substitution.float_tuple_getitem_switch 0.60% : 0.000005s : 12: substitution.fold_const_symbol 1.98% : 0.000015s : 17: substitution.graph_param_transform 50.24% : 0.000381s : 7: substitution.inline 1.79% : 0.000014s : 24: substitution.j_node_and_user_rematch 3.41% : 0.000026s : 2: substitution.less_batch_normalization 0.85% : 0.000006s : 6: substitution.load_eliminater 1.67% : 0.000013s : 4: substitution.minmaximum_grad 0.43% : 0.000003s : 2: substitution.opt_reshape 2.26% : 0.000017s : 24: substitution.remove_not_recompute_node 0.99% : 0.000007s : 4: substitution.replace_old_param 3.23% : 0.000025s : 4: substitution.reshape_eliminate 4.83% : 0.000037s : 8: substitution.tuple_list_convert_item_index_to_positive 2.11% : 0.000016s : 8: substitution.tuple_list_get_item_const_eliminator 3.04% : 0.000023s : 8: substitution.tuple_list_get_item_depend_reorder 7.75% : 0.000059s : 12: substitution.tuple_list_get_item_eliminator 3.02% : 0.000023s : 8: substitution.tuple_list_get_set_item_eliminator 4.42% : 0.000034s : 12: substitution.updatestate_pure_node_eliminater 3.48% : 0.000026s : 14: substitution.updatestate_useless_node_eliminater ------[type_inference.] 1.495524 2 99.62% : 1.489914s : 1: type_inference.infer 0.38% : 0.005610s : 1: type_inference.specialize ------[replace.] 0.000072 7 100.00% : 0.000072s : 7: replace.inline ------[match.] 0.000377 7 100.00% : 0.000377s : 7: match.inline ------[predicate.] 0.000748 4469 0.92% : 0.000007s : 45: predicate.accumulaten_eliminater 1.42% : 0.000011s : 17: predicate.ad_related_special_op_eliminate 0.66% : 0.000005s : 34: predicate.addn_check_dump 0.95% : 0.000007s : 45: predicate.addn_zero_filter 0.89% : 0.000007s : 45: predicate.adjust_all_reduce_mul_add 2.16% : 0.000016s : 79: predicate.arithmetic_simplify 0.88% : 0.000007s : 45: predicate.cast_eliminate 0.66% : 0.000005s : 34: predicate.check_bprop_eliminate 0.74% : 0.000006s : 34: predicate.compare_switch_simplify 0.19% : 0.000001s : 17: predicate.const_output_eliminate 0.70% : 0.000005s : 34: predicate.depend_value_elim 1.03% : 0.000008s : 45: predicate.dict_get_item_const_eliminator 1.00% : 0.000007s : 45: predicate.dict_get_item_eliminator 0.95% : 0.000007s : 45: predicate.dict_set_item_eliminator 1.14% : 0.000009s : 34: predicate.dumpgradient_eliminate 0.21% : 0.000002s : 17: predicate.elim_not_effective 0.49% : 0.000004s : 17: predicate.elim_shapecalc_of_broadcastargs 1.20% : 0.000009s : 62: predicate.environ_add_const_eliminate 1.22% : 0.000009s : 62: predicate.environ_get_add_eliminate 1.17% : 0.000009s : 62: predicate.environ_get_depend_swap 1.89% : 0.000014s : 96: predicate.environ_get_eliminate 1.23% : 0.000009s : 62: predicate.environ_get_set_eliminate 1.09% : 0.000008s : 52: predicate.exchange_switch_depend_value 1.58% : 0.000012s : 52: predicate.float_depend_g_call 0.72% : 0.000005s : 34: predicate.float_environ_get_switch 1.09% : 0.000008s : 51: predicate.float_tuple_getitem_switch 0.18% : 0.000001s : 17: predicate.fold_const_symbol 0.73% : 0.000005s : 34: predicate.get_grad_eliminate 0.22% : 0.000002s : 17: predicate.graph_param_transform 0.69% : 0.000005s : 34: predicate.incorporate_call 0.63% : 0.000005s : 34: predicate.incorporate_call_switch 5.78% : 0.000043s : 199: predicate.inline 0.97% : 0.000007s : 34: predicate.inline_without_move 0.36% : 0.000003s : 34: predicate.j_node_and_user_rematch 0.92% : 0.000007s : 36: predicate.less_batch_normalization 1.65% : 0.000012s : 79: predicate.list_to_tuple_eliminator_ 2.50% : 0.000019s : 124: predicate.load_eliminater 0.90% : 0.000007s : 17: predicate.loop_unroll_after_grad 1.39% : 0.000010s : 67: predicate.loop_unroll_before_grad 1.77% : 0.000013s : 79: predicate.make_slice_get_slice_eliminator 0.70% : 0.000005s : 34: predicate.merge_addn 0.70% : 0.000005s : 34: predicate.micro_step_allgather_replace 0.71% : 0.000005s : 34: predicate.mini_step_allgather_replace 0.87% : 0.000007s : 45: predicate.minmaximum_grad 1.00% : 0.000007s : 17: predicate.mutable_eliminate 0.44% : 0.000003s : 17: predicate.opt_reshape 0.38% : 0.000003s : 17: predicate.parallel_virtual_node 1.62% : 0.000012s : 52: predicate.partial_defer_inline 1.38% : 0.000010s : 62: predicate.partial_eliminate 0.99% : 0.000007s : 45: predicate.print_const_string_wrapper 0.67% : 0.000005s : 34: predicate.reduce_all_const_elim 1.15% : 0.000009s : 45: predicate.reduce_eliminate 2.43% : 0.000018s : 124: predicate.redundant_stop_gradient_eliminater 0.38% : 0.000003s : 34: predicate.remove_not_recompute_node 1.20% : 0.000009s : 79: predicate.replace_applicator 0.42% : 0.000003s : 34: predicate.replace_old_param 0.25% : 0.000002s : 17: predicate.reset_defer_inline 0.97% : 0.000007s : 45: predicate.reshape_eliminate 0.69% : 0.000005s : 34: predicate.row_tensor_add_zeros_like 0.41% : 0.000003s : 17: predicate.row_tensor_eliminate 0.93% : 0.000007s : 34: predicate.same_eliminate 0.49% : 0.000004s : 38: predicate.set_cell_output_no_recompute 0.84% : 0.000006s : 34: predicate.shard_identity_eliminate 0.77% : 0.000006s : 34: predicate.special_op_eliminate 0.84% : 0.000006s : 34: predicate.specialize_transform 1.02% : 0.000008s : 34: predicate.split_environ_get_set_with_tuple_value 0.83% : 0.000006s : 34: predicate.stack_unstack_eliminate 0.41% : 0.000003s : 17: predicate.switch_call_monad_eliminater 1.21% : 0.000009s : 52: predicate.switch_defer_inline 1.87% : 0.000014s : 86: predicate.switch_layer_defer_inline 3.79% : 0.000028s : 170: predicate.switch_simplify 0.92% : 0.000007s : 45: predicate.tile_eliminate 0.88% : 0.000007s : 45: predicate.transpose_eliminate 1.69% : 0.000013s : 79: predicate.tuple_list_convert_item_index_to_positive 1.85% : 0.000014s : 79: predicate.tuple_list_get_item_const_eliminator 1.66% : 0.000012s : 79: predicate.tuple_list_get_item_depend_reorder 3.17% : 0.000024s : 113: predicate.tuple_list_get_item_eliminator 1.80% : 0.000013s : 79: predicate.tuple_list_get_set_item_eliminator 2.64% : 0.000020s : 113: predicate.tuple_list_set_item_eliminator 1.67% : 0.000013s : 79: predicate.tuple_to_list_eliminator_ 2.42% : 0.000018s : 124: predicate.updatestate_pure_node_eliminater 3.35% : 0.000025s : 158: predicate.updatestate_useless_node_eliminater 0.38% : 0.000003s : 17: predicate.value_based_eliminate 0.78% : 0.000006s : 34: predicate.virtual_dataset_eliminate 0.81% : 0.000006s : 34: predicate.virtual_output_eliminate 0.34% : 0.000003s : 17: predicate.virtual_view_grad_eliminate 0.38% : 0.000003s : 17: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.206337 64 45.83% : 0.094568s : 55: func_graph_cloner_run.FuncGraphClonerGraph 54.17% : 0.111769s : 9: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.959117 192 0.00% : 0.000004s : 1: ForceFp32Comm 1.04% : 0.020379s : 1: add_attr 1.04% : 0.020359s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000161s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.02% : 0.000395s : 1: auto_monad 0.00% : 0.000075s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.03% : 0.000607s : 1: bootstrap 0.00% : 0.000047s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000043s : 1: control_data_broadcast_order 0.00% : 0.000030s : 1: convert_after_rewriter 0.00% : 0.000084s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000028s : 1: environ_conv 0.00% : 0.000037s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000013s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000011s : 1: label_micro_interleaved_index 0.03% : 0.000652s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.04% : 0.000866s : 1: mutable_eliminate 0.00% : 0.000015s : 1: offloading_packed_experts 0.00% : 0.000044s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000046s : 1: opt.transform.mutable_eliminate 0.23% : 0.004463s : 78: opt.transform.opt_a 0.01% : 0.000134s : 1: opt.transform.opt_after_cconv 0.01% : 0.000113s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000538s : 28: opt.transform.opt_b 0.01% : 0.000222s : 2: opt.transform.opt_trans_graph 0.01% : 0.000143s : 4: opt.transform.symbol_engine_opt 6.40% : 0.125351s : 1: opt_a 0.02% : 0.000315s : 1: opt_after_cconv 1.90% : 0.037262s : 1: opt_after_jit_grad 0.04% : 0.000778s : 1: opt_b 6.64% : 0.130118s : 1: optimize 0.00% : 0.000049s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000015s : 1: order_py_execute_after_rewriter 0.00% : 0.000064s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000012s : 1: overlap_grad_ring_attention 0.00% : 0.000004s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000013s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.00% : 0.000069s : 1: pre_auto_parallel 0.00% : 0.000052s : 1: py_interpret_to_execute 0.00% : 0.000040s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.00% : 0.000095s : 1: remove_dup_value 0.31% : 0.006121s : 1: renormalize.infer 5.73% : 0.112211s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000461s : 1: rewriter_after_opt_a 0.01% : 0.000186s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000022s : 1: swap_dp_allreduce_reducescatter 0.01% : 0.000236s : 1: symbol_engine_optimizer 0.01% : 0.000269s : 1: tuple_transform 76.34% : 1.495674s : 1: type_inference . [hook] pytest_runtest_teardown:test_matmul_ffn_3584_3584[False-0-mstype0-1024-32] tests/st/infer/ops/test_internal_ops/test_matmul_qkv_silu.py::test_matmul_ffn_3584_3584[False-0-mstype0-1024-32],max_mem:114.0M =============================== 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 ================== 2 passed, 25 warnings in 74.20s (0:01:14) ===================