==================================================Ascend ============================= test session starts ============================== platform linux -- Python 3.9.19, pytest-6.2.5, py-1.11.0, pluggy-1.5.0 rootdir: /home/jenkins/mindspore/testcases/testcases/tests/st/infer/ops/test_internal_ops, configfile: ../../../../../../../../sault/virtual_test/virtualenv_002/sault/config/pytest.ini plugins: mock-3.14.0, hydra-core-1.3.2, forked-1.6.0, anyio-4.9.0, xdist-1.32.0 collected 2 items test_paged_attention.py [WARNING] ME(159070:281472894226224,MainProcess):2026-01-29-17:37:21.829.624 [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 = 0.0898293, [21] [bootstrap]: 0.0007835 [type_inference]: 0.044722 [event_method]: 1.359e-05 [auto_monad]: 9.443e-05 [graph_reusing]: 5.02e-06 [inline]: 2.83e-06 [add_attr]: 0.0083701, [1] [add_attr_with_inline]: 0.00835523, [1] [Cycle 1]: 0.00010343, [2] [tag_attr]: 2.112e-05 [meta_addattr_fg_expand]: 4.25e-06 [parallel-infer-symbol]: 3.78999e-06 [pre_auto_parallel]: 4.921e-05 [insert-virtual-dataset]: 3.11999e-06 [parallel-infer-symbol-second]: 7.29982e-07 [dataset_repeat_opt]: 2.51e-06 [pipeline_split]: 1.76e-06 [optimize]: 0.0346298, [53] [py_interpret_to_execute]: 2.369e-05 [rewriter_before_opt_a]: 8.204e-05 [opt_a]: 0.0032785, [2] [Cycle 1]: 0.00224811, [45] [expand_dump_flag]: 2.69999e-06 [switch_simplify]: 3.025e-05 [loop_unroll]: 1.724e-05 [a_1]: 0.00042105 [with_stream_mark]: 2.234e-05 [recompute_prepare]: 1.407e-05 [updatestate_depend_eliminate]: 5.50001e-06 [updatestate_assign_eliminate]: 4.90001e-06 [updatestate_loads_eliminate]: 5.10001e-06 [parameter_eliminate]: 2.66999e-06 [a_2]: 0.00013824 [accelerated_algorithm]: 1.189e-05 [shard]: 2.64999e-06 [meta_shard_fg_expand]: 2.21e-06 [shard_inline]: 1.001e-05 [merge_send_recv]: 1.174e-05 [auto_parallel]: 1.065e-05 [parallel]: 5.31e-05 [flash_sp]: 1.261e-05 [merge_comm]: 5.57001e-06 [allreduce_fusion]: 4.58999e-06 [matmul_add_comm_reduction]: 1.216e-05 [allreduce_slice_to_reducescatter]: 9.00007e-07 [virtual_shard_identity]: 1.499e-05 [virtual_dataset]: 1.073e-05 [get_grad_eliminate_]: 1.009e-05 [virtual_output]: 1.057e-05 [merge_forward]: 5.81e-06 [cell_reuse_recompute_pass]: 2.16003e-06 [offload_activation]: 1.11e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.077e-05 [merge_recompute_call_nodes]: 1.92001e-06 [before_grad]: 1.557e-05 [set_forward_comm_id_for_comm_node_pass]: 5.91998e-06 [meta_fg_expand]: 4.23001e-06 [flash_sp_send_recv_attached]: 3.65e-06 [receive_attached]: 1.534e-05 [after_resolve]: 2.377e-05 [a_after_grad]: 1.766e-05 [renormalize]: 0.00078231 [add_forward_monad_depend]: 8.35001e-06 [auto_monad_grad]: 2.48998e-06 [auto_monad_eliminator]: 2.147e-05 [cse]: 8.798e-05 [a_3]: 8.201e-05 [Cycle 2]: 0.00101666, [45] [expand_dump_flag]: 3.01999e-06 [switch_simplify]: 1.381e-05 [loop_unroll]: 1.026e-05 [a_1]: 0.00024625 [with_stream_mark]: 2.063e-05 [recompute_prepare]: 1.064e-05 [updatestate_depend_eliminate]: 5.19e-06 [updatestate_assign_eliminate]: 4.48001e-06 [updatestate_loads_eliminate]: 4.53001e-06 [parameter_eliminate]: 1.94999e-06 [a_2]: 0.00013124 [accelerated_algorithm]: 1.005e-05 [shard]: 2.61e-06 [meta_shard_fg_expand]: 2.36e-06 [shard_inline]: 1.055e-05 [merge_send_recv]: 8.22998e-06 [auto_parallel]: 1.031e-05 [parallel]: 6.91999e-06 [flash_sp]: 4.04002e-06 [merge_comm]: 5.58002e-06 [allreduce_fusion]: 4.64998e-06 [matmul_add_comm_reduction]: 1.089e-05 [allreduce_slice_to_reducescatter]: 8.70001e-07 [virtual_shard_identity]: 1.219e-05 [virtual_dataset]: 1.065e-05 [get_grad_eliminate_]: 1.061e-05 [virtual_output]: 9.84999e-06 [merge_forward]: 5.66e-06 [cell_reuse_recompute_pass]: 2.19999e-06 [offload_activation]: 1.089e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.957e-05 [merge_recompute_call_nodes]: 1.40001e-06 [before_grad]: 1.537e-05 [set_forward_comm_id_for_comm_node_pass]: 5.84999e-06 [meta_fg_expand]: 3.11999e-06 [flash_sp_send_recv_attached]: 2.50002e-06 [receive_attached]: 2.86999e-06 [after_resolve]: 2.042e-05 [a_after_grad]: 1.644e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 3.03e-06 [auto_monad_grad]: 2.14e-06 [auto_monad_eliminator]: 1.423e-05 [cse]: 3.359e-05 [a_3]: 6.536e-05 [py_interpret_to_execute_after_opt_a]: 1.905e-05 [slice_cell_reuse_recomputed_activation]: 2.36e-06 [rewriter_after_opt_a]: 8.685e-05 [convert_after_rewriter]: 1.173e-05 [order_py_execute_after_rewriter]: 7.07002e-06 [mutable_eliminate]: 0.00074201 [opt_b]: 0.00035105, [1] [Cycle 1]: 0.00034162, [7] [b_1]: 0.00021559 [b_2]: 1.345e-05 [updatestate_depend_eliminate]: 1.173e-05 [updatestate_assign_eliminate]: 4.73001e-06 [updatestate_loads_eliminate]: 4.28999e-06 [renormalize]: 7.29982e-07 [cse]: 5.335e-05 [optimize_parallel_all_gather_comm]: 2.245e-05 [overlap_param_gather]: 5.30999e-06 [cconv]: 3.454e-05 [loop_unroll]: 0.0287052 [opt_after_cconv]: 0.00021158, [1] [Cycle 1]: 0.0001979, [7] [c_1]: 5.484e-05 [parameter_eliminate]: 6.43998e-06 [updatestate_depend_eliminate]: 1.798e-05 [updatestate_assign_eliminate]: 5.29e-06 [updatestate_loads_eliminate]: 4.50001e-06 [cse]: 6.96e-05 [renormalize]: 8.59989e-07 [remove_dup_value]: 7.907e-05 [tuple_transform]: 0.00012498, [1] [Cycle 1]: 0.00011851, [4] [d_1]: 8.08e-05 [none_parameter_eliminate]: 2.29001e-06 [renormalize]: 6.00005e-07 [switch_simplify]: 1.252e-05 [partial_unused_args_eliminate]: 2.44001e-06 [add_recomputation]: 7.675e-05 [cse_after_recomputation]: 3.803e-05, [1] [Cycle 1]: 3.213e-05, [1] [cse]: 2.522e-05 [environ_conv]: 2.66e-05 [swap_dp_allreduce_reducescatter]: 8.48001e-06 [bias_add_comm_swap]: 4.31002e-06 [label_micro_interleaved_index]: 9.87999e-06 [label_fine_grained_interleaved_index]: 2.96001e-06 [merge_cast_opt]: 1.54998e-06 [slice_recompute_activation]: 2.31e-06 [micro_interleaved_order_control]: 2.72001e-06 [assign_add_opt]: 1.49998e-06 [ForceFp32Comm]: 1.15001e-06 [remove_cast_before_assign_add]: 1.59e-06 [full_micro_interleaved_order_control]: 2.22001e-06 [reorder_send_recv_between_fp_bp]: 3.00002e-06 [comm_op_add_attrs]: 1.12e-06 [add_comm_op_reuse_tag]: 1.07e-06 [interleave_split_concat_branches]: 1.16002e-06 [interleave_parallel_branches]: 1.08001e-06 [overlap_opt_shard_in_pipeline]: 2.611e-05 [overlap_opt_shard_grad_in_pipeline]: 1.84e-06 [control_data_broadcast_order]: 2.211e-05 [grouped_pairwise_exchange_alltoall]: 1.57001e-06 [offloading_packed_experts]: 6.72002e-06 [overlap_recompute_and_grad_model_parallel]: 6.19001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.22e-06 [overlap_recompute_allgather_and_fa_grad]: 1.34998e-06 [overlap_recompute_comm]: 2.54999e-06 [overlap_grad_ring_attention]: 5.47001e-06 [overlap_grad_flash_sp]: 4.342e-05 [begin_end_overlap_inline]: 5.19998e-07 [split_matmul_comm_elemetwise]: 2.74001e-06 [split_layernorm_comm]: 2.07999e-06 [handle_group_info]: 1.25999e-06 [symbol_engine_optimizer]: 0.00023905, [1] [Cycle 1]: 0.00023079, [6] [build]: 9.96e-05 [elim_shapecalc]: 2.547e-05 [elim_not_effective]: 2.744e-05 [opt_reshape]: 1.205e-05 [fold_const_symbol]: 2.056e-05 [renormalize]: 1.50001e-07 [detach_backward]: 2.57001e-06 [pipeline_parallel_scheduler]: 2.12001e-06 [auto_monad_reorder]: 3.486e-05 [get_jit_bprop_graph]: 2.46e-06 [rewriter_after_jit_bprop_graph]: 6.08002e-06 [opt_after_jit_grad]: 0.00082678 [validate]: 8.46e-05 Sums bootstrap : 0.000783s : 0.98% type_inference : 0.044722s : 55.70% event_method : 0.000014s : 0.02% auto_monad : 0.000094s : 0.12% graph_reusing : 0.000005s : 0.01% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000021s : 0.03% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.01% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000049s : 0.06% 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 : 0.000024s : 0.03% optimize.rewriter_before_opt_a : 0.000082s : 0.10% optimize.opt_a.expand_dump_flag : 0.000006s : 0.01% optimize.opt_a.switch_simplify : 0.000044s : 0.05% optimize.opt_a.loop_unroll : 0.000028s : 0.03% optimize.opt_a.a_1 : 0.000667s : 0.83% optimize.opt_a.with_stream_mark : 0.000043s : 0.05% optimize.opt_a.recompute_prepare : 0.000025s : 0.03% optimize.opt_a.updatestate_depend_eliminate : 0.000011s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000009s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000010s : 0.01% optimize.opt_a.parameter_eliminate : 0.000005s : 0.01% optimize.opt_a.a_2 : 0.000269s : 0.34% optimize.opt_a.accelerated_algorithm : 0.000022s : 0.03% optimize.opt_a.shard : 0.000005s : 0.01% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.01% optimize.opt_a.shard_inline : 0.000021s : 0.03% optimize.opt_a.merge_send_recv : 0.000020s : 0.02% optimize.opt_a.auto_parallel : 0.000021s : 0.03% optimize.opt_a.parallel : 0.000060s : 0.07% optimize.opt_a.flash_sp : 0.000017s : 0.02% optimize.opt_a.merge_comm : 0.000011s : 0.01% optimize.opt_a.allreduce_fusion : 0.000009s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000023s : 0.03% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000027s : 0.03% optimize.opt_a.virtual_dataset : 0.000021s : 0.03% optimize.opt_a.get_grad_eliminate_ : 0.000021s : 0.03% optimize.opt_a.virtual_output : 0.000020s : 0.03% optimize.opt_a.merge_forward : 0.000011s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.01% optimize.opt_a.offload_activation : 0.000022s : 0.03% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000040s : 0.05% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000031s : 0.04% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000012s : 0.01% optimize.opt_a.meta_fg_expand : 0.000007s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.01% optimize.opt_a.receive_attached : 0.000018s : 0.02% optimize.opt_a.after_resolve : 0.000044s : 0.06% optimize.opt_a.a_after_grad : 0.000034s : 0.04% optimize.opt_a.renormalize : 0.000782s : 0.97% optimize.opt_a.add_forward_monad_depend : 0.000011s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.01% optimize.opt_a.auto_monad_eliminator : 0.000036s : 0.04% optimize.opt_a.cse : 0.000122s : 0.15% optimize.opt_a.a_3 : 0.000147s : 0.18% optimize.py_interpret_to_execute_after_opt_a : 0.000019s : 0.02% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000087s : 0.11% optimize.convert_after_rewriter : 0.000012s : 0.01% optimize.order_py_execute_after_rewriter : 0.000007s : 0.01% optimize.mutable_eliminate : 0.000742s : 0.92% optimize.opt_b.b_1 : 0.000216s : 0.27% optimize.opt_b.b_2 : 0.000013s : 0.02% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000004s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000053s : 0.07% optimize.optimize_parallel_all_gather_comm : 0.000022s : 0.03% optimize.overlap_param_gather : 0.000005s : 0.01% optimize.cconv : 0.000035s : 0.04% optimize.loop_unroll : 0.028705s : 35.75% optimize.opt_after_cconv.c_1 : 0.000055s : 0.07% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000018s : 0.02% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.01% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.01% optimize.opt_after_cconv.cse : 0.000070s : 0.09% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000079s : 0.10% optimize.tuple_transform.d_1 : 0.000081s : 0.10% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000001s : 0.00% optimize.tuple_transform.switch_simplify : 0.000013s : 0.02% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000077s : 0.10% optimize.cse_after_recomputation.cse : 0.000025s : 0.03% optimize.environ_conv : 0.000027s : 0.03% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.01% optimize.bias_add_comm_swap : 0.000004s : 0.01% optimize.label_micro_interleaved_index : 0.000010s : 0.01% 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 : 0.000002s : 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 : 0.000026s : 0.03% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000022s : 0.03% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.01% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 0.01% 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 : 0.000005s : 0.01% optimize.overlap_grad_flash_sp : 0.000043s : 0.05% 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 : 0.000100s : 0.12% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000025s : 0.03% optimize.symbol_engine_optimizer.elim_not_effective : 0.000027s : 0.03% optimize.symbol_engine_optimizer.opt_reshape : 0.000012s : 0.02% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000021s : 0.03% 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 : 0.000035s : 0.04% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.01% opt_after_jit_grad : 0.000827s : 1.03% validate : 0.000085s : 0.11% Time group info: ------[substitution.] 0.000152 33 6.83% : 0.000010s : 2: substitution.elim_not_effective 5.52% : 0.000008s : 2: substitution.fold_const_symbol 5.34% : 0.000008s : 8: substitution.graph_param_transform 68.58% : 0.000104s : 1: substitution.inline 3.21% : 0.000005s : 4: substitution.j_node_and_user_rematch 4.16% : 0.000006s : 4: substitution.remove_not_recompute_node 6.36% : 0.000010s : 12: substitution.replace_old_param ------[type_inference.] 0.044629 2 98.83% : 0.044106s : 1: type_inference.infer 1.17% : 0.000523s : 1: type_inference.specialize ------[replace.] 0.000020 1 100.00% : 0.000020s : 1: replace.inline ------[match.] 0.000103 1 100.00% : 0.000103s : 1: match.inline ------[predicate.] 0.000240 1879 0.75% : 0.000002s : 17: predicate.accumulaten_eliminater 1.74% : 0.000004s : 8: predicate.ad_related_special_op_eliminate 0.65% : 0.000002s : 16: predicate.addn_check_dump 0.76% : 0.000002s : 17: predicate.addn_zero_filter 0.68% : 0.000002s : 17: predicate.adjust_all_reduce_mul_add 1.72% : 0.000004s : 33: predicate.arithmetic_simplify 0.82% : 0.000002s : 17: predicate.cast_eliminate 0.82% : 0.000002s : 16: predicate.check_bprop_eliminate 0.68% : 0.000002s : 16: predicate.compare_switch_simplify 0.26% : 0.000001s : 8: predicate.const_output_eliminate 0.72% : 0.000002s : 16: predicate.depend_value_elim 0.81% : 0.000002s : 17: predicate.dict_get_item_const_eliminator 0.88% : 0.000002s : 17: predicate.dict_get_item_eliminator 0.75% : 0.000002s : 17: predicate.dict_set_item_eliminator 1.65% : 0.000004s : 16: predicate.dumpgradient_eliminate 0.31% : 0.000001s : 8: predicate.elim_not_effective 0.60% : 0.000001s : 8: predicate.elim_shapecalc_of_broadcastargs 1.08% : 0.000003s : 25: predicate.environ_add_const_eliminate 1.02% : 0.000002s : 25: predicate.environ_get_add_eliminate 1.05% : 0.000003s : 25: predicate.environ_get_depend_swap 1.79% : 0.000004s : 41: predicate.environ_get_eliminate 1.02% : 0.000002s : 25: predicate.environ_get_set_eliminate 0.76% : 0.000002s : 18: predicate.exchange_switch_depend_value 1.55% : 0.000004s : 18: predicate.float_depend_g_call 0.63% : 0.000002s : 16: predicate.float_environ_get_switch 0.98% : 0.000002s : 24: predicate.float_tuple_getitem_switch 0.28% : 0.000001s : 8: predicate.fold_const_symbol 0.91% : 0.000002s : 16: predicate.get_grad_eliminate 0.39% : 0.000001s : 8: predicate.graph_param_transform 0.71% : 0.000002s : 16: predicate.incorporate_call 0.63% : 0.000001s : 16: predicate.incorporate_call_switch 6.24% : 0.000015s : 83: predicate.inline 1.48% : 0.000004s : 16: predicate.inline_without_move 0.53% : 0.000001s : 16: predicate.j_node_and_user_rematch 1.04% : 0.000002s : 16: predicate.less_batch_normalization 1.74% : 0.000004s : 33: predicate.list_to_tuple_eliminator_ 2.16% : 0.000005s : 50: predicate.load_eliminater 2.78% : 0.000007s : 8: predicate.loop_unroll_after_grad 1.17% : 0.000003s : 25: predicate.loop_unroll_before_grad 1.86% : 0.000004s : 33: predicate.make_slice_get_slice_eliminator 0.74% : 0.000002s : 16: predicate.merge_addn 0.73% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.77% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.70% : 0.000002s : 17: predicate.minmaximum_grad 1.32% : 0.000003s : 8: predicate.mutable_eliminate 0.58% : 0.000001s : 8: predicate.opt_reshape 0.48% : 0.000001s : 8: predicate.parallel_virtual_node 0.91% : 0.000002s : 18: predicate.partial_defer_inline 1.22% : 0.000003s : 25: predicate.partial_eliminate 0.71% : 0.000002s : 17: predicate.print_const_string_wrapper 0.70% : 0.000002s : 16: predicate.reduce_all_const_elim 0.96% : 0.000002s : 17: predicate.reduce_eliminate 2.37% : 0.000006s : 50: predicate.redundant_stop_gradient_eliminater 0.74% : 0.000002s : 16: predicate.remove_not_recompute_node 1.32% : 0.000003s : 33: predicate.replace_applicator 0.72% : 0.000002s : 16: predicate.replace_old_param 0.43% : 0.000001s : 8: predicate.reset_defer_inline 0.81% : 0.000002s : 17: predicate.reshape_eliminate 0.76% : 0.000002s : 16: predicate.row_tensor_add_zeros_like 0.60% : 0.000001s : 8: predicate.row_tensor_eliminate 0.93% : 0.000002s : 16: predicate.same_eliminate 0.70% : 0.000002s : 16: predicate.set_cell_output_no_recompute 1.11% : 0.000003s : 16: predicate.shard_identity_eliminate 0.78% : 0.000002s : 16: predicate.special_op_eliminate 0.78% : 0.000002s : 16: predicate.specialize_transform 1.28% : 0.000003s : 16: predicate.split_environ_get_set_with_tuple_value 1.09% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.46% : 0.000001s : 8: predicate.switch_call_monad_eliminater 0.80% : 0.000002s : 18: predicate.switch_defer_inline 1.51% : 0.000004s : 34: predicate.switch_layer_defer_inline 3.94% : 0.000009s : 67: predicate.switch_simplify 0.78% : 0.000002s : 17: predicate.tile_eliminate 0.75% : 0.000002s : 17: predicate.transpose_eliminate 1.66% : 0.000004s : 33: predicate.tuple_list_convert_item_index_to_positive 1.49% : 0.000004s : 33: predicate.tuple_list_get_item_const_eliminator 1.41% : 0.000003s : 33: predicate.tuple_list_get_item_depend_reorder 3.13% : 0.000008s : 49: predicate.tuple_list_get_item_eliminator 1.49% : 0.000004s : 33: predicate.tuple_list_get_set_item_eliminator 2.34% : 0.000006s : 49: predicate.tuple_list_set_item_eliminator 1.53% : 0.000004s : 33: predicate.tuple_to_list_eliminator_ 2.10% : 0.000005s : 50: predicate.updatestate_pure_node_eliminater 2.88% : 0.000007s : 66: predicate.updatestate_useless_node_eliminater 0.38% : 0.000001s : 8: predicate.value_based_eliminate 0.93% : 0.000002s : 16: predicate.virtual_dataset_eliminate 0.93% : 0.000002s : 16: predicate.virtual_output_eliminate 0.34% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.52% : 0.000001s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000494 6 52.63% : 0.000260s : 3: func_graph_cloner_run.FuncGraphClonerGraph 47.37% : 0.000234s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.135327 192 0.00% : 0.000005s : 1: ForceFp32Comm 6.19% : 0.008376s : 1: add_attr 6.18% : 0.008359s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.06% : 0.000082s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.07% : 0.000100s : 1: auto_monad 0.03% : 0.000042s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.01% : 0.000008s : 1: bias_add_comm_swap 0.61% : 0.000820s : 1: bootstrap 0.03% : 0.000039s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.02% : 0.000027s : 1: control_data_broadcast_order 0.01% : 0.000017s : 1: convert_after_rewriter 0.03% : 0.000042s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.02% : 0.000031s : 1: environ_conv 0.02% : 0.000021s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.01% : 0.000009s : 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 0.01% : 0.000013s : 1: label_micro_interleaved_index 21.23% : 0.028732s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.56% : 0.000755s : 1: mutable_eliminate 0.01% : 0.000010s : 1: offloading_packed_experts 0.04% : 0.000052s : 1: opt.transform.loop_unroll_optimizer 0.02% : 0.000027s : 1: opt.transform.mutable_eliminate 1.01% : 0.001366s : 78: opt.transform.opt_a 0.04% : 0.000053s : 1: opt.transform.opt_after_cconv 0.04% : 0.000050s : 1: opt.transform.opt_after_jit_grad 0.15% : 0.000199s : 28: opt.transform.opt_b 0.07% : 0.000090s : 2: opt.transform.opt_trans_graph 0.06% : 0.000079s : 4: opt.transform.symbol_engine_opt 2.43% : 0.003282s : 1: opt_a 0.16% : 0.000216s : 1: opt_after_cconv 0.62% : 0.000844s : 1: opt_after_jit_grad 0.26% : 0.000355s : 1: opt_b 25.59% : 0.034636s : 1: optimize 0.02% : 0.000026s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000010s : 1: order_py_execute_after_rewriter 0.04% : 0.000048s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000009s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.02% : 0.000032s : 1: overlap_opt_shard_in_pipeline 0.01% : 0.000009s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000009s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.01% : 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% : 0.000005s : 1: pipeline_split 0.04% : 0.000055s : 1: pre_auto_parallel 0.02% : 0.000028s : 1: py_interpret_to_execute 0.02% : 0.000023s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.06% : 0.000084s : 1: remove_dup_value 0.29% : 0.000395s : 1: renormalize.infer 0.28% : 0.000377s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.07% : 0.000095s : 1: rewriter_after_opt_a 0.06% : 0.000087s : 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 0.01% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.18% : 0.000242s : 1: symbol_engine_optimizer 0.09% : 0.000128s : 1: tuple_transform 33.06% : 0.044744s : 1: type_inference .[WARNING] PRE_ACT(159070,ffff83dfcf30,python3.9):2026-01-29-17:38:02.727.889 [mindspore/ccsrc/runtime/memory/mem_pool/abstract_dynamic_mem_pool.cc:1109] FreeIdleMemsByEagerFree] Eager free count : 1, free memory : 1357689856, real free : 1358954496, not free : 0. [hook] pytest_runtest_teardown:test_paged_attention_fd_long[0] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_fd_long[0],max_mem:1392.0M [WARNING] ME(159070:281472894226224,MainProcess):2026-01-29-17:38:03.354.775 [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 = 0.192434, [21] [bootstrap]: 0.00486486 [type_inference]: 0.0765266 [event_method]: 6.903e-05 [auto_monad]: 9.994e-05 [graph_reusing]: 6.93e-06 [inline]: 4.33001e-06 [add_attr]: 0.0966957, [1] [add_attr_with_inline]: 0.0966763, [1] [Cycle 1]: 8.21e-05, [2] [tag_attr]: 2.542e-05 [meta_addattr_fg_expand]: 3.88001e-06 [parallel-infer-symbol]: 3.95e-06 [pre_auto_parallel]: 4.514e-05 [insert-virtual-dataset]: 3.26001e-06 [parallel-infer-symbol-second]: 9.39996e-07 [dataset_repeat_opt]: 2.16998e-06 [pipeline_split]: 1.73002e-06 [optimize]: 0.00689832, [53] [py_interpret_to_execute]: 3.323e-05 [rewriter_before_opt_a]: 8.824e-05 [opt_a]: 0.00376532, [2] [Cycle 1]: 0.00266211, [45] [expand_dump_flag]: 3.21999e-06 [switch_simplify]: 3.16e-05 [loop_unroll]: 1.9e-05 [a_1]: 0.0004591 [with_stream_mark]: 2.685e-05 [recompute_prepare]: 1.214e-05 [updatestate_depend_eliminate]: 6.01998e-06 [updatestate_assign_eliminate]: 5.22e-06 [updatestate_loads_eliminate]: 4.70999e-06 [parameter_eliminate]: 2.34001e-06 [a_2]: 0.00013916 [accelerated_algorithm]: 1.123e-05 [shard]: 2.71e-06 [meta_shard_fg_expand]: 2.56e-06 [shard_inline]: 1.092e-05 [merge_send_recv]: 1.058e-05 [auto_parallel]: 9.02e-06 [parallel]: 4.016e-05 [flash_sp]: 1.182e-05 [merge_comm]: 5.66e-06 [allreduce_fusion]: 5.27999e-06 [matmul_add_comm_reduction]: 1.207e-05 [allreduce_slice_to_reducescatter]: 9.99979e-07 [virtual_shard_identity]: 1.219e-05 [virtual_dataset]: 1.624e-05 [get_grad_eliminate_]: 1.138e-05 [virtual_output]: 1.801e-05 [merge_forward]: 6.38003e-06 [cell_reuse_recompute_pass]: 1.44e-06 [offload_activation]: 1.422e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.049e-05 [merge_recompute_call_nodes]: 1.60999e-06 [before_grad]: 1.994e-05 [set_forward_comm_id_for_comm_node_pass]: 5.67999e-06 [meta_fg_expand]: 3.55e-06 [flash_sp_send_recv_attached]: 3.04999e-06 [receive_attached]: 2.68998e-06 [after_resolve]: 2.544e-05 [a_after_grad]: 8.233e-05 [renormalize]: 0.00111204 [add_forward_monad_depend]: 7.55e-06 [auto_monad_grad]: 2.88e-06 [auto_monad_eliminator]: 2.045e-05 [cse]: 6.19e-05 [a_3]: 8.313e-05 [Cycle 2]: 0.00108951, [45] [expand_dump_flag]: 2.48998e-06 [switch_simplify]: 1.245e-05 [loop_unroll]: 1.06e-05 [a_1]: 0.00026343 [with_stream_mark]: 2.219e-05 [recompute_prepare]: 1.143e-05 [updatestate_depend_eliminate]: 5.66e-06 [updatestate_assign_eliminate]: 5.19998e-06 [updatestate_loads_eliminate]: 5.30999e-06 [parameter_eliminate]: 1.88002e-06 [a_2]: 0.00013164 [accelerated_algorithm]: 1.096e-05 [shard]: 3.88001e-06 [meta_shard_fg_expand]: 2.45002e-06 [shard_inline]: 1.111e-05 [merge_send_recv]: 9.27999e-06 [auto_parallel]: 9.88998e-06 [parallel]: 9.25999e-06 [flash_sp]: 4.50001e-06 [merge_comm]: 5.30999e-06 [allreduce_fusion]: 5.41998e-06 [matmul_add_comm_reduction]: 9.15999e-06 [allreduce_slice_to_reducescatter]: 8.2e-07 [virtual_shard_identity]: 1.176e-05 [virtual_dataset]: 9.91e-06 [get_grad_eliminate_]: 9.81e-06 [virtual_output]: 1.027e-05 [merge_forward]: 6.51999e-06 [cell_reuse_recompute_pass]: 3.19001e-06 [offload_activation]: 1.29e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.167e-05 [merge_recompute_call_nodes]: 1.45001e-06 [before_grad]: 1.458e-05 [set_forward_comm_id_for_comm_node_pass]: 5.32999e-06 [meta_fg_expand]: 3.14999e-06 [flash_sp_send_recv_attached]: 1.45999e-06 [receive_attached]: 2.03997e-06 [after_resolve]: 2.075e-05 [a_after_grad]: 1.674e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 1.96e-06 [auto_monad_grad]: 2.68998e-06 [auto_monad_eliminator]: 1.261e-05 [cse]: 5.446e-05 [a_3]: 6.512e-05 [py_interpret_to_execute_after_opt_a]: 2.96e-05 [slice_cell_reuse_recomputed_activation]: 2.31998e-06 [rewriter_after_opt_a]: 6.875e-05 [convert_after_rewriter]: 1.134e-05 [order_py_execute_after_rewriter]: 7.64002e-06 [mutable_eliminate]: 0.00082496 [opt_b]: 0.00036822, [1] [Cycle 1]: 0.00035742, [7] [b_1]: 0.00021864 [b_2]: 1.301e-05 [updatestate_depend_eliminate]: 1.201e-05 [updatestate_assign_eliminate]: 4.84e-06 [updatestate_loads_eliminate]: 4.82e-06 [renormalize]: 6.39993e-07 [cse]: 5.967e-05 [optimize_parallel_all_gather_comm]: 2.935e-05 [overlap_param_gather]: 3.41999e-06 [cconv]: 3.854e-05 [loop_unroll]: 0.00051428 [opt_after_cconv]: 0.00016168, [1] [Cycle 1]: 0.00015403, [7] [c_1]: 4.894e-05 [parameter_eliminate]: 6.36998e-06 [updatestate_depend_eliminate]: 7.99002e-06 [updatestate_assign_eliminate]: 4.18999e-06 [updatestate_loads_eliminate]: 4.22998e-06 [cse]: 4.442e-05 [renormalize]: 7.79983e-07 [remove_dup_value]: 7.619e-05 [tuple_transform]: 0.00011259, [1] [Cycle 1]: 0.00010713, [4] [d_1]: 7.272e-05 [none_parameter_eliminate]: 2.48e-06 [renormalize]: 1.39989e-07 [switch_simplify]: 1.083e-05 [partial_unused_args_eliminate]: 2.13998e-06 [add_recomputation]: 7.094e-05 [cse_after_recomputation]: 4.211e-05, [1] [Cycle 1]: 3.648e-05, [1] [cse]: 2.939e-05 [environ_conv]: 8.23999e-06 [swap_dp_allreduce_reducescatter]: 7.5e-06 [bias_add_comm_swap]: 3.37002e-06 [label_micro_interleaved_index]: 5.45001e-06 [label_fine_grained_interleaved_index]: 3.13998e-06 [merge_cast_opt]: 1.35999e-06 [slice_recompute_activation]: 2.50002e-06 [micro_interleaved_order_control]: 2.74001e-06 [assign_add_opt]: 1.39998e-06 [ForceFp32Comm]: 1.24998e-06 [remove_cast_before_assign_add]: 1.44e-06 [full_micro_interleaved_order_control]: 2.28002e-06 [reorder_send_recv_between_fp_bp]: 3.38e-06 [comm_op_add_attrs]: 1.09e-06 [add_comm_op_reuse_tag]: 1.12e-06 [interleave_split_concat_branches]: 1.30001e-06 [interleave_parallel_branches]: 1.62001e-06 [overlap_opt_shard_in_pipeline]: 2.70997e-06 [overlap_opt_shard_grad_in_pipeline]: 2.43e-06 [control_data_broadcast_order]: 1.785e-05 [grouped_pairwise_exchange_alltoall]: 2.10002e-06 [offloading_packed_experts]: 6.39001e-06 [overlap_recompute_and_grad_model_parallel]: 9.94001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.64998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.67999e-06 [overlap_recompute_comm]: 2.49999e-06 [overlap_grad_ring_attention]: 5.68002e-06 [overlap_grad_flash_sp]: 2.89e-05 [begin_end_overlap_inline]: 6.69999e-07 [split_matmul_comm_elemetwise]: 2.66e-06 [split_layernorm_comm]: 1.74998e-06 [handle_group_info]: 1.07e-06 [symbol_engine_optimizer]: 0.00023567, [1] [Cycle 1]: 0.00023043, [6] [build]: 0.00010418 [elim_shapecalc]: 2.492e-05 [elim_not_effective]: 2.568e-05 [opt_reshape]: 1.15e-05 [fold_const_symbol]: 2.084e-05 [renormalize]: 2.30008e-07 [detach_backward]: 2.41998e-06 [pipeline_parallel_scheduler]: 1.54998e-06 [auto_monad_reorder]: 3.25e-05 [get_jit_bprop_graph]: 1.99e-06 [rewriter_after_jit_bprop_graph]: 5.28002e-06 [opt_after_jit_grad]: 0.00093565 [validate]: 8.075e-05 Sums bootstrap : 0.004865s : 5.49% type_inference : 0.076527s : 86.38% event_method : 0.000069s : 0.08% auto_monad : 0.000100s : 0.11% graph_reusing : 0.000007s : 0.01% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000025s : 0.03% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000045s : 0.05% 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 : 0.000033s : 0.04% optimize.rewriter_before_opt_a : 0.000088s : 0.10% optimize.opt_a.expand_dump_flag : 0.000006s : 0.01% optimize.opt_a.switch_simplify : 0.000044s : 0.05% optimize.opt_a.loop_unroll : 0.000030s : 0.03% optimize.opt_a.a_1 : 0.000723s : 0.82% optimize.opt_a.with_stream_mark : 0.000049s : 0.06% optimize.opt_a.recompute_prepare : 0.000024s : 0.03% optimize.opt_a.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000010s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000010s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000271s : 0.31% optimize.opt_a.accelerated_algorithm : 0.000022s : 0.03% optimize.opt_a.shard : 0.000007s : 0.01% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.01% optimize.opt_a.shard_inline : 0.000022s : 0.02% optimize.opt_a.merge_send_recv : 0.000020s : 0.02% optimize.opt_a.auto_parallel : 0.000019s : 0.02% optimize.opt_a.parallel : 0.000049s : 0.06% optimize.opt_a.flash_sp : 0.000016s : 0.02% optimize.opt_a.merge_comm : 0.000011s : 0.01% optimize.opt_a.allreduce_fusion : 0.000011s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000021s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000024s : 0.03% optimize.opt_a.virtual_dataset : 0.000026s : 0.03% optimize.opt_a.get_grad_eliminate_ : 0.000021s : 0.02% optimize.opt_a.virtual_output : 0.000028s : 0.03% optimize.opt_a.merge_forward : 0.000013s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.01% optimize.opt_a.offload_activation : 0.000027s : 0.03% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000042s : 0.05% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000035s : 0.04% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000011s : 0.01% optimize.opt_a.meta_fg_expand : 0.000007s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.01% optimize.opt_a.receive_attached : 0.000005s : 0.01% optimize.opt_a.after_resolve : 0.000046s : 0.05% optimize.opt_a.a_after_grad : 0.000099s : 0.11% optimize.opt_a.renormalize : 0.001112s : 1.26% optimize.opt_a.add_forward_monad_depend : 0.000010s : 0.01% optimize.opt_a.auto_monad_grad : 0.000006s : 0.01% optimize.opt_a.auto_monad_eliminator : 0.000033s : 0.04% optimize.opt_a.cse : 0.000116s : 0.13% optimize.opt_a.a_3 : 0.000148s : 0.17% optimize.py_interpret_to_execute_after_opt_a : 0.000030s : 0.03% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000069s : 0.08% optimize.convert_after_rewriter : 0.000011s : 0.01% optimize.order_py_execute_after_rewriter : 0.000008s : 0.01% optimize.mutable_eliminate : 0.000825s : 0.93% optimize.opt_b.b_1 : 0.000219s : 0.25% optimize.opt_b.b_2 : 0.000013s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000060s : 0.07% optimize.optimize_parallel_all_gather_comm : 0.000029s : 0.03% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000039s : 0.04% optimize.loop_unroll : 0.000514s : 0.58% optimize.opt_after_cconv.c_1 : 0.000049s : 0.06% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000008s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.cse : 0.000044s : 0.05% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000076s : 0.09% optimize.tuple_transform.d_1 : 0.000073s : 0.08% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000011s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000071s : 0.08% optimize.cse_after_recomputation.cse : 0.000029s : 0.03% optimize.environ_conv : 0.000008s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000007s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.01% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 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 : 0.000002s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000018s : 0.02% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.01% optimize.overlap_recompute_and_grad_model_parallel : 0.000010s : 0.01% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.01% optimize.overlap_grad_flash_sp : 0.000029s : 0.03% 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 : 0.000104s : 0.12% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000025s : 0.03% optimize.symbol_engine_optimizer.elim_not_effective : 0.000026s : 0.03% optimize.symbol_engine_optimizer.opt_reshape : 0.000012s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000021s : 0.02% 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 : 0.000032s : 0.04% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.01% opt_after_jit_grad : 0.000936s : 1.06% validate : 0.000081s : 0.09% Time group info: ------[substitution.] 0.000160 33 3.13% : 0.000005s : 2: substitution.elim_not_effective 4.96% : 0.000008s : 2: substitution.fold_const_symbol 4.90% : 0.000008s : 8: substitution.graph_param_transform 75.32% : 0.000121s : 1: substitution.inline 2.56% : 0.000004s : 4: substitution.j_node_and_user_rematch 3.43% : 0.000005s : 4: substitution.remove_not_recompute_node 5.71% : 0.000009s : 12: substitution.replace_old_param ------[type_inference.] 0.076365 2 88.56% : 0.067631s : 1: type_inference.infer 11.44% : 0.008734s : 1: type_inference.specialize ------[replace.] 0.000024 1 100.00% : 0.000024s : 1: replace.inline ------[match.] 0.000119 1 100.00% : 0.000119s : 1: match.inline ------[predicate.] 0.000250 1879 0.72% : 0.000002s : 17: predicate.accumulaten_eliminater 1.94% : 0.000005s : 8: predicate.ad_related_special_op_eliminate 0.74% : 0.000002s : 16: predicate.addn_check_dump 0.72% : 0.000002s : 17: predicate.addn_zero_filter 0.77% : 0.000002s : 17: predicate.adjust_all_reduce_mul_add 1.69% : 0.000004s : 33: predicate.arithmetic_simplify 0.79% : 0.000002s : 17: predicate.cast_eliminate 0.86% : 0.000002s : 16: predicate.check_bprop_eliminate 0.65% : 0.000002s : 16: predicate.compare_switch_simplify 0.25% : 0.000001s : 8: predicate.const_output_eliminate 0.71% : 0.000002s : 16: predicate.depend_value_elim 0.82% : 0.000002s : 17: predicate.dict_get_item_const_eliminator 0.91% : 0.000002s : 17: predicate.dict_get_item_eliminator 0.80% : 0.000002s : 17: predicate.dict_set_item_eliminator 2.06% : 0.000005s : 16: predicate.dumpgradient_eliminate 0.38% : 0.000001s : 8: predicate.elim_not_effective 0.62% : 0.000002s : 8: predicate.elim_shapecalc_of_broadcastargs 1.06% : 0.000003s : 25: predicate.environ_add_const_eliminate 1.07% : 0.000003s : 25: predicate.environ_get_add_eliminate 0.99% : 0.000002s : 25: predicate.environ_get_depend_swap 1.81% : 0.000005s : 41: predicate.environ_get_eliminate 1.06% : 0.000003s : 25: predicate.environ_get_set_eliminate 0.79% : 0.000002s : 18: predicate.exchange_switch_depend_value 1.58% : 0.000004s : 18: predicate.float_depend_g_call 0.66% : 0.000002s : 16: predicate.float_environ_get_switch 1.06% : 0.000003s : 24: predicate.float_tuple_getitem_switch 0.26% : 0.000001s : 8: predicate.fold_const_symbol 0.82% : 0.000002s : 16: predicate.get_grad_eliminate 0.31% : 0.000001s : 8: predicate.graph_param_transform 0.66% : 0.000002s : 16: predicate.incorporate_call 0.62% : 0.000002s : 16: predicate.incorporate_call_switch 5.69% : 0.000014s : 83: predicate.inline 1.11% : 0.000003s : 16: predicate.inline_without_move 0.48% : 0.000001s : 16: predicate.j_node_and_user_rematch 0.92% : 0.000002s : 16: predicate.less_batch_normalization 1.45% : 0.000004s : 33: predicate.list_to_tuple_eliminator_ 2.15% : 0.000005s : 50: predicate.load_eliminater 1.09% : 0.000003s : 8: predicate.loop_unroll_after_grad 1.22% : 0.000003s : 25: predicate.loop_unroll_before_grad 5.67% : 0.000014s : 33: predicate.make_slice_get_slice_eliminator 0.74% : 0.000002s : 16: predicate.merge_addn 0.69% : 0.000002s : 16: predicate.micro_step_allgather_replace 0.71% : 0.000002s : 16: predicate.mini_step_allgather_replace 0.65% : 0.000002s : 17: predicate.minmaximum_grad 1.66% : 0.000004s : 8: predicate.mutable_eliminate 0.42% : 0.000001s : 8: predicate.opt_reshape 0.40% : 0.000001s : 8: predicate.parallel_virtual_node 0.95% : 0.000002s : 18: predicate.partial_defer_inline 1.15% : 0.000003s : 25: predicate.partial_eliminate 0.71% : 0.000002s : 17: predicate.print_const_string_wrapper 0.70% : 0.000002s : 16: predicate.reduce_all_const_elim 1.00% : 0.000002s : 17: predicate.reduce_eliminate 2.12% : 0.000005s : 50: predicate.redundant_stop_gradient_eliminater 0.71% : 0.000002s : 16: predicate.remove_not_recompute_node 1.47% : 0.000004s : 33: predicate.replace_applicator 0.79% : 0.000002s : 16: predicate.replace_old_param 0.42% : 0.000001s : 8: predicate.reset_defer_inline 0.82% : 0.000002s : 17: predicate.reshape_eliminate 0.88% : 0.000002s : 16: predicate.row_tensor_add_zeros_like 0.41% : 0.000001s : 8: predicate.row_tensor_eliminate 1.08% : 0.000003s : 16: predicate.same_eliminate 0.61% : 0.000002s : 16: predicate.set_cell_output_no_recompute 0.98% : 0.000002s : 16: predicate.shard_identity_eliminate 0.95% : 0.000002s : 16: predicate.special_op_eliminate 0.73% : 0.000002s : 16: predicate.specialize_transform 1.21% : 0.000003s : 16: predicate.split_environ_get_set_with_tuple_value 1.13% : 0.000003s : 16: predicate.stack_unstack_eliminate 0.45% : 0.000001s : 8: predicate.switch_call_monad_eliminater 0.78% : 0.000002s : 18: predicate.switch_defer_inline 1.54% : 0.000004s : 34: predicate.switch_layer_defer_inline 3.34% : 0.000008s : 67: predicate.switch_simplify 0.77% : 0.000002s : 17: predicate.tile_eliminate 0.76% : 0.000002s : 17: predicate.transpose_eliminate 1.39% : 0.000003s : 33: predicate.tuple_list_convert_item_index_to_positive 1.38% : 0.000003s : 33: predicate.tuple_list_get_item_const_eliminator 1.49% : 0.000004s : 33: predicate.tuple_list_get_item_depend_reorder 2.90% : 0.000007s : 49: predicate.tuple_list_get_item_eliminator 1.38% : 0.000003s : 33: predicate.tuple_list_get_set_item_eliminator 2.27% : 0.000006s : 49: predicate.tuple_list_set_item_eliminator 1.66% : 0.000004s : 33: predicate.tuple_to_list_eliminator_ 1.98% : 0.000005s : 50: predicate.updatestate_pure_node_eliminater 2.83% : 0.000007s : 66: predicate.updatestate_useless_node_eliminater 0.41% : 0.000001s : 8: predicate.value_based_eliminate 0.80% : 0.000002s : 16: predicate.virtual_dataset_eliminate 1.04% : 0.000003s : 16: predicate.virtual_output_eliminate 0.35% : 0.000001s : 8: predicate.virtual_view_grad_eliminate 0.42% : 0.000001s : 8: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.006547 6 7.67% : 0.000502s : 3: func_graph_cloner_run.FuncGraphClonerGraph 92.33% : 0.006044s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.298971 192 0.00% : 0.000004s : 1: ForceFp32Comm 32.35% : 0.096702s : 1: add_attr 32.34% : 0.096681s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.03% : 0.000076s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.04% : 0.000108s : 1: auto_monad 0.01% : 0.000037s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 1.65% : 0.004926s : 1: bootstrap 0.01% : 0.000044s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.01% : 0.000022s : 1: control_data_broadcast_order 0.01% : 0.000016s : 1: convert_after_rewriter 0.02% : 0.000045s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000012s : 1: environ_conv 0.04% : 0.000108s : 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% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000009s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.18% : 0.000525s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.28% : 0.000840s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.01% : 0.000020s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000027s : 1: opt.transform.mutable_eliminate 0.50% : 0.001509s : 78: opt.transform.opt_a 0.02% : 0.000048s : 1: opt.transform.opt_after_cconv 0.02% : 0.000073s : 1: opt.transform.opt_after_jit_grad 0.07% : 0.000200s : 28: opt.transform.opt_b 0.03% : 0.000081s : 2: opt.transform.opt_trans_graph 0.03% : 0.000079s : 4: opt.transform.symbol_engine_opt 1.26% : 0.003769s : 1: opt_a 0.06% : 0.000165s : 1: opt_after_cconv 0.32% : 0.000955s : 1: opt_after_jit_grad 0.12% : 0.000372s : 1: opt_b 2.31% : 0.006905s : 1: optimize 0.01% : 0.000034s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.01% : 0.000032s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000009s : 1: overlap_grad_ring_attention 0.00% : 0.000009s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 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% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000050s : 1: pre_auto_parallel 0.01% : 0.000038s : 1: py_interpret_to_execute 0.01% : 0.000034s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.03% : 0.000081s : 1: remove_dup_value 0.16% : 0.000479s : 1: renormalize.infer 0.21% : 0.000622s : 1: renormalize.specialize 0.00% : 0.000012s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000074s : 1: rewriter_after_opt_a 0.03% : 0.000093s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.08% : 0.000242s : 1: symbol_engine_optimizer 0.04% : 0.000116s : 1: tuple_transform 27.57% : 0.082441s : 1: type_inference .[WARNING] PRE_ACT(159070,ffff83dfcf30,python3.9):2026-01-29-17:38:19.556.090 [mindspore/ccsrc/runtime/memory/mem_pool/abstract_dynamic_mem_pool.cc:1109] FreeIdleMemsByEagerFree] Eager free count : 2, free memory : 1357689856, real free : 1358954496, not free : 0. [hook] pytest_runtest_teardown:test_paged_attention_fd_long[1] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_fd_long[1],max_mem:1392.0M =============================== 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 97.02s (0:01:37) ===================