==================================================Ascend ============================= test session starts ============================== platform linux -- Python 3.9.19, pytest-6.2.5, py-1.11.0, pluggy-1.5.0 rootdir: /home/jenkins/mindspore/testcases/testcases/tests/st/infer/ops/test_internal_ops, configfile: ../../../../../../../../sault/virtual_test/virtualenv_007/sault/config/pytest.ini plugins: mock-3.14.0, hydra-core-1.3.2, forked-1.6.0, anyio-4.9.0, xdist-1.32.0 collected 1 item test_paged_attention.py [WARNING] ME(154569:281473892511536,MainProcess):2026-01-29-17:37:18.889.315 [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 = 0.159083, [21] [bootstrap]: 0.00072799 [type_inference]: 0.142016 [event_method]: 1.912e-05 [auto_monad]: 0.00010094 [graph_reusing]: 4.90001e-06 [inline]: 3.14999e-06 [add_attr]: 0.00842397, [1] [add_attr_with_inline]: 0.0084099, [1] [Cycle 1]: 9.005e-05, [2] [tag_attr]: 2.13e-05 [meta_addattr_fg_expand]: 4.90001e-06 [parallel-infer-symbol]: 3.44001e-06 [pre_auto_parallel]: 4.787e-05 [insert-virtual-dataset]: 2.66e-06 [parallel-infer-symbol-second]: 7.99977e-07 [dataset_repeat_opt]: 2.12999e-06 [pipeline_split]: 2.05002e-06 [optimize]: 0.00692513, [53] [py_interpret_to_execute]: 2.693e-05 [rewriter_before_opt_a]: 8.735e-05 [opt_a]: 0.00393245, [2] [Cycle 1]: 0.00253332, [45] [expand_dump_flag]: 2.37999e-06 [switch_simplify]: 3.297e-05 [loop_unroll]: 2.098e-05 [a_1]: 0.0006449 [with_stream_mark]: 2.522e-05 [recompute_prepare]: 1.549e-05 [updatestate_depend_eliminate]: 6.04999e-06 [updatestate_assign_eliminate]: 4.88001e-06 [updatestate_loads_eliminate]: 4.83001e-06 [parameter_eliminate]: 1.98002e-06 [a_2]: 0.00014688 [accelerated_algorithm]: 1.182e-05 [shard]: 2.34999e-06 [meta_shard_fg_expand]: 2.12999e-06 [shard_inline]: 1.147e-05 [merge_send_recv]: 1.066e-05 [auto_parallel]: 9.69999e-06 [parallel]: 5.348e-05 [flash_sp]: 1.156e-05 [merge_comm]: 6.71999e-06 [allreduce_fusion]: 4.77e-06 [matmul_add_comm_reduction]: 1.213e-05 [allreduce_slice_to_reducescatter]: 7.89994e-07 [virtual_shard_identity]: 1.405e-05 [virtual_dataset]: 1.094e-05 [get_grad_eliminate_]: 1.031e-05 [virtual_output]: 1.059e-05 [merge_forward]: 5.79e-06 [cell_reuse_recompute_pass]: 1.64e-06 [offload_activation]: 1.2e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.01e-05 [merge_recompute_call_nodes]: 2.14999e-06 [before_grad]: 1.614e-05 [set_forward_comm_id_for_comm_node_pass]: 4.94e-06 [meta_fg_expand]: 3.88999e-06 [flash_sp_send_recv_attached]: 2.88e-06 [receive_attached]: 2.39999e-06 [after_resolve]: 2.207e-05 [a_after_grad]: 1.76e-05 [renormalize]: 0.00082071 [add_forward_monad_depend]: 5.91e-06 [auto_monad_grad]: 2.88998e-06 [auto_monad_eliminator]: 2.066e-05 [cse]: 0.00012711 [a_3]: 8.489e-05 [Cycle 2]: 0.00138692, [45] [expand_dump_flag]: 2.48002e-06 [switch_simplify]: 1.35e-05 [loop_unroll]: 1.132e-05 [a_1]: 0.00033288 [with_stream_mark]: 2.007e-05 [recompute_prepare]: 1.161e-05 [updatestate_depend_eliminate]: 5.54e-06 [updatestate_assign_eliminate]: 4.18999e-06 [updatestate_loads_eliminate]: 4.30999e-06 [parameter_eliminate]: 1.72999e-06 [a_2]: 0.00039047 [accelerated_algorithm]: 1.384e-05 [shard]: 2.52001e-06 [meta_shard_fg_expand]: 2.53e-06 [shard_inline]: 1.146e-05 [merge_send_recv]: 1.071e-05 [auto_parallel]: 1.022e-05 [parallel]: 7.76001e-06 [flash_sp]: 4.53001e-06 [merge_comm]: 5.27999e-06 [allreduce_fusion]: 4.60001e-06 [matmul_add_comm_reduction]: 9.22999e-06 [allreduce_slice_to_reducescatter]: 8.59989e-07 [virtual_shard_identity]: 1.33e-05 [virtual_dataset]: 1.139e-05 [get_grad_eliminate_]: 1.111e-05 [virtual_output]: 1.104e-05 [merge_forward]: 5.32999e-06 [cell_reuse_recompute_pass]: 2.29999e-06 [offload_activation]: 9.94999e-06 [cell_reuse_handle_not_recompute_node_pass]: 2.004e-05 [merge_recompute_call_nodes]: 1.00001e-06 [before_grad]: 1.457e-05 [set_forward_comm_id_for_comm_node_pass]: 4.95001e-06 [meta_fg_expand]: 3.24001e-06 [flash_sp_send_recv_attached]: 1.25999e-06 [receive_attached]: 2.16e-06 [after_resolve]: 2.267e-05 [a_after_grad]: 1.726e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 3.03e-06 [auto_monad_grad]: 1.80001e-06 [auto_monad_eliminator]: 1.329e-05 [cse]: 4.092e-05 [a_3]: 6.828e-05 [py_interpret_to_execute_after_opt_a]: 2.017e-05 [slice_cell_reuse_recomputed_activation]: 2.16e-06 [rewriter_after_opt_a]: 8.879e-05 [convert_after_rewriter]: 1.073e-05 [order_py_execute_after_rewriter]: 7.09001e-06 [mutable_eliminate]: 0.00073674 [opt_b]: 0.00034702, [1] [Cycle 1]: 0.00033766, [7] [b_1]: 0.00022357 [b_2]: 1.256e-05 [updatestate_depend_eliminate]: 9.86998e-06 [updatestate_assign_eliminate]: 4.79002e-06 [updatestate_loads_eliminate]: 4.12e-06 [renormalize]: 1.00001e-06 [cse]: 4.426e-05 [optimize_parallel_all_gather_comm]: 2.38e-05 [overlap_param_gather]: 5.97999e-06 [cconv]: 3.524e-05 [loop_unroll]: 0.00052465 [opt_after_cconv]: 0.00016089, [1] [Cycle 1]: 0.00015373, [7] [c_1]: 5.893e-05 [parameter_eliminate]: 3.81001e-06 [updatestate_depend_eliminate]: 8.33001e-06 [updatestate_assign_eliminate]: 4.23999e-06 [updatestate_loads_eliminate]: 4.03001e-06 [cse]: 3.954e-05 [renormalize]: 4.00003e-07 [remove_dup_value]: 6.016e-05 [tuple_transform]: 0.00012108, [1] [Cycle 1]: 0.00011589, [4] [d_1]: 8.344e-05 [none_parameter_eliminate]: 1.71e-06 [renormalize]: 2.19996e-07 [switch_simplify]: 1.177e-05 [partial_unused_args_eliminate]: 2.07999e-06 [add_recomputation]: 6.638e-05 [cse_after_recomputation]: 3.492e-05, [1] [Cycle 1]: 2.962e-05, [1] [cse]: 2.343e-05 [environ_conv]: 2.082e-05 [swap_dp_allreduce_reducescatter]: 7.27002e-06 [bias_add_comm_swap]: 2.74001e-06 [label_micro_interleaved_index]: 5.16002e-06 [label_fine_grained_interleaved_index]: 2.78e-06 [merge_cast_opt]: 1.76003e-06 [slice_recompute_activation]: 2.40002e-06 [micro_interleaved_order_control]: 2.56e-06 [assign_add_opt]: 1.35001e-06 [ForceFp32Comm]: 1.09e-06 [remove_cast_before_assign_add]: 1.05001e-06 [full_micro_interleaved_order_control]: 2.32999e-06 [reorder_send_recv_between_fp_bp]: 3.03e-06 [comm_op_add_attrs]: 1.10999e-06 [add_comm_op_reuse_tag]: 1.10001e-06 [interleave_split_concat_branches]: 1.15001e-06 [interleave_parallel_branches]: 1.08001e-06 [overlap_opt_shard_in_pipeline]: 2.396e-05 [overlap_opt_shard_grad_in_pipeline]: 1.70001e-06 [control_data_broadcast_order]: 1.934e-05 [grouped_pairwise_exchange_alltoall]: 1.97001e-06 [offloading_packed_experts]: 5.44998e-06 [overlap_recompute_and_grad_model_parallel]: 6.56999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.34e-06 [overlap_recompute_allgather_and_fa_grad]: 1.47001e-06 [overlap_recompute_comm]: 2.36998e-06 [overlap_grad_ring_attention]: 1.718e-05 [overlap_grad_flash_sp]: 3.909e-05 [begin_end_overlap_inline]: 5.19998e-07 [split_matmul_comm_elemetwise]: 2.27999e-06 [split_layernorm_comm]: 1.71e-06 [handle_group_info]: 1.07e-06 [symbol_engine_optimizer]: 0.00020274, [1] [Cycle 1]: 0.00019796, [6] [build]: 8.796e-05 [elim_shapecalc]: 1.647e-05 [elim_not_effective]: 2.76e-05 [opt_reshape]: 1.146e-05 [fold_const_symbol]: 2.24e-05 [renormalize]: 1.79978e-07 [detach_backward]: 2.37999e-06 [pipeline_parallel_scheduler]: 1.47001e-06 [auto_monad_reorder]: 2.897e-05 [get_jit_bprop_graph]: 2.12999e-06 [rewriter_after_jit_bprop_graph]: 4.63001e-06 [opt_after_jit_grad]: 0.00053211 [validate]: 6.6e-05 Sums bootstrap : 0.000728s : 0.49% type_inference : 0.142016s : 94.93% event_method : 0.000019s : 0.01% auto_monad : 0.000101s : 0.07% graph_reusing : 0.000005s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000021s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000003s : 0.00% pre_auto_parallel : 0.000048s : 0.03% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000027s : 0.02% optimize.rewriter_before_opt_a : 0.000087s : 0.06% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000046s : 0.03% optimize.opt_a.loop_unroll : 0.000032s : 0.02% optimize.opt_a.a_1 : 0.000978s : 0.65% optimize.opt_a.with_stream_mark : 0.000045s : 0.03% optimize.opt_a.recompute_prepare : 0.000027s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000009s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000009s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000537s : 0.36% optimize.opt_a.accelerated_algorithm : 0.000026s : 0.02% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000023s : 0.02% optimize.opt_a.merge_send_recv : 0.000021s : 0.01% optimize.opt_a.auto_parallel : 0.000020s : 0.01% optimize.opt_a.parallel : 0.000061s : 0.04% optimize.opt_a.flash_sp : 0.000016s : 0.01% optimize.opt_a.merge_comm : 0.000012s : 0.01% optimize.opt_a.allreduce_fusion : 0.000009s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000021s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000027s : 0.02% optimize.opt_a.virtual_dataset : 0.000022s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000021s : 0.01% optimize.opt_a.virtual_output : 0.000022s : 0.01% optimize.opt_a.merge_forward : 0.000011s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000022s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000040s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000031s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000010s : 0.01% optimize.opt_a.meta_fg_expand : 0.000007s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000045s : 0.03% optimize.opt_a.a_after_grad : 0.000035s : 0.02% optimize.opt_a.renormalize : 0.000821s : 0.55% optimize.opt_a.add_forward_monad_depend : 0.000009s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000034s : 0.02% optimize.opt_a.cse : 0.000168s : 0.11% optimize.opt_a.a_3 : 0.000153s : 0.10% optimize.py_interpret_to_execute_after_opt_a : 0.000020s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000089s : 0.06% optimize.convert_after_rewriter : 0.000011s : 0.01% optimize.order_py_execute_after_rewriter : 0.000007s : 0.00% optimize.mutable_eliminate : 0.000737s : 0.49% optimize.opt_b.b_1 : 0.000224s : 0.15% optimize.opt_b.b_2 : 0.000013s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000010s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000044s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000024s : 0.02% optimize.overlap_param_gather : 0.000006s : 0.00% optimize.cconv : 0.000035s : 0.02% optimize.loop_unroll : 0.000525s : 0.35% optimize.opt_after_cconv.c_1 : 0.000059s : 0.04% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% 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 : 0.000040s : 0.03% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000060s : 0.04% optimize.tuple_transform.d_1 : 0.000083s : 0.06% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000012s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000066s : 0.04% optimize.cse_after_recomputation.cse : 0.000023s : 0.02% optimize.environ_conv : 0.000021s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000007s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000005s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000024s : 0.02% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000019s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000005s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 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 : 0.000017s : 0.01% optimize.overlap_grad_flash_sp : 0.000039s : 0.03% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000088s : 0.06% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000016s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000028s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000011s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000022s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000029s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.00% opt_after_jit_grad : 0.000532s : 0.36% validate : 0.000066s : 0.04% Time group info: ------[substitution.] 0.000153 39 7.13% : 0.000011s : 2: substitution.elim_not_effective 5.81% : 0.000009s : 2: substitution.fold_const_symbol 5.62% : 0.000009s : 10: substitution.graph_param_transform 68.11% : 0.000104s : 1: substitution.inline 2.61% : 0.000004s : 4: substitution.j_node_and_user_rematch 3.55% : 0.000005s : 4: substitution.remove_not_recompute_node 7.18% : 0.000011s : 16: substitution.replace_old_param ------[type_inference.] 0.141909 2 99.58% : 0.141308s : 1: type_inference.infer 0.42% : 0.000601s : 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.] 0.000494 2335 0.40% : 0.000002s : 21: predicate.accumulaten_eliminater 0.39% : 0.000002s : 10: predicate.ad_related_special_op_eliminate 0.38% : 0.000002s : 20: predicate.addn_check_dump 0.55% : 0.000003s : 21: predicate.addn_zero_filter 0.37% : 0.000002s : 21: predicate.adjust_all_reduce_mul_add 1.03% : 0.000005s : 41: predicate.arithmetic_simplify 0.40% : 0.000002s : 21: predicate.cast_eliminate 0.42% : 0.000002s : 20: predicate.check_bprop_eliminate 0.37% : 0.000002s : 20: predicate.compare_switch_simplify 0.15% : 0.000001s : 10: predicate.const_output_eliminate 0.45% : 0.000002s : 20: predicate.depend_value_elim 0.44% : 0.000002s : 21: predicate.dict_get_item_const_eliminator 0.51% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.42% : 0.000002s : 21: predicate.dict_set_item_eliminator 0.57% : 0.000003s : 20: predicate.dumpgradient_eliminate 0.18% : 0.000001s : 10: predicate.elim_not_effective 0.22% : 0.000001s : 10: predicate.elim_shapecalc_of_broadcastargs 0.66% : 0.000003s : 31: predicate.environ_add_const_eliminate 0.57% : 0.000003s : 31: predicate.environ_get_add_eliminate 0.56% : 0.000003s : 31: predicate.environ_get_depend_swap 1.10% : 0.000005s : 51: predicate.environ_get_eliminate 0.57% : 0.000003s : 31: predicate.environ_get_set_eliminate 0.40% : 0.000002s : 22: predicate.exchange_switch_depend_value 0.83% : 0.000004s : 22: predicate.float_depend_g_call 0.37% : 0.000002s : 20: predicate.float_environ_get_switch 0.55% : 0.000003s : 30: predicate.float_tuple_getitem_switch 0.16% : 0.000001s : 10: predicate.fold_const_symbol 0.44% : 0.000002s : 20: predicate.get_grad_eliminate 0.22% : 0.000001s : 10: predicate.graph_param_transform 0.61% : 0.000003s : 20: predicate.incorporate_call 0.35% : 0.000002s : 20: predicate.incorporate_call_switch 3.01% : 0.000015s : 103: predicate.inline 0.54% : 0.000003s : 20: predicate.inline_without_move 0.30% : 0.000001s : 20: predicate.j_node_and_user_rematch 0.54% : 0.000003s : 20: predicate.less_batch_normalization 0.93% : 0.000005s : 41: predicate.list_to_tuple_eliminator_ 1.16% : 0.000006s : 62: predicate.load_eliminater 0.58% : 0.000003s : 10: predicate.loop_unroll_after_grad 0.66% : 0.000003s : 31: predicate.loop_unroll_before_grad 0.97% : 0.000005s : 41: predicate.make_slice_get_slice_eliminator 0.41% : 0.000002s : 20: predicate.merge_addn 0.40% : 0.000002s : 20: predicate.micro_step_allgather_replace 0.39% : 0.000002s : 20: predicate.mini_step_allgather_replace 0.37% : 0.000002s : 21: predicate.minmaximum_grad 0.63% : 0.000003s : 10: predicate.mutable_eliminate 0.24% : 0.000001s : 10: predicate.opt_reshape 0.22% : 0.000001s : 10: predicate.parallel_virtual_node 0.53% : 0.000003s : 22: predicate.partial_defer_inline 0.68% : 0.000003s : 31: predicate.partial_eliminate 0.38% : 0.000002s : 21: predicate.print_const_string_wrapper 0.39% : 0.000002s : 20: predicate.reduce_all_const_elim 0.51% : 0.000003s : 21: predicate.reduce_eliminate 1.15% : 0.000006s : 62: predicate.redundant_stop_gradient_eliminater 0.43% : 0.000002s : 20: predicate.remove_not_recompute_node 0.80% : 0.000004s : 41: predicate.replace_applicator 0.42% : 0.000002s : 20: predicate.replace_old_param 0.22% : 0.000001s : 10: predicate.reset_defer_inline 0.41% : 0.000002s : 21: predicate.reshape_eliminate 0.42% : 0.000002s : 20: predicate.row_tensor_add_zeros_like 0.23% : 0.000001s : 10: predicate.row_tensor_eliminate 0.55% : 0.000003s : 20: predicate.same_eliminate 0.36% : 0.000002s : 20: predicate.set_cell_output_no_recompute 0.62% : 0.000003s : 20: predicate.shard_identity_eliminate 0.48% : 0.000002s : 20: predicate.special_op_eliminate 0.44% : 0.000002s : 20: predicate.specialize_transform 0.67% : 0.000003s : 20: predicate.split_environ_get_set_with_tuple_value 0.60% : 0.000003s : 20: predicate.stack_unstack_eliminate 0.24% : 0.000001s : 10: predicate.switch_call_monad_eliminater 0.45% : 0.000002s : 22: predicate.switch_defer_inline 0.83% : 0.000004s : 42: predicate.switch_layer_defer_inline 1.82% : 0.000009s : 83: predicate.switch_simplify 0.40% : 0.000002s : 21: predicate.tile_eliminate 0.40% : 0.000002s : 21: predicate.transpose_eliminate 0.85% : 0.000004s : 41: predicate.tuple_list_convert_item_index_to_positive 0.83% : 0.000004s : 41: predicate.tuple_list_get_item_const_eliminator 0.78% : 0.000004s : 41: predicate.tuple_list_get_item_depend_reorder 49.71% : 0.000246s : 61: predicate.tuple_list_get_item_eliminator 0.81% : 0.000004s : 41: predicate.tuple_list_get_set_item_eliminator 1.27% : 0.000006s : 61: predicate.tuple_list_set_item_eliminator 0.81% : 0.000004s : 41: predicate.tuple_to_list_eliminator_ 1.11% : 0.000006s : 62: predicate.updatestate_pure_node_eliminater 1.65% : 0.000008s : 82: predicate.updatestate_useless_node_eliminater 0.20% : 0.000001s : 10: predicate.value_based_eliminate 0.47% : 0.000002s : 20: predicate.virtual_dataset_eliminate 0.54% : 0.000003s : 20: predicate.virtual_output_eliminate 0.24% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.30% : 0.000001s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000553 6 49.82% : 0.000276s : 3: func_graph_cloner_run.FuncGraphClonerGraph 50.18% : 0.000277s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.177568 192 0.00% : 0.000004s : 1: ForceFp32Comm 4.75% : 0.008430s : 1: add_attr 4.74% : 0.008414s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.04% : 0.000071s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.06% : 0.000107s : 1: auto_monad 0.02% : 0.000033s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.43% : 0.000761s : 1: bootstrap 0.02% : 0.000039s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000023s : 1: control_data_broadcast_order 0.01% : 0.000014s : 1: convert_after_rewriter 0.02% : 0.000038s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000026s : 1: environ_conv 0.02% : 0.000027s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000009s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.30% : 0.000534s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.42% : 0.000747s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.01% : 0.000023s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000025s : 1: opt.transform.mutable_eliminate 1.11% : 0.001966s : 78: opt.transform.opt_a 0.03% : 0.000057s : 1: opt.transform.opt_after_cconv 0.02% : 0.000040s : 1: opt.transform.opt_after_jit_grad 0.12% : 0.000208s : 28: opt.transform.opt_b 0.05% : 0.000093s : 2: opt.transform.opt_trans_graph 0.04% : 0.000074s : 4: opt.transform.symbol_engine_opt 2.22% : 0.003936s : 1: opt_a 0.09% : 0.000165s : 1: opt_after_cconv 0.30% : 0.000541s : 1: opt_after_jit_grad 0.20% : 0.000351s : 1: opt_b 3.90% : 0.006931s : 1: optimize 0.02% : 0.000028s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000010s : 1: order_py_execute_after_rewriter 0.02% : 0.000043s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000022s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.02% : 0.000028s : 1: overlap_opt_shard_in_pipeline 0.01% : 0.000010s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000010s : 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% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.03% : 0.000052s : 1: pre_auto_parallel 0.02% : 0.000031s : 1: py_interpret_to_execute 0.01% : 0.000024s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.04% : 0.000065s : 1: remove_dup_value 0.24% : 0.000433s : 1: renormalize.infer 0.21% : 0.000378s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.05% : 0.000094s : 1: rewriter_after_opt_a 0.05% : 0.000092s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.01% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.12% : 0.000206s : 1: symbol_engine_optimizer 0.07% : 0.000124s : 1: tuple_transform 79.99% : 0.142037s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_pangu38b_1[QuantMethod.INT_CUBE-0] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_pangu38b_1[QuantMethod.INT_CUBE-0],max_mem:1052.0M =============================== 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 ================== 1 passed, 25 warnings in 418.90s (0:06:58) ==================