==================================================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 2 items test_paged_attention.py [WARNING] ME(167516:281472989335344,MainProcess):2026-01-29-17:37:49.723.191 [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 = 0.0356402, [21] [bootstrap]: 0.00070147 [type_inference]: 0.0205794 [event_method]: 1.228e-05 [auto_monad]: 8.298e-05 [graph_reusing]: 4.48999e-06 [inline]: 2.58e-06 [add_attr]: 0.00789179, [1] [add_attr_with_inline]: 0.0078789, [1] [Cycle 1]: 8.007e-05, [2] [tag_attr]: 1.832e-05 [meta_addattr_fg_expand]: 4.11001e-06 [parallel-infer-symbol]: 3.8e-06 [pre_auto_parallel]: 4.128e-05 [insert-virtual-dataset]: 2.61999e-06 [parallel-infer-symbol-second]: 8.09989e-07 [dataset_repeat_opt]: 1.56998e-06 [pipeline_split]: 1.76e-06 [optimize]: 0.00555881, [53] [py_interpret_to_execute]: 2.33e-05 [rewriter_before_opt_a]: 7.254e-05 [opt_a]: 0.00297631, [2] [Cycle 1]: 0.00200861, [45] [expand_dump_flag]: 2.37999e-06 [switch_simplify]: 3.105e-05 [loop_unroll]: 1.955e-05 [a_1]: 0.00041045 [with_stream_mark]: 1.804e-05 [recompute_prepare]: 1.422e-05 [updatestate_depend_eliminate]: 5.47001e-06 [updatestate_assign_eliminate]: 4.91002e-06 [updatestate_loads_eliminate]: 5.22e-06 [parameter_eliminate]: 1.72001e-06 [a_2]: 0.00014131 [accelerated_algorithm]: 1.148e-05 [shard]: 2.12001e-06 [meta_shard_fg_expand]: 2.06e-06 [shard_inline]: 1.089e-05 [merge_send_recv]: 2.807e-05 [auto_parallel]: 8.95999e-06 [parallel]: 4.31e-05 [flash_sp]: 1.869e-05 [merge_comm]: 5.67999e-06 [allreduce_fusion]: 4.88001e-06 [matmul_add_comm_reduction]: 1.124e-05 [allreduce_slice_to_reducescatter]: 7.39994e-07 [virtual_shard_identity]: 1.377e-05 [virtual_dataset]: 1.066e-05 [get_grad_eliminate_]: 1.008e-05 [virtual_output]: 1.049e-05 [merge_forward]: 5.56002e-06 [cell_reuse_recompute_pass]: 1.68002e-06 [offload_activation]: 1.052e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.744e-05 [merge_recompute_call_nodes]: 1.48002e-06 [before_grad]: 1.491e-05 [set_forward_comm_id_for_comm_node_pass]: 5.22e-06 [meta_fg_expand]: 3.33e-06 [flash_sp_send_recv_attached]: 2.76999e-06 [receive_attached]: 1.113e-05 [after_resolve]: 2.269e-05 [a_after_grad]: 1.622e-05 [renormalize]: 0.00060992 [add_forward_monad_depend]: 5.61e-06 [auto_monad_grad]: 2.53998e-06 [auto_monad_eliminator]: 1.647e-05 [cse]: 0.00010135 [a_3]: 7.871e-05 [Cycle 2]: 0.00095568, [45] [expand_dump_flag]: 1.27e-06 [switch_simplify]: 1.202e-05 [loop_unroll]: 1.031e-05 [a_1]: 0.00024638 [with_stream_mark]: 1.397e-05 [recompute_prepare]: 1.032e-05 [updatestate_depend_eliminate]: 5.32001e-06 [updatestate_assign_eliminate]: 4.33999e-06 [updatestate_loads_eliminate]: 5.01002e-06 [parameter_eliminate]: 2.34999e-06 [a_2]: 0.00012965 [accelerated_algorithm]: 1.11e-05 [shard]: 1.32e-06 [meta_shard_fg_expand]: 1.79998e-06 [shard_inline]: 1.024e-05 [merge_send_recv]: 7.46001e-06 [auto_parallel]: 8.92e-06 [parallel]: 5.99999e-06 [flash_sp]: 3.69002e-06 [merge_comm]: 4.37998e-06 [allreduce_fusion]: 4.32e-06 [matmul_add_comm_reduction]: 7.53999e-06 [allreduce_slice_to_reducescatter]: 3.7998e-07 [virtual_shard_identity]: 1.234e-05 [virtual_dataset]: 1.005e-05 [get_grad_eliminate_]: 9.50001e-06 [virtual_output]: 9.41e-06 [merge_forward]: 5.00001e-06 [cell_reuse_recompute_pass]: 1.45001e-06 [offload_activation]: 8.81002e-06 [cell_reuse_handle_not_recompute_node_pass]: 1.925e-05 [merge_recompute_call_nodes]: 1.04e-06 [before_grad]: 1.411e-05 [set_forward_comm_id_for_comm_node_pass]: 4.88001e-06 [meta_fg_expand]: 2.71e-06 [flash_sp_send_recv_attached]: 1.11002e-06 [receive_attached]: 1.74e-06 [after_resolve]: 2.148e-05 [a_after_grad]: 1.658e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 2.14999e-06 [auto_monad_grad]: 1.59998e-06 [auto_monad_eliminator]: 1.001e-05 [cse]: 3.014e-05 [a_3]: 6.379e-05 [py_interpret_to_execute_after_opt_a]: 1.32e-05 [slice_cell_reuse_recomputed_activation]: 2.78998e-06 [rewriter_after_opt_a]: 6.558e-05 [convert_after_rewriter]: 1.908e-05 [order_py_execute_after_rewriter]: 7.18998e-06 [mutable_eliminate]: 0.00062859 [opt_b]: 0.0003193, [1] [Cycle 1]: 0.00031172, [7] [b_1]: 0.0002095 [b_2]: 1.218e-05 [updatestate_depend_eliminate]: 7.51999e-06 [updatestate_assign_eliminate]: 4.24002e-06 [updatestate_loads_eliminate]: 4.42e-06 [renormalize]: 9.89996e-07 [cse]: 3.876e-05 [optimize_parallel_all_gather_comm]: 1.993e-05 [overlap_param_gather]: 4.00998e-06 [cconv]: 2.794e-05 [loop_unroll]: 0.00044618 [opt_after_cconv]: 0.00014611, [1] [Cycle 1]: 0.00013974, [7] [c_1]: 5.252e-05 [parameter_eliminate]: 3.16001e-06 [updatestate_depend_eliminate]: 7.15003e-06 [updatestate_assign_eliminate]: 4e-06 [updatestate_loads_eliminate]: 4.41002e-06 [cse]: 3.638e-05 [renormalize]: 3.89991e-07 [remove_dup_value]: 5.07e-05 [tuple_transform]: 0.00010812, [1] [Cycle 1]: 0.000103, [4] [d_1]: 7.199e-05 [none_parameter_eliminate]: 1.75001e-06 [renormalize]: 1.60013e-07 [switch_simplify]: 1.107e-05 [partial_unused_args_eliminate]: 1.91e-06 [add_recomputation]: 5.45e-05 [cse_after_recomputation]: 3.241e-05, [1] [Cycle 1]: 2.758e-05, [1] [cse]: 2.183e-05 [environ_conv]: 1.576e-05 [swap_dp_allreduce_reducescatter]: 7.70998e-06 [bias_add_comm_swap]: 2.58e-06 [label_micro_interleaved_index]: 4.38001e-06 [label_fine_grained_interleaved_index]: 2.66999e-06 [merge_cast_opt]: 1.50999e-06 [slice_recompute_activation]: 2.37001e-06 [micro_interleaved_order_control]: 2.54001e-06 [assign_add_opt]: 1.31002e-06 [ForceFp32Comm]: 9.89996e-07 [remove_cast_before_assign_add]: 1.10001e-06 [full_micro_interleaved_order_control]: 2.07999e-06 [reorder_send_recv_between_fp_bp]: 2.48e-06 [comm_op_add_attrs]: 1.01002e-06 [add_comm_op_reuse_tag]: 9.40025e-07 [interleave_split_concat_branches]: 1.43002e-06 [interleave_parallel_branches]: 1.04e-06 [overlap_opt_shard_in_pipeline]: 1.481e-05 [overlap_opt_shard_grad_in_pipeline]: 1.72999e-06 [control_data_broadcast_order]: 1.557e-05 [grouped_pairwise_exchange_alltoall]: 1.91e-06 [offloading_packed_experts]: 4.87e-06 [overlap_recompute_and_grad_model_parallel]: 5.30001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.23002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.34e-06 [overlap_recompute_comm]: 2.61999e-06 [overlap_grad_ring_attention]: 4.77e-06 [overlap_grad_flash_sp]: 3.078e-05 [begin_end_overlap_inline]: 9.00007e-07 [split_matmul_comm_elemetwise]: 2.19001e-06 [split_layernorm_comm]: 1.89999e-06 [handle_group_info]: 9.39996e-07 [symbol_engine_optimizer]: 0.00017784, [1] [Cycle 1]: 0.00017317, [6] [build]: 7.386e-05 [elim_shapecalc]: 1.587e-05 [elim_not_effective]: 2.302e-05 [opt_reshape]: 1.085e-05 [fold_const_symbol]: 1.872e-05 [renormalize]: 4.40021e-07 [detach_backward]: 2.04e-06 [pipeline_parallel_scheduler]: 1.59e-06 [auto_monad_reorder]: 2.64e-05 [get_jit_bprop_graph]: 1.74e-06 [rewriter_after_jit_bprop_graph]: 2.71e-06 [opt_after_jit_grad]: 0.000507 [validate]: 6.025e-05 Sums bootstrap : 0.000701s : 2.62% type_inference : 0.020579s : 76.78% event_method : 0.000012s : 0.05% auto_monad : 0.000083s : 0.31% graph_reusing : 0.000004s : 0.02% inline : 0.000003s : 0.01% add_attr.add_attr_with_inline.tag_attr : 0.000018s : 0.07% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.02% parallel-infer-symbol : 0.000004s : 0.01% pre_auto_parallel : 0.000041s : 0.15% insert-virtual-dataset : 0.000003s : 0.01% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.01% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000023s : 0.09% optimize.rewriter_before_opt_a : 0.000073s : 0.27% optimize.opt_a.expand_dump_flag : 0.000004s : 0.01% optimize.opt_a.switch_simplify : 0.000043s : 0.16% optimize.opt_a.loop_unroll : 0.000030s : 0.11% optimize.opt_a.a_1 : 0.000657s : 2.45% optimize.opt_a.with_stream_mark : 0.000032s : 0.12% optimize.opt_a.recompute_prepare : 0.000025s : 0.09% optimize.opt_a.updatestate_depend_eliminate : 0.000011s : 0.04% optimize.opt_a.updatestate_assign_eliminate : 0.000009s : 0.03% optimize.opt_a.updatestate_loads_eliminate : 0.000010s : 0.04% optimize.opt_a.parameter_eliminate : 0.000004s : 0.02% optimize.opt_a.a_2 : 0.000271s : 1.01% optimize.opt_a.accelerated_algorithm : 0.000023s : 0.08% optimize.opt_a.shard : 0.000003s : 0.01% optimize.opt_a.meta_shard_fg_expand : 0.000004s : 0.01% optimize.opt_a.shard_inline : 0.000021s : 0.08% optimize.opt_a.merge_send_recv : 0.000036s : 0.13% optimize.opt_a.auto_parallel : 0.000018s : 0.07% optimize.opt_a.parallel : 0.000049s : 0.18% optimize.opt_a.flash_sp : 0.000022s : 0.08% optimize.opt_a.merge_comm : 0.000010s : 0.04% optimize.opt_a.allreduce_fusion : 0.000009s : 0.03% optimize.opt_a.matmul_add_comm_reduction : 0.000019s : 0.07% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000026s : 0.10% optimize.opt_a.virtual_dataset : 0.000021s : 0.08% optimize.opt_a.get_grad_eliminate_ : 0.000020s : 0.07% optimize.opt_a.virtual_output : 0.000020s : 0.07% optimize.opt_a.merge_forward : 0.000011s : 0.04% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.01% optimize.opt_a.offload_activation : 0.000019s : 0.07% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000037s : 0.14% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.01% optimize.opt_a.before_grad : 0.000029s : 0.11% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000010s : 0.04% optimize.opt_a.meta_fg_expand : 0.000006s : 0.02% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.01% optimize.opt_a.receive_attached : 0.000013s : 0.05% optimize.opt_a.after_resolve : 0.000044s : 0.16% optimize.opt_a.a_after_grad : 0.000033s : 0.12% optimize.opt_a.renormalize : 0.000610s : 2.28% optimize.opt_a.add_forward_monad_depend : 0.000008s : 0.03% optimize.opt_a.auto_monad_grad : 0.000004s : 0.02% optimize.opt_a.auto_monad_eliminator : 0.000026s : 0.10% optimize.opt_a.cse : 0.000131s : 0.49% optimize.opt_a.a_3 : 0.000143s : 0.53% optimize.py_interpret_to_execute_after_opt_a : 0.000013s : 0.05% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.01% optimize.rewriter_after_opt_a : 0.000066s : 0.24% optimize.convert_after_rewriter : 0.000019s : 0.07% optimize.order_py_execute_after_rewriter : 0.000007s : 0.03% optimize.mutable_eliminate : 0.000629s : 2.35% optimize.opt_b.b_1 : 0.000210s : 0.78% optimize.opt_b.b_2 : 0.000012s : 0.05% optimize.opt_b.updatestate_depend_eliminate : 0.000008s : 0.03% optimize.opt_b.updatestate_assign_eliminate : 0.000004s : 0.02% optimize.opt_b.updatestate_loads_eliminate : 0.000004s : 0.02% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000039s : 0.14% optimize.optimize_parallel_all_gather_comm : 0.000020s : 0.07% optimize.overlap_param_gather : 0.000004s : 0.01% optimize.cconv : 0.000028s : 0.10% optimize.loop_unroll : 0.000446s : 1.66% optimize.opt_after_cconv.c_1 : 0.000053s : 0.20% optimize.opt_after_cconv.parameter_eliminate : 0.000003s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000007s : 0.03% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000004s : 0.01% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.02% optimize.opt_after_cconv.cse : 0.000036s : 0.14% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000051s : 0.19% optimize.tuple_transform.d_1 : 0.000072s : 0.27% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000011s : 0.04% optimize.partial_unused_args_eliminate : 0.000002s : 0.01% optimize.add_recomputation : 0.000054s : 0.20% optimize.cse_after_recomputation.cse : 0.000022s : 0.08% optimize.environ_conv : 0.000016s : 0.06% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.03% optimize.bias_add_comm_swap : 0.000003s : 0.01% optimize.label_micro_interleaved_index : 0.000004s : 0.02% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.01% optimize.merge_cast_opt : 0.000002s : 0.01% optimize.slice_recompute_activation : 0.000002s : 0.01% optimize.micro_interleaved_order_control : 0.000003s : 0.01% 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 : 0.01% optimize.reorder_send_recv_between_fp_bp : 0.000002s : 0.01% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.01% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000015s : 0.06% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000016s : 0.06% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000005s : 0.02% optimize.overlap_recompute_and_grad_model_parallel : 0.000005s : 0.02% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.01% optimize.overlap_grad_ring_attention : 0.000005s : 0.02% optimize.overlap_grad_flash_sp : 0.000031s : 0.11% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.01% optimize.split_layernorm_comm : 0.000002s : 0.01% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000074s : 0.28% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000016s : 0.06% optimize.symbol_engine_optimizer.elim_not_effective : 0.000023s : 0.09% optimize.symbol_engine_optimizer.opt_reshape : 0.000011s : 0.04% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000019s : 0.07% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.01% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000026s : 0.10% get_jit_bprop_graph : 0.000002s : 0.01% rewriter_after_jit_bprop_graph : 0.000003s : 0.01% opt_after_jit_grad : 0.000507s : 1.89% validate : 0.000060s : 0.22% Time group info: ------[substitution.] 0.000128 36 6.07% : 0.000008s : 2: substitution.elim_not_effective 5.15% : 0.000007s : 2: substitution.fold_const_symbol 5.70% : 0.000007s : 9: substitution.graph_param_transform 68.28% : 0.000088s : 1: substitution.inline 2.90% : 0.000004s : 4: substitution.j_node_and_user_rematch 4.42% : 0.000006s : 4: substitution.remove_not_recompute_node 7.48% : 0.000010s : 14: substitution.replace_old_param ------[type_inference.] 0.020497 2 97.73% : 0.020031s : 1: type_inference.infer 2.27% : 0.000466s : 1: type_inference.specialize ------[replace.] 0.000018 1 100.00% : 0.000018s : 1: replace.inline ------[match.] 0.000087 1 100.00% : 0.000087s : 1: match.inline ------[predicate.] 0.000223 2107 0.82% : 0.000002s : 19: predicate.accumulaten_eliminater 0.87% : 0.000002s : 9: predicate.ad_related_special_op_eliminate 0.83% : 0.000002s : 18: predicate.addn_check_dump 0.87% : 0.000002s : 19: predicate.addn_zero_filter 0.76% : 0.000002s : 19: predicate.adjust_all_reduce_mul_add 2.04% : 0.000005s : 37: predicate.arithmetic_simplify 0.86% : 0.000002s : 19: predicate.cast_eliminate 0.82% : 0.000002s : 18: predicate.check_bprop_eliminate 0.77% : 0.000002s : 18: predicate.compare_switch_simplify 0.30% : 0.000001s : 9: predicate.const_output_eliminate 0.79% : 0.000002s : 18: predicate.depend_value_elim 0.88% : 0.000002s : 19: predicate.dict_get_item_const_eliminator 0.93% : 0.000002s : 19: predicate.dict_get_item_eliminator 0.85% : 0.000002s : 19: predicate.dict_set_item_eliminator 1.17% : 0.000003s : 18: predicate.dumpgradient_eliminate 0.38% : 0.000001s : 9: predicate.elim_not_effective 0.49% : 0.000001s : 9: predicate.elim_shapecalc_of_broadcastargs 1.25% : 0.000003s : 28: predicate.environ_add_const_eliminate 1.13% : 0.000003s : 28: predicate.environ_get_add_eliminate 1.10% : 0.000002s : 28: predicate.environ_get_depend_swap 1.95% : 0.000004s : 46: predicate.environ_get_eliminate 1.12% : 0.000003s : 28: predicate.environ_get_set_eliminate 0.91% : 0.000002s : 20: predicate.exchange_switch_depend_value 1.48% : 0.000003s : 20: predicate.float_depend_g_call 0.75% : 0.000002s : 18: predicate.float_environ_get_switch 1.13% : 0.000003s : 27: predicate.float_tuple_getitem_switch 0.31% : 0.000001s : 9: predicate.fold_const_symbol 0.86% : 0.000002s : 18: predicate.get_grad_eliminate 0.43% : 0.000001s : 9: predicate.graph_param_transform 0.76% : 0.000002s : 18: predicate.incorporate_call 0.70% : 0.000002s : 18: predicate.incorporate_call_switch 5.50% : 0.000012s : 93: predicate.inline 1.00% : 0.000002s : 18: predicate.inline_without_move 0.57% : 0.000001s : 18: predicate.j_node_and_user_rematch 1.12% : 0.000002s : 18: predicate.less_batch_normalization 1.82% : 0.000004s : 37: predicate.list_to_tuple_eliminator_ 2.28% : 0.000005s : 56: predicate.load_eliminater 0.93% : 0.000002s : 9: predicate.loop_unroll_after_grad 1.38% : 0.000003s : 28: predicate.loop_unroll_before_grad 2.05% : 0.000005s : 37: predicate.make_slice_get_slice_eliminator 0.86% : 0.000002s : 18: predicate.merge_addn 0.80% : 0.000002s : 18: predicate.micro_step_allgather_replace 0.83% : 0.000002s : 18: predicate.mini_step_allgather_replace 0.74% : 0.000002s : 19: predicate.minmaximum_grad 1.04% : 0.000002s : 9: predicate.mutable_eliminate 0.46% : 0.000001s : 9: predicate.opt_reshape 0.44% : 0.000001s : 9: predicate.parallel_virtual_node 0.98% : 0.000002s : 20: predicate.partial_defer_inline 1.37% : 0.000003s : 28: predicate.partial_eliminate 0.93% : 0.000002s : 19: predicate.print_const_string_wrapper 0.78% : 0.000002s : 18: predicate.reduce_all_const_elim 1.12% : 0.000002s : 19: predicate.reduce_eliminate 2.36% : 0.000005s : 56: predicate.redundant_stop_gradient_eliminater 0.95% : 0.000002s : 18: predicate.remove_not_recompute_node 1.56% : 0.000003s : 37: predicate.replace_applicator 0.82% : 0.000002s : 18: predicate.replace_old_param 0.36% : 0.000001s : 9: predicate.reset_defer_inline 0.78% : 0.000002s : 19: predicate.reshape_eliminate 0.84% : 0.000002s : 18: predicate.row_tensor_add_zeros_like 0.46% : 0.000001s : 9: predicate.row_tensor_eliminate 1.09% : 0.000002s : 18: predicate.same_eliminate 0.77% : 0.000002s : 18: predicate.set_cell_output_no_recompute 1.20% : 0.000003s : 18: predicate.shard_identity_eliminate 0.87% : 0.000002s : 18: predicate.special_op_eliminate 0.86% : 0.000002s : 18: predicate.specialize_transform 1.00% : 0.000002s : 18: predicate.split_environ_get_set_with_tuple_value 1.01% : 0.000002s : 18: predicate.stack_unstack_eliminate 0.49% : 0.000001s : 9: predicate.switch_call_monad_eliminater 0.86% : 0.000002s : 20: predicate.switch_defer_inline 1.66% : 0.000004s : 38: predicate.switch_layer_defer_inline 3.65% : 0.000008s : 75: predicate.switch_simplify 0.86% : 0.000002s : 19: predicate.tile_eliminate 0.79% : 0.000002s : 19: predicate.transpose_eliminate 1.42% : 0.000003s : 37: predicate.tuple_list_convert_item_index_to_positive 1.57% : 0.000004s : 37: predicate.tuple_list_get_item_const_eliminator 1.49% : 0.000003s : 37: predicate.tuple_list_get_item_depend_reorder 2.76% : 0.000006s : 55: predicate.tuple_list_get_item_eliminator 1.48% : 0.000003s : 37: predicate.tuple_list_get_set_item_eliminator 2.45% : 0.000005s : 55: predicate.tuple_list_set_item_eliminator 1.73% : 0.000004s : 37: predicate.tuple_to_list_eliminator_ 2.22% : 0.000005s : 56: predicate.updatestate_pure_node_eliminater 3.17% : 0.000007s : 74: predicate.updatestate_useless_node_eliminater 0.42% : 0.000001s : 9: predicate.value_based_eliminate 0.92% : 0.000002s : 18: predicate.virtual_dataset_eliminate 0.97% : 0.000002s : 18: predicate.virtual_output_eliminate 0.38% : 0.000001s : 9: predicate.virtual_view_grad_eliminate 0.47% : 0.000001s : 9: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000413 6 53.10% : 0.000219s : 3: func_graph_cloner_run.FuncGraphClonerGraph 46.90% : 0.000194s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.051369 192 0.01% : 0.000004s : 1: ForceFp32Comm 15.37% : 0.007897s : 1: add_attr 15.35% : 0.007883s : 1: add_attr_with_inline 0.01% : 0.000003s : 1: add_comm_op_reuse_tag 0.11% : 0.000058s : 1: add_recomputation 0.01% : 0.000004s : 1: assign_add_opt 0.17% : 0.000088s : 1: auto_monad 0.06% : 0.000031s : 1: auto_monad_reorder 0.01% : 0.000004s : 1: begin_end_overlap_inline 0.01% : 0.000005s : 1: bias_add_comm_swap 1.44% : 0.000737s : 1: bootstrap 0.06% : 0.000031s : 1: cconv 0.01% : 0.000004s : 1: comm_op_add_attrs 0.04% : 0.000019s : 1: control_data_broadcast_order 0.04% : 0.000023s : 1: convert_after_rewriter 0.07% : 0.000035s : 1: cse_after_recomputation 0.01% : 0.000004s : 1: dataset_repeat_opt 0.01% : 0.000005s : 1: detach_backward 0.04% : 0.000019s : 1: environ_conv 0.03% : 0.000018s : 1: event_method 0.01% : 0.000005s : 1: full_micro_interleaved_order_control 0.01% : 0.000005s : 1: get_jit_bprop_graph 0.02% : 0.000008s : 1: graph_reusing 0.01% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.01% : 0.000004s : 1: handle_group_info 0.01% : 0.000006s : 1: inline 0.01% : 0.000006s : 1: insert-virtual-dataset 0.01% : 0.000004s : 1: interleave_parallel_branches 0.01% : 0.000004s : 1: interleave_split_concat_branches 0.01% : 0.000006s : 1: label_fine_grained_interleaved_index 0.01% : 0.000007s : 1: label_micro_interleaved_index 0.88% : 0.000454s : 1: loop_unroll 0.01% : 0.000004s : 1: merge_cast_opt 0.01% : 0.000005s : 1: micro_interleaved_order_control 1.24% : 0.000637s : 1: mutable_eliminate 0.01% : 0.000008s : 1: offloading_packed_experts 0.04% : 0.000020s : 1: opt.transform.loop_unroll_optimizer 0.04% : 0.000020s : 1: opt.transform.mutable_eliminate 2.63% : 0.001350s : 78: opt.transform.opt_a 0.10% : 0.000051s : 1: opt.transform.opt_after_cconv 0.07% : 0.000038s : 1: opt.transform.opt_after_jit_grad 0.38% : 0.000194s : 28: opt.transform.opt_b 0.16% : 0.000081s : 2: opt.transform.opt_trans_graph 0.13% : 0.000065s : 4: opt.transform.symbol_engine_opt 5.80% : 0.002980s : 1: opt_a 0.29% : 0.000149s : 1: opt_after_cconv 1.01% : 0.000517s : 1: opt_after_jit_grad 0.63% : 0.000323s : 1: opt_b 10.83% : 0.005563s : 1: optimize 0.05% : 0.000023s : 1: optimize_parallel_all_gather_comm 0.02% : 0.000010s : 1: order_py_execute_after_rewriter 0.07% : 0.000034s : 1: overlap_grad_flash_sp 0.01% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.02% : 0.000008s : 1: overlap_grad_ring_attention 0.01% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.04% : 0.000018s : 1: overlap_opt_shard_in_pipeline 0.01% : 0.000007s : 1: overlap_param_gather 0.01% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.02% : 0.000008s : 1: overlap_recompute_and_grad_model_parallel 0.01% : 0.000005s : 1: overlap_recompute_comm 0.01% : 0.000007s : 1: parallel-infer-symbol 0.01% : 0.000004s : 1: parallel-infer-symbol-second 0.01% : 0.000005s : 1: partial_unused_args_eliminate 0.01% : 0.000005s : 1: pipeline_parallel_scheduler 0.01% : 0.000005s : 1: pipeline_split 0.09% : 0.000046s : 1: pre_auto_parallel 0.05% : 0.000027s : 1: py_interpret_to_execute 0.03% : 0.000017s : 1: py_interpret_to_execute_after_opt_a 0.01% : 0.000004s : 1: remove_cast_before_assign_add 0.11% : 0.000055s : 1: remove_dup_value 0.58% : 0.000298s : 1: renormalize.infer 0.59% : 0.000304s : 1: renormalize.specialize 0.01% : 0.000005s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000006s : 1: rewriter_after_jit_bprop_graph 0.14% : 0.000070s : 1: rewriter_after_opt_a 0.15% : 0.000077s : 1: rewriter_before_opt_a 0.01% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.01% : 0.000005s : 1: slice_recompute_activation 0.01% : 0.000005s : 1: split_layernorm_comm 0.01% : 0.000005s : 1: split_matmul_comm_elemetwise 0.02% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.35% : 0.000180s : 1: symbol_engine_optimizer 0.22% : 0.000111s : 1: tuple_transform 40.09% : 0.020595s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_large_gsq[0] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_large_gsq[0],max_mem:522.0M [WARNING] ME(167516:281472989335344,MainProcess):2026-01-29-17:45:42.494.213 [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 = 0.0169493, [21] [bootstrap]: 0.0006736 [type_inference]: 0.00532596 [event_method]: 1.357e-05 [auto_monad]: 5.544e-05 [graph_reusing]: 5.15999e-06 [inline]: 2.29999e-06 [add_attr]: 0.00393866, [1] [add_attr_with_inline]: 0.00392542, [1] [Cycle 1]: 6.528e-05, [2] [tag_attr]: 1.893e-05 [meta_addattr_fg_expand]: 3.75e-06 [parallel-infer-symbol]: 3.12002e-06 [pre_auto_parallel]: 3.363e-05 [insert-virtual-dataset]: 2.71e-06 [parallel-infer-symbol-second]: 6.50005e-07 [dataset_repeat_opt]: 2.19001e-06 [pipeline_split]: 1.60999e-06 [optimize]: 0.00609556, [53] [py_interpret_to_execute]: 2.791e-05 [rewriter_before_opt_a]: 6.794e-05 [opt_a]: 0.00329926, [2] [Cycle 1]: 0.0022091, [45] [expand_dump_flag]: 2.88e-06 [switch_simplify]: 3.047e-05 [loop_unroll]: 1.865e-05 [a_1]: 0.00043647 [with_stream_mark]: 2.261e-05 [recompute_prepare]: 1.329e-05 [updatestate_depend_eliminate]: 5.51e-06 [updatestate_assign_eliminate]: 5.19998e-06 [updatestate_loads_eliminate]: 5.12999e-06 [parameter_eliminate]: 2.72001e-06 [a_2]: 0.00013972 [accelerated_algorithm]: 1.106e-05 [shard]: 2.91999e-06 [meta_shard_fg_expand]: 2.34999e-06 [shard_inline]: 1.061e-05 [merge_send_recv]: 1.047e-05 [auto_parallel]: 9.39e-06 [parallel]: 3.078e-05 [flash_sp]: 1.047e-05 [merge_comm]: 5.71e-06 [allreduce_fusion]: 5.10001e-06 [matmul_add_comm_reduction]: 1.215e-05 [allreduce_slice_to_reducescatter]: 6.69999e-07 [virtual_shard_identity]: 1.394e-05 [virtual_dataset]: 1.077e-05 [get_grad_eliminate_]: 1.029e-05 [virtual_output]: 1.015e-05 [merge_forward]: 5.74e-06 [cell_reuse_recompute_pass]: 1.60999e-06 [offload_activation]: 1.162e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.831e-05 [merge_recompute_call_nodes]: 1.39e-06 [before_grad]: 1.558e-05 [set_forward_comm_id_for_comm_node_pass]: 6.04001e-06 [meta_fg_expand]: 2.98e-06 [flash_sp_send_recv_attached]: 2.51998e-06 [receive_attached]: 2.35997e-06 [after_resolve]: 2.239e-05 [a_after_grad]: 1.596e-05 [renormalize]: 0.00081855 [add_forward_monad_depend]: 5.65001e-06 [auto_monad_grad]: 2.51998e-06 [auto_monad_eliminator]: 1.88e-05 [cse]: 5.519e-05 [a_3]: 7.908e-05 [Cycle 2]: 0.00107894, [45] [expand_dump_flag]: 2.02999e-06 [switch_simplify]: 1.332e-05 [loop_unroll]: 1.036e-05 [a_1]: 0.00025393 [with_stream_mark]: 1.545e-05 [recompute_prepare]: 1.014e-05 [updatestate_depend_eliminate]: 4.88001e-06 [updatestate_assign_eliminate]: 4.68001e-06 [updatestate_loads_eliminate]: 5.71e-06 [parameter_eliminate]: 1.18001e-06 [a_2]: 0.00013151 [accelerated_algorithm]: 1.033e-05 [shard]: 2.84001e-06 [meta_shard_fg_expand]: 1.65001e-06 [shard_inline]: 9.99999e-06 [merge_send_recv]: 7.99002e-06 [auto_parallel]: 8.47998e-06 [parallel]: 6.06e-06 [flash_sp]: 4.15e-06 [merge_comm]: 9.07999e-06 [allreduce_fusion]: 4.90999e-06 [matmul_add_comm_reduction]: 8.99e-06 [allreduce_slice_to_reducescatter]: 5.39992e-07 [virtual_shard_identity]: 1.1e-05 [virtual_dataset]: 1.021e-05 [get_grad_eliminate_]: 9.77001e-06 [virtual_output]: 9.49999e-06 [merge_forward]: 4.79998e-06 [cell_reuse_recompute_pass]: 1.66e-06 [offload_activation]: 9.61998e-06 [cell_reuse_handle_not_recompute_node_pass]: 2.12e-05 [merge_recompute_call_nodes]: 1.08001e-06 [before_grad]: 1.44e-05 [set_forward_comm_id_for_comm_node_pass]: 5.41998e-06 [meta_fg_expand]: 2.66999e-06 [flash_sp_send_recv_attached]: 1.28002e-06 [receive_attached]: 5.47001e-06 [after_resolve]: 2.216e-05 [a_after_grad]: 1.777e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.49001e-06 [auto_monad_grad]: 1.49e-06 [auto_monad_eliminator]: 1.073e-05 [cse]: 4.686e-05 [a_3]: 6.662e-05 [py_interpret_to_execute_after_opt_a]: 2.302e-05 [slice_cell_reuse_recomputed_activation]: 2.29999e-06 [rewriter_after_opt_a]: 5.933e-05 [convert_after_rewriter]: 2.766e-05 [order_py_execute_after_rewriter]: 7.78001e-06 [mutable_eliminate]: 0.00061287 [opt_b]: 0.0003619, [1] [Cycle 1]: 0.00035412, [7] [b_1]: 0.00021545 [b_2]: 1.248e-05 [updatestate_depend_eliminate]: 8.72e-06 [updatestate_assign_eliminate]: 4.39002e-06 [updatestate_loads_eliminate]: 4.67998e-06 [renormalize]: 5.29981e-07 [cse]: 5.584e-05 [optimize_parallel_all_gather_comm]: 2.607e-05 [overlap_param_gather]: 3.25e-06 [cconv]: 3.038e-05 [loop_unroll]: 0.00048182 [opt_after_cconv]: 0.00016956, [1] [Cycle 1]: 0.00016293, [7] [c_1]: 5.351e-05 [parameter_eliminate]: 3.45e-06 [updatestate_depend_eliminate]: 8.06001e-06 [updatestate_assign_eliminate]: 4.37e-06 [updatestate_loads_eliminate]: 4.42e-06 [cse]: 4.33e-05 [renormalize]: 3.10014e-07 [remove_dup_value]: 6.441e-05 [tuple_transform]: 0.0001203, [1] [Cycle 1]: 0.00011546, [4] [d_1]: 7.527e-05 [none_parameter_eliminate]: 2.00002e-06 [renormalize]: 2.19996e-07 [switch_simplify]: 1.218e-05 [partial_unused_args_eliminate]: 1.76e-06 [add_recomputation]: 6.7e-05 [cse_after_recomputation]: 3.874e-05, [1] [Cycle 1]: 3.337e-05, [1] [cse]: 2.662e-05 [environ_conv]: 6.87002e-06 [swap_dp_allreduce_reducescatter]: 9.74999e-06 [bias_add_comm_swap]: 2.56e-06 [label_micro_interleaved_index]: 4.75999e-06 [label_fine_grained_interleaved_index]: 2.76999e-06 [merge_cast_opt]: 1.27e-06 [slice_recompute_activation]: 2.02001e-06 [micro_interleaved_order_control]: 2.58003e-06 [assign_add_opt]: 1.24e-06 [ForceFp32Comm]: 7.09988e-07 [remove_cast_before_assign_add]: 1.40001e-06 [full_micro_interleaved_order_control]: 2.40002e-06 [reorder_send_recv_between_fp_bp]: 3.23e-06 [comm_op_add_attrs]: 1.00999e-06 [add_comm_op_reuse_tag]: 1.23002e-06 [interleave_split_concat_branches]: 1.34998e-06 [interleave_parallel_branches]: 1.22999e-06 [overlap_opt_shard_in_pipeline]: 2.02001e-06 [overlap_opt_shard_grad_in_pipeline]: 1.66e-06 [control_data_broadcast_order]: 1.838e-05 [grouped_pairwise_exchange_alltoall]: 1.57001e-06 [offloading_packed_experts]: 4.79002e-06 [overlap_recompute_and_grad_model_parallel]: 5.21998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.39e-06 [overlap_recompute_allgather_and_fa_grad]: 1.37e-06 [overlap_recompute_comm]: 2.34999e-06 [overlap_grad_ring_attention]: 5.61e-06 [overlap_grad_flash_sp]: 2.346e-05 [begin_end_overlap_inline]: 5.29981e-07 [split_matmul_comm_elemetwise]: 2.29999e-06 [split_layernorm_comm]: 1.59998e-06 [handle_group_info]: 1.14e-06 [symbol_engine_optimizer]: 0.0001925, [1] [Cycle 1]: 0.00018788, [6] [build]: 8.109e-05 [elim_shapecalc]: 1.607e-05 [elim_not_effective]: 2.275e-05 [opt_reshape]: 1.065e-05 [fold_const_symbol]: 1.898e-05 [renormalize]: 1.8999e-07 [detach_backward]: 2.49999e-06 [pipeline_parallel_scheduler]: 1.50001e-06 [auto_monad_reorder]: 2.82e-05 [get_jit_bprop_graph]: 1.97999e-06 [rewriter_after_jit_bprop_graph]: 4.37e-06 [opt_after_jit_grad]: 0.00054164 [validate]: 5.124e-05 Sums bootstrap : 0.000674s : 5.70% type_inference : 0.005326s : 45.09% event_method : 0.000014s : 0.11% auto_monad : 0.000055s : 0.47% graph_reusing : 0.000005s : 0.04% inline : 0.000002s : 0.02% add_attr.add_attr_with_inline.tag_attr : 0.000019s : 0.16% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.03% parallel-infer-symbol : 0.000003s : 0.03% pre_auto_parallel : 0.000034s : 0.28% insert-virtual-dataset : 0.000003s : 0.02% parallel-infer-symbol-second : 0.000001s : 0.01% dataset_repeat_opt : 0.000002s : 0.02% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000028s : 0.24% optimize.rewriter_before_opt_a : 0.000068s : 0.58% optimize.opt_a.expand_dump_flag : 0.000005s : 0.04% optimize.opt_a.switch_simplify : 0.000044s : 0.37% optimize.opt_a.loop_unroll : 0.000029s : 0.25% optimize.opt_a.a_1 : 0.000690s : 5.84% optimize.opt_a.with_stream_mark : 0.000038s : 0.32% optimize.opt_a.recompute_prepare : 0.000023s : 0.20% optimize.opt_a.updatestate_depend_eliminate : 0.000010s : 0.09% optimize.opt_a.updatestate_assign_eliminate : 0.000010s : 0.08% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.09% optimize.opt_a.parameter_eliminate : 0.000004s : 0.03% optimize.opt_a.a_2 : 0.000271s : 2.30% optimize.opt_a.accelerated_algorithm : 0.000021s : 0.18% optimize.opt_a.shard : 0.000006s : 0.05% optimize.opt_a.meta_shard_fg_expand : 0.000004s : 0.03% optimize.opt_a.shard_inline : 0.000021s : 0.17% optimize.opt_a.merge_send_recv : 0.000018s : 0.16% optimize.opt_a.auto_parallel : 0.000018s : 0.15% optimize.opt_a.parallel : 0.000037s : 0.31% optimize.opt_a.flash_sp : 0.000015s : 0.12% optimize.opt_a.merge_comm : 0.000015s : 0.13% optimize.opt_a.allreduce_fusion : 0.000010s : 0.08% optimize.opt_a.matmul_add_comm_reduction : 0.000021s : 0.18% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000025s : 0.21% optimize.opt_a.virtual_dataset : 0.000021s : 0.18% optimize.opt_a.get_grad_eliminate_ : 0.000020s : 0.17% optimize.opt_a.virtual_output : 0.000020s : 0.17% optimize.opt_a.merge_forward : 0.000011s : 0.09% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.03% optimize.opt_a.offload_activation : 0.000021s : 0.18% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000040s : 0.33% optimize.opt_a.merge_recompute_call_nodes : 0.000002s : 0.02% optimize.opt_a.before_grad : 0.000030s : 0.25% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000011s : 0.10% optimize.opt_a.meta_fg_expand : 0.000006s : 0.05% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.03% optimize.opt_a.receive_attached : 0.000008s : 0.07% optimize.opt_a.after_resolve : 0.000045s : 0.38% optimize.opt_a.a_after_grad : 0.000034s : 0.29% optimize.opt_a.renormalize : 0.000819s : 6.93% optimize.opt_a.add_forward_monad_depend : 0.000008s : 0.07% optimize.opt_a.auto_monad_grad : 0.000004s : 0.03% optimize.opt_a.auto_monad_eliminator : 0.000030s : 0.25% optimize.opt_a.cse : 0.000102s : 0.86% optimize.opt_a.a_3 : 0.000146s : 1.23% optimize.py_interpret_to_execute_after_opt_a : 0.000023s : 0.19% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.02% optimize.rewriter_after_opt_a : 0.000059s : 0.50% optimize.convert_after_rewriter : 0.000028s : 0.23% optimize.order_py_execute_after_rewriter : 0.000008s : 0.07% optimize.mutable_eliminate : 0.000613s : 5.19% optimize.opt_b.b_1 : 0.000215s : 1.82% optimize.opt_b.b_2 : 0.000012s : 0.11% optimize.opt_b.updatestate_depend_eliminate : 0.000009s : 0.07% optimize.opt_b.updatestate_assign_eliminate : 0.000004s : 0.04% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.04% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000056s : 0.47% optimize.optimize_parallel_all_gather_comm : 0.000026s : 0.22% optimize.overlap_param_gather : 0.000003s : 0.03% optimize.cconv : 0.000030s : 0.26% optimize.loop_unroll : 0.000482s : 4.08% optimize.opt_after_cconv.c_1 : 0.000054s : 0.45% optimize.opt_after_cconv.parameter_eliminate : 0.000003s : 0.03% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000008s : 0.07% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000004s : 0.04% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.04% optimize.opt_after_cconv.cse : 0.000043s : 0.37% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000064s : 0.55% optimize.tuple_transform.d_1 : 0.000075s : 0.64% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.02% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000012s : 0.10% optimize.partial_unused_args_eliminate : 0.000002s : 0.01% optimize.add_recomputation : 0.000067s : 0.57% optimize.cse_after_recomputation.cse : 0.000027s : 0.23% optimize.environ_conv : 0.000007s : 0.06% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 0.08% optimize.bias_add_comm_swap : 0.000003s : 0.02% optimize.label_micro_interleaved_index : 0.000005s : 0.04% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.02% optimize.merge_cast_opt : 0.000001s : 0.01% optimize.slice_recompute_activation : 0.000002s : 0.02% optimize.micro_interleaved_order_control : 0.000003s : 0.02% optimize.assign_add_opt : 0.000001s : 0.01% optimize.ForceFp32Comm : 0.000001s : 0.01% optimize.remove_cast_before_assign_add : 0.000001s : 0.01% optimize.full_micro_interleaved_order_control : 0.000002s : 0.02% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.03% optimize.comm_op_add_attrs : 0.000001s : 0.01% optimize.add_comm_op_reuse_tag : 0.000001s : 0.01% optimize.interleave_split_concat_branches : 0.000001s : 0.01% optimize.interleave_parallel_branches : 0.000001s : 0.01% optimize.overlap_opt_shard_in_pipeline : 0.000002s : 0.02% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000018s : 0.16% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000005s : 0.04% optimize.overlap_recompute_and_grad_model_parallel : 0.000005s : 0.04% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.01% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.01% optimize.overlap_recompute_comm : 0.000002s : 0.02% optimize.overlap_grad_ring_attention : 0.000006s : 0.05% optimize.overlap_grad_flash_sp : 0.000023s : 0.20% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.02% optimize.split_layernorm_comm : 0.000002s : 0.01% optimize.handle_group_info : 0.000001s : 0.01% optimize.symbol_engine_optimizer.build : 0.000081s : 0.69% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000016s : 0.14% optimize.symbol_engine_optimizer.elim_not_effective : 0.000023s : 0.19% optimize.symbol_engine_optimizer.opt_reshape : 0.000011s : 0.09% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000019s : 0.16% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.02% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000028s : 0.24% get_jit_bprop_graph : 0.000002s : 0.02% rewriter_after_jit_bprop_graph : 0.000004s : 0.04% opt_after_jit_grad : 0.000542s : 4.59% validate : 0.000051s : 0.43% Time group info: ------[substitution.] 0.000139 36 2.83% : 0.000004s : 2: substitution.elim_not_effective 4.28% : 0.000006s : 2: substitution.fold_const_symbol 5.51% : 0.000008s : 9: substitution.graph_param_transform 74.54% : 0.000104s : 1: substitution.inline 2.76% : 0.000004s : 4: substitution.j_node_and_user_rematch 3.59% : 0.000005s : 4: substitution.remove_not_recompute_node 6.50% : 0.000009s : 14: substitution.replace_old_param ------[type_inference.] 0.005229 2 88.81% : 0.004644s : 1: type_inference.infer 11.19% : 0.000585s : 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.] 0.000231 2107 0.84% : 0.000002s : 19: predicate.accumulaten_eliminater 0.95% : 0.000002s : 9: predicate.ad_related_special_op_eliminate 0.72% : 0.000002s : 18: predicate.addn_check_dump 0.84% : 0.000002s : 19: predicate.addn_zero_filter 0.71% : 0.000002s : 19: predicate.adjust_all_reduce_mul_add 1.79% : 0.000004s : 37: predicate.arithmetic_simplify 0.81% : 0.000002s : 19: predicate.cast_eliminate 0.81% : 0.000002s : 18: predicate.check_bprop_eliminate 0.76% : 0.000002s : 18: predicate.compare_switch_simplify 0.31% : 0.000001s : 9: predicate.const_output_eliminate 0.76% : 0.000002s : 18: predicate.depend_value_elim 0.83% : 0.000002s : 19: predicate.dict_get_item_const_eliminator 0.91% : 0.000002s : 19: predicate.dict_get_item_eliminator 0.81% : 0.000002s : 19: predicate.dict_set_item_eliminator 1.46% : 0.000003s : 18: predicate.dumpgradient_eliminate 0.44% : 0.000001s : 9: predicate.elim_not_effective 0.53% : 0.000001s : 9: predicate.elim_shapecalc_of_broadcastargs 1.18% : 0.000003s : 28: predicate.environ_add_const_eliminate 1.11% : 0.000003s : 28: predicate.environ_get_add_eliminate 1.10% : 0.000003s : 28: predicate.environ_get_depend_swap 1.97% : 0.000005s : 46: predicate.environ_get_eliminate 1.12% : 0.000003s : 28: predicate.environ_get_set_eliminate 0.83% : 0.000002s : 20: predicate.exchange_switch_depend_value 1.62% : 0.000004s : 20: predicate.float_depend_g_call 0.72% : 0.000002s : 18: predicate.float_environ_get_switch 1.07% : 0.000002s : 27: predicate.float_tuple_getitem_switch 0.34% : 0.000001s : 9: predicate.fold_const_symbol 0.82% : 0.000002s : 18: predicate.get_grad_eliminate 0.36% : 0.000001s : 9: predicate.graph_param_transform 0.75% : 0.000002s : 18: predicate.incorporate_call 0.71% : 0.000002s : 18: predicate.incorporate_call_switch 5.46% : 0.000013s : 93: predicate.inline 1.29% : 0.000003s : 18: predicate.inline_without_move 0.56% : 0.000001s : 18: predicate.j_node_and_user_rematch 0.88% : 0.000002s : 18: predicate.less_batch_normalization 1.82% : 0.000004s : 37: predicate.list_to_tuple_eliminator_ 2.26% : 0.000005s : 56: predicate.load_eliminater 1.15% : 0.000003s : 9: predicate.loop_unroll_after_grad 1.32% : 0.000003s : 28: predicate.loop_unroll_before_grad 1.69% : 0.000004s : 37: predicate.make_slice_get_slice_eliminator 0.78% : 0.000002s : 18: predicate.merge_addn 0.78% : 0.000002s : 18: predicate.micro_step_allgather_replace 0.81% : 0.000002s : 18: predicate.mini_step_allgather_replace 0.74% : 0.000002s : 19: predicate.minmaximum_grad 1.30% : 0.000003s : 9: predicate.mutable_eliminate 0.46% : 0.000001s : 9: predicate.opt_reshape 0.46% : 0.000001s : 9: predicate.parallel_virtual_node 1.03% : 0.000002s : 20: predicate.partial_defer_inline 1.35% : 0.000003s : 28: predicate.partial_eliminate 0.83% : 0.000002s : 19: predicate.print_const_string_wrapper 0.76% : 0.000002s : 18: predicate.reduce_all_const_elim 1.03% : 0.000002s : 19: predicate.reduce_eliminate 2.30% : 0.000005s : 56: predicate.redundant_stop_gradient_eliminater 0.76% : 0.000002s : 18: predicate.remove_not_recompute_node 1.51% : 0.000003s : 37: predicate.replace_applicator 0.86% : 0.000002s : 18: predicate.replace_old_param 0.37% : 0.000001s : 9: predicate.reset_defer_inline 0.90% : 0.000002s : 19: predicate.reshape_eliminate 0.91% : 0.000002s : 18: predicate.row_tensor_add_zeros_like 0.54% : 0.000001s : 9: predicate.row_tensor_eliminate 1.04% : 0.000002s : 18: predicate.same_eliminate 0.66% : 0.000002s : 18: predicate.set_cell_output_no_recompute 1.19% : 0.000003s : 18: predicate.shard_identity_eliminate 1.05% : 0.000002s : 18: predicate.special_op_eliminate 0.83% : 0.000002s : 18: predicate.specialize_transform 1.14% : 0.000003s : 18: predicate.split_environ_get_set_with_tuple_value 1.07% : 0.000002s : 18: predicate.stack_unstack_eliminate 0.48% : 0.000001s : 9: predicate.switch_call_monad_eliminater 0.90% : 0.000002s : 20: predicate.switch_defer_inline 1.66% : 0.000004s : 38: predicate.switch_layer_defer_inline 3.65% : 0.000008s : 75: predicate.switch_simplify 0.84% : 0.000002s : 19: predicate.tile_eliminate 0.87% : 0.000002s : 19: predicate.transpose_eliminate 1.54% : 0.000004s : 37: predicate.tuple_list_convert_item_index_to_positive 1.65% : 0.000004s : 37: predicate.tuple_list_get_item_const_eliminator 1.53% : 0.000004s : 37: predicate.tuple_list_get_item_depend_reorder 2.96% : 0.000007s : 55: predicate.tuple_list_get_item_eliminator 1.51% : 0.000003s : 37: predicate.tuple_list_get_set_item_eliminator 2.41% : 0.000006s : 55: predicate.tuple_list_set_item_eliminator 1.61% : 0.000004s : 37: predicate.tuple_to_list_eliminator_ 2.24% : 0.000005s : 56: predicate.updatestate_pure_node_eliminater 3.13% : 0.000007s : 74: predicate.updatestate_useless_node_eliminater 0.54% : 0.000001s : 9: predicate.value_based_eliminate 0.84% : 0.000002s : 18: predicate.virtual_dataset_eliminate 0.85% : 0.000002s : 18: predicate.virtual_output_eliminate 0.36% : 0.000001s : 9: predicate.virtual_view_grad_eliminate 0.58% : 0.000001s : 9: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000627 6 53.96% : 0.000338s : 3: func_graph_cloner_run.FuncGraphClonerGraph 46.04% : 0.000289s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.029519 192 0.01% : 0.000004s : 1: ForceFp32Comm 13.36% : 0.003944s : 1: add_attr 13.31% : 0.003929s : 1: add_attr_with_inline 0.01% : 0.000004s : 1: add_comm_op_reuse_tag 0.25% : 0.000074s : 1: add_recomputation 0.01% : 0.000004s : 1: assign_add_opt 0.21% : 0.000061s : 1: auto_monad 0.11% : 0.000033s : 1: auto_monad_reorder 0.02% : 0.000005s : 1: begin_end_overlap_inline 0.02% : 0.000006s : 1: bias_add_comm_swap 2.39% : 0.000705s : 1: bootstrap 0.12% : 0.000034s : 1: cconv 0.01% : 0.000004s : 1: comm_op_add_attrs 0.08% : 0.000022s : 1: control_data_broadcast_order 0.11% : 0.000033s : 1: convert_after_rewriter 0.15% : 0.000045s : 1: cse_after_recomputation 0.02% : 0.000005s : 1: dataset_repeat_opt 0.02% : 0.000006s : 1: detach_backward 0.04% : 0.000010s : 1: environ_conv 0.07% : 0.000020s : 1: event_method 0.02% : 0.000006s : 1: full_micro_interleaved_order_control 0.02% : 0.000006s : 1: get_jit_bprop_graph 0.03% : 0.000009s : 1: graph_reusing 0.02% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.01% : 0.000004s : 1: handle_group_info 0.02% : 0.000006s : 1: inline 0.02% : 0.000006s : 1: insert-virtual-dataset 0.02% : 0.000007s : 1: interleave_parallel_branches 0.01% : 0.000004s : 1: interleave_split_concat_branches 0.03% : 0.000010s : 1: label_fine_grained_interleaved_index 0.03% : 0.000008s : 1: label_micro_interleaved_index 1.67% : 0.000494s : 1: loop_unroll 0.02% : 0.000005s : 1: merge_cast_opt 0.03% : 0.000008s : 1: micro_interleaved_order_control 2.11% : 0.000623s : 1: mutable_eliminate 0.03% : 0.000008s : 1: offloading_packed_experts 0.07% : 0.000020s : 1: opt.transform.loop_unroll_optimizer 0.08% : 0.000022s : 1: opt.transform.mutable_eliminate 4.71% : 0.001392s : 78: opt.transform.opt_a 0.18% : 0.000052s : 1: opt.transform.opt_after_cconv 0.14% : 0.000040s : 1: opt.transform.opt_after_jit_grad 0.68% : 0.000200s : 28: opt.transform.opt_b 0.29% : 0.000085s : 2: opt.transform.opt_trans_graph 0.22% : 0.000064s : 4: opt.transform.symbol_engine_opt 11.19% : 0.003303s : 1: opt_a 0.59% : 0.000173s : 1: opt_after_cconv 1.87% : 0.000551s : 1: opt_after_jit_grad 1.24% : 0.000367s : 1: opt_b 20.69% : 0.006106s : 1: optimize 0.10% : 0.000030s : 1: optimize_parallel_all_gather_comm 0.04% : 0.000012s : 1: order_py_execute_after_rewriter 0.09% : 0.000027s : 1: overlap_grad_flash_sp 0.02% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.04% : 0.000012s : 1: overlap_grad_ring_attention 0.02% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.02% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.02% : 0.000007s : 1: overlap_param_gather 0.01% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.03% : 0.000009s : 1: overlap_recompute_and_grad_model_parallel 0.02% : 0.000006s : 1: overlap_recompute_comm 0.02% : 0.000007s : 1: parallel-infer-symbol 0.01% : 0.000004s : 1: parallel-infer-symbol-second 0.03% : 0.000008s : 1: partial_unused_args_eliminate 0.02% : 0.000005s : 1: pipeline_parallel_scheduler 0.02% : 0.000005s : 1: pipeline_split 0.13% : 0.000038s : 1: pre_auto_parallel 0.11% : 0.000032s : 1: py_interpret_to_execute 0.09% : 0.000028s : 1: py_interpret_to_execute_after_opt_a 0.02% : 0.000007s : 1: remove_cast_before_assign_add 0.23% : 0.000069s : 1: remove_dup_value 1.34% : 0.000395s : 1: renormalize.infer 1.40% : 0.000414s : 1: renormalize.specialize 0.02% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.03% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.22% : 0.000064s : 1: rewriter_after_opt_a 0.24% : 0.000072s : 1: rewriter_before_opt_a 0.03% : 0.000008s : 1: slice_cell_reuse_recomputed_activation 0.02% : 0.000005s : 1: slice_recompute_activation 0.02% : 0.000005s : 1: split_layernorm_comm 0.03% : 0.000008s : 1: split_matmul_comm_elemetwise 0.04% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.66% : 0.000196s : 1: symbol_engine_optimizer 0.42% : 0.000123s : 1: tuple_transform 18.10% : 0.005344s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_large_gsq[1] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_large_gsq[1],max_mem:522.0M =============================== 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 588.07s (0:09:48) ==================