==================================================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_001/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 4 items test_paged_attention.py [WARNING] ME(168185:281473465110320,MainProcess):2026-01-29-17:38:01.839.266 [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 = 0.327217, [21] [bootstrap]: 0.00079096 [type_inference]: 0.178402 [event_method]: 1.631e-05 [auto_monad]: 8.556e-05 [graph_reusing]: 4.77e-06 [inline]: 2.61e-06 [add_attr]: 0.140961, [1] [add_attr_with_inline]: 0.140948, [1] [Cycle 1]: 9.316e-05, [2] [tag_attr]: 2.103e-05 [meta_addattr_fg_expand]: 3.67998e-06 [parallel-infer-symbol]: 3.61001e-06 [pre_auto_parallel]: 5.018e-05 [insert-virtual-dataset]: 2.39999e-06 [parallel-infer-symbol-second]: 7.7e-07 [dataset_repeat_opt]: 1.95001e-06 [pipeline_split]: 1.53002e-06 [optimize]: 0.00608301, [53] [py_interpret_to_execute]: 2.573e-05 [rewriter_before_opt_a]: 8.857e-05 [opt_a]: 0.00327256, [2] [Cycle 1]: 0.00225974, [45] [expand_dump_flag]: 3.48999e-06 [switch_simplify]: 3.534e-05 [loop_unroll]: 2.089e-05 [a_1]: 0.00048067 [with_stream_mark]: 2.404e-05 [recompute_prepare]: 1.426e-05 [updatestate_depend_eliminate]: 5.71998e-06 [updatestate_assign_eliminate]: 5.00999e-06 [updatestate_loads_eliminate]: 4.99e-06 [parameter_eliminate]: 2.30002e-06 [a_2]: 0.00015421 [accelerated_algorithm]: 1.124e-05 [shard]: 2.64999e-06 [meta_shard_fg_expand]: 2.14e-06 [shard_inline]: 1.154e-05 [merge_send_recv]: 1.028e-05 [auto_parallel]: 9.39e-06 [parallel]: 4.954e-05 [flash_sp]: 1.272e-05 [merge_comm]: 6.23002e-06 [allreduce_fusion]: 4.89e-06 [matmul_add_comm_reduction]: 1.144e-05 [allreduce_slice_to_reducescatter]: 1.14e-06 [virtual_shard_identity]: 1.433e-05 [virtual_dataset]: 1.163e-05 [get_grad_eliminate_]: 1.096e-05 [virtual_output]: 1.064e-05 [merge_forward]: 5.79e-06 [cell_reuse_recompute_pass]: 1.50999e-06 [offload_activation]: 1.179e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.892e-05 [merge_recompute_call_nodes]: 1.45999e-06 [before_grad]: 1.487e-05 [set_forward_comm_id_for_comm_node_pass]: 5.35999e-06 [meta_fg_expand]: 3.58e-06 [flash_sp_send_recv_attached]: 2.32999e-06 [receive_attached]: 1.394e-05 [after_resolve]: 2.397e-05 [a_after_grad]: 1.739e-05 [renormalize]: 0.00076726 [add_forward_monad_depend]: 1.149e-05 [auto_monad_grad]: 2.81e-06 [auto_monad_eliminator]: 1.727e-05 [cse]: 7.836e-05 [a_3]: 8.017e-05 [Cycle 2]: 0.0010004, [45] [expand_dump_flag]: 1.84998e-06 [switch_simplify]: 1.342e-05 [loop_unroll]: 1.109e-05 [a_1]: 0.00027792 [with_stream_mark]: 1.675e-05 [recompute_prepare]: 1.094e-05 [updatestate_depend_eliminate]: 5.05001e-06 [updatestate_assign_eliminate]: 4.33999e-06 [updatestate_loads_eliminate]: 4.07e-06 [parameter_eliminate]: 9.09989e-07 [a_2]: 0.00013544 [accelerated_algorithm]: 1.03e-05 [shard]: 1.87001e-06 [meta_shard_fg_expand]: 1.64e-06 [shard_inline]: 1.013e-05 [merge_send_recv]: 6.86999e-06 [auto_parallel]: 7.66001e-06 [parallel]: 5.27999e-06 [flash_sp]: 3.81001e-06 [merge_comm]: 4.68999e-06 [allreduce_fusion]: 4.37e-06 [matmul_add_comm_reduction]: 8.74e-06 [allreduce_slice_to_reducescatter]: 7.50006e-07 [virtual_shard_identity]: 1.139e-05 [virtual_dataset]: 1.018e-05 [get_grad_eliminate_]: 1.02e-05 [virtual_output]: 1.031e-05 [merge_forward]: 5.10001e-06 [cell_reuse_recompute_pass]: 1.97001e-06 [offload_activation]: 1.097e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.734e-05 [merge_recompute_call_nodes]: 9.09989e-07 [before_grad]: 1.337e-05 [set_forward_comm_id_for_comm_node_pass]: 5.57999e-06 [meta_fg_expand]: 2.85998e-06 [flash_sp_send_recv_attached]: 1.10999e-06 [receive_attached]: 1.39e-06 [after_resolve]: 2.051e-05 [a_after_grad]: 1.653e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 2.29999e-06 [auto_monad_grad]: 1.27e-06 [auto_monad_eliminator]: 1.041e-05 [cse]: 3.126e-05 [a_3]: 6.799e-05 [py_interpret_to_execute_after_opt_a]: 1.689e-05 [slice_cell_reuse_recomputed_activation]: 1.99e-06 [rewriter_after_opt_a]: 7.839e-05 [convert_after_rewriter]: 1.174e-05 [order_py_execute_after_rewriter]: 7.17002e-06 [mutable_eliminate]: 0.00068838 [opt_b]: 0.0003389, [1] [Cycle 1]: 0.00033069, [7] [b_1]: 0.00021962 [b_2]: 1.264e-05 [updatestate_depend_eliminate]: 1.046e-05 [updatestate_assign_eliminate]: 4.43001e-06 [updatestate_loads_eliminate]: 3.98001e-06 [renormalize]: 9.09989e-07 [cse]: 4.295e-05 [optimize_parallel_all_gather_comm]: 2.006e-05 [overlap_param_gather]: 1.89999e-06 [cconv]: 3.168e-05 [loop_unroll]: 0.00048331 [opt_after_cconv]: 0.00015436, [1] [Cycle 1]: 0.00014667, [7] [c_1]: 5.7e-05 [parameter_eliminate]: 5.22e-06 [updatestate_depend_eliminate]: 8.23999e-06 [updatestate_assign_eliminate]: 4.3e-06 [updatestate_loads_eliminate]: 3.91001e-06 [cse]: 3.519e-05 [renormalize]: 3.50003e-07 [remove_dup_value]: 5.783e-05 [tuple_transform]: 0.00011642, [1] [Cycle 1]: 0.00011163, [4] [d_1]: 8.056e-05 [none_parameter_eliminate]: 1.97999e-06 [renormalize]: 2.30008e-07 [switch_simplify]: 1.137e-05 [partial_unused_args_eliminate]: 1.82999e-06 [add_recomputation]: 6.397e-05 [cse_after_recomputation]: 3.041e-05, [1] [Cycle 1]: 2.585e-05, [1] [cse]: 2.013e-05 [environ_conv]: 1.96e-05 [swap_dp_allreduce_reducescatter]: 6.79999e-06 [bias_add_comm_swap]: 2.79999e-06 [label_micro_interleaved_index]: 4.17e-06 [label_fine_grained_interleaved_index]: 2.54001e-06 [merge_cast_opt]: 1.22999e-06 [slice_recompute_activation]: 2.09999e-06 [micro_interleaved_order_control]: 2.53003e-06 [assign_add_opt]: 1.45001e-06 [ForceFp32Comm]: 8.2e-07 [remove_cast_before_assign_add]: 1.20001e-06 [full_micro_interleaved_order_control]: 2.48e-06 [reorder_send_recv_between_fp_bp]: 2.49001e-06 [comm_op_add_attrs]: 1.12999e-06 [add_comm_op_reuse_tag]: 1.30999e-06 [interleave_split_concat_branches]: 1.10001e-06 [interleave_parallel_branches]: 1.04e-06 [overlap_opt_shard_in_pipeline]: 2.389e-05 [overlap_opt_shard_grad_in_pipeline]: 2.11e-06 [control_data_broadcast_order]: 1.652e-05 [grouped_pairwise_exchange_alltoall]: 1.40999e-06 [offloading_packed_experts]: 5.07999e-06 [overlap_recompute_and_grad_model_parallel]: 5.37001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.13001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.23002e-06 [overlap_recompute_comm]: 2.17999e-06 [overlap_grad_ring_attention]: 5.17999e-06 [overlap_grad_flash_sp]: 3.87e-05 [begin_end_overlap_inline]: 4.59986e-07 [split_matmul_comm_elemetwise]: 2.27999e-06 [split_layernorm_comm]: 1.71e-06 [handle_group_info]: 1.49e-06 [symbol_engine_optimizer]: 0.00019157, [1] [Cycle 1]: 0.00018688, [6] [build]: 8.281e-05 [elim_shapecalc]: 1.61e-05 [elim_not_effective]: 2.49e-05 [opt_reshape]: 1.084e-05 [fold_const_symbol]: 1.991e-05 [renormalize]: 6.79982e-07 [detach_backward]: 2.29999e-06 [pipeline_parallel_scheduler]: 1.52001e-06 [auto_monad_reorder]: 2.825e-05 [get_jit_bprop_graph]: 1.99e-06 [rewriter_after_jit_bprop_graph]: 4.14002e-06 [opt_after_jit_grad]: 0.0005401 [validate]: 6.57e-05 Sums bootstrap : 0.000791s : 0.43% type_inference : 0.178402s : 96.30% event_method : 0.000016s : 0.01% auto_monad : 0.000086s : 0.05% 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 : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000050s : 0.03% insert-virtual-dataset : 0.000002s : 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 : 0.000026s : 0.01% optimize.rewriter_before_opt_a : 0.000089s : 0.05% optimize.opt_a.expand_dump_flag : 0.000005s : 0.00% optimize.opt_a.switch_simplify : 0.000049s : 0.03% optimize.opt_a.loop_unroll : 0.000032s : 0.02% optimize.opt_a.a_1 : 0.000759s : 0.41% optimize.opt_a.with_stream_mark : 0.000041s : 0.02% optimize.opt_a.recompute_prepare : 0.000025s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000011s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000009s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000009s : 0.00% optimize.opt_a.parameter_eliminate : 0.000003s : 0.00% optimize.opt_a.a_2 : 0.000290s : 0.16% optimize.opt_a.accelerated_algorithm : 0.000022s : 0.01% optimize.opt_a.shard : 0.000005s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000004s : 0.00% optimize.opt_a.shard_inline : 0.000022s : 0.01% optimize.opt_a.merge_send_recv : 0.000017s : 0.01% optimize.opt_a.auto_parallel : 0.000017s : 0.01% optimize.opt_a.parallel : 0.000055s : 0.03% optimize.opt_a.flash_sp : 0.000017s : 0.01% optimize.opt_a.merge_comm : 0.000011s : 0.01% optimize.opt_a.allreduce_fusion : 0.000009s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000020s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000026s : 0.01% optimize.opt_a.virtual_dataset : 0.000022s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000021s : 0.01% optimize.opt_a.virtual_output : 0.000021s : 0.01% optimize.opt_a.merge_forward : 0.000011s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.00% optimize.opt_a.offload_activation : 0.000023s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000036s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000002s : 0.00% optimize.opt_a.before_grad : 0.000028s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000011s : 0.01% optimize.opt_a.meta_fg_expand : 0.000006s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000003s : 0.00% optimize.opt_a.receive_attached : 0.000015s : 0.01% optimize.opt_a.after_resolve : 0.000044s : 0.02% optimize.opt_a.a_after_grad : 0.000034s : 0.02% optimize.opt_a.renormalize : 0.000767s : 0.41% optimize.opt_a.add_forward_monad_depend : 0.000014s : 0.01% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000028s : 0.01% optimize.opt_a.cse : 0.000110s : 0.06% optimize.opt_a.a_3 : 0.000148s : 0.08% optimize.py_interpret_to_execute_after_opt_a : 0.000017s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000078s : 0.04% optimize.convert_after_rewriter : 0.000012s : 0.01% optimize.order_py_execute_after_rewriter : 0.000007s : 0.00% optimize.mutable_eliminate : 0.000688s : 0.37% optimize.opt_b.b_1 : 0.000220s : 0.12% 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 : 0.000004s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000043s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000020s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000032s : 0.02% optimize.loop_unroll : 0.000483s : 0.26% optimize.opt_after_cconv.c_1 : 0.000057s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000008s : 0.00% 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 : 0.000035s : 0.02% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000058s : 0.03% optimize.tuple_transform.d_1 : 0.000081s : 0.04% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000011s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000064s : 0.03% optimize.cse_after_recomputation.cse : 0.000020s : 0.01% optimize.environ_conv : 0.000020s : 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 : 0.000004s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000002s : 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 : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000017s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000001s : 0.00% optimize.offloading_packed_experts : 0.000005s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000005s : 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 : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000039s : 0.02% optimize.begin_end_overlap_inline : 0.000000s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000083s : 0.04% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000016s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000025s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000011s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000020s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000028s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000004s : 0.00% opt_after_jit_grad : 0.000540s : 0.29% validate : 0.000066s : 0.04% Time group info: ------[substitution.] 0.000153 39 5.82% : 0.000009s : 2: substitution.elim_not_effective 4.89% : 0.000007s : 2: substitution.fold_const_symbol 5.53% : 0.000008s : 10: substitution.graph_param_transform 71.31% : 0.000109s : 1: substitution.inline 2.43% : 0.000004s : 4: substitution.j_node_and_user_rematch 3.59% : 0.000005s : 4: substitution.remove_not_recompute_node 6.42% : 0.000010s : 16: substitution.replace_old_param ------[type_inference.] 0.178306 2 99.71% : 0.177782s : 1: type_inference.infer 0.29% : 0.000524s : 1: type_inference.specialize ------[replace.] 0.000019 1 100.00% : 0.000019s : 1: replace.inline ------[match.] 0.000108 1 100.00% : 0.000108s : 1: match.inline ------[predicate.] 0.000252 2335 0.83% : 0.000002s : 21: predicate.accumulaten_eliminater 0.81% : 0.000002s : 10: predicate.ad_related_special_op_eliminate 0.74% : 0.000002s : 20: predicate.addn_check_dump 0.82% : 0.000002s : 21: predicate.addn_zero_filter 0.75% : 0.000002s : 21: predicate.adjust_all_reduce_mul_add 1.88% : 0.000005s : 41: predicate.arithmetic_simplify 0.82% : 0.000002s : 21: predicate.cast_eliminate 0.82% : 0.000002s : 20: predicate.check_bprop_eliminate 0.69% : 0.000002s : 20: predicate.compare_switch_simplify 0.29% : 0.000001s : 10: predicate.const_output_eliminate 0.95% : 0.000002s : 20: predicate.depend_value_elim 0.85% : 0.000002s : 21: predicate.dict_get_item_const_eliminator 1.07% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.78% : 0.000002s : 21: predicate.dict_set_item_eliminator 1.25% : 0.000003s : 20: predicate.dumpgradient_eliminate 0.36% : 0.000001s : 10: predicate.elim_not_effective 0.52% : 0.000001s : 10: predicate.elim_shapecalc_of_broadcastargs 1.15% : 0.000003s : 31: predicate.environ_add_const_eliminate 1.08% : 0.000003s : 31: predicate.environ_get_add_eliminate 1.08% : 0.000003s : 31: predicate.environ_get_depend_swap 1.93% : 0.000005s : 51: predicate.environ_get_eliminate 1.10% : 0.000003s : 31: predicate.environ_get_set_eliminate 0.82% : 0.000002s : 22: predicate.exchange_switch_depend_value 1.59% : 0.000004s : 22: predicate.float_depend_g_call 0.76% : 0.000002s : 20: predicate.float_environ_get_switch 1.12% : 0.000003s : 30: predicate.float_tuple_getitem_switch 0.32% : 0.000001s : 10: predicate.fold_const_symbol 1.03% : 0.000003s : 20: predicate.get_grad_eliminate 0.44% : 0.000001s : 10: predicate.graph_param_transform 0.75% : 0.000002s : 20: predicate.incorporate_call 0.71% : 0.000002s : 20: predicate.incorporate_call_switch 5.51% : 0.000014s : 103: predicate.inline 0.96% : 0.000002s : 20: predicate.inline_without_move 0.57% : 0.000001s : 20: predicate.j_node_and_user_rematch 0.99% : 0.000002s : 20: predicate.less_batch_normalization 1.64% : 0.000004s : 41: predicate.list_to_tuple_eliminator_ 2.36% : 0.000006s : 62: predicate.load_eliminater 1.11% : 0.000003s : 10: predicate.loop_unroll_after_grad 1.49% : 0.000004s : 31: predicate.loop_unroll_before_grad 1.78% : 0.000004s : 41: predicate.make_slice_get_slice_eliminator 0.78% : 0.000002s : 20: predicate.merge_addn 0.79% : 0.000002s : 20: predicate.micro_step_allgather_replace 0.77% : 0.000002s : 20: predicate.mini_step_allgather_replace 0.75% : 0.000002s : 21: predicate.minmaximum_grad 1.46% : 0.000004s : 10: predicate.mutable_eliminate 0.44% : 0.000001s : 10: predicate.opt_reshape 0.50% : 0.000001s : 10: predicate.parallel_virtual_node 1.02% : 0.000003s : 22: predicate.partial_defer_inline 1.30% : 0.000003s : 31: predicate.partial_eliminate 0.82% : 0.000002s : 21: predicate.print_const_string_wrapper 0.77% : 0.000002s : 20: predicate.reduce_all_const_elim 1.02% : 0.000003s : 21: predicate.reduce_eliminate 2.30% : 0.000006s : 62: predicate.redundant_stop_gradient_eliminater 0.78% : 0.000002s : 20: predicate.remove_not_recompute_node 1.58% : 0.000004s : 41: predicate.replace_applicator 0.66% : 0.000002s : 20: predicate.replace_old_param 0.53% : 0.000001s : 10: predicate.reset_defer_inline 0.83% : 0.000002s : 21: predicate.reshape_eliminate 0.80% : 0.000002s : 20: predicate.row_tensor_add_zeros_like 0.44% : 0.000001s : 10: predicate.row_tensor_eliminate 0.98% : 0.000002s : 20: predicate.same_eliminate 0.69% : 0.000002s : 20: predicate.set_cell_output_no_recompute 1.11% : 0.000003s : 20: predicate.shard_identity_eliminate 0.78% : 0.000002s : 20: predicate.special_op_eliminate 0.87% : 0.000002s : 20: predicate.specialize_transform 1.04% : 0.000003s : 20: predicate.split_environ_get_set_with_tuple_value 1.08% : 0.000003s : 20: predicate.stack_unstack_eliminate 0.55% : 0.000001s : 10: predicate.switch_call_monad_eliminater 0.89% : 0.000002s : 22: predicate.switch_defer_inline 1.77% : 0.000004s : 42: predicate.switch_layer_defer_inline 3.77% : 0.000010s : 83: predicate.switch_simplify 0.86% : 0.000002s : 21: predicate.tile_eliminate 0.89% : 0.000002s : 21: predicate.transpose_eliminate 1.57% : 0.000004s : 41: predicate.tuple_list_convert_item_index_to_positive 1.59% : 0.000004s : 41: predicate.tuple_list_get_item_const_eliminator 1.55% : 0.000004s : 41: predicate.tuple_list_get_item_depend_reorder 2.87% : 0.000007s : 61: predicate.tuple_list_get_item_eliminator 1.55% : 0.000004s : 41: predicate.tuple_list_get_set_item_eliminator 2.49% : 0.000006s : 61: predicate.tuple_list_set_item_eliminator 1.60% : 0.000004s : 41: predicate.tuple_to_list_eliminator_ 2.23% : 0.000006s : 62: predicate.updatestate_pure_node_eliminater 3.24% : 0.000008s : 82: predicate.updatestate_useless_node_eliminater 0.46% : 0.000001s : 10: predicate.value_based_eliminate 0.88% : 0.000002s : 20: predicate.virtual_dataset_eliminate 0.89% : 0.000002s : 20: predicate.virtual_output_eliminate 0.39% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.53% : 0.000001s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000489 6 52.14% : 0.000255s : 3: func_graph_cloner_run.FuncGraphClonerGraph 47.86% : 0.000234s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.476856 192 0.00% : 0.000004s : 1: ForceFp32Comm 29.56% : 0.140967s : 1: add_attr 29.56% : 0.140952s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.01% : 0.000068s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.02% : 0.000091s : 1: auto_monad 0.01% : 0.000033s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.17% : 0.000825s : 1: bootstrap 0.01% : 0.000036s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000020s : 1: control_data_broadcast_order 0.00% : 0.000015s : 1: convert_after_rewriter 0.01% : 0.000033s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000005s : 1: detach_backward 0.00% : 0.000023s : 1: environ_conv 0.00% : 0.000023s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000008s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000006s : 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% : 0.000007s : 1: label_micro_interleaved_index 0.10% : 0.000496s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000005s : 1: micro_interleaved_order_control 0.15% : 0.000698s : 1: mutable_eliminate 0.00% : 0.000008s : 1: offloading_packed_experts 0.00% : 0.000021s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000024s : 1: opt.transform.mutable_eliminate 0.31% : 0.001487s : 78: opt.transform.opt_a 0.01% : 0.000056s : 1: opt.transform.opt_after_cconv 0.01% : 0.000041s : 1: opt.transform.opt_after_jit_grad 0.04% : 0.000206s : 28: opt.transform.opt_b 0.02% : 0.000090s : 2: opt.transform.opt_trans_graph 0.01% : 0.000068s : 4: opt.transform.symbol_engine_opt 0.69% : 0.003276s : 1: opt_a 0.03% : 0.000158s : 1: opt_after_cconv 0.12% : 0.000553s : 1: opt_after_jit_grad 0.07% : 0.000343s : 1: opt_b 1.28% : 0.006088s : 1: optimize 0.00% : 0.000024s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000010s : 1: order_py_execute_after_rewriter 0.01% : 0.000043s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000008s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.01% : 0.000027s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000008s : 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 0.01% : 0.000055s : 1: pre_auto_parallel 0.01% : 0.000030s : 1: py_interpret_to_execute 0.00% : 0.000020s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000062s : 1: remove_dup_value 0.09% : 0.000418s : 1: renormalize.infer 0.07% : 0.000340s : 1: renormalize.specialize 0.00% : 0.000005s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000007s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000084s : 1: rewriter_after_opt_a 0.02% : 0.000095s : 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% : 0.000004s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000010s : 1: swap_dp_allreduce_reducescatter 0.04% : 0.000194s : 1: symbol_engine_optimizer 0.02% : 0.000119s : 1: tuple_transform 37.42% : 0.178423s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_bnsd[QuantMethod.FP16_VEC-0] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_bnsd[QuantMethod.FP16_VEC-0],max_mem:484.0M [WARNING] ME(168185:281473465110320,MainProcess):2026-01-29-17:38:34.311.928 [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 = 0.107796, [21] [bootstrap]: 0.00089608 [type_inference]: 0.0689047 [event_method]: 2.096e-05 [auto_monad]: 8.51e-05 [graph_reusing]: 5.64998e-06 [inline]: 3.3e-06 [add_attr]: 0.00736123, [1] [add_attr_with_inline]: 0.00733942, [1] [Cycle 1]: 9.868e-05, [2] [tag_attr]: 2.879e-05 [meta_addattr_fg_expand]: 5.00999e-06 [parallel-infer-symbol]: 4.19002e-06 [pre_auto_parallel]: 6.518e-05 [insert-virtual-dataset]: 2.74001e-06 [parallel-infer-symbol-second]: 6.50005e-07 [dataset_repeat_opt]: 2.56e-06 [pipeline_split]: 1.72001e-06 [optimize]: 0.0292693, [53] [py_interpret_to_execute]: 8.235e-05 [rewriter_before_opt_a]: 9.873e-05 [opt_a]: 0.0255186, [2] [Cycle 1]: 0.0240237, [45] [expand_dump_flag]: 4.02e-06 [switch_simplify]: 3.487e-05 [loop_unroll]: 2.124e-05 [a_1]: 0.00058489 [with_stream_mark]: 2.892e-05 [recompute_prepare]: 1.53e-05 [updatestate_depend_eliminate]: 5.93002e-06 [updatestate_assign_eliminate]: 5.55001e-06 [updatestate_loads_eliminate]: 5.47999e-06 [parameter_eliminate]: 2.16998e-06 [a_2]: 0.00017209 [accelerated_algorithm]: 1.837e-05 [shard]: 3.18e-06 [meta_shard_fg_expand]: 5.63002e-06 [shard_inline]: 1.275e-05 [merge_send_recv]: 1.188e-05 [auto_parallel]: 1.05e-05 [parallel]: 3.937e-05 [flash_sp]: 1.187e-05 [merge_comm]: 6.81001e-06 [allreduce_fusion]: 5.62001e-06 [matmul_add_comm_reduction]: 1.353e-05 [allreduce_slice_to_reducescatter]: 7.7e-07 [virtual_shard_identity]: 2.303e-05 [virtual_dataset]: 1.858e-05 [get_grad_eliminate_]: 1.988e-05 [virtual_output]: 1.884e-05 [merge_forward]: 6.17999e-06 [cell_reuse_recompute_pass]: 1.91e-06 [offload_activation]: 1.45e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.239e-05 [merge_recompute_call_nodes]: 1.87999e-06 [before_grad]: 3.155e-05 [set_forward_comm_id_for_comm_node_pass]: 1.233e-05 [meta_fg_expand]: 5.36002e-06 [flash_sp_send_recv_attached]: 2.93e-06 [receive_attached]: 2.801e-05 [after_resolve]: 4.239e-05 [a_after_grad]: 4.094e-05 [renormalize]: 0.0219825 [add_forward_monad_depend]: 1.87e-05 [auto_monad_grad]: 2.71e-06 [auto_monad_eliminator]: 2.83e-05 [cse]: 9.797e-05 [a_3]: 0.00011686 [Cycle 2]: 0.00147616, [45] [expand_dump_flag]: 2.65002e-06 [switch_simplify]: 1.654e-05 [loop_unroll]: 1.413e-05 [a_1]: 0.00034643 [with_stream_mark]: 2.974e-05 [recompute_prepare]: 1.654e-05 [updatestate_depend_eliminate]: 7.77e-06 [updatestate_assign_eliminate]: 5.88998e-06 [updatestate_loads_eliminate]: 6.38e-06 [parameter_eliminate]: 2.47001e-06 [a_2]: 0.00016319 [accelerated_algorithm]: 1.486e-05 [shard]: 2.96999e-06 [meta_shard_fg_expand]: 2.97002e-06 [shard_inline]: 1.729e-05 [merge_send_recv]: 1.216e-05 [auto_parallel]: 1.254e-05 [parallel]: 1.101e-05 [flash_sp]: 5.30001e-06 [merge_comm]: 6.27001e-06 [allreduce_fusion]: 5.46998e-06 [matmul_add_comm_reduction]: 1.5e-05 [allreduce_slice_to_reducescatter]: 9.89996e-07 [virtual_shard_identity]: 1.943e-05 [virtual_dataset]: 1.232e-05 [get_grad_eliminate_]: 1.195e-05 [virtual_output]: 1.293e-05 [merge_forward]: 7.51001e-06 [cell_reuse_recompute_pass]: 3.30003e-06 [offload_activation]: 1.611e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.184e-05 [merge_recompute_call_nodes]: 1.85001e-06 [before_grad]: 2.22e-05 [set_forward_comm_id_for_comm_node_pass]: 8.82e-06 [meta_fg_expand]: 5.77001e-06 [flash_sp_send_recv_attached]: 1.74e-06 [receive_attached]: 2.89001e-06 [after_resolve]: 2.947e-05 [a_after_grad]: 2.022e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 3.01001e-06 [auto_monad_grad]: 1.84998e-06 [auto_monad_eliminator]: 1.637e-05 [cse]: 6.862e-05 [a_3]: 7.869e-05 [py_interpret_to_execute_after_opt_a]: 3.429e-05 [slice_cell_reuse_recomputed_activation]: 2.32001e-06 [rewriter_after_opt_a]: 7.002e-05 [convert_after_rewriter]: 1.001e-05 [order_py_execute_after_rewriter]: 7.06001e-06 [mutable_eliminate]: 0.0009486 [opt_b]: 0.00044049, [1] [Cycle 1]: 0.00042921, [7] [b_1]: 0.0002476 [b_2]: 1.491e-05 [updatestate_depend_eliminate]: 1.201e-05 [updatestate_assign_eliminate]: 5.43002e-06 [updatestate_loads_eliminate]: 4.93001e-06 [renormalize]: 6.59988e-07 [cse]: 8.239e-05 [optimize_parallel_all_gather_comm]: 2.513e-05 [overlap_param_gather]: 2.58e-06 [cconv]: 4.212e-05 [loop_unroll]: 0.00061354 [opt_after_cconv]: 0.00021395, [1] [Cycle 1]: 0.00020481, [7] [c_1]: 6.386e-05 [parameter_eliminate]: 5.64e-06 [updatestate_depend_eliminate]: 9.07999e-06 [updatestate_assign_eliminate]: 4.65001e-06 [updatestate_loads_eliminate]: 4.33001e-06 [cse]: 5.64e-05 [renormalize]: 4.80009e-07 [remove_dup_value]: 8.194e-05 [tuple_transform]: 0.00015762, [1] [Cycle 1]: 0.00015077, [4] [d_1]: 0.00010183 [none_parameter_eliminate]: 2.22999e-06 [renormalize]: 1.8999e-07 [switch_simplify]: 1.282e-05 [partial_unused_args_eliminate]: 2.18998e-06 [add_recomputation]: 7.278e-05 [cse_after_recomputation]: 4.879e-05, [1] [Cycle 1]: 4.156e-05, [1] [cse]: 2.955e-05 [environ_conv]: 1.042e-05 [swap_dp_allreduce_reducescatter]: 8.47e-06 [bias_add_comm_swap]: 3.31001e-06 [label_micro_interleaved_index]: 6.07999e-06 [label_fine_grained_interleaved_index]: 3.3e-06 [merge_cast_opt]: 1.26002e-06 [slice_recompute_activation]: 2.27999e-06 [micro_interleaved_order_control]: 2.99999e-06 [assign_add_opt]: 1.79e-06 [ForceFp32Comm]: 7.89994e-07 [remove_cast_before_assign_add]: 1.05999e-06 [full_micro_interleaved_order_control]: 2.19999e-06 [reorder_send_recv_between_fp_bp]: 3.18998e-06 [comm_op_add_attrs]: 1.04e-06 [add_comm_op_reuse_tag]: 1.02998e-06 [interleave_split_concat_branches]: 1.27999e-06 [interleave_parallel_branches]: 1.43002e-06 [overlap_opt_shard_in_pipeline]: 1.24998e-06 [overlap_opt_shard_grad_in_pipeline]: 1.79998e-06 [control_data_broadcast_order]: 2.302e-05 [grouped_pairwise_exchange_alltoall]: 1.62999e-06 [offloading_packed_experts]: 5.64e-06 [overlap_recompute_and_grad_model_parallel]: 7e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.64998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.98002e-06 [overlap_recompute_comm]: 2.48e-06 [overlap_grad_ring_attention]: 8.45001e-06 [overlap_grad_flash_sp]: 2.465e-05 [begin_end_overlap_inline]: 5.10016e-07 [split_matmul_comm_elemetwise]: 2.25002e-06 [split_layernorm_comm]: 1.94e-06 [handle_group_info]: 1.03001e-06 [symbol_engine_optimizer]: 0.00026187, [1] [Cycle 1]: 0.00025251, [6] [build]: 0.0001042 [elim_shapecalc]: 2.78e-05 [elim_not_effective]: 2.215e-05 [opt_reshape]: 1.725e-05 [fold_const_symbol]: 2.498e-05 [renormalize]: 1.80007e-07 [detach_backward]: 2.40002e-06 [pipeline_parallel_scheduler]: 1.54998e-06 [auto_monad_reorder]: 3.926e-05 [get_jit_bprop_graph]: 1.89e-06 [rewriter_after_jit_bprop_graph]: 6.51e-06 [opt_after_jit_grad]: 0.00079928 [validate]: 7.799e-05 Sums bootstrap : 0.000896s : 0.91% type_inference : 0.068905s : 69.81% event_method : 0.000021s : 0.02% auto_monad : 0.000085s : 0.09% graph_reusing : 0.000006s : 0.01% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000029s : 0.03% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.01% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000065s : 0.07% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000082s : 0.08% optimize.rewriter_before_opt_a : 0.000099s : 0.10% optimize.opt_a.expand_dump_flag : 0.000007s : 0.01% optimize.opt_a.switch_simplify : 0.000051s : 0.05% optimize.opt_a.loop_unroll : 0.000035s : 0.04% optimize.opt_a.a_1 : 0.000931s : 0.94% optimize.opt_a.with_stream_mark : 0.000059s : 0.06% optimize.opt_a.recompute_prepare : 0.000032s : 0.03% optimize.opt_a.updatestate_depend_eliminate : 0.000014s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000011s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.01% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000335s : 0.34% optimize.opt_a.accelerated_algorithm : 0.000033s : 0.03% optimize.opt_a.shard : 0.000006s : 0.01% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.01% optimize.opt_a.shard_inline : 0.000030s : 0.03% optimize.opt_a.merge_send_recv : 0.000024s : 0.02% optimize.opt_a.auto_parallel : 0.000023s : 0.02% optimize.opt_a.parallel : 0.000050s : 0.05% optimize.opt_a.flash_sp : 0.000017s : 0.02% optimize.opt_a.merge_comm : 0.000013s : 0.01% optimize.opt_a.allreduce_fusion : 0.000011s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000029s : 0.03% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000042s : 0.04% optimize.opt_a.virtual_dataset : 0.000031s : 0.03% optimize.opt_a.get_grad_eliminate_ : 0.000032s : 0.03% optimize.opt_a.virtual_output : 0.000032s : 0.03% optimize.opt_a.merge_forward : 0.000014s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.01% optimize.opt_a.offload_activation : 0.000031s : 0.03% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000064s : 0.07% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000054s : 0.05% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000021s : 0.02% optimize.opt_a.meta_fg_expand : 0.000011s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000031s : 0.03% optimize.opt_a.after_resolve : 0.000072s : 0.07% optimize.opt_a.a_after_grad : 0.000061s : 0.06% optimize.opt_a.renormalize : 0.021983s : 22.27% optimize.opt_a.add_forward_monad_depend : 0.000022s : 0.02% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000045s : 0.05% optimize.opt_a.cse : 0.000167s : 0.17% optimize.opt_a.a_3 : 0.000196s : 0.20% optimize.py_interpret_to_execute_after_opt_a : 0.000034s : 0.03% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000070s : 0.07% optimize.convert_after_rewriter : 0.000010s : 0.01% optimize.order_py_execute_after_rewriter : 0.000007s : 0.01% optimize.mutable_eliminate : 0.000949s : 0.96% optimize.opt_b.b_1 : 0.000248s : 0.25% optimize.opt_b.b_2 : 0.000015s : 0.02% optimize.opt_b.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000082s : 0.08% optimize.optimize_parallel_all_gather_comm : 0.000025s : 0.03% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000042s : 0.04% optimize.loop_unroll : 0.000614s : 0.62% optimize.opt_after_cconv.c_1 : 0.000064s : 0.06% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.cse : 0.000056s : 0.06% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000082s : 0.08% optimize.tuple_transform.d_1 : 0.000102s : 0.10% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000013s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000073s : 0.07% optimize.cse_after_recomputation.cse : 0.000030s : 0.03% optimize.environ_conv : 0.000010s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.01% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000023s : 0.02% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.01% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.01% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000008s : 0.01% optimize.overlap_grad_flash_sp : 0.000025s : 0.02% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000104s : 0.11% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000028s : 0.03% optimize.symbol_engine_optimizer.elim_not_effective : 0.000022s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000017s : 0.02% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000025s : 0.03% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000039s : 0.04% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.01% opt_after_jit_grad : 0.000799s : 0.81% validate : 0.000078s : 0.08% Time group info: ------[substitution.] 0.000221 39 1.69% : 0.000004s : 2: substitution.elim_not_effective 3.97% : 0.000009s : 2: substitution.fold_const_symbol 3.82% : 0.000008s : 10: substitution.graph_param_transform 80.15% : 0.000177s : 1: substitution.inline 2.29% : 0.000005s : 4: substitution.j_node_and_user_rematch 2.71% : 0.000006s : 4: substitution.remove_not_recompute_node 5.37% : 0.000012s : 16: substitution.replace_old_param ------[type_inference.] 0.068741 2 97.60% : 0.067091s : 1: type_inference.infer 2.40% : 0.001650s : 1: type_inference.specialize ------[replace.] 0.000029 1 100.00% : 0.000029s : 1: replace.inline ------[match.] 0.000175 1 100.00% : 0.000175s : 1: match.inline ------[predicate.] 0.000286 2335 0.79% : 0.000002s : 21: predicate.accumulaten_eliminater 1.21% : 0.000003s : 10: predicate.ad_related_special_op_eliminate 0.67% : 0.000002s : 20: predicate.addn_check_dump 0.89% : 0.000003s : 21: predicate.addn_zero_filter 0.67% : 0.000002s : 21: predicate.adjust_all_reduce_mul_add 2.35% : 0.000007s : 41: predicate.arithmetic_simplify 0.80% : 0.000002s : 21: predicate.cast_eliminate 0.76% : 0.000002s : 20: predicate.check_bprop_eliminate 0.84% : 0.000002s : 20: predicate.compare_switch_simplify 0.26% : 0.000001s : 10: predicate.const_output_eliminate 1.14% : 0.000003s : 20: predicate.depend_value_elim 0.81% : 0.000002s : 21: predicate.dict_get_item_const_eliminator 1.05% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.85% : 0.000002s : 21: predicate.dict_set_item_eliminator 1.29% : 0.000004s : 20: predicate.dumpgradient_eliminate 0.31% : 0.000001s : 10: predicate.elim_not_effective 0.55% : 0.000002s : 10: predicate.elim_shapecalc_of_broadcastargs 1.13% : 0.000003s : 31: predicate.environ_add_const_eliminate 1.01% : 0.000003s : 31: predicate.environ_get_add_eliminate 1.21% : 0.000003s : 31: predicate.environ_get_depend_swap 1.81% : 0.000005s : 51: predicate.environ_get_eliminate 1.04% : 0.000003s : 31: predicate.environ_get_set_eliminate 0.77% : 0.000002s : 22: predicate.exchange_switch_depend_value 1.39% : 0.000004s : 22: predicate.float_depend_g_call 0.67% : 0.000002s : 20: predicate.float_environ_get_switch 1.04% : 0.000003s : 30: predicate.float_tuple_getitem_switch 0.28% : 0.000001s : 10: predicate.fold_const_symbol 0.95% : 0.000003s : 20: predicate.get_grad_eliminate 0.37% : 0.000001s : 10: predicate.graph_param_transform 0.70% : 0.000002s : 20: predicate.incorporate_call 0.61% : 0.000002s : 20: predicate.incorporate_call_switch 5.14% : 0.000015s : 103: predicate.inline 0.98% : 0.000003s : 20: predicate.inline_without_move 0.51% : 0.000001s : 20: predicate.j_node_and_user_rematch 1.48% : 0.000004s : 20: predicate.less_batch_normalization 1.70% : 0.000005s : 41: predicate.list_to_tuple_eliminator_ 2.25% : 0.000006s : 62: predicate.load_eliminater 1.10% : 0.000003s : 10: predicate.loop_unroll_after_grad 1.33% : 0.000004s : 31: predicate.loop_unroll_before_grad 1.74% : 0.000005s : 41: predicate.make_slice_get_slice_eliminator 0.76% : 0.000002s : 20: predicate.merge_addn 0.74% : 0.000002s : 20: predicate.micro_step_allgather_replace 0.73% : 0.000002s : 20: predicate.mini_step_allgather_replace 0.77% : 0.000002s : 21: predicate.minmaximum_grad 1.25% : 0.000004s : 10: predicate.mutable_eliminate 0.45% : 0.000001s : 10: predicate.opt_reshape 0.54% : 0.000002s : 10: predicate.parallel_virtual_node 1.07% : 0.000003s : 22: predicate.partial_defer_inline 1.15% : 0.000003s : 31: predicate.partial_eliminate 0.76% : 0.000002s : 21: predicate.print_const_string_wrapper 0.72% : 0.000002s : 20: predicate.reduce_all_const_elim 1.18% : 0.000003s : 21: predicate.reduce_eliminate 2.14% : 0.000006s : 62: predicate.redundant_stop_gradient_eliminater 0.70% : 0.000002s : 20: predicate.remove_not_recompute_node 1.59% : 0.000005s : 41: predicate.replace_applicator 0.70% : 0.000002s : 20: predicate.replace_old_param 0.36% : 0.000001s : 10: predicate.reset_defer_inline 0.77% : 0.000002s : 21: predicate.reshape_eliminate 0.76% : 0.000002s : 20: predicate.row_tensor_add_zeros_like 0.60% : 0.000002s : 10: predicate.row_tensor_eliminate 1.07% : 0.000003s : 20: predicate.same_eliminate 0.66% : 0.000002s : 20: predicate.set_cell_output_no_recompute 0.98% : 0.000003s : 20: predicate.shard_identity_eliminate 1.01% : 0.000003s : 20: predicate.special_op_eliminate 0.80% : 0.000002s : 20: predicate.specialize_transform 1.40% : 0.000004s : 20: predicate.split_environ_get_set_with_tuple_value 1.33% : 0.000004s : 20: predicate.stack_unstack_eliminate 0.45% : 0.000001s : 10: predicate.switch_call_monad_eliminater 0.83% : 0.000002s : 22: predicate.switch_defer_inline 1.59% : 0.000005s : 42: predicate.switch_layer_defer_inline 3.70% : 0.000011s : 83: predicate.switch_simplify 0.74% : 0.000002s : 21: predicate.tile_eliminate 0.81% : 0.000002s : 21: predicate.transpose_eliminate 1.91% : 0.000005s : 41: predicate.tuple_list_convert_item_index_to_positive 1.73% : 0.000005s : 41: predicate.tuple_list_get_item_const_eliminator 1.42% : 0.000004s : 41: predicate.tuple_list_get_item_depend_reorder 3.27% : 0.000009s : 61: predicate.tuple_list_get_item_eliminator 1.81% : 0.000005s : 41: predicate.tuple_list_get_set_item_eliminator 2.73% : 0.000008s : 61: predicate.tuple_list_set_item_eliminator 1.52% : 0.000004s : 41: predicate.tuple_to_list_eliminator_ 1.99% : 0.000006s : 62: predicate.updatestate_pure_node_eliminater 3.05% : 0.000009s : 82: predicate.updatestate_useless_node_eliminater 0.37% : 0.000001s : 10: predicate.value_based_eliminate 0.80% : 0.000002s : 20: predicate.virtual_dataset_eliminate 0.89% : 0.000003s : 20: predicate.virtual_output_eliminate 0.45% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.51% : 0.000001s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.001710 6 33.23% : 0.000568s : 3: func_graph_cloner_run.FuncGraphClonerGraph 66.77% : 0.001142s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.168676 192 0.00% : 0.000007s : 1: ForceFp32Comm 4.37% : 0.007370s : 1: add_attr 4.36% : 0.007348s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.05% : 0.000078s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.05% : 0.000091s : 1: auto_monad 0.03% : 0.000044s : 1: auto_monad_reorder 0.00% : 0.000007s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.55% : 0.000933s : 1: bootstrap 0.03% : 0.000052s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.02% : 0.000028s : 1: control_data_broadcast_order 0.01% : 0.000014s : 1: convert_after_rewriter 0.03% : 0.000053s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.01% : 0.000015s : 1: environ_conv 0.02% : 0.000030s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.01% : 0.000010s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.01% : 0.000009s : 1: insert-virtual-dataset 0.00% : 0.000006s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000008s : 1: label_fine_grained_interleaved_index 0.01% : 0.000014s : 1: label_micro_interleaved_index 0.37% : 0.000627s : 1: loop_unroll 0.00% : 0.000007s : 1: merge_cast_opt 0.00% : 0.000007s : 1: micro_interleaved_order_control 0.57% : 0.000965s : 1: mutable_eliminate 0.01% : 0.000010s : 1: offloading_packed_experts 0.01% : 0.000025s : 1: opt.transform.loop_unroll_optimizer 0.02% : 0.000034s : 1: opt.transform.mutable_eliminate 1.13% : 0.001906s : 78: opt.transform.opt_a 0.04% : 0.000062s : 1: opt.transform.opt_after_cconv 0.05% : 0.000078s : 1: opt.transform.opt_after_jit_grad 0.14% : 0.000229s : 28: opt.transform.opt_b 0.07% : 0.000111s : 2: opt.transform.opt_trans_graph 0.05% : 0.000087s : 4: opt.transform.symbol_engine_opt 15.14% : 0.025531s : 1: opt_a 0.13% : 0.000221s : 1: opt_after_cconv 0.49% : 0.000822s : 1: opt_after_jit_grad 0.26% : 0.000446s : 1: opt_b 17.36% : 0.029278s : 1: optimize 0.02% : 0.000029s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000012s : 1: order_py_execute_after_rewriter 0.02% : 0.000030s : 1: overlap_grad_flash_sp 0.00% : 0.000006s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000015s : 1: overlap_grad_ring_attention 0.01% : 0.000011s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.01% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000007s : 1: partial_unused_args_eliminate 0.00% : 0.000007s : 1: pipeline_parallel_scheduler 0.00% : 0.000008s : 1: pipeline_split 0.04% : 0.000070s : 1: pre_auto_parallel 0.05% : 0.000091s : 1: py_interpret_to_execute 0.02% : 0.000039s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.05% : 0.000089s : 1: remove_dup_value 12.37% : 0.020868s : 1: renormalize.infer 0.65% : 0.001092s : 1: renormalize.specialize 0.01% : 0.000012s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.05% : 0.000077s : 1: rewriter_after_opt_a 0.06% : 0.000105s : 1: rewriter_before_opt_a 0.01% : 0.000010s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.01% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.16% : 0.000269s : 1: symbol_engine_optimizer 0.10% : 0.000162s : 1: tuple_transform 40.87% : 0.068940s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_bnsd[QuantMethod.FP16_VEC-1] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_bnsd[QuantMethod.FP16_VEC-1],max_mem:484.0M [WARNING] ME(168185:281473465110320,MainProcess):2026-01-29-17:38:42.229.337 [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 = 0.171706, [21] [bootstrap]: 0.00092944 [type_inference]: 0.153674 [event_method]: 1.473e-05 [auto_monad]: 5.993e-05 [graph_reusing]: 4.77e-06 [inline]: 2.54999e-06 [add_attr]: 0.007171, [1] [add_attr_with_inline]: 0.00715516, [1] [Cycle 1]: 8.903e-05, [2] [tag_attr]: 3.113e-05 [meta_addattr_fg_expand]: 5.22999e-06 [parallel-infer-symbol]: 3.6e-06 [pre_auto_parallel]: 4.719e-05 [insert-virtual-dataset]: 2.31e-06 [parallel-infer-symbol-second]: 7.79983e-07 [dataset_repeat_opt]: 2.09e-06 [pipeline_split]: 1.52999e-06 [optimize]: 0.0086922, [53] [py_interpret_to_execute]: 5.721e-05 [rewriter_before_opt_a]: 9.739e-05 [opt_a]: 0.00500439, [2] [Cycle 1]: 0.00356251, [45] [expand_dump_flag]: 7.53999e-06 [switch_simplify]: 3.205e-05 [loop_unroll]: 2.112e-05 [a_1]: 0.00062907 [with_stream_mark]: 2.946e-05 [recompute_prepare]: 2.098e-05 [updatestate_depend_eliminate]: 7.15998e-06 [updatestate_assign_eliminate]: 9.37999e-06 [updatestate_loads_eliminate]: 5.23002e-06 [parameter_eliminate]: 2.18002e-06 [a_2]: 0.00017849 [accelerated_algorithm]: 1.933e-05 [shard]: 2.71999e-06 [meta_shard_fg_expand]: 4.11001e-06 [shard_inline]: 1.202e-05 [merge_send_recv]: 1.183e-05 [auto_parallel]: 9.17001e-06 [parallel]: 4.186e-05 [flash_sp]: 1.139e-05 [merge_comm]: 6.43e-06 [allreduce_fusion]: 5.44e-06 [matmul_add_comm_reduction]: 1.644e-05 [allreduce_slice_to_reducescatter]: 9.39996e-07 [virtual_shard_identity]: 1.877e-05 [virtual_dataset]: 1.892e-05 [get_grad_eliminate_]: 1.532e-05 [virtual_output]: 1.688e-05 [merge_forward]: 6.58998e-06 [cell_reuse_recompute_pass]: 2.14e-06 [offload_activation]: 1.493e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.807e-05 [merge_recompute_call_nodes]: 2.08002e-06 [before_grad]: 2.479e-05 [set_forward_comm_id_for_comm_node_pass]: 5.74e-06 [meta_fg_expand]: 4.4e-06 [flash_sp_send_recv_attached]: 3.35e-06 [receive_attached]: 2.43e-06 [after_resolve]: 3.555e-05 [a_after_grad]: 2.726e-05 [renormalize]: 0.00151332 [add_forward_monad_depend]: 1.426e-05 [auto_monad_grad]: 3.05998e-06 [auto_monad_eliminator]: 2.329e-05 [cse]: 8.852e-05 [a_3]: 9.374e-05 [Cycle 2]: 0.00142337, [45] [expand_dump_flag]: 2.03002e-06 [switch_simplify]: 1.474e-05 [loop_unroll]: 1.332e-05 [a_1]: 0.00031477 [with_stream_mark]: 2.244e-05 [recompute_prepare]: 1.386e-05 [updatestate_depend_eliminate]: 6.09999e-06 [updatestate_assign_eliminate]: 5.07999e-06 [updatestate_loads_eliminate]: 5.69e-06 [parameter_eliminate]: 1.74998e-06 [a_2]: 0.00014276 [accelerated_algorithm]: 5.416e-05 [shard]: 2.83e-06 [meta_shard_fg_expand]: 4.02e-06 [shard_inline]: 1.86e-05 [merge_send_recv]: 1.125e-05 [auto_parallel]: 1.183e-05 [parallel]: 1.129e-05 [flash_sp]: 4.20999e-06 [merge_comm]: 5.22e-06 [allreduce_fusion]: 5.01997e-06 [matmul_add_comm_reduction]: 1.408e-05 [allreduce_slice_to_reducescatter]: 6.80011e-07 [virtual_shard_identity]: 1.4e-05 [virtual_dataset]: 1.197e-05 [get_grad_eliminate_]: 1.169e-05 [virtual_output]: 1.208e-05 [merge_forward]: 6.71e-06 [cell_reuse_recompute_pass]: 2.68e-06 [offload_activation]: 1.278e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.491e-05 [merge_recompute_call_nodes]: 1.71e-06 [before_grad]: 1.67e-05 [set_forward_comm_id_for_comm_node_pass]: 5.64e-06 [meta_fg_expand]: 3.73999e-06 [flash_sp_send_recv_attached]: 1.05001e-06 [receive_attached]: 2.81e-06 [after_resolve]: 2.806e-05 [a_after_grad]: 1.902e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 2.91999e-06 [auto_monad_grad]: 1.72001e-06 [auto_monad_eliminator]: 1.161e-05 [cse]: 6.942e-05 [a_3]: 7.1e-05 [py_interpret_to_execute_after_opt_a]: 3.366e-05 [slice_cell_reuse_recomputed_activation]: 2.31e-06 [rewriter_after_opt_a]: 6.854e-05 [convert_after_rewriter]: 8.82999e-06 [order_py_execute_after_rewriter]: 7.15e-06 [mutable_eliminate]: 0.0009017 [opt_b]: 0.00046027, [1] [Cycle 1]: 0.00044968, [7] [b_1]: 0.0002748 [b_2]: 1.572e-05 [updatestate_depend_eliminate]: 1.076e-05 [updatestate_assign_eliminate]: 7e-06 [updatestate_loads_eliminate]: 5.00999e-06 [renormalize]: 8.39995e-07 [cse]: 7.05e-05 [optimize_parallel_all_gather_comm]: 2.391e-05 [overlap_param_gather]: 4.73001e-06 [cconv]: 4.158e-05 [loop_unroll]: 0.0006385 [opt_after_cconv]: 0.00021406, [1] [Cycle 1]: 0.00020103, [7] [c_1]: 6.624e-05 [parameter_eliminate]: 6.06e-06 [updatestate_depend_eliminate]: 8.75001e-06 [updatestate_assign_eliminate]: 4.24002e-06 [updatestate_loads_eliminate]: 4.23001e-06 [cse]: 5.678e-05 [renormalize]: 7.09988e-07 [remove_dup_value]: 7.996e-05 [tuple_transform]: 0.00017397, [1] [Cycle 1]: 0.000168, [4] [d_1]: 0.00011235 [none_parameter_eliminate]: 2.32001e-06 [renormalize]: 1.69995e-07 [switch_simplify]: 1.726e-05 [partial_unused_args_eliminate]: 2.41e-06 [add_recomputation]: 7.726e-05 [cse_after_recomputation]: 5.168e-05, [1] [Cycle 1]: 4.383e-05, [1] [cse]: 3.405e-05 [environ_conv]: 9.19e-06 [swap_dp_allreduce_reducescatter]: 7.25003e-06 [bias_add_comm_swap]: 3.16001e-06 [label_micro_interleaved_index]: 5.14003e-06 [label_fine_grained_interleaved_index]: 3.46001e-06 [merge_cast_opt]: 1.75001e-06 [slice_recompute_activation]: 2.27001e-06 [micro_interleaved_order_control]: 6.62002e-06 [assign_add_opt]: 1.29e-06 [ForceFp32Comm]: 8.70001e-07 [remove_cast_before_assign_add]: 1.04e-06 [full_micro_interleaved_order_control]: 2.64001e-06 [reorder_send_recv_between_fp_bp]: 2.91e-06 [comm_op_add_attrs]: 1.10001e-06 [add_comm_op_reuse_tag]: 1.17999e-06 [interleave_split_concat_branches]: 4e-06 [interleave_parallel_branches]: 1.15999e-06 [overlap_opt_shard_in_pipeline]: 3.26999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.73002e-06 [control_data_broadcast_order]: 2.004e-05 [grouped_pairwise_exchange_alltoall]: 1.92999e-06 [offloading_packed_experts]: 6.02001e-06 [overlap_recompute_and_grad_model_parallel]: 7.18e-06 [overlap_grad_matmul_and_grad_allreduce]: 3.76001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.57001e-06 [overlap_recompute_comm]: 2.51e-06 [overlap_grad_ring_attention]: 5.54e-06 [overlap_grad_flash_sp]: 2.421e-05 [begin_end_overlap_inline]: 8.59989e-07 [split_matmul_comm_elemetwise]: 2.41e-06 [split_layernorm_comm]: 1.99999e-06 [handle_group_info]: 1.74e-06 [symbol_engine_optimizer]: 0.00025522, [1] [Cycle 1]: 0.00024926, [6] [build]: 9.991e-05 [elim_shapecalc]: 2.664e-05 [elim_not_effective]: 2.49e-05 [opt_reshape]: 1.854e-05 [fold_const_symbol]: 2.334e-05 [renormalize]: 1.80007e-07 [detach_backward]: 2.63e-06 [pipeline_parallel_scheduler]: 1.86e-06 [auto_monad_reorder]: 3.637e-05 [get_jit_bprop_graph]: 2.31998e-06 [rewriter_after_jit_bprop_graph]: 1.011e-05 [opt_after_jit_grad]: 0.00077027 [validate]: 7.432e-05 Sums bootstrap : 0.000929s : 0.57% type_inference : 0.153674s : 94.38% event_method : 0.000015s : 0.01% auto_monad : 0.000060s : 0.04% graph_reusing : 0.000005s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000031s : 0.02% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000047s : 0.03% insert-virtual-dataset : 0.000002s : 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 : 0.000057s : 0.04% optimize.rewriter_before_opt_a : 0.000097s : 0.06% optimize.opt_a.expand_dump_flag : 0.000010s : 0.01% optimize.opt_a.switch_simplify : 0.000047s : 0.03% optimize.opt_a.loop_unroll : 0.000034s : 0.02% optimize.opt_a.a_1 : 0.000944s : 0.58% optimize.opt_a.with_stream_mark : 0.000052s : 0.03% optimize.opt_a.recompute_prepare : 0.000035s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000014s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000321s : 0.20% optimize.opt_a.accelerated_algorithm : 0.000073s : 0.05% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000008s : 0.00% optimize.opt_a.shard_inline : 0.000031s : 0.02% optimize.opt_a.merge_send_recv : 0.000023s : 0.01% optimize.opt_a.auto_parallel : 0.000021s : 0.01% optimize.opt_a.parallel : 0.000053s : 0.03% optimize.opt_a.flash_sp : 0.000016s : 0.01% optimize.opt_a.merge_comm : 0.000012s : 0.01% optimize.opt_a.allreduce_fusion : 0.000010s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000031s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000033s : 0.02% optimize.opt_a.virtual_dataset : 0.000031s : 0.02% optimize.opt_a.get_grad_eliminate_ : 0.000027s : 0.02% optimize.opt_a.virtual_output : 0.000029s : 0.02% optimize.opt_a.merge_forward : 0.000013s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.00% optimize.opt_a.offload_activation : 0.000028s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000053s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000041s : 0.03% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000011s : 0.01% optimize.opt_a.meta_fg_expand : 0.000008s : 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 : 0.000064s : 0.04% optimize.opt_a.a_after_grad : 0.000046s : 0.03% optimize.opt_a.renormalize : 0.001513s : 0.93% optimize.opt_a.add_forward_monad_depend : 0.000017s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000035s : 0.02% optimize.opt_a.cse : 0.000158s : 0.10% optimize.opt_a.a_3 : 0.000165s : 0.10% optimize.py_interpret_to_execute_after_opt_a : 0.000034s : 0.02% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000069s : 0.04% optimize.convert_after_rewriter : 0.000009s : 0.01% optimize.order_py_execute_after_rewriter : 0.000007s : 0.00% optimize.mutable_eliminate : 0.000902s : 0.55% optimize.opt_b.b_1 : 0.000275s : 0.17% optimize.opt_b.b_2 : 0.000016s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000007s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000071s : 0.04% optimize.optimize_parallel_all_gather_comm : 0.000024s : 0.01% optimize.overlap_param_gather : 0.000005s : 0.00% optimize.cconv : 0.000042s : 0.03% optimize.loop_unroll : 0.000639s : 0.39% optimize.opt_after_cconv.c_1 : 0.000066s : 0.04% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 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 : 0.000057s : 0.03% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000080s : 0.05% optimize.tuple_transform.d_1 : 0.000112s : 0.07% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000017s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000077s : 0.05% optimize.cse_after_recomputation.cse : 0.000034s : 0.02% optimize.environ_conv : 0.000009s : 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 : 0.000007s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000004s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000020s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000004s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000024s : 0.01% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000002s : 0.00% optimize.symbol_engine_optimizer.build : 0.000100s : 0.06% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000027s : 0.02% optimize.symbol_engine_optimizer.elim_not_effective : 0.000025s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000019s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000023s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000036s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000010s : 0.01% opt_after_jit_grad : 0.000770s : 0.47% validate : 0.000074s : 0.05% Time group info: ------[substitution.] 0.000196 39 2.98% : 0.000006s : 2: substitution.elim_not_effective 3.97% : 0.000008s : 2: substitution.fold_const_symbol 4.61% : 0.000009s : 10: substitution.graph_param_transform 77.41% : 0.000152s : 1: substitution.inline 2.55% : 0.000005s : 4: substitution.j_node_and_user_rematch 3.06% : 0.000006s : 4: substitution.remove_not_recompute_node 5.42% : 0.000011s : 16: substitution.replace_old_param ------[type_inference.] 0.153552 2 99.32% : 0.152502s : 1: type_inference.infer 0.68% : 0.001050s : 1: type_inference.specialize ------[replace.] 0.000029 1 100.00% : 0.000029s : 1: replace.inline ------[match.] 0.000150 1 100.00% : 0.000150s : 1: match.inline ------[predicate.] 0.000283 2335 0.85% : 0.000002s : 21: predicate.accumulaten_eliminater 1.04% : 0.000003s : 10: predicate.ad_related_special_op_eliminate 0.71% : 0.000002s : 20: predicate.addn_check_dump 0.83% : 0.000002s : 21: predicate.addn_zero_filter 0.75% : 0.000002s : 21: predicate.adjust_all_reduce_mul_add 2.11% : 0.000006s : 41: predicate.arithmetic_simplify 0.79% : 0.000002s : 21: predicate.cast_eliminate 0.81% : 0.000002s : 20: predicate.check_bprop_eliminate 0.70% : 0.000002s : 20: predicate.compare_switch_simplify 0.27% : 0.000001s : 10: predicate.const_output_eliminate 0.72% : 0.000002s : 20: predicate.depend_value_elim 0.86% : 0.000002s : 21: predicate.dict_get_item_const_eliminator 1.03% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.99% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.24% : 0.000003s : 20: predicate.dumpgradient_eliminate 0.37% : 0.000001s : 10: predicate.elim_not_effective 0.59% : 0.000002s : 10: predicate.elim_shapecalc_of_broadcastargs 1.35% : 0.000004s : 31: predicate.environ_add_const_eliminate 1.03% : 0.000003s : 31: predicate.environ_get_add_eliminate 1.03% : 0.000003s : 31: predicate.environ_get_depend_swap 1.89% : 0.000005s : 51: predicate.environ_get_eliminate 1.15% : 0.000003s : 31: predicate.environ_get_set_eliminate 0.80% : 0.000002s : 22: predicate.exchange_switch_depend_value 1.35% : 0.000004s : 22: predicate.float_depend_g_call 0.66% : 0.000002s : 20: predicate.float_environ_get_switch 0.99% : 0.000003s : 30: predicate.float_tuple_getitem_switch 0.27% : 0.000001s : 10: predicate.fold_const_symbol 1.06% : 0.000003s : 20: predicate.get_grad_eliminate 0.37% : 0.000001s : 10: predicate.graph_param_transform 0.68% : 0.000002s : 20: predicate.incorporate_call 0.61% : 0.000002s : 20: predicate.incorporate_call_switch 4.94% : 0.000014s : 103: predicate.inline 0.79% : 0.000002s : 20: predicate.inline_without_move 0.60% : 0.000002s : 20: predicate.j_node_and_user_rematch 1.12% : 0.000003s : 20: predicate.less_batch_normalization 1.48% : 0.000004s : 41: predicate.list_to_tuple_eliminator_ 2.16% : 0.000006s : 62: predicate.load_eliminater 1.12% : 0.000003s : 10: predicate.loop_unroll_after_grad 1.20% : 0.000003s : 31: predicate.loop_unroll_before_grad 1.93% : 0.000005s : 41: predicate.make_slice_get_slice_eliminator 0.81% : 0.000002s : 20: predicate.merge_addn 0.86% : 0.000002s : 20: predicate.micro_step_allgather_replace 0.83% : 0.000002s : 20: predicate.mini_step_allgather_replace 0.68% : 0.000002s : 21: predicate.minmaximum_grad 1.52% : 0.000004s : 10: predicate.mutable_eliminate 0.49% : 0.000001s : 10: predicate.opt_reshape 0.62% : 0.000002s : 10: predicate.parallel_virtual_node 0.98% : 0.000003s : 22: predicate.partial_defer_inline 1.23% : 0.000003s : 31: predicate.partial_eliminate 0.85% : 0.000002s : 21: predicate.print_const_string_wrapper 0.79% : 0.000002s : 20: predicate.reduce_all_const_elim 1.13% : 0.000003s : 21: predicate.reduce_eliminate 2.36% : 0.000007s : 62: predicate.redundant_stop_gradient_eliminater 0.79% : 0.000002s : 20: predicate.remove_not_recompute_node 1.36% : 0.000004s : 41: predicate.replace_applicator 0.69% : 0.000002s : 20: predicate.replace_old_param 0.34% : 0.000001s : 10: predicate.reset_defer_inline 1.00% : 0.000003s : 21: predicate.reshape_eliminate 0.84% : 0.000002s : 20: predicate.row_tensor_add_zeros_like 0.61% : 0.000002s : 10: predicate.row_tensor_eliminate 1.04% : 0.000003s : 20: predicate.same_eliminate 0.63% : 0.000002s : 20: predicate.set_cell_output_no_recompute 0.87% : 0.000002s : 20: predicate.shard_identity_eliminate 1.10% : 0.000003s : 20: predicate.special_op_eliminate 0.77% : 0.000002s : 20: predicate.specialize_transform 1.07% : 0.000003s : 20: predicate.split_environ_get_set_with_tuple_value 1.20% : 0.000003s : 20: predicate.stack_unstack_eliminate 0.52% : 0.000001s : 10: predicate.switch_call_monad_eliminater 0.86% : 0.000002s : 22: predicate.switch_defer_inline 1.60% : 0.000005s : 42: predicate.switch_layer_defer_inline 3.49% : 0.000010s : 83: predicate.switch_simplify 1.02% : 0.000003s : 21: predicate.tile_eliminate 1.03% : 0.000003s : 21: predicate.transpose_eliminate 1.87% : 0.000005s : 41: predicate.tuple_list_convert_item_index_to_positive 1.82% : 0.000005s : 41: predicate.tuple_list_get_item_const_eliminator 1.76% : 0.000005s : 41: predicate.tuple_list_get_item_depend_reorder 3.15% : 0.000009s : 61: predicate.tuple_list_get_item_eliminator 1.52% : 0.000004s : 41: predicate.tuple_list_get_set_item_eliminator 2.64% : 0.000007s : 61: predicate.tuple_list_set_item_eliminator 1.43% : 0.000004s : 41: predicate.tuple_to_list_eliminator_ 2.18% : 0.000006s : 62: predicate.updatestate_pure_node_eliminater 3.09% : 0.000009s : 82: predicate.updatestate_useless_node_eliminater 0.51% : 0.000001s : 10: predicate.value_based_eliminate 0.97% : 0.000003s : 20: predicate.virtual_dataset_eliminate 0.85% : 0.000002s : 20: predicate.virtual_output_eliminate 0.50% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.47% : 0.000001s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.001320 6 47.08% : 0.000622s : 3: func_graph_cloner_run.FuncGraphClonerGraph 52.92% : 0.000699s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.191360 192 0.00% : 0.000004s : 1: ForceFp32Comm 3.75% : 0.007179s : 1: add_attr 3.74% : 0.007159s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.04% : 0.000082s : 1: add_recomputation 0.00% : 0.000007s : 1: assign_add_opt 0.03% : 0.000065s : 1: auto_monad 0.02% : 0.000041s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000009s : 1: bias_add_comm_swap 0.51% : 0.000975s : 1: bootstrap 0.02% : 0.000047s : 1: cconv 0.00% : 0.000007s : 1: comm_op_add_attrs 0.01% : 0.000024s : 1: control_data_broadcast_order 0.01% : 0.000013s : 1: convert_after_rewriter 0.03% : 0.000055s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000016s : 1: environ_conv 0.01% : 0.000022s : 1: event_method 0.00% : 0.000009s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000008s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000007s : 1: handle_group_info 0.00% : 0.000005s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000007s : 1: interleave_split_concat_branches 0.00% : 0.000009s : 1: label_fine_grained_interleaved_index 0.00% : 0.000009s : 1: label_micro_interleaved_index 0.34% : 0.000654s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.01% : 0.000010s : 1: micro_interleaved_order_control 0.48% : 0.000917s : 1: mutable_eliminate 0.01% : 0.000013s : 1: offloading_packed_experts 0.01% : 0.000025s : 1: opt.transform.loop_unroll_optimizer 0.02% : 0.000029s : 1: opt.transform.mutable_eliminate 0.96% : 0.001831s : 78: opt.transform.opt_a 0.03% : 0.000065s : 1: opt.transform.opt_after_cconv 0.03% : 0.000067s : 1: opt.transform.opt_after_jit_grad 0.13% : 0.000250s : 28: opt.transform.opt_b 0.07% : 0.000127s : 2: opt.transform.opt_trans_graph 0.05% : 0.000088s : 4: opt.transform.symbol_engine_opt 2.62% : 0.005009s : 1: opt_a 0.11% : 0.000218s : 1: opt_after_cconv 0.41% : 0.000786s : 1: opt_after_jit_grad 0.24% : 0.000468s : 1: opt_b 4.55% : 0.008700s : 1: optimize 0.02% : 0.000031s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000015s : 1: order_py_execute_after_rewriter 0.01% : 0.000028s : 1: overlap_grad_flash_sp 0.00% : 0.000007s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000014s : 1: overlap_grad_ring_attention 0.01% : 0.000014s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000009s : 1: overlap_opt_shard_in_pipeline 0.01% : 0.000011s : 1: overlap_param_gather 0.00% : 0.000007s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000009s : 1: partial_unused_args_eliminate 0.00% : 0.000009s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.03% : 0.000051s : 1: pre_auto_parallel 0.03% : 0.000062s : 1: py_interpret_to_execute 0.02% : 0.000038s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.04% : 0.000085s : 1: remove_dup_value 0.34% : 0.000654s : 1: renormalize.infer 0.44% : 0.000846s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000014s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000074s : 1: rewriter_after_opt_a 0.05% : 0.000103s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000008s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.01% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.14% : 0.000259s : 1: symbol_engine_optimizer 0.09% : 0.000177s : 1: tuple_transform 80.32% : 0.153698s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_bnsd[QuantMethod.INT_CUBE-0] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_bnsd[QuantMethod.INT_CUBE-0],max_mem:484.0M [WARNING] ME(168185:281473465110320,MainProcess):2026-01-29-17:38:46.649.756 [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 = 0.207152, [21] [bootstrap]: 0.00084391 [type_inference]: 0.108186 [event_method]: 1.948e-05 [auto_monad]: 6.253e-05 [graph_reusing]: 5.32001e-06 [inline]: 3.44001e-06 [add_attr]: 0.00594313, [1] [add_attr_with_inline]: 0.00592424, [1] [Cycle 1]: 8.438e-05, [2] [tag_attr]: 2.866e-05 [meta_addattr_fg_expand]: 6.61e-06 [parallel-infer-symbol]: 4.03001e-06 [pre_auto_parallel]: 4.277e-05 [insert-virtual-dataset]: 2.36998e-06 [parallel-infer-symbol-second]: 7.10017e-07 [dataset_repeat_opt]: 2.07999e-06 [pipeline_split]: 1.66e-06 [optimize]: 0.0909929, [53] [py_interpret_to_execute]: 5.421e-05 [rewriter_before_opt_a]: 9.397e-05 [opt_a]: 0.0872582, [2] [Cycle 1]: 0.0857618, [45] [expand_dump_flag]: 4.00998e-06 [switch_simplify]: 3.745e-05 [loop_unroll]: 2.083e-05 [a_1]: 0.00109863 [with_stream_mark]: 3.802e-05 [recompute_prepare]: 3.661e-05 [updatestate_depend_eliminate]: 7.41999e-06 [updatestate_assign_eliminate]: 6.20002e-06 [updatestate_loads_eliminate]: 5.44e-06 [parameter_eliminate]: 2.98e-06 [a_2]: 0.00023994 [accelerated_algorithm]: 2.457e-05 [shard]: 3.28e-06 [meta_shard_fg_expand]: 8.23999e-06 [shard_inline]: 2.075e-05 [merge_send_recv]: 1.714e-05 [auto_parallel]: 1.395e-05 [parallel]: 3.574e-05 [flash_sp]: 1.539e-05 [merge_comm]: 7.24001e-06 [allreduce_fusion]: 5.85002e-06 [matmul_add_comm_reduction]: 1.422e-05 [allreduce_slice_to_reducescatter]: 1.30999e-06 [virtual_shard_identity]: 3.152e-05 [virtual_dataset]: 2.129e-05 [get_grad_eliminate_]: 2.704e-05 [virtual_output]: 1.915e-05 [merge_forward]: 1.027e-05 [cell_reuse_recompute_pass]: 2.18002e-06 [offload_activation]: 2.259e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.428e-05 [merge_recompute_call_nodes]: 2.27999e-06 [before_grad]: 4.069e-05 [set_forward_comm_id_for_comm_node_pass]: 8.27003e-06 [meta_fg_expand]: 3.833e-05 [flash_sp_send_recv_attached]: 4.57e-06 [receive_attached]: 3.14001e-06 [after_resolve]: 6.195e-05 [a_after_grad]: 3.991e-05 [renormalize]: 0.0828858 [add_forward_monad_depend]: 1.516e-05 [auto_monad_grad]: 2.88998e-06 [auto_monad_eliminator]: 2.951e-05 [cse]: 0.00010269 [a_3]: 0.00011412 [Cycle 2]: 0.00147849, [45] [expand_dump_flag]: 2.83e-06 [switch_simplify]: 1.58e-05 [loop_unroll]: 1.318e-05 [a_1]: 0.00032566 [with_stream_mark]: 2.471e-05 [recompute_prepare]: 1.352e-05 [updatestate_depend_eliminate]: 6.18002e-06 [updatestate_assign_eliminate]: 5.44e-06 [updatestate_loads_eliminate]: 5.49e-06 [parameter_eliminate]: 2.16e-06 [a_2]: 0.00021195 [accelerated_algorithm]: 1.403e-05 [shard]: 3.28998e-06 [meta_shard_fg_expand]: 3.61999e-06 [shard_inline]: 1.261e-05 [merge_send_recv]: 1.197e-05 [auto_parallel]: 1.285e-05 [parallel]: 1.17e-05 [flash_sp]: 4.80999e-06 [merge_comm]: 5.05001e-06 [allreduce_fusion]: 5.02e-06 [matmul_add_comm_reduction]: 1.259e-05 [allreduce_slice_to_reducescatter]: 1.42999e-06 [virtual_shard_identity]: 1.553e-05 [virtual_dataset]: 1.31e-05 [get_grad_eliminate_]: 1.235e-05 [virtual_output]: 1.197e-05 [merge_forward]: 6.70002e-06 [cell_reuse_recompute_pass]: 3.35998e-06 [offload_activation]: 2.065e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.619e-05 [merge_recompute_call_nodes]: 1.53002e-06 [before_grad]: 2.253e-05 [set_forward_comm_id_for_comm_node_pass]: 8.94e-06 [meta_fg_expand]: 4.67998e-06 [flash_sp_send_recv_attached]: 1.70001e-06 [receive_attached]: 2.89001e-06 [after_resolve]: 2.904e-05 [a_after_grad]: 2.037e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 2.78e-06 [auto_monad_grad]: 1.92999e-06 [auto_monad_eliminator]: 1.212e-05 [cse]: 7.395e-05 [a_3]: 7.261e-05 [py_interpret_to_execute_after_opt_a]: 2.891e-05 [slice_cell_reuse_recomputed_activation]: 1.85001e-06 [rewriter_after_opt_a]: 6.242e-05 [convert_after_rewriter]: 9.02e-06 [order_py_execute_after_rewriter]: 7.03e-06 [mutable_eliminate]: 0.00087096 [opt_b]: 0.00045461, [1] [Cycle 1]: 0.00044501, [7] [b_1]: 0.00024855 [b_2]: 1.4e-05 [updatestate_depend_eliminate]: 1.114e-05 [updatestate_assign_eliminate]: 4.72e-06 [updatestate_loads_eliminate]: 4.52e-06 [renormalize]: 8.30012e-07 [cse]: 9.833e-05 [optimize_parallel_all_gather_comm]: 2.409e-05 [overlap_param_gather]: 2.17999e-06 [cconv]: 3.574e-05 [loop_unroll]: 0.00058715 [opt_after_cconv]: 0.0002111, [1] [Cycle 1]: 0.0002035, [7] [c_1]: 6.598e-05 [parameter_eliminate]: 5.61e-06 [updatestate_depend_eliminate]: 9.10001e-06 [updatestate_assign_eliminate]: 4.61002e-06 [updatestate_loads_eliminate]: 4.59002e-06 [cse]: 6.095e-05 [renormalize]: 6.80011e-07 [remove_dup_value]: 8.055e-05 [tuple_transform]: 0.00016767, [1] [Cycle 1]: 0.00016047, [4] [d_1]: 0.00010995 [none_parameter_eliminate]: 2.22001e-06 [renormalize]: 1.40019e-07 [switch_simplify]: 1.362e-05 [partial_unused_args_eliminate]: 1.69e-06 [add_recomputation]: 9.375e-05 [cse_after_recomputation]: 6.789e-05, [1] [Cycle 1]: 5.864e-05, [1] [cse]: 4.068e-05 [environ_conv]: 9.14e-06 [swap_dp_allreduce_reducescatter]: 1.358e-05 [bias_add_comm_swap]: 2.54999e-06 [label_micro_interleaved_index]: 5.97999e-06 [label_fine_grained_interleaved_index]: 3.13e-06 [merge_cast_opt]: 1.55999e-06 [slice_recompute_activation]: 2.31e-06 [micro_interleaved_order_control]: 2.68e-06 [assign_add_opt]: 1.33002e-06 [ForceFp32Comm]: 8.40024e-07 [remove_cast_before_assign_add]: 1.65001e-06 [full_micro_interleaved_order_control]: 2.36e-06 [reorder_send_recv_between_fp_bp]: 3.46999e-06 [comm_op_add_attrs]: 1.38002e-06 [add_comm_op_reuse_tag]: 1.03001e-06 [interleave_split_concat_branches]: 1.52999e-06 [interleave_parallel_branches]: 1.57999e-06 [overlap_opt_shard_in_pipeline]: 1.38002e-06 [overlap_opt_shard_grad_in_pipeline]: 2.06e-06 [control_data_broadcast_order]: 2.139e-05 [grouped_pairwise_exchange_alltoall]: 1.60999e-06 [offloading_packed_experts]: 5.09998e-06 [overlap_recompute_and_grad_model_parallel]: 9.59e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.55999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.72001e-06 [overlap_recompute_comm]: 2.71999e-06 [overlap_grad_ring_attention]: 5.97999e-06 [overlap_grad_flash_sp]: 2.316e-05 [begin_end_overlap_inline]: 5.39992e-07 [split_matmul_comm_elemetwise]: 2.19999e-06 [split_layernorm_comm]: 2.04e-06 [handle_group_info]: 1.08001e-06 [symbol_engine_optimizer]: 0.00030858, [1] [Cycle 1]: 0.00030149, [6] [build]: 0.00010972 [elim_shapecalc]: 3.805e-05 [elim_not_effective]: 2.646e-05 [opt_reshape]: 2.144e-05 [fold_const_symbol]: 3.21e-05 [renormalize]: 2.50002e-07 [detach_backward]: 3.3e-06 [pipeline_parallel_scheduler]: 1.76e-06 [auto_monad_reorder]: 3.804e-05 [get_jit_bprop_graph]: 2.07999e-06 [rewriter_after_jit_bprop_graph]: 9.14e-06 [opt_after_jit_grad]: 0.0007133 [validate]: 6.435e-05 Sums bootstrap : 0.000844s : 0.42% type_inference : 0.108186s : 54.27% event_method : 0.000019s : 0.01% auto_monad : 0.000063s : 0.03% graph_reusing : 0.000005s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000029s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000007s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000043s : 0.02% insert-virtual-dataset : 0.000002s : 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 : 0.000054s : 0.03% optimize.rewriter_before_opt_a : 0.000094s : 0.05% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000053s : 0.03% optimize.opt_a.loop_unroll : 0.000034s : 0.02% optimize.opt_a.a_1 : 0.001424s : 0.71% optimize.opt_a.with_stream_mark : 0.000063s : 0.03% optimize.opt_a.recompute_prepare : 0.000050s : 0.03% optimize.opt_a.updatestate_depend_eliminate : 0.000014s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.01% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000452s : 0.23% optimize.opt_a.accelerated_algorithm : 0.000039s : 0.02% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000012s : 0.01% optimize.opt_a.shard_inline : 0.000033s : 0.02% optimize.opt_a.merge_send_recv : 0.000029s : 0.01% optimize.opt_a.auto_parallel : 0.000027s : 0.01% optimize.opt_a.parallel : 0.000047s : 0.02% optimize.opt_a.flash_sp : 0.000020s : 0.01% optimize.opt_a.merge_comm : 0.000012s : 0.01% optimize.opt_a.allreduce_fusion : 0.000011s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000027s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000047s : 0.02% optimize.opt_a.virtual_dataset : 0.000034s : 0.02% optimize.opt_a.get_grad_eliminate_ : 0.000039s : 0.02% optimize.opt_a.virtual_output : 0.000031s : 0.02% optimize.opt_a.merge_forward : 0.000017s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000043s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000070s : 0.04% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000063s : 0.03% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000017s : 0.01% optimize.opt_a.meta_fg_expand : 0.000043s : 0.02% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000091s : 0.05% optimize.opt_a.a_after_grad : 0.000060s : 0.03% optimize.opt_a.renormalize : 0.082886s : 41.58% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000042s : 0.02% optimize.opt_a.cse : 0.000177s : 0.09% optimize.opt_a.a_3 : 0.000187s : 0.09% optimize.py_interpret_to_execute_after_opt_a : 0.000029s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000062s : 0.03% optimize.convert_after_rewriter : 0.000009s : 0.00% optimize.order_py_execute_after_rewriter : 0.000007s : 0.00% optimize.mutable_eliminate : 0.000871s : 0.44% optimize.opt_b.b_1 : 0.000249s : 0.12% optimize.opt_b.b_2 : 0.000014s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000098s : 0.05% optimize.optimize_parallel_all_gather_comm : 0.000024s : 0.01% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000036s : 0.02% optimize.loop_unroll : 0.000587s : 0.29% optimize.opt_after_cconv.c_1 : 0.000066s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000061s : 0.03% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000081s : 0.04% optimize.tuple_transform.d_1 : 0.000110s : 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 : 0.000014s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000094s : 0.05% optimize.cse_after_recomputation.cse : 0.000041s : 0.02% optimize.environ_conv : 0.000009s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000014s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000002s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000002s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000021s : 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 : 0.000010s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000023s : 0.01% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000110s : 0.06% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000038s : 0.02% optimize.symbol_engine_optimizer.elim_not_effective : 0.000026s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000021s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000032s : 0.02% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000038s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000009s : 0.00% opt_after_jit_grad : 0.000713s : 0.36% validate : 0.000064s : 0.03% Time group info: ------[substitution.] 0.000223 39 1.75% : 0.000004s : 2: substitution.elim_not_effective 3.89% : 0.000009s : 2: substitution.fold_const_symbol 3.95% : 0.000009s : 10: substitution.graph_param_transform 79.14% : 0.000176s : 1: substitution.inline 2.32% : 0.000005s : 4: substitution.j_node_and_user_rematch 3.01% : 0.000007s : 4: substitution.remove_not_recompute_node 5.94% : 0.000013s : 16: substitution.replace_old_param ------[type_inference.] 0.108037 2 98.20% : 0.106089s : 1: type_inference.infer 1.80% : 0.001949s : 1: type_inference.specialize ------[replace.] 0.000033 1 100.00% : 0.000033s : 1: replace.inline ------[match.] 0.000173 1 100.00% : 0.000173s : 1: match.inline ------[predicate.] 0.000308 2335 0.79% : 0.000002s : 21: predicate.accumulaten_eliminater 0.78% : 0.000002s : 10: predicate.ad_related_special_op_eliminate 0.75% : 0.000002s : 20: predicate.addn_check_dump 0.91% : 0.000003s : 21: predicate.addn_zero_filter 0.85% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 2.09% : 0.000006s : 41: predicate.arithmetic_simplify 1.02% : 0.000003s : 21: predicate.cast_eliminate 0.75% : 0.000002s : 20: predicate.check_bprop_eliminate 0.68% : 0.000002s : 20: predicate.compare_switch_simplify 0.23% : 0.000001s : 10: predicate.const_output_eliminate 0.78% : 0.000002s : 20: predicate.depend_value_elim 0.85% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 1.05% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.83% : 0.000003s : 21: predicate.dict_set_item_eliminator 0.93% : 0.000003s : 20: predicate.dumpgradient_eliminate 0.27% : 0.000001s : 10: predicate.elim_not_effective 0.51% : 0.000002s : 10: predicate.elim_shapecalc_of_broadcastargs 1.22% : 0.000004s : 31: predicate.environ_add_const_eliminate 1.21% : 0.000004s : 31: predicate.environ_get_add_eliminate 1.22% : 0.000004s : 31: predicate.environ_get_depend_swap 2.23% : 0.000007s : 51: predicate.environ_get_eliminate 1.09% : 0.000003s : 31: predicate.environ_get_set_eliminate 0.81% : 0.000002s : 22: predicate.exchange_switch_depend_value 1.41% : 0.000004s : 22: predicate.float_depend_g_call 0.73% : 0.000002s : 20: predicate.float_environ_get_switch 1.12% : 0.000003s : 30: predicate.float_tuple_getitem_switch 0.26% : 0.000001s : 10: predicate.fold_const_symbol 1.16% : 0.000004s : 20: predicate.get_grad_eliminate 0.31% : 0.000001s : 10: predicate.graph_param_transform 0.80% : 0.000002s : 20: predicate.incorporate_call 0.61% : 0.000002s : 20: predicate.incorporate_call_switch 5.11% : 0.000016s : 103: predicate.inline 0.93% : 0.000003s : 20: predicate.inline_without_move 0.48% : 0.000001s : 20: predicate.j_node_and_user_rematch 1.12% : 0.000003s : 20: predicate.less_batch_normalization 1.92% : 0.000006s : 41: predicate.list_to_tuple_eliminator_ 2.09% : 0.000006s : 62: predicate.load_eliminater 0.87% : 0.000003s : 10: predicate.loop_unroll_after_grad 1.36% : 0.000004s : 31: predicate.loop_unroll_before_grad 2.00% : 0.000006s : 41: predicate.make_slice_get_slice_eliminator 0.81% : 0.000002s : 20: predicate.merge_addn 0.75% : 0.000002s : 20: predicate.micro_step_allgather_replace 0.87% : 0.000003s : 20: predicate.mini_step_allgather_replace 0.73% : 0.000002s : 21: predicate.minmaximum_grad 1.05% : 0.000003s : 10: predicate.mutable_eliminate 0.53% : 0.000002s : 10: predicate.opt_reshape 0.55% : 0.000002s : 10: predicate.parallel_virtual_node 1.25% : 0.000004s : 22: predicate.partial_defer_inline 1.26% : 0.000004s : 31: predicate.partial_eliminate 0.89% : 0.000003s : 21: predicate.print_const_string_wrapper 0.81% : 0.000002s : 20: predicate.reduce_all_const_elim 1.20% : 0.000004s : 21: predicate.reduce_eliminate 2.13% : 0.000007s : 62: predicate.redundant_stop_gradient_eliminater 0.72% : 0.000002s : 20: predicate.remove_not_recompute_node 1.52% : 0.000005s : 41: predicate.replace_applicator 0.68% : 0.000002s : 20: predicate.replace_old_param 0.36% : 0.000001s : 10: predicate.reset_defer_inline 0.92% : 0.000003s : 21: predicate.reshape_eliminate 0.73% : 0.000002s : 20: predicate.row_tensor_add_zeros_like 0.41% : 0.000001s : 10: predicate.row_tensor_eliminate 1.07% : 0.000003s : 20: predicate.same_eliminate 0.65% : 0.000002s : 20: predicate.set_cell_output_no_recompute 1.00% : 0.000003s : 20: predicate.shard_identity_eliminate 0.81% : 0.000003s : 20: predicate.special_op_eliminate 0.72% : 0.000002s : 20: predicate.specialize_transform 1.18% : 0.000004s : 20: predicate.split_environ_get_set_with_tuple_value 1.11% : 0.000003s : 20: predicate.stack_unstack_eliminate 0.45% : 0.000001s : 10: predicate.switch_call_monad_eliminater 0.88% : 0.000003s : 22: predicate.switch_defer_inline 1.55% : 0.000005s : 42: predicate.switch_layer_defer_inline 4.00% : 0.000012s : 83: predicate.switch_simplify 0.88% : 0.000003s : 21: predicate.tile_eliminate 0.70% : 0.000002s : 21: predicate.transpose_eliminate 1.96% : 0.000006s : 41: predicate.tuple_list_convert_item_index_to_positive 1.74% : 0.000005s : 41: predicate.tuple_list_get_item_const_eliminator 1.70% : 0.000005s : 41: predicate.tuple_list_get_item_depend_reorder 3.00% : 0.000009s : 61: predicate.tuple_list_get_item_eliminator 1.53% : 0.000005s : 41: predicate.tuple_list_get_set_item_eliminator 2.78% : 0.000009s : 61: predicate.tuple_list_set_item_eliminator 1.71% : 0.000005s : 41: predicate.tuple_to_list_eliminator_ 2.17% : 0.000007s : 62: predicate.updatestate_pure_node_eliminater 2.97% : 0.000009s : 82: predicate.updatestate_useless_node_eliminater 0.45% : 0.000001s : 10: predicate.value_based_eliminate 0.89% : 0.000003s : 20: predicate.virtual_dataset_eliminate 0.99% : 0.000003s : 20: predicate.virtual_output_eliminate 0.35% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.46% : 0.000001s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.002478 6 31.53% : 0.000781s : 3: func_graph_cloner_run.FuncGraphClonerGraph 68.47% : 0.001697s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.389912 192 0.00% : 0.000011s : 1: ForceFp32Comm 1.53% : 0.005951s : 1: add_attr 1.52% : 0.005929s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.03% : 0.000099s : 1: add_recomputation 0.00% : 0.000017s : 1: assign_add_opt 0.02% : 0.000068s : 1: auto_monad 0.01% : 0.000043s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000012s : 1: bias_add_comm_swap 0.23% : 0.000883s : 1: bootstrap 0.01% : 0.000041s : 1: cconv 0.00% : 0.000009s : 1: comm_op_add_attrs 0.01% : 0.000026s : 1: control_data_broadcast_order 0.00% : 0.000014s : 1: convert_after_rewriter 0.02% : 0.000075s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000014s : 1: environ_conv 0.01% : 0.000027s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000009s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000011s : 1: interleave_split_concat_branches 0.00% : 0.000018s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.15% : 0.000602s : 1: loop_unroll 0.00% : 0.000013s : 1: merge_cast_opt 0.00% : 0.000010s : 1: micro_interleaved_order_control 0.23% : 0.000888s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.01% : 0.000023s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000028s : 1: opt.transform.mutable_eliminate 0.64% : 0.002494s : 78: opt.transform.opt_a 0.02% : 0.000064s : 1: opt.transform.opt_after_cconv 0.02% : 0.000066s : 1: opt.transform.opt_after_jit_grad 0.06% : 0.000227s : 28: opt.transform.opt_b 0.03% : 0.000121s : 2: opt.transform.opt_trans_graph 0.03% : 0.000113s : 4: opt.transform.symbol_engine_opt 22.38% : 0.087264s : 1: opt_a 0.06% : 0.000216s : 1: opt_after_cconv 0.19% : 0.000726s : 1: opt_after_jit_grad 0.12% : 0.000465s : 1: opt_b 23.34% : 0.091002s : 1: optimize 0.01% : 0.000029s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.01% : 0.000028s : 1: overlap_grad_flash_sp 0.00% : 0.000008s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000016s : 1: overlap_grad_ring_attention 0.01% : 0.000029s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000006s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000014s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000013s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000049s : 1: pre_auto_parallel 0.02% : 0.000061s : 1: py_interpret_to_execute 0.01% : 0.000034s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000012s : 1: remove_cast_before_assign_add 0.02% : 0.000088s : 1: remove_dup_value 20.95% : 0.081685s : 1: renormalize.infer 0.30% : 0.001174s : 1: renormalize.specialize 0.00% : 0.000011s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000012s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000068s : 1: rewriter_after_opt_a 0.03% : 0.000101s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000011s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000009s : 1: split_matmul_comm_elemetwise 0.01% : 0.000020s : 1: swap_dp_allreduce_reducescatter 0.08% : 0.000317s : 1: symbol_engine_optimizer 0.04% : 0.000171s : 1: tuple_transform 27.76% : 0.108220s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_bnsd[QuantMethod.INT_CUBE-1] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_bnsd[QuantMethod.INT_CUBE-1],max_mem:484.0M =============================== 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 ================== 4 passed, 25 warnings in 116.34s (0:01:56) ==================