==================================================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_005/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(168548:281473185062704,MainProcess):2026-01-29-17:37:45.759.513 [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 = 0.30847, [21] [bootstrap]: 0.0007856 [type_inference]: 0.0790439 [event_method]: 1.5e-05 [auto_monad]: 8.739e-05 [graph_reusing]: 5.51e-06 [inline]: 2.85002e-06 [add_attr]: 0.00860761, [1] [add_attr_with_inline]: 0.00859204, [1] [Cycle 1]: 0.00010116, [2] [tag_attr]: 2.324e-05 [meta_addattr_fg_expand]: 4.23999e-06 [parallel-infer-symbol]: 3.61999e-06 [pre_auto_parallel]: 4.332e-05 [insert-virtual-dataset]: 2.51e-06 [parallel-infer-symbol-second]: 9.20001e-07 [dataset_repeat_opt]: 2.44999e-06 [pipeline_split]: 1.84e-06 [optimize]: 0.218647, [53] [py_interpret_to_execute]: 3.06e-05 [rewriter_before_opt_a]: 8.125e-05 [opt_a]: 0.00342997, [2] [Cycle 1]: 0.00239321, [45] [expand_dump_flag]: 3.08e-06 [switch_simplify]: 3.395e-05 [loop_unroll]: 1.846e-05 [a_1]: 0.00048198 [with_stream_mark]: 2.389e-05 [recompute_prepare]: 1.333e-05 [updatestate_depend_eliminate]: 5.19003e-06 [updatestate_assign_eliminate]: 4.92e-06 [updatestate_loads_eliminate]: 4.73001e-06 [parameter_eliminate]: 1.89e-06 [a_2]: 0.00014942 [accelerated_algorithm]: 1.151e-05 [shard]: 2.69999e-06 [meta_shard_fg_expand]: 1.87001e-06 [shard_inline]: 1.147e-05 [merge_send_recv]: 9.89999e-06 [auto_parallel]: 7.88001e-06 [parallel]: 6.161e-05 [flash_sp]: 1.247e-05 [merge_comm]: 5.77999e-06 [allreduce_fusion]: 4.68001e-06 [matmul_add_comm_reduction]: 1.245e-05 [allreduce_slice_to_reducescatter]: 6.69999e-07 [virtual_shard_identity]: 1.453e-05 [virtual_dataset]: 1.113e-05 [get_grad_eliminate_]: 1.047e-05 [virtual_output]: 1.091e-05 [merge_forward]: 6.06998e-06 [cell_reuse_recompute_pass]: 1.40999e-06 [offload_activation]: 1.231e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.842e-05 [merge_recompute_call_nodes]: 2.44999e-06 [before_grad]: 1.625e-05 [set_forward_comm_id_for_comm_node_pass]: 5.62999e-06 [meta_fg_expand]: 3.52002e-06 [flash_sp_send_recv_attached]: 3.14001e-06 [receive_attached]: 1.192e-05 [after_resolve]: 2.484e-05 [a_after_grad]: 1.657e-05 [renormalize]: 0.00087402 [add_forward_monad_depend]: 7.16001e-06 [auto_monad_grad]: 2.89999e-06 [auto_monad_eliminator]: 2.046e-05 [cse]: 8.269e-05 [a_3]: 8.756e-05 [Cycle 2]: 0.0010228, [45] [expand_dump_flag]: 2.32999e-06 [switch_simplify]: 1.355e-05 [loop_unroll]: 1.013e-05 [a_1]: 0.00028005 [with_stream_mark]: 2.034e-05 [recompute_prepare]: 1.21e-05 [updatestate_depend_eliminate]: 5.14e-06 [updatestate_assign_eliminate]: 4.48001e-06 [updatestate_loads_eliminate]: 4.38999e-06 [parameter_eliminate]: 1.91e-06 [a_2]: 0.00013366 [accelerated_algorithm]: 1.099e-05 [shard]: 1.91998e-06 [meta_shard_fg_expand]: 2.31998e-06 [shard_inline]: 1.06e-05 [merge_send_recv]: 8.39998e-06 [auto_parallel]: 1.007e-05 [parallel]: 7.88999e-06 [flash_sp]: 3.98999e-06 [merge_comm]: 5.46e-06 [allreduce_fusion]: 4.63999e-06 [matmul_add_comm_reduction]: 1.104e-05 [allreduce_slice_to_reducescatter]: 8.59989e-07 [virtual_shard_identity]: 1.193e-05 [virtual_dataset]: 1.034e-05 [get_grad_eliminate_]: 1.035e-05 [virtual_output]: 9.84001e-06 [merge_forward]: 4.89998e-06 [cell_reuse_recompute_pass]: 2.04999e-06 [offload_activation]: 1.124e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.852e-05 [merge_recompute_call_nodes]: 1.30999e-06 [before_grad]: 1.398e-05 [set_forward_comm_id_for_comm_node_pass]: 4.98001e-06 [meta_fg_expand]: 3.13e-06 [flash_sp_send_recv_attached]: 1.38002e-06 [receive_attached]: 2.02999e-06 [after_resolve]: 2.282e-05 [a_after_grad]: 1.599e-05 [renormalize]: 7.99773e-08 [add_forward_monad_depend]: 1.97999e-06 [auto_monad_grad]: 1.02998e-06 [auto_monad_eliminator]: 9.81e-06 [cse]: 3.308e-05 [a_3]: 6.766e-05 [py_interpret_to_execute_after_opt_a]: 1.824e-05 [slice_cell_reuse_recomputed_activation]: 2.09e-06 [rewriter_after_opt_a]: 8.663e-05 [convert_after_rewriter]: 1.181e-05 [order_py_execute_after_rewriter]: 7.26001e-06 [mutable_eliminate]: 0.00071575 [opt_b]: 0.00034566, [1] [Cycle 1]: 0.00033719, [7] [b_1]: 0.00022851 [b_2]: 1.292e-05 [updatestate_depend_eliminate]: 9.77001e-06 [updatestate_assign_eliminate]: 4.18001e-06 [updatestate_loads_eliminate]: 4.04002e-06 [renormalize]: 3.89991e-07 [cse]: 4.212e-05 [optimize_parallel_all_gather_comm]: 2.173e-05 [overlap_param_gather]: 3.85e-06 [cconv]: 3.416e-05 [loop_unroll]: 0.00045699 [opt_after_cconv]: 0.00015572, [1] [Cycle 1]: 0.00014834, [7] [c_1]: 5.629e-05 [parameter_eliminate]: 4.16001e-06 [updatestate_depend_eliminate]: 8.17e-06 [updatestate_assign_eliminate]: 4.02e-06 [updatestate_loads_eliminate]: 3.75998e-06 [cse]: 3.693e-05 [renormalize]: 4.30009e-07 [remove_dup_value]: 5.858e-05 [tuple_transform]: 0.00011954, [1] [Cycle 1]: 0.00011389, [4] [d_1]: 8.076e-05 [none_parameter_eliminate]: 2.14999e-06 [renormalize]: 2.40019e-07 [switch_simplify]: 1.226e-05 [partial_unused_args_eliminate]: 1.93002e-06 [add_recomputation]: 6.625e-05 [cse_after_recomputation]: 3.371e-05, [1] [Cycle 1]: 2.884e-05, [1] [cse]: 2.274e-05 [environ_conv]: 1.92e-05 [swap_dp_allreduce_reducescatter]: 7.6e-06 [bias_add_comm_swap]: 3.14999e-06 [label_micro_interleaved_index]: 5.68002e-06 [label_fine_grained_interleaved_index]: 3.11999e-06 [merge_cast_opt]: 1.20001e-06 [slice_recompute_activation]: 2.37999e-06 [micro_interleaved_order_control]: 2.37999e-06 [assign_add_opt]: 1.96e-06 [ForceFp32Comm]: 1.02e-06 [remove_cast_before_assign_add]: 1.34e-06 [full_micro_interleaved_order_control]: 2.25002e-06 [reorder_send_recv_between_fp_bp]: 3.43e-06 [comm_op_add_attrs]: 1.12e-06 [add_comm_op_reuse_tag]: 1.40001e-06 [interleave_split_concat_branches]: 1.36002e-06 [interleave_parallel_branches]: 1.05001e-06 [overlap_opt_shard_in_pipeline]: 2.413e-05 [overlap_opt_shard_grad_in_pipeline]: 1.74e-06 [control_data_broadcast_order]: 1.878e-05 [grouped_pairwise_exchange_alltoall]: 1.65001e-06 [offloading_packed_experts]: 4.99e-06 [overlap_recompute_and_grad_model_parallel]: 5.67999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.18001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.904e-05 [overlap_recompute_comm]: 5.23002e-06 [overlap_grad_ring_attention]: 3.66e-05 [overlap_grad_flash_sp]: 5.975e-05 [begin_end_overlap_inline]: 9.50007e-07 [split_matmul_comm_elemetwise]: 2.37001e-06 [split_layernorm_comm]: 2.14e-06 [handle_group_info]: 1.09e-06 [symbol_engine_optimizer]: 0.00033957, [1] [Cycle 1]: 0.00032606, [6] [build]: 0.00013556 [elim_shapecalc]: 5.092e-05 [elim_not_effective]: 4.572e-05 [opt_reshape]: 1.684e-05 [fold_const_symbol]: 2.482e-05 [renormalize]: 8.09989e-07 [detach_backward]: 3.33e-06 [pipeline_parallel_scheduler]: 1.57001e-06 [auto_monad_reorder]: 4.465e-05 [get_jit_bprop_graph]: 2.34999e-06 [rewriter_after_jit_bprop_graph]: 7.58001e-06 [opt_after_jit_grad]: 0.0008827 [validate]: 8.515e-05 Sums bootstrap : 0.000786s : 0.91% type_inference : 0.079044s : 91.22% event_method : 0.000015s : 0.02% auto_monad : 0.000087s : 0.10% graph_reusing : 0.000006s : 0.01% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000023s : 0.03% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000043s : 0.05% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000031s : 0.04% optimize.rewriter_before_opt_a : 0.000081s : 0.09% optimize.opt_a.expand_dump_flag : 0.000005s : 0.01% optimize.opt_a.switch_simplify : 0.000047s : 0.05% optimize.opt_a.loop_unroll : 0.000029s : 0.03% optimize.opt_a.a_1 : 0.000762s : 0.88% optimize.opt_a.with_stream_mark : 0.000044s : 0.05% optimize.opt_a.recompute_prepare : 0.000025s : 0.03% optimize.opt_a.updatestate_depend_eliminate : 0.000010s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000009s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000009s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000283s : 0.33% optimize.opt_a.accelerated_algorithm : 0.000022s : 0.03% optimize.opt_a.shard : 0.000005s : 0.01% optimize.opt_a.meta_shard_fg_expand : 0.000004s : 0.00% optimize.opt_a.shard_inline : 0.000022s : 0.03% optimize.opt_a.merge_send_recv : 0.000018s : 0.02% optimize.opt_a.auto_parallel : 0.000018s : 0.02% optimize.opt_a.parallel : 0.000070s : 0.08% optimize.opt_a.flash_sp : 0.000016s : 0.02% optimize.opt_a.merge_comm : 0.000011s : 0.01% optimize.opt_a.allreduce_fusion : 0.000009s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000023s : 0.03% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000026s : 0.03% optimize.opt_a.virtual_dataset : 0.000021s : 0.02% optimize.opt_a.get_grad_eliminate_ : 0.000021s : 0.02% optimize.opt_a.virtual_output : 0.000021s : 0.02% 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 : 0.000024s : 0.03% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000037s : 0.04% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000030s : 0.03% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000011s : 0.01% optimize.opt_a.meta_fg_expand : 0.000007s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.01% optimize.opt_a.receive_attached : 0.000014s : 0.02% optimize.opt_a.after_resolve : 0.000048s : 0.06% optimize.opt_a.a_after_grad : 0.000033s : 0.04% optimize.opt_a.renormalize : 0.000874s : 1.01% optimize.opt_a.add_forward_monad_depend : 0.000009s : 0.01% optimize.opt_a.auto_monad_grad : 0.000004s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000030s : 0.03% optimize.opt_a.cse : 0.000116s : 0.13% optimize.opt_a.a_3 : 0.000155s : 0.18% optimize.py_interpret_to_execute_after_opt_a : 0.000018s : 0.02% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000087s : 0.10% optimize.convert_after_rewriter : 0.000012s : 0.01% optimize.order_py_execute_after_rewriter : 0.000007s : 0.01% optimize.mutable_eliminate : 0.000716s : 0.83% optimize.opt_b.b_1 : 0.000229s : 0.26% 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 : 0.000000s : 0.00% optimize.opt_b.cse : 0.000042s : 0.05% optimize.optimize_parallel_all_gather_comm : 0.000022s : 0.03% optimize.overlap_param_gather : 0.000004s : 0.00% optimize.cconv : 0.000034s : 0.04% optimize.loop_unroll : 0.000457s : 0.53% optimize.opt_after_cconv.c_1 : 0.000056s : 0.06% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000008s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.cse : 0.000037s : 0.04% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000059s : 0.07% optimize.tuple_transform.d_1 : 0.000081s : 0.09% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000012s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000066s : 0.08% optimize.cse_after_recomputation.cse : 0.000023s : 0.03% optimize.environ_conv : 0.000019s : 0.02% 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 : 0.000002s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000024s : 0.03% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000019s : 0.02% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000005s : 0.01% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 0.01% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000019s : 0.02% optimize.overlap_recompute_comm : 0.000005s : 0.01% optimize.overlap_grad_ring_attention : 0.000037s : 0.04% optimize.overlap_grad_flash_sp : 0.000060s : 0.07% 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 : 0.000136s : 0.16% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000051s : 0.06% optimize.symbol_engine_optimizer.elim_not_effective : 0.000046s : 0.05% 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 : 0.000001s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000045s : 0.05% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.01% opt_after_jit_grad : 0.000883s : 1.02% validate : 0.000085s : 0.10% Time group info: ------[substitution.] 0.000176 39 9.90% : 0.000017s : 2: substitution.elim_not_effective 5.51% : 0.000010s : 2: substitution.fold_const_symbol 5.11% : 0.000009s : 10: substitution.graph_param_transform 67.65% : 0.000119s : 1: substitution.inline 2.49% : 0.000004s : 4: substitution.j_node_and_user_rematch 3.08% : 0.000005s : 4: substitution.remove_not_recompute_node 6.25% : 0.000011s : 16: substitution.replace_old_param ------[type_inference.] 0.078946 2 99.31% : 0.078403s : 1: type_inference.infer 0.69% : 0.000543s : 1: type_inference.specialize ------[replace.] 0.000020 1 100.00% : 0.000020s : 1: replace.inline ------[match.] 0.000118 1 100.00% : 0.000118s : 1: match.inline ------[predicate.] 0.000254 2335 0.77% : 0.000002s : 21: predicate.accumulaten_eliminater 1.33% : 0.000003s : 10: predicate.ad_related_special_op_eliminate 0.70% : 0.000002s : 20: predicate.addn_check_dump 0.76% : 0.000002s : 21: predicate.addn_zero_filter 0.71% : 0.000002s : 21: predicate.adjust_all_reduce_mul_add 1.86% : 0.000005s : 41: predicate.arithmetic_simplify 0.76% : 0.000002s : 21: predicate.cast_eliminate 0.76% : 0.000002s : 20: predicate.check_bprop_eliminate 0.69% : 0.000002s : 20: predicate.compare_switch_simplify 0.32% : 0.000001s : 10: predicate.const_output_eliminate 0.79% : 0.000002s : 20: predicate.depend_value_elim 0.86% : 0.000002s : 21: predicate.dict_get_item_const_eliminator 0.88% : 0.000002s : 21: predicate.dict_get_item_eliminator 0.75% : 0.000002s : 21: predicate.dict_set_item_eliminator 3.14% : 0.000008s : 20: predicate.dumpgradient_eliminate 0.58% : 0.000001s : 10: predicate.elim_not_effective 1.01% : 0.000003s : 10: predicate.elim_shapecalc_of_broadcastargs 1.12% : 0.000003s : 31: predicate.environ_add_const_eliminate 1.09% : 0.000003s : 31: predicate.environ_get_add_eliminate 1.05% : 0.000003s : 31: predicate.environ_get_depend_swap 1.87% : 0.000005s : 51: predicate.environ_get_eliminate 1.08% : 0.000003s : 31: predicate.environ_get_set_eliminate 0.79% : 0.000002s : 22: predicate.exchange_switch_depend_value 1.59% : 0.000004s : 22: predicate.float_depend_g_call 0.70% : 0.000002s : 20: predicate.float_environ_get_switch 1.03% : 0.000003s : 30: predicate.float_tuple_getitem_switch 0.30% : 0.000001s : 10: predicate.fold_const_symbol 1.00% : 0.000003s : 20: predicate.get_grad_eliminate 0.43% : 0.000001s : 10: predicate.graph_param_transform 0.73% : 0.000002s : 20: predicate.incorporate_call 0.67% : 0.000002s : 20: predicate.incorporate_call_switch 5.26% : 0.000013s : 103: predicate.inline 0.99% : 0.000003s : 20: predicate.inline_without_move 0.58% : 0.000001s : 20: predicate.j_node_and_user_rematch 1.09% : 0.000003s : 20: predicate.less_batch_normalization 1.55% : 0.000004s : 41: predicate.list_to_tuple_eliminator_ 2.18% : 0.000006s : 62: predicate.load_eliminater 0.87% : 0.000002s : 10: predicate.loop_unroll_after_grad 1.24% : 0.000003s : 31: predicate.loop_unroll_before_grad 1.67% : 0.000004s : 41: predicate.make_slice_get_slice_eliminator 0.74% : 0.000002s : 20: predicate.merge_addn 0.73% : 0.000002s : 20: predicate.micro_step_allgather_replace 0.75% : 0.000002s : 20: predicate.mini_step_allgather_replace 0.69% : 0.000002s : 21: predicate.minmaximum_grad 1.36% : 0.000003s : 10: predicate.mutable_eliminate 0.78% : 0.000002s : 10: predicate.opt_reshape 0.54% : 0.000001s : 10: predicate.parallel_virtual_node 1.01% : 0.000003s : 22: predicate.partial_defer_inline 1.27% : 0.000003s : 31: predicate.partial_eliminate 0.75% : 0.000002s : 21: predicate.print_const_string_wrapper 0.82% : 0.000002s : 20: predicate.reduce_all_const_elim 1.02% : 0.000003s : 21: predicate.reduce_eliminate 2.20% : 0.000006s : 62: predicate.redundant_stop_gradient_eliminater 0.85% : 0.000002s : 20: predicate.remove_not_recompute_node 1.41% : 0.000004s : 41: predicate.replace_applicator 0.82% : 0.000002s : 20: predicate.replace_old_param 0.48% : 0.000001s : 10: predicate.reset_defer_inline 0.84% : 0.000002s : 21: predicate.reshape_eliminate 0.79% : 0.000002s : 20: predicate.row_tensor_add_zeros_like 0.50% : 0.000001s : 10: predicate.row_tensor_eliminate 1.10% : 0.000003s : 20: predicate.same_eliminate 0.68% : 0.000002s : 20: predicate.set_cell_output_no_recompute 1.09% : 0.000003s : 20: predicate.shard_identity_eliminate 0.89% : 0.000002s : 20: predicate.special_op_eliminate 0.80% : 0.000002s : 20: predicate.specialize_transform 1.10% : 0.000003s : 20: predicate.split_environ_get_set_with_tuple_value 0.98% : 0.000002s : 20: predicate.stack_unstack_eliminate 0.42% : 0.000001s : 10: predicate.switch_call_monad_eliminater 0.83% : 0.000002s : 22: predicate.switch_defer_inline 1.57% : 0.000004s : 42: predicate.switch_layer_defer_inline 3.74% : 0.000010s : 83: predicate.switch_simplify 0.80% : 0.000002s : 21: predicate.tile_eliminate 0.74% : 0.000002s : 21: predicate.transpose_eliminate 1.49% : 0.000004s : 41: predicate.tuple_list_convert_item_index_to_positive 1.52% : 0.000004s : 41: predicate.tuple_list_get_item_const_eliminator 1.57% : 0.000004s : 41: predicate.tuple_list_get_item_depend_reorder 2.94% : 0.000007s : 61: predicate.tuple_list_get_item_eliminator 1.47% : 0.000004s : 41: predicate.tuple_list_get_set_item_eliminator 2.36% : 0.000006s : 61: predicate.tuple_list_set_item_eliminator 1.71% : 0.000004s : 41: predicate.tuple_to_list_eliminator_ 2.12% : 0.000005s : 62: predicate.updatestate_pure_node_eliminater 3.08% : 0.000008s : 82: predicate.updatestate_useless_node_eliminater 0.41% : 0.000001s : 10: predicate.value_based_eliminate 0.89% : 0.000002s : 20: predicate.virtual_dataset_eliminate 0.86% : 0.000002s : 20: predicate.virtual_output_eliminate 0.45% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.47% : 0.000001s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000536 6 51.63% : 0.000277s : 3: func_graph_cloner_run.FuncGraphClonerGraph 48.37% : 0.000259s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.326401 192 0.00% : 0.000004s : 1: ForceFp32Comm 2.64% : 0.008614s : 1: add_attr 2.63% : 0.008597s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000071s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.03% : 0.000093s : 1: auto_monad 0.02% : 0.000050s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.25% : 0.000829s : 1: bootstrap 0.01% : 0.000038s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000023s : 1: control_data_broadcast_order 0.00% : 0.000015s : 1: convert_after_rewriter 0.01% : 0.000037s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.01% : 0.000023s : 1: environ_conv 0.01% : 0.000021s : 1: event_method 0.00% : 0.000005s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000009s : 1: graph_reusing 0.00% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000006s : 1: label_fine_grained_interleaved_index 0.00% : 0.000008s : 1: label_micro_interleaved_index 0.14% : 0.000468s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.22% : 0.000727s : 1: mutable_eliminate 0.00% : 0.000008s : 1: offloading_packed_experts 0.01% : 0.000020s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000025s : 1: opt.transform.mutable_eliminate 0.46% : 0.001490s : 78: opt.transform.opt_a 0.02% : 0.000055s : 1: opt.transform.opt_after_cconv 0.02% : 0.000051s : 1: opt.transform.opt_after_jit_grad 0.07% : 0.000213s : 28: opt.transform.opt_b 0.03% : 0.000091s : 2: opt.transform.opt_trans_graph 0.04% : 0.000128s : 4: opt.transform.symbol_engine_opt 1.05% : 0.003433s : 1: opt_a 0.05% : 0.000160s : 1: opt_after_cconv 0.28% : 0.000900s : 1: opt_after_jit_grad 0.11% : 0.000350s : 1: opt_b 66.99% : 0.218654s : 1: optimize 0.01% : 0.000025s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000010s : 1: order_py_execute_after_rewriter 0.02% : 0.000064s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000042s : 1: overlap_grad_ring_attention 0.00% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.01% : 0.000028s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.02% : 0.000080s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000009s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000010s : 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% : 0.000007s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000047s : 1: pre_auto_parallel 0.01% : 0.000035s : 1: py_interpret_to_execute 0.01% : 0.000021s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000063s : 1: remove_dup_value 0.14% : 0.000446s : 1: renormalize.infer 0.13% : 0.000416s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.000094s : 1: rewriter_after_opt_a 0.03% : 0.000086s : 1: rewriter_before_opt_a 0.00% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.11% : 0.000343s : 1: symbol_engine_optimizer 0.04% : 0.000122s : 1: tuple_transform 24.22% : 0.079067s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_jiutian[QuantMethod.FP16_VEC-0] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_jiutian[QuantMethod.FP16_VEC-0],max_mem:728.0M [WARNING] ME(168548:281473185062704,MainProcess):2026-01-29-17:40:23.204.035 [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 = 0.200122, [21] [bootstrap]: 0.00147866 [type_inference]: 0.0833799 [event_method]: 2.069e-05 [auto_monad]: 7.731e-05 [graph_reusing]: 5.80002e-06 [inline]: 3.55e-06 [add_attr]: 0.103153, [1] [add_attr_with_inline]: 0.103133, [1] [Cycle 1]: 8.623e-05, [2] [tag_attr]: 2.75e-05 [meta_addattr_fg_expand]: 4.08001e-06 [parallel-infer-symbol]: 3.75e-06 [pre_auto_parallel]: 8.238e-05 [insert-virtual-dataset]: 3.06999e-06 [parallel-infer-symbol-second]: 7.30011e-07 [dataset_repeat_opt]: 2.09999e-06 [pipeline_split]: 1.99e-06 [optimize]: 0.0106754, [53] [py_interpret_to_execute]: 0.00010379 [rewriter_before_opt_a]: 0.00013707 [opt_a]: 0.0057339, [2] [Cycle 1]: 0.00390973, [45] [expand_dump_flag]: 3.09999e-06 [switch_simplify]: 3.711e-05 [loop_unroll]: 1.944e-05 [a_1]: 0.00052629 [with_stream_mark]: 2.555e-05 [recompute_prepare]: 1.578e-05 [updatestate_depend_eliminate]: 6.07001e-06 [updatestate_assign_eliminate]: 5.74e-06 [updatestate_loads_eliminate]: 5.31002e-06 [parameter_eliminate]: 2.02001e-06 [a_2]: 0.00014908 [accelerated_algorithm]: 1.228e-05 [shard]: 2.64999e-06 [meta_shard_fg_expand]: 3.26001e-06 [shard_inline]: 1.123e-05 [merge_send_recv]: 1.128e-05 [auto_parallel]: 8.60999e-06 [parallel]: 3.49e-05 [flash_sp]: 1.15e-05 [merge_comm]: 5.41002e-06 [allreduce_fusion]: 5.15001e-06 [matmul_add_comm_reduction]: 1.292e-05 [allreduce_slice_to_reducescatter]: 1.01002e-06 [virtual_shard_identity]: 1.624e-05 [virtual_dataset]: 1.748e-05 [get_grad_eliminate_]: 1.628e-05 [virtual_output]: 1.297e-05 [merge_forward]: 6.56e-06 [cell_reuse_recompute_pass]: 1.82001e-06 [offload_activation]: 1.415e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.538e-05 [merge_recompute_call_nodes]: 1.45999e-06 [before_grad]: 2.045e-05 [set_forward_comm_id_for_comm_node_pass]: 5.95002e-06 [meta_fg_expand]: 4.02e-06 [flash_sp_send_recv_attached]: 2.49001e-06 [receive_attached]: 3.66999e-06 [after_resolve]: 2.943e-05 [a_after_grad]: 2.541e-05 [renormalize]: 0.00217298 [add_forward_monad_depend]: 1.007e-05 [auto_monad_grad]: 2.86999e-06 [auto_monad_eliminator]: 2.492e-05 [cse]: 5.986e-05 [a_3]: 9.2e-05 [Cycle 2]: 0.00180831, [45] [expand_dump_flag]: 2.56e-06 [switch_simplify]: 1.488e-05 [loop_unroll]: 1.134e-05 [a_1]: 0.00029639 [with_stream_mark]: 2.165e-05 [recompute_prepare]: 1.398e-05 [updatestate_depend_eliminate]: 6.10002e-06 [updatestate_assign_eliminate]: 5.17999e-06 [updatestate_loads_eliminate]: 5.84e-06 [parameter_eliminate]: 2.73e-06 [a_2]: 0.00014126 [accelerated_algorithm]: 1.216e-05 [shard]: 3.53e-06 [meta_shard_fg_expand]: 3.3e-06 [shard_inline]: 1.341e-05 [merge_send_recv]: 1.314e-05 [auto_parallel]: 1.199e-05 [parallel]: 1.117e-05 [flash_sp]: 4.80999e-06 [merge_comm]: 2.696e-05 [allreduce_fusion]: 4.75999e-06 [matmul_add_comm_reduction]: 1.377e-05 [allreduce_slice_to_reducescatter]: 8.79983e-07 [virtual_shard_identity]: 1.342e-05 [virtual_dataset]: 1.114e-05 [get_grad_eliminate_]: 1.134e-05 [virtual_output]: 1.191e-05 [merge_forward]: 6.34999e-06 [cell_reuse_recompute_pass]: 3.28e-06 [offload_activation]: 3.611e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.507e-05 [merge_recompute_call_nodes]: 2.07999e-06 [before_grad]: 1.678e-05 [set_forward_comm_id_for_comm_node_pass]: 6.71e-06 [meta_fg_expand]: 4.06001e-06 [flash_sp_send_recv_attached]: 1.99e-06 [receive_attached]: 2.85002e-06 [after_resolve]: 5.663e-05 [a_after_grad]: 1.858e-05 [renormalize]: 7.00238e-08 [add_forward_monad_depend]: 3.31999e-06 [auto_monad_grad]: 2.53e-06 [auto_monad_eliminator]: 1.614e-05 [cse]: 6.564e-05 [a_3]: 7.423e-05 [py_interpret_to_execute_after_opt_a]: 4.828e-05 [slice_cell_reuse_recomputed_activation]: 2.37999e-06 [rewriter_after_opt_a]: 0.00012435 [convert_after_rewriter]: 3.225e-05 [order_py_execute_after_rewriter]: 7.66999e-06 [mutable_eliminate]: 0.00113512 [opt_b]: 0.0005937, [1] [Cycle 1]: 0.00058205, [7] [b_1]: 0.00025822 [b_2]: 1.488e-05 [updatestate_depend_eliminate]: 1.344e-05 [updatestate_assign_eliminate]: 5.29e-06 [updatestate_loads_eliminate]: 5.17999e-06 [renormalize]: 5.90022e-07 [cse]: 0.00011968 [optimize_parallel_all_gather_comm]: 3.074e-05 [overlap_param_gather]: 3.41001e-06 [cconv]: 4.506e-05 [loop_unroll]: 0.00089548 [opt_after_cconv]: 0.00022975, [1] [Cycle 1]: 0.00022034, [7] [c_1]: 6.125e-05 [parameter_eliminate]: 6.71999e-06 [updatestate_depend_eliminate]: 1.012e-05 [updatestate_assign_eliminate]: 4.52e-06 [updatestate_loads_eliminate]: 4.38001e-06 [cse]: 8.237e-05 [renormalize]: 7.00005e-07 [remove_dup_value]: 7.343e-05 [tuple_transform]: 0.00014707, [1] [Cycle 1]: 0.00014118, [4] [d_1]: 9.962e-05 [none_parameter_eliminate]: 2.87002e-06 [renormalize]: 2.00002e-07 [switch_simplify]: 1.271e-05 [partial_unused_args_eliminate]: 2.45002e-06 [add_recomputation]: 0.00011367 [cse_after_recomputation]: 7.497e-05, [1] [Cycle 1]: 6.768e-05, [1] [cse]: 5.499e-05 [environ_conv]: 8.89e-06 [swap_dp_allreduce_reducescatter]: 1.13e-05 [bias_add_comm_swap]: 3.43e-06 [label_micro_interleaved_index]: 7.35e-06 [label_fine_grained_interleaved_index]: 3.14999e-06 [merge_cast_opt]: 1.49e-06 [slice_recompute_activation]: 2.32999e-06 [micro_interleaved_order_control]: 2.36e-06 [assign_add_opt]: 1.37e-06 [ForceFp32Comm]: 8.39995e-07 [remove_cast_before_assign_add]: 1.04e-06 [full_micro_interleaved_order_control]: 2.46e-06 [reorder_send_recv_between_fp_bp]: 3.38999e-06 [comm_op_add_attrs]: 1.23002e-06 [add_comm_op_reuse_tag]: 1.17999e-06 [interleave_split_concat_branches]: 1.37e-06 [interleave_parallel_branches]: 1.73002e-06 [overlap_opt_shard_in_pipeline]: 2.94001e-06 [overlap_opt_shard_grad_in_pipeline]: 2.04e-06 [control_data_broadcast_order]: 2.503e-05 [grouped_pairwise_exchange_alltoall]: 1.65001e-06 [offloading_packed_experts]: 5.75001e-06 [overlap_recompute_and_grad_model_parallel]: 6.93e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.29e-06 [overlap_recompute_allgather_and_fa_grad]: 4.79e-06 [overlap_recompute_comm]: 2.41998e-06 [overlap_grad_ring_attention]: 5.96e-06 [overlap_grad_flash_sp]: 5.271e-05 [begin_end_overlap_inline]: 5.40022e-07 [split_matmul_comm_elemetwise]: 3.05998e-06 [split_layernorm_comm]: 2.14999e-06 [handle_group_info]: 1.02e-06 [symbol_engine_optimizer]: 0.00041201, [1] [Cycle 1]: 0.00040548, [6] [build]: 0.00017599 [elim_shapecalc]: 3.04e-05 [elim_not_effective]: 5.787e-05 [opt_reshape]: 1.487e-05 [fold_const_symbol]: 2.524e-05 [renormalize]: 3.00002e-07 [detach_backward]: 3.23e-06 [pipeline_parallel_scheduler]: 1.64e-06 [auto_monad_reorder]: 3.987e-05 [get_jit_bprop_graph]: 2.78003e-06 [rewriter_after_jit_bprop_graph]: 7.53999e-06 [opt_after_jit_grad]: 0.00087506 [validate]: 6.894e-05 Sums bootstrap : 0.001479s : 1.56% type_inference : 0.083380s : 88.14% event_method : 0.000021s : 0.02% auto_monad : 0.000077s : 0.08% graph_reusing : 0.000006s : 0.01% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000028s : 0.03% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000082s : 0.09% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000104s : 0.11% optimize.rewriter_before_opt_a : 0.000137s : 0.14% optimize.opt_a.expand_dump_flag : 0.000006s : 0.01% optimize.opt_a.switch_simplify : 0.000052s : 0.05% optimize.opt_a.loop_unroll : 0.000031s : 0.03% optimize.opt_a.a_1 : 0.000823s : 0.87% optimize.opt_a.with_stream_mark : 0.000047s : 0.05% optimize.opt_a.recompute_prepare : 0.000030s : 0.03% optimize.opt_a.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000011s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.01% optimize.opt_a.parameter_eliminate : 0.000005s : 0.01% optimize.opt_a.a_2 : 0.000290s : 0.31% optimize.opt_a.accelerated_algorithm : 0.000024s : 0.03% optimize.opt_a.shard : 0.000006s : 0.01% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.01% optimize.opt_a.shard_inline : 0.000025s : 0.03% optimize.opt_a.merge_send_recv : 0.000024s : 0.03% optimize.opt_a.auto_parallel : 0.000021s : 0.02% optimize.opt_a.parallel : 0.000046s : 0.05% optimize.opt_a.flash_sp : 0.000016s : 0.02% optimize.opt_a.merge_comm : 0.000032s : 0.03% optimize.opt_a.allreduce_fusion : 0.000010s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000027s : 0.03% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000030s : 0.03% optimize.opt_a.virtual_dataset : 0.000029s : 0.03% optimize.opt_a.get_grad_eliminate_ : 0.000028s : 0.03% optimize.opt_a.virtual_output : 0.000025s : 0.03% optimize.opt_a.merge_forward : 0.000013s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.01% optimize.opt_a.offload_activation : 0.000050s : 0.05% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000050s : 0.05% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000037s : 0.04% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000013s : 0.01% optimize.opt_a.meta_fg_expand : 0.000008s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.00% optimize.opt_a.receive_attached : 0.000007s : 0.01% optimize.opt_a.after_resolve : 0.000086s : 0.09% optimize.opt_a.a_after_grad : 0.000044s : 0.05% optimize.opt_a.renormalize : 0.002173s : 2.30% optimize.opt_a.add_forward_monad_depend : 0.000013s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.01% optimize.opt_a.auto_monad_eliminator : 0.000041s : 0.04% optimize.opt_a.cse : 0.000125s : 0.13% optimize.opt_a.a_3 : 0.000166s : 0.18% optimize.py_interpret_to_execute_after_opt_a : 0.000048s : 0.05% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000124s : 0.13% optimize.convert_after_rewriter : 0.000032s : 0.03% optimize.order_py_execute_after_rewriter : 0.000008s : 0.01% optimize.mutable_eliminate : 0.001135s : 1.20% optimize.opt_b.b_1 : 0.000258s : 0.27% optimize.opt_b.b_2 : 0.000015s : 0.02% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000120s : 0.13% optimize.optimize_parallel_all_gather_comm : 0.000031s : 0.03% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000045s : 0.05% optimize.loop_unroll : 0.000895s : 0.95% optimize.opt_after_cconv.c_1 : 0.000061s : 0.06% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 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 : 0.000082s : 0.09% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000073s : 0.08% optimize.tuple_transform.d_1 : 0.000100s : 0.11% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 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 : 0.000114s : 0.12% optimize.cse_after_recomputation.cse : 0.000055s : 0.06% optimize.environ_conv : 0.000009s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000011s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 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 : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000002s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000025s : 0.03% 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 : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000005s : 0.01% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.01% optimize.overlap_grad_flash_sp : 0.000053s : 0.06% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000176s : 0.19% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000030s : 0.03% optimize.symbol_engine_optimizer.elim_not_effective : 0.000058s : 0.06% optimize.symbol_engine_optimizer.opt_reshape : 0.000015s : 0.02% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000025s : 0.03% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000040s : 0.04% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000008s : 0.01% opt_after_jit_grad : 0.000875s : 0.93% validate : 0.000069s : 0.07% Time group info: ------[substitution.] 0.000214 39 14.35% : 0.000031s : 2: substitution.elim_not_effective 4.56% : 0.000010s : 2: substitution.fold_const_symbol 4.24% : 0.000009s : 10: substitution.graph_param_transform 66.15% : 0.000142s : 1: substitution.inline 2.48% : 0.000005s : 4: substitution.j_node_and_user_rematch 2.28% : 0.000005s : 4: substitution.remove_not_recompute_node 5.92% : 0.000013s : 16: substitution.replace_old_param ------[type_inference.] 0.083213 2 96.81% : 0.080558s : 1: type_inference.infer 3.19% : 0.002655s : 1: type_inference.specialize ------[replace.] 0.000022 1 100.00% : 0.000022s : 1: replace.inline ------[match.] 0.000141 1 100.00% : 0.000141s : 1: match.inline ------[predicate.] 0.000276 2335 0.91% : 0.000003s : 21: predicate.accumulaten_eliminater 1.10% : 0.000003s : 10: predicate.ad_related_special_op_eliminate 0.69% : 0.000002s : 20: predicate.addn_check_dump 0.74% : 0.000002s : 21: predicate.addn_zero_filter 0.69% : 0.000002s : 21: predicate.adjust_all_reduce_mul_add 2.17% : 0.000006s : 41: predicate.arithmetic_simplify 0.81% : 0.000002s : 21: predicate.cast_eliminate 0.75% : 0.000002s : 20: predicate.check_bprop_eliminate 0.68% : 0.000002s : 20: predicate.compare_switch_simplify 0.32% : 0.000001s : 10: predicate.const_output_eliminate 0.81% : 0.000002s : 20: predicate.depend_value_elim 0.83% : 0.000002s : 21: predicate.dict_get_item_const_eliminator 1.05% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.93% : 0.000003s : 21: predicate.dict_set_item_eliminator 2.07% : 0.000006s : 20: predicate.dumpgradient_eliminate 0.38% : 0.000001s : 10: predicate.elim_not_effective 0.59% : 0.000002s : 10: predicate.elim_shapecalc_of_broadcastargs 1.20% : 0.000003s : 31: predicate.environ_add_const_eliminate 1.13% : 0.000003s : 31: predicate.environ_get_add_eliminate 1.02% : 0.000003s : 31: predicate.environ_get_depend_swap 1.97% : 0.000005s : 51: predicate.environ_get_eliminate 1.05% : 0.000003s : 31: predicate.environ_get_set_eliminate 0.71% : 0.000002s : 22: predicate.exchange_switch_depend_value 1.51% : 0.000004s : 22: predicate.float_depend_g_call 0.69% : 0.000002s : 20: predicate.float_environ_get_switch 1.03% : 0.000003s : 30: predicate.float_tuple_getitem_switch 0.31% : 0.000001s : 10: predicate.fold_const_symbol 0.96% : 0.000003s : 20: predicate.get_grad_eliminate 0.32% : 0.000001s : 10: predicate.graph_param_transform 0.67% : 0.000002s : 20: predicate.incorporate_call 0.63% : 0.000002s : 20: predicate.incorporate_call_switch 5.53% : 0.000015s : 103: predicate.inline 0.91% : 0.000003s : 20: predicate.inline_without_move 0.52% : 0.000001s : 20: predicate.j_node_and_user_rematch 1.01% : 0.000003s : 20: predicate.less_batch_normalization 1.64% : 0.000005s : 41: predicate.list_to_tuple_eliminator_ 2.20% : 0.000006s : 62: predicate.load_eliminater 1.48% : 0.000004s : 10: predicate.loop_unroll_after_grad 1.19% : 0.000003s : 31: predicate.loop_unroll_before_grad 1.85% : 0.000005s : 41: predicate.make_slice_get_slice_eliminator 0.72% : 0.000002s : 20: predicate.merge_addn 0.67% : 0.000002s : 20: predicate.micro_step_allgather_replace 0.67% : 0.000002s : 20: predicate.mini_step_allgather_replace 0.64% : 0.000002s : 21: predicate.minmaximum_grad 1.52% : 0.000004s : 10: predicate.mutable_eliminate 0.57% : 0.000002s : 10: predicate.opt_reshape 0.48% : 0.000001s : 10: predicate.parallel_virtual_node 0.95% : 0.000003s : 22: predicate.partial_defer_inline 1.15% : 0.000003s : 31: predicate.partial_eliminate 0.82% : 0.000002s : 21: predicate.print_const_string_wrapper 0.71% : 0.000002s : 20: predicate.reduce_all_const_elim 1.12% : 0.000003s : 21: predicate.reduce_eliminate 2.26% : 0.000006s : 62: predicate.redundant_stop_gradient_eliminater 0.78% : 0.000002s : 20: predicate.remove_not_recompute_node 1.42% : 0.000004s : 41: predicate.replace_applicator 0.83% : 0.000002s : 20: predicate.replace_old_param 0.52% : 0.000001s : 10: predicate.reset_defer_inline 0.87% : 0.000002s : 21: predicate.reshape_eliminate 0.83% : 0.000002s : 20: predicate.row_tensor_add_zeros_like 0.59% : 0.000002s : 10: predicate.row_tensor_eliminate 1.03% : 0.000003s : 20: predicate.same_eliminate 0.85% : 0.000002s : 20: predicate.set_cell_output_no_recompute 0.99% : 0.000003s : 20: predicate.shard_identity_eliminate 0.85% : 0.000002s : 20: predicate.special_op_eliminate 0.86% : 0.000002s : 20: predicate.specialize_transform 1.16% : 0.000003s : 20: predicate.split_environ_get_set_with_tuple_value 1.08% : 0.000003s : 20: predicate.stack_unstack_eliminate 0.46% : 0.000001s : 10: predicate.switch_call_monad_eliminater 0.83% : 0.000002s : 22: predicate.switch_defer_inline 1.57% : 0.000004s : 42: predicate.switch_layer_defer_inline 3.44% : 0.000009s : 83: predicate.switch_simplify 0.79% : 0.000002s : 21: predicate.tile_eliminate 0.83% : 0.000002s : 21: predicate.transpose_eliminate 1.56% : 0.000004s : 41: predicate.tuple_list_convert_item_index_to_positive 1.62% : 0.000004s : 41: predicate.tuple_list_get_item_const_eliminator 1.38% : 0.000004s : 41: predicate.tuple_list_get_item_depend_reorder 2.89% : 0.000008s : 61: predicate.tuple_list_get_item_eliminator 1.50% : 0.000004s : 41: predicate.tuple_list_get_set_item_eliminator 2.80% : 0.000008s : 61: predicate.tuple_list_set_item_eliminator 1.57% : 0.000004s : 41: predicate.tuple_to_list_eliminator_ 1.99% : 0.000005s : 62: predicate.updatestate_pure_node_eliminater 2.93% : 0.000008s : 82: predicate.updatestate_useless_node_eliminater 0.54% : 0.000001s : 10: predicate.value_based_eliminate 0.98% : 0.000003s : 20: predicate.virtual_dataset_eliminate 1.23% : 0.000003s : 20: predicate.virtual_output_eliminate 0.49% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.57% : 0.000002s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.002871 6 38.98% : 0.001119s : 3: func_graph_cloner_run.FuncGraphClonerGraph 61.02% : 0.001752s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.318238 192 0.00% : 0.000004s : 1: ForceFp32Comm 32.42% : 0.103160s : 1: add_attr 32.41% : 0.103138s : 1: add_attr_with_inline 0.00% : 0.000007s : 1: add_comm_op_reuse_tag 0.04% : 0.000120s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.03% : 0.000084s : 1: auto_monad 0.01% : 0.000045s : 1: auto_monad_reorder 0.01% : 0.000028s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.48% : 0.001534s : 1: bootstrap 0.02% : 0.000050s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000029s : 1: control_data_broadcast_order 0.01% : 0.000039s : 1: convert_after_rewriter 0.02% : 0.000078s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000012s : 1: environ_conv 0.01% : 0.000029s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000008s : 1: insert-virtual-dataset 0.00% : 0.000006s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000016s : 1: label_fine_grained_interleaved_index 0.00% : 0.000011s : 1: label_micro_interleaved_index 0.29% : 0.000911s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000010s : 1: micro_interleaved_order_control 0.36% : 0.001154s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.01% : 0.000032s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000033s : 1: opt.transform.mutable_eliminate 0.52% : 0.001664s : 78: opt.transform.opt_a 0.02% : 0.000060s : 1: opt.transform.opt_after_cconv 0.02% : 0.000067s : 1: opt.transform.opt_after_jit_grad 0.07% : 0.000238s : 28: opt.transform.opt_b 0.03% : 0.000109s : 2: opt.transform.opt_trans_graph 0.04% : 0.000122s : 4: opt.transform.symbol_engine_opt 1.80% : 0.005740s : 1: opt_a 0.08% : 0.000239s : 1: opt_after_cconv 0.28% : 0.000895s : 1: opt_after_jit_grad 0.20% : 0.000624s : 1: opt_b 3.36% : 0.010683s : 1: optimize 0.02% : 0.000061s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.02% : 0.000059s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000009s : 1: overlap_grad_ring_attention 0.00% : 0.000009s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000009s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000013s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.03% : 0.000089s : 1: pre_auto_parallel 0.04% : 0.000130s : 1: py_interpret_to_execute 0.02% : 0.000079s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000078s : 1: remove_dup_value 0.20% : 0.000627s : 1: renormalize.infer 0.48% : 0.001533s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000015s : 1: rewriter_after_jit_bprop_graph 0.07% : 0.000227s : 1: rewriter_after_opt_a 0.04% : 0.000143s : 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% : 0.000009s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000015s : 1: swap_dp_allreduce_reducescatter 0.13% : 0.000415s : 1: symbol_engine_optimizer 0.05% : 0.000150s : 1: tuple_transform 26.21% : 0.083413s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_jiutian[QuantMethod.FP16_VEC-1] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_jiutian[QuantMethod.FP16_VEC-1],max_mem:728.0M [WARNING] ME(168548:281473185062704,MainProcess):2026-01-29-17:42:49.383.89 [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 = 0.0567622, [21] [bootstrap]: 0.00100292 [type_inference]: 0.01046 [event_method]: 1.69e-05 [auto_monad]: 9.396e-05 [graph_reusing]: 5.35999e-06 [inline]: 2.71999e-06 [add_attr]: 0.0233186, [1] [add_attr_with_inline]: 0.0232996, [1] [Cycle 1]: 0.00016874, [2] [tag_attr]: 2.802e-05 [meta_addattr_fg_expand]: 4.59002e-06 [parallel-infer-symbol]: 4.50001e-06 [pre_auto_parallel]: 0.0001082 [insert-virtual-dataset]: 3.4e-06 [parallel-infer-symbol-second]: 8.50006e-07 [dataset_repeat_opt]: 2.12999e-06 [pipeline_split]: 1.65001e-06 [optimize]: 0.011562, [53] [py_interpret_to_execute]: 7.627e-05 [rewriter_before_opt_a]: 0.00011959 [opt_a]: 0.00645715, [2] [Cycle 1]: 0.00450066, [45] [expand_dump_flag]: 3.55e-06 [switch_simplify]: 3.521e-05 [loop_unroll]: 2.14e-05 [a_1]: 0.00063113 [with_stream_mark]: 6.565e-05 [recompute_prepare]: 2.168e-05 [updatestate_depend_eliminate]: 6.95002e-06 [updatestate_assign_eliminate]: 2.603e-05 [updatestate_loads_eliminate]: 5.57001e-06 [parameter_eliminate]: 2.51998e-06 [a_2]: 0.00016827 [accelerated_algorithm]: 1.455e-05 [shard]: 2.74999e-06 [meta_shard_fg_expand]: 2.88998e-06 [shard_inline]: 1.366e-05 [merge_send_recv]: 1.263e-05 [auto_parallel]: 1.212e-05 [parallel]: 6.185e-05 [flash_sp]: 1.362e-05 [merge_comm]: 6.17999e-06 [allreduce_fusion]: 8.57e-06 [matmul_add_comm_reduction]: 1.333e-05 [allreduce_slice_to_reducescatter]: 1.14e-06 [virtual_shard_identity]: 2.417e-05 [virtual_dataset]: 1.69e-05 [get_grad_eliminate_]: 3.759e-05 [virtual_output]: 1.292e-05 [merge_forward]: 8.57e-06 [cell_reuse_recompute_pass]: 2.44999e-06 [offload_activation]: 4.258e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.783e-05 [merge_recompute_call_nodes]: 1.92999e-06 [before_grad]: 2.043e-05 [set_forward_comm_id_for_comm_node_pass]: 8.60001e-06 [meta_fg_expand]: 4.79e-06 [flash_sp_send_recv_attached]: 3.78001e-06 [receive_attached]: 2.81e-06 [after_resolve]: 3.15e-05 [a_after_grad]: 2.503e-05 [renormalize]: 0.00193753 [add_forward_monad_depend]: 1.307e-05 [auto_monad_grad]: 3.08e-06 [auto_monad_eliminator]: 2.835e-05 [cse]: 8.722e-05 [a_3]: 0.00010296 [Cycle 2]: 0.00193186, [45] [expand_dump_flag]: 2.89001e-06 [switch_simplify]: 1.673e-05 [loop_unroll]: 1.239e-05 [a_1]: 0.00031118 [with_stream_mark]: 2.993e-05 [recompute_prepare]: 1.962e-05 [updatestate_depend_eliminate]: 6.66e-06 [updatestate_assign_eliminate]: 5.09e-06 [updatestate_loads_eliminate]: 5.71e-06 [parameter_eliminate]: 2.58998e-06 [a_2]: 0.00015137 [accelerated_algorithm]: 1.808e-05 [shard]: 2.76e-06 [meta_shard_fg_expand]: 4.39998e-06 [shard_inline]: 1.592e-05 [merge_send_recv]: 1.387e-05 [auto_parallel]: 1.243e-05 [parallel]: 1.36e-05 [flash_sp]: 4.92999e-06 [merge_comm]: 5.97001e-06 [allreduce_fusion]: 6.75998e-06 [matmul_add_comm_reduction]: 1.29e-05 [allreduce_slice_to_reducescatter]: 6.10016e-07 [virtual_shard_identity]: 2.173e-05 [virtual_dataset]: 1.248e-05 [get_grad_eliminate_]: 1.219e-05 [virtual_output]: 1.376e-05 [merge_forward]: 3.456e-05 [cell_reuse_recompute_pass]: 3.43e-06 [offload_activation]: 3.779e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.418e-05 [merge_recompute_call_nodes]: 2.46e-06 [before_grad]: 1.785e-05 [set_forward_comm_id_for_comm_node_pass]: 8.09002e-06 [meta_fg_expand]: 4.36002e-06 [flash_sp_send_recv_attached]: 2.37999e-06 [receive_attached]: 2.78e-06 [after_resolve]: 3.748e-05 [a_after_grad]: 2.002e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 4.78001e-06 [auto_monad_grad]: 3.55e-06 [auto_monad_eliminator]: 2.024e-05 [cse]: 8.31e-05 [a_3]: 8.377e-05 [py_interpret_to_execute_after_opt_a]: 3.297e-05 [slice_cell_reuse_recomputed_activation]: 3.63e-06 [rewriter_after_opt_a]: 0.00015015 [convert_after_rewriter]: 1.398e-05 [order_py_execute_after_rewriter]: 8.90999e-06 [mutable_eliminate]: 0.00121687 [opt_b]: 0.00050141, [1] [Cycle 1]: 0.00048956, [7] [b_1]: 0.00025669 [b_2]: 1.497e-05 [updatestate_depend_eliminate]: 9.91e-06 [updatestate_assign_eliminate]: 5.16998e-06 [updatestate_loads_eliminate]: 5.52999e-06 [renormalize]: 1.18001e-06 [cse]: 8.667e-05 [optimize_parallel_all_gather_comm]: 5.944e-05 [overlap_param_gather]: 2.468e-05 [cconv]: 3.987e-05 [loop_unroll]: 0.00084428 [opt_after_cconv]: 0.00031201, [1] [Cycle 1]: 0.00030291, [7] [c_1]: 8.728e-05 [parameter_eliminate]: 6.73998e-06 [updatestate_depend_eliminate]: 1.117e-05 [updatestate_assign_eliminate]: 4.80001e-06 [updatestate_loads_eliminate]: 4.52e-06 [cse]: 9.044e-05 [renormalize]: 8.70001e-07 [remove_dup_value]: 7.628e-05 [tuple_transform]: 0.00025422, [1] [Cycle 1]: 0.0002212, [4] [d_1]: 0.00015128 [none_parameter_eliminate]: 2.82002e-06 [renormalize]: 2.9002e-07 [switch_simplify]: 1.549e-05 [partial_unused_args_eliminate]: 2.78998e-06 [add_recomputation]: 0.00014696 [cse_after_recomputation]: 6.751e-05, [1] [Cycle 1]: 6.061e-05, [1] [cse]: 5.231e-05 [environ_conv]: 1.073e-05 [swap_dp_allreduce_reducescatter]: 8.02e-06 [bias_add_comm_swap]: 4.43999e-06 [label_micro_interleaved_index]: 8.97e-06 [label_fine_grained_interleaved_index]: 2.93e-06 [merge_cast_opt]: 1.64998e-06 [slice_recompute_activation]: 2.32999e-06 [micro_interleaved_order_control]: 2.39001e-06 [assign_add_opt]: 1.50999e-06 [ForceFp32Comm]: 9.20001e-07 [remove_cast_before_assign_add]: 9.39996e-07 [full_micro_interleaved_order_control]: 2.61e-06 [reorder_send_recv_between_fp_bp]: 2.96999e-06 [comm_op_add_attrs]: 1.22e-06 [add_comm_op_reuse_tag]: 1.02e-06 [interleave_split_concat_branches]: 1.57999e-06 [interleave_parallel_branches]: 1.21997e-06 [overlap_opt_shard_in_pipeline]: 2.185e-05 [overlap_opt_shard_grad_in_pipeline]: 2.51998e-06 [control_data_broadcast_order]: 2.377e-05 [grouped_pairwise_exchange_alltoall]: 1.66e-06 [offloading_packed_experts]: 5.34998e-06 [overlap_recompute_and_grad_model_parallel]: 6.81001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.76e-06 [overlap_recompute_allgather_and_fa_grad]: 2.539e-05 [overlap_recompute_comm]: 2.78998e-06 [overlap_grad_ring_attention]: 7.4e-06 [overlap_grad_flash_sp]: 2.676e-05 [begin_end_overlap_inline]: 5.09986e-07 [split_matmul_comm_elemetwise]: 2.69999e-06 [split_layernorm_comm]: 1.67999e-06 [handle_group_info]: 1.02e-06 [symbol_engine_optimizer]: 0.00036348, [1] [Cycle 1]: 0.00033335, [6] [build]: 0.00010953 [elim_shapecalc]: 3.076e-05 [elim_not_effective]: 4.696e-05 [opt_reshape]: 1.585e-05 [fold_const_symbol]: 2.954e-05 [renormalize]: 7.60017e-07 [detach_backward]: 3.78001e-06 [pipeline_parallel_scheduler]: 1.87999e-06 [auto_monad_reorder]: 3.717e-05 [get_jit_bprop_graph]: 2.79999e-06 [rewriter_after_jit_bprop_graph]: 1.283e-05 [opt_after_jit_grad]: 0.00967143 [validate]: 0.00011738 Sums bootstrap : 0.001003s : 3.30% type_inference : 0.010460s : 34.45% event_method : 0.000017s : 0.06% auto_monad : 0.000094s : 0.31% graph_reusing : 0.000005s : 0.02% inline : 0.000003s : 0.01% add_attr.add_attr_with_inline.tag_attr : 0.000028s : 0.09% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.02% parallel-infer-symbol : 0.000005s : 0.01% pre_auto_parallel : 0.000108s : 0.36% insert-virtual-dataset : 0.000003s : 0.01% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.01% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000076s : 0.25% optimize.rewriter_before_opt_a : 0.000120s : 0.39% optimize.opt_a.expand_dump_flag : 0.000006s : 0.02% optimize.opt_a.switch_simplify : 0.000052s : 0.17% optimize.opt_a.loop_unroll : 0.000034s : 0.11% optimize.opt_a.a_1 : 0.000942s : 3.10% optimize.opt_a.with_stream_mark : 0.000096s : 0.31% optimize.opt_a.recompute_prepare : 0.000041s : 0.14% optimize.opt_a.updatestate_depend_eliminate : 0.000014s : 0.04% optimize.opt_a.updatestate_assign_eliminate : 0.000031s : 0.10% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.04% optimize.opt_a.parameter_eliminate : 0.000005s : 0.02% optimize.opt_a.a_2 : 0.000320s : 1.05% optimize.opt_a.accelerated_algorithm : 0.000033s : 0.11% optimize.opt_a.shard : 0.000006s : 0.02% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.02% optimize.opt_a.shard_inline : 0.000030s : 0.10% optimize.opt_a.merge_send_recv : 0.000026s : 0.09% optimize.opt_a.auto_parallel : 0.000025s : 0.08% optimize.opt_a.parallel : 0.000075s : 0.25% optimize.opt_a.flash_sp : 0.000019s : 0.06% optimize.opt_a.merge_comm : 0.000012s : 0.04% optimize.opt_a.allreduce_fusion : 0.000015s : 0.05% optimize.opt_a.matmul_add_comm_reduction : 0.000026s : 0.09% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000046s : 0.15% optimize.opt_a.virtual_dataset : 0.000029s : 0.10% optimize.opt_a.get_grad_eliminate_ : 0.000050s : 0.16% optimize.opt_a.virtual_output : 0.000027s : 0.09% optimize.opt_a.merge_forward : 0.000043s : 0.14% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.02% optimize.opt_a.offload_activation : 0.000080s : 0.26% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000062s : 0.20% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.01% optimize.opt_a.before_grad : 0.000038s : 0.13% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000017s : 0.05% optimize.opt_a.meta_fg_expand : 0.000009s : 0.03% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.02% optimize.opt_a.receive_attached : 0.000006s : 0.02% optimize.opt_a.after_resolve : 0.000069s : 0.23% optimize.opt_a.a_after_grad : 0.000045s : 0.15% optimize.opt_a.renormalize : 0.001938s : 6.38% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.06% optimize.opt_a.auto_monad_grad : 0.000007s : 0.02% optimize.opt_a.auto_monad_eliminator : 0.000049s : 0.16% optimize.opt_a.cse : 0.000170s : 0.56% optimize.opt_a.a_3 : 0.000187s : 0.62% optimize.py_interpret_to_execute_after_opt_a : 0.000033s : 0.11% optimize.slice_cell_reuse_recomputed_activation : 0.000004s : 0.01% optimize.rewriter_after_opt_a : 0.000150s : 0.49% optimize.convert_after_rewriter : 0.000014s : 0.05% optimize.order_py_execute_after_rewriter : 0.000009s : 0.03% optimize.mutable_eliminate : 0.001217s : 4.01% optimize.opt_b.b_1 : 0.000257s : 0.85% optimize.opt_b.b_2 : 0.000015s : 0.05% optimize.opt_b.updatestate_depend_eliminate : 0.000010s : 0.03% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.02% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.02% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000087s : 0.29% optimize.optimize_parallel_all_gather_comm : 0.000059s : 0.20% optimize.overlap_param_gather : 0.000025s : 0.08% optimize.cconv : 0.000040s : 0.13% optimize.loop_unroll : 0.000844s : 2.78% optimize.opt_after_cconv.c_1 : 0.000087s : 0.29% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.02% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000011s : 0.04% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.02% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.01% optimize.opt_after_cconv.cse : 0.000090s : 0.30% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000076s : 0.25% optimize.tuple_transform.d_1 : 0.000151s : 0.50% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000015s : 0.05% optimize.partial_unused_args_eliminate : 0.000003s : 0.01% optimize.add_recomputation : 0.000147s : 0.48% optimize.cse_after_recomputation.cse : 0.000052s : 0.17% optimize.environ_conv : 0.000011s : 0.04% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.03% optimize.bias_add_comm_swap : 0.000004s : 0.01% optimize.label_micro_interleaved_index : 0.000009s : 0.03% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.01% optimize.merge_cast_opt : 0.000002s : 0.01% optimize.slice_recompute_activation : 0.000002s : 0.01% optimize.micro_interleaved_order_control : 0.000002s : 0.01% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.01% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.01% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.01% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000022s : 0.07% optimize.overlap_opt_shard_grad_in_pipeline : 0.000003s : 0.01% optimize.control_data_broadcast_order : 0.000024s : 0.08% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000005s : 0.02% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.02% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.01% optimize.overlap_recompute_allgather_and_fa_grad : 0.000025s : 0.08% optimize.overlap_recompute_comm : 0.000003s : 0.01% optimize.overlap_grad_ring_attention : 0.000007s : 0.02% optimize.overlap_grad_flash_sp : 0.000027s : 0.09% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.01% optimize.split_layernorm_comm : 0.000002s : 0.01% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000110s : 0.36% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000031s : 0.10% optimize.symbol_engine_optimizer.elim_not_effective : 0.000047s : 0.15% optimize.symbol_engine_optimizer.opt_reshape : 0.000016s : 0.05% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000030s : 0.10% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000004s : 0.01% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000037s : 0.12% get_jit_bprop_graph : 0.000003s : 0.01% rewriter_after_jit_bprop_graph : 0.000013s : 0.04% opt_after_jit_grad : 0.009671s : 31.85% validate : 0.000117s : 0.39% Time group info: ------[substitution.] 0.000242 39 10.02% : 0.000024s : 2: substitution.elim_not_effective 4.43% : 0.000011s : 2: substitution.fold_const_symbol 4.28% : 0.000010s : 10: substitution.graph_param_transform 71.21% : 0.000172s : 1: substitution.inline 2.26% : 0.000005s : 4: substitution.j_node_and_user_rematch 2.45% : 0.000006s : 4: substitution.remove_not_recompute_node 5.34% : 0.000013s : 16: substitution.replace_old_param ------[type_inference.] 0.010218 2 85.46% : 0.008732s : 1: type_inference.infer 14.54% : 0.001486s : 1: type_inference.specialize ------[replace.] 0.000024 1 100.00% : 0.000024s : 1: replace.inline ------[match.] 0.000171 1 100.00% : 0.000171s : 1: match.inline ------[predicate.] 0.000301 2335 0.81% : 0.000002s : 21: predicate.accumulaten_eliminater 2.11% : 0.000006s : 10: predicate.ad_related_special_op_eliminate 0.63% : 0.000002s : 20: predicate.addn_check_dump 0.82% : 0.000002s : 21: predicate.addn_zero_filter 0.76% : 0.000002s : 21: predicate.adjust_all_reduce_mul_add 1.97% : 0.000006s : 41: predicate.arithmetic_simplify 0.72% : 0.000002s : 21: predicate.cast_eliminate 0.72% : 0.000002s : 20: predicate.check_bprop_eliminate 0.63% : 0.000002s : 20: predicate.compare_switch_simplify 0.25% : 0.000001s : 10: predicate.const_output_eliminate 0.83% : 0.000002s : 20: predicate.depend_value_elim 0.75% : 0.000002s : 21: predicate.dict_get_item_const_eliminator 0.87% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.78% : 0.000002s : 21: predicate.dict_set_item_eliminator 2.43% : 0.000007s : 20: predicate.dumpgradient_eliminate 0.57% : 0.000002s : 10: predicate.elim_not_effective 0.59% : 0.000002s : 10: predicate.elim_shapecalc_of_broadcastargs 1.07% : 0.000003s : 31: predicate.environ_add_const_eliminate 0.97% : 0.000003s : 31: predicate.environ_get_add_eliminate 1.05% : 0.000003s : 31: predicate.environ_get_depend_swap 1.90% : 0.000006s : 51: predicate.environ_get_eliminate 1.05% : 0.000003s : 31: predicate.environ_get_set_eliminate 0.73% : 0.000002s : 22: predicate.exchange_switch_depend_value 1.66% : 0.000005s : 22: predicate.float_depend_g_call 0.66% : 0.000002s : 20: predicate.float_environ_get_switch 1.06% : 0.000003s : 30: predicate.float_tuple_getitem_switch 0.26% : 0.000001s : 10: predicate.fold_const_symbol 0.94% : 0.000003s : 20: predicate.get_grad_eliminate 0.37% : 0.000001s : 10: predicate.graph_param_transform 0.63% : 0.000002s : 20: predicate.incorporate_call 0.59% : 0.000002s : 20: predicate.incorporate_call_switch 5.21% : 0.000016s : 103: predicate.inline 1.30% : 0.000004s : 20: predicate.inline_without_move 0.55% : 0.000002s : 20: predicate.j_node_and_user_rematch 1.19% : 0.000004s : 20: predicate.less_batch_normalization 1.79% : 0.000005s : 41: predicate.list_to_tuple_eliminator_ 2.08% : 0.000006s : 62: predicate.load_eliminater 1.33% : 0.000004s : 10: predicate.loop_unroll_after_grad 1.22% : 0.000004s : 31: predicate.loop_unroll_before_grad 1.87% : 0.000006s : 41: predicate.make_slice_get_slice_eliminator 0.66% : 0.000002s : 20: predicate.merge_addn 0.75% : 0.000002s : 20: predicate.micro_step_allgather_replace 0.72% : 0.000002s : 20: predicate.mini_step_allgather_replace 0.66% : 0.000002s : 21: predicate.minmaximum_grad 1.55% : 0.000005s : 10: predicate.mutable_eliminate 0.48% : 0.000001s : 10: predicate.opt_reshape 0.68% : 0.000002s : 10: predicate.parallel_virtual_node 0.96% : 0.000003s : 22: predicate.partial_defer_inline 1.12% : 0.000003s : 31: predicate.partial_eliminate 0.74% : 0.000002s : 21: predicate.print_const_string_wrapper 0.73% : 0.000002s : 20: predicate.reduce_all_const_elim 1.10% : 0.000003s : 21: predicate.reduce_eliminate 2.19% : 0.000007s : 62: predicate.redundant_stop_gradient_eliminater 0.86% : 0.000003s : 20: predicate.remove_not_recompute_node 1.44% : 0.000004s : 41: predicate.replace_applicator 0.87% : 0.000003s : 20: predicate.replace_old_param 0.44% : 0.000001s : 10: predicate.reset_defer_inline 0.82% : 0.000002s : 21: predicate.reshape_eliminate 0.84% : 0.000003s : 20: predicate.row_tensor_add_zeros_like 0.47% : 0.000001s : 10: predicate.row_tensor_eliminate 1.20% : 0.000004s : 20: predicate.same_eliminate 0.84% : 0.000003s : 20: predicate.set_cell_output_no_recompute 1.20% : 0.000004s : 20: predicate.shard_identity_eliminate 0.89% : 0.000003s : 20: predicate.special_op_eliminate 0.76% : 0.000002s : 20: predicate.specialize_transform 1.35% : 0.000004s : 20: predicate.split_environ_get_set_with_tuple_value 0.96% : 0.000003s : 20: predicate.stack_unstack_eliminate 0.53% : 0.000002s : 10: predicate.switch_call_monad_eliminater 0.78% : 0.000002s : 22: predicate.switch_defer_inline 1.60% : 0.000005s : 42: predicate.switch_layer_defer_inline 3.51% : 0.000011s : 83: predicate.switch_simplify 0.75% : 0.000002s : 21: predicate.tile_eliminate 0.72% : 0.000002s : 21: predicate.transpose_eliminate 1.51% : 0.000005s : 41: predicate.tuple_list_convert_item_index_to_positive 1.57% : 0.000005s : 41: predicate.tuple_list_get_item_const_eliminator 1.41% : 0.000004s : 41: predicate.tuple_list_get_item_depend_reorder 2.81% : 0.000008s : 61: predicate.tuple_list_get_item_eliminator 1.59% : 0.000005s : 41: predicate.tuple_list_get_set_item_eliminator 2.64% : 0.000008s : 61: predicate.tuple_list_set_item_eliminator 1.53% : 0.000005s : 41: predicate.tuple_to_list_eliminator_ 1.98% : 0.000006s : 62: predicate.updatestate_pure_node_eliminater 2.83% : 0.000009s : 82: predicate.updatestate_useless_node_eliminater 0.42% : 0.000001s : 10: predicate.value_based_eliminate 1.01% : 0.000003s : 20: predicate.virtual_dataset_eliminate 0.88% : 0.000003s : 20: predicate.virtual_output_eliminate 0.37% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.53% : 0.000002s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.001815 6 43.63% : 0.000792s : 3: func_graph_cloner_run.FuncGraphClonerGraph 56.37% : 0.001023s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.095925 192 0.00% : 0.000004s : 1: ForceFp32Comm 24.32% : 0.023332s : 1: add_attr 24.29% : 0.023304s : 1: add_attr_with_inline 0.03% : 0.000024s : 1: add_comm_op_reuse_tag 0.16% : 0.000154s : 1: add_recomputation 0.01% : 0.000005s : 1: assign_add_opt 0.10% : 0.000100s : 1: auto_monad 0.04% : 0.000043s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.03% : 0.000029s : 1: bias_add_comm_swap 1.16% : 0.001117s : 1: bootstrap 0.05% : 0.000044s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.03% : 0.000032s : 1: control_data_broadcast_order 0.02% : 0.000019s : 1: convert_after_rewriter 0.10% : 0.000092s : 1: cse_after_recomputation 0.01% : 0.000005s : 1: dataset_repeat_opt 0.01% : 0.000007s : 1: detach_backward 0.02% : 0.000015s : 1: environ_conv 0.03% : 0.000024s : 1: event_method 0.01% : 0.000006s : 1: full_micro_interleaved_order_control 0.01% : 0.000006s : 1: get_jit_bprop_graph 0.01% : 0.000010s : 1: graph_reusing 0.01% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.01% : 0.000006s : 1: inline 0.01% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.01% : 0.000005s : 1: interleave_split_concat_branches 0.01% : 0.000006s : 1: label_fine_grained_interleaved_index 0.01% : 0.000012s : 1: label_micro_interleaved_index 0.90% : 0.000860s : 1: loop_unroll 0.01% : 0.000005s : 1: merge_cast_opt 0.03% : 0.000030s : 1: micro_interleaved_order_control 1.32% : 0.001264s : 1: mutable_eliminate 0.01% : 0.000009s : 1: offloading_packed_experts 0.03% : 0.000031s : 1: opt.transform.loop_unroll_optimizer 0.04% : 0.000036s : 1: opt.transform.mutable_eliminate 1.94% : 0.001863s : 78: opt.transform.opt_a 0.09% : 0.000086s : 1: opt.transform.opt_after_cconv 0.10% : 0.000095s : 1: opt.transform.opt_after_jit_grad 0.24% : 0.000232s : 28: opt.transform.opt_b 0.17% : 0.000163s : 2: opt.transform.opt_trans_graph 0.12% : 0.000116s : 4: opt.transform.symbol_engine_opt 6.74% : 0.006463s : 1: opt_a 0.36% : 0.000342s : 1: opt_after_cconv 10.12% : 0.009706s : 1: opt_after_jit_grad 0.53% : 0.000510s : 1: opt_b 12.06% : 0.011569s : 1: optimize 0.13% : 0.000127s : 1: optimize_parallel_all_gather_comm 0.02% : 0.000016s : 1: order_py_execute_after_rewriter 0.03% : 0.000032s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.04% : 0.000034s : 1: overlap_grad_ring_attention 0.01% : 0.000011s : 1: overlap_opt_shard_grad_in_pipeline 0.03% : 0.000026s : 1: overlap_opt_shard_in_pipeline 0.03% : 0.000030s : 1: overlap_param_gather 0.03% : 0.000030s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.01% : 0.000006s : 1: overlap_recompute_comm 0.01% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.03% : 0.000027s : 1: partial_unused_args_eliminate 0.01% : 0.000009s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.12% : 0.000115s : 1: pre_auto_parallel 0.09% : 0.000088s : 1: py_interpret_to_execute 0.07% : 0.000066s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.09% : 0.000082s : 1: remove_dup_value 0.70% : 0.000671s : 1: renormalize.infer 1.30% : 0.001249s : 1: renormalize.specialize 0.01% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.02% : 0.000017s : 1: rewriter_after_jit_bprop_graph 0.16% : 0.000158s : 1: rewriter_after_opt_a 0.13% : 0.000128s : 1: rewriter_before_opt_a 0.01% : 0.000008s : 1: slice_cell_reuse_recomputed_activation 0.01% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.01% : 0.000006s : 1: split_matmul_comm_elemetwise 0.01% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.38% : 0.000367s : 1: symbol_engine_optimizer 0.27% : 0.000258s : 1: tuple_transform 10.94% : 0.010490s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_jiutian[QuantMethod.INT_CUBE-0] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_jiutian[QuantMethod.INT_CUBE-0],max_mem:728.0M [WARNING] ME(168548:281473185062704,MainProcess):2026-01-29-17:43:32.322.729 [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 = 0.208117, [21] [bootstrap]: 0.00548955 [type_inference]: 0.0953517 [event_method]: 1.869e-05 [auto_monad]: 0.0001098 [graph_reusing]: 5.47999e-06 [inline]: 3.45e-06 [add_attr]: 0.0434735, [1] [add_attr_with_inline]: 0.0434339, [1] [Cycle 1]: 8.481e-05, [2] [tag_attr]: 2.658e-05 [meta_addattr_fg_expand]: 5.05999e-06 [parallel-infer-symbol]: 3.78999e-06 [pre_auto_parallel]: 4.163e-05 [insert-virtual-dataset]: 2.36998e-06 [parallel-infer-symbol-second]: 6.49976e-07 [dataset_repeat_opt]: 1.94e-06 [pipeline_split]: 1.54e-06 [optimize]: 0.0570011, [53] [py_interpret_to_execute]: 3.743e-05 [rewriter_before_opt_a]: 0.00441717 [opt_a]: 0.0282956, [2] [Cycle 1]: 0.022642, [45] [expand_dump_flag]: 5.46e-06 [switch_simplify]: 4.39e-05 [loop_unroll]: 2.507e-05 [a_1]: 0.00531739 [with_stream_mark]: 9.217e-05 [recompute_prepare]: 3.567e-05 [updatestate_depend_eliminate]: 1.097e-05 [updatestate_assign_eliminate]: 6.03998e-06 [updatestate_loads_eliminate]: 5.42001e-06 [parameter_eliminate]: 2.99999e-06 [a_2]: 0.00022107 [accelerated_algorithm]: 2.186e-05 [shard]: 7.08e-06 [meta_shard_fg_expand]: 4.85999e-06 [shard_inline]: 1.782e-05 [merge_send_recv]: 1.784e-05 [auto_parallel]: 1.821e-05 [parallel]: 0.00469294 [flash_sp]: 2.441e-05 [merge_comm]: 1.437e-05 [allreduce_fusion]: 5.46998e-06 [matmul_add_comm_reduction]: 1.499e-05 [allreduce_slice_to_reducescatter]: 8.00006e-07 [virtual_shard_identity]: 3.607e-05 [virtual_dataset]: 1.698e-05 [get_grad_eliminate_]: 2.302e-05 [virtual_output]: 1.961e-05 [merge_forward]: 6.94001e-06 [cell_reuse_recompute_pass]: 3.85e-06 [offload_activation]: 2.401e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.201e-05 [merge_recompute_call_nodes]: 1.60999e-06 [before_grad]: 3.023e-05 [set_forward_comm_id_for_comm_node_pass]: 5.62001e-06 [meta_fg_expand]: 6.51999e-06 [flash_sp_send_recv_attached]: 3.33998e-06 [receive_attached]: 2.75002e-06 [after_resolve]: 4.387e-05 [a_after_grad]: 0.0027049 [renormalize]: 0.00800773 [add_forward_monad_depend]: 1.783e-05 [auto_monad_grad]: 3.03e-06 [auto_monad_eliminator]: 2.609e-05 [cse]: 9.154e-05 [a_3]: 0.00010349 [Cycle 2]: 0.00563164, [45] [expand_dump_flag]: 2.27999e-06 [switch_simplify]: 1.568e-05 [loop_unroll]: 1.338e-05 [a_1]: 0.00030238 [with_stream_mark]: 2.223e-05 [recompute_prepare]: 1.468e-05 [updatestate_depend_eliminate]: 6.38e-06 [updatestate_assign_eliminate]: 5.15001e-06 [updatestate_loads_eliminate]: 5.67001e-06 [parameter_eliminate]: 2.09999e-06 [a_2]: 0.00451954 [accelerated_algorithm]: 1.768e-05 [shard]: 3.86001e-06 [meta_shard_fg_expand]: 3.52002e-06 [shard_inline]: 1.564e-05 [merge_send_recv]: 1.784e-05 [auto_parallel]: 1.434e-05 [parallel]: 1.12e-05 [flash_sp]: 5.32001e-06 [merge_comm]: 5.96e-06 [allreduce_fusion]: 4.89e-06 [matmul_add_comm_reduction]: 1.323e-05 [allreduce_slice_to_reducescatter]: 1.25001e-06 [virtual_shard_identity]: 1.348e-05 [virtual_dataset]: 1.207e-05 [get_grad_eliminate_]: 1.12e-05 [virtual_output]: 1.112e-05 [merge_forward]: 6.25002e-06 [cell_reuse_recompute_pass]: 3.43e-06 [offload_activation]: 1.343e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.473e-05 [merge_recompute_call_nodes]: 1.57999e-06 [before_grad]: 1.651e-05 [set_forward_comm_id_for_comm_node_pass]: 5.26002e-06 [meta_fg_expand]: 4.81002e-06 [flash_sp_send_recv_attached]: 1.55001e-06 [receive_attached]: 2.32999e-06 [after_resolve]: 2.633e-05 [a_after_grad]: 1.894e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 3.95e-06 [auto_monad_grad]: 2.12999e-06 [auto_monad_eliminator]: 1.415e-05 [cse]: 6.186e-05 [a_3]: 7.256e-05 [py_interpret_to_execute_after_opt_a]: 2.528e-05 [slice_cell_reuse_recomputed_activation]: 2.43002e-06 [rewriter_after_opt_a]: 0.00013038 [convert_after_rewriter]: 1.053e-05 [order_py_execute_after_rewriter]: 6.91001e-06 [mutable_eliminate]: 0.00893205 [opt_b]: 0.00052118, [1] [Cycle 1]: 0.00050215, [7] [b_1]: 0.00029356 [b_2]: 1.357e-05 [updatestate_depend_eliminate]: 1.484e-05 [updatestate_assign_eliminate]: 4.97e-06 [updatestate_loads_eliminate]: 4.97999e-06 [renormalize]: 8.59989e-07 [cse]: 0.00011223 [optimize_parallel_all_gather_comm]: 2.851e-05 [overlap_param_gather]: 3.40998e-06 [cconv]: 0.00316119 [loop_unroll]: 0.00162916 [opt_after_cconv]: 0.00033299, [1] [Cycle 1]: 0.00031597, [7] [c_1]: 6.639e-05 [parameter_eliminate]: 7.04001e-06 [updatestate_depend_eliminate]: 1.174e-05 [updatestate_assign_eliminate]: 5.00001e-06 [updatestate_loads_eliminate]: 4.74e-06 [cse]: 0.00014785 [renormalize]: 1.16002e-06 [remove_dup_value]: 8.1e-05 [tuple_transform]: 0.00468813, [1] [Cycle 1]: 0.00468036, [4] [d_1]: 0.00460549 [none_parameter_eliminate]: 4.87998e-06 [renormalize]: 4.69998e-07 [switch_simplify]: 2.074e-05 [partial_unused_args_eliminate]: 3.33998e-06 [add_recomputation]: 0.00012946 [cse_after_recomputation]: 6.541e-05, [1] [Cycle 1]: 5.794e-05, [1] [cse]: 4.902e-05 [environ_conv]: 1.103e-05 [swap_dp_allreduce_reducescatter]: 1.016e-05 [bias_add_comm_swap]: 3.41999e-06 [label_micro_interleaved_index]: 8.13999e-06 [label_fine_grained_interleaved_index]: 3.01001e-06 [merge_cast_opt]: 1.59e-06 [slice_recompute_activation]: 2.41e-06 [micro_interleaved_order_control]: 2.45002e-06 [assign_add_opt]: 1.27e-06 [ForceFp32Comm]: 1.07e-06 [remove_cast_before_assign_add]: 1.03001e-06 [full_micro_interleaved_order_control]: 3.09001e-06 [reorder_send_recv_between_fp_bp]: 3.16001e-06 [comm_op_add_attrs]: 1.06002e-06 [add_comm_op_reuse_tag]: 1.00001e-06 [interleave_split_concat_branches]: 1.30001e-06 [interleave_parallel_branches]: 1.19e-06 [overlap_opt_shard_in_pipeline]: 2.75002e-06 [overlap_opt_shard_grad_in_pipeline]: 1.72999e-06 [control_data_broadcast_order]: 2.621e-05 [grouped_pairwise_exchange_alltoall]: 1.91998e-06 [offloading_packed_experts]: 1.118e-05 [overlap_recompute_and_grad_model_parallel]: 6.48998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.35001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.52001e-06 [overlap_recompute_comm]: 2.68e-06 [overlap_grad_ring_attention]: 5.40999e-06 [overlap_grad_flash_sp]: 6.872e-05 [begin_end_overlap_inline]: 5.69999e-07 [split_matmul_comm_elemetwise]: 2.24001e-06 [split_layernorm_comm]: 2.24999e-06 [handle_group_info]: 1.84e-06 [symbol_engine_optimizer]: 0.00385993, [1] [Cycle 1]: 0.00385273, [6] [build]: 0.00361423 [elim_shapecalc]: 5.358e-05 [elim_not_effective]: 3.763e-05 [opt_reshape]: 2.649e-05 [fold_const_symbol]: 2.777e-05 [renormalize]: 9.70002e-07 [detach_backward]: 3.4e-06 [pipeline_parallel_scheduler]: 2.02001e-06 [auto_monad_reorder]: 0.00174469 [get_jit_bprop_graph]: 2.29999e-06 [rewriter_after_jit_bprop_graph]: 1.575e-05 [opt_after_jit_grad]: 0.0044387 [validate]: 0.00013766 Sums bootstrap : 0.005490s : 3.38% type_inference : 0.095352s : 58.67% event_method : 0.000019s : 0.01% auto_monad : 0.000110s : 0.07% graph_reusing : 0.000005s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000027s : 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 : 0.000042s : 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 : 0.000037s : 0.02% optimize.rewriter_before_opt_a : 0.004417s : 2.72% optimize.opt_a.expand_dump_flag : 0.000008s : 0.00% optimize.opt_a.switch_simplify : 0.000060s : 0.04% optimize.opt_a.loop_unroll : 0.000038s : 0.02% optimize.opt_a.a_1 : 0.005620s : 3.46% optimize.opt_a.with_stream_mark : 0.000114s : 0.07% optimize.opt_a.recompute_prepare : 0.000050s : 0.03% optimize.opt_a.updatestate_depend_eliminate : 0.000017s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000011s : 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 : 0.004741s : 2.92% optimize.opt_a.accelerated_algorithm : 0.000040s : 0.02% optimize.opt_a.shard : 0.000011s : 0.01% optimize.opt_a.meta_shard_fg_expand : 0.000008s : 0.01% optimize.opt_a.shard_inline : 0.000033s : 0.02% optimize.opt_a.merge_send_recv : 0.000036s : 0.02% optimize.opt_a.auto_parallel : 0.000033s : 0.02% optimize.opt_a.parallel : 0.004704s : 2.89% optimize.opt_a.flash_sp : 0.000030s : 0.02% optimize.opt_a.merge_comm : 0.000020s : 0.01% optimize.opt_a.allreduce_fusion : 0.000010s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000028s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000050s : 0.03% optimize.opt_a.virtual_dataset : 0.000029s : 0.02% optimize.opt_a.get_grad_eliminate_ : 0.000034s : 0.02% optimize.opt_a.virtual_output : 0.000031s : 0.02% optimize.opt_a.merge_forward : 0.000013s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000007s : 0.00% optimize.opt_a.offload_activation : 0.000037s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000077s : 0.05% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.00% optimize.opt_a.before_grad : 0.000047s : 0.03% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000011s : 0.01% 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 : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000070s : 0.04% optimize.opt_a.a_after_grad : 0.002724s : 1.68% optimize.opt_a.renormalize : 0.008008s : 4.93% optimize.opt_a.add_forward_monad_depend : 0.000022s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000040s : 0.02% optimize.opt_a.cse : 0.000153s : 0.09% optimize.opt_a.a_3 : 0.000176s : 0.11% optimize.py_interpret_to_execute_after_opt_a : 0.000025s : 0.02% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.00% optimize.rewriter_after_opt_a : 0.000130s : 0.08% optimize.convert_after_rewriter : 0.000011s : 0.01% optimize.order_py_execute_after_rewriter : 0.000007s : 0.00% optimize.mutable_eliminate : 0.008932s : 5.50% optimize.opt_b.b_1 : 0.000294s : 0.18% optimize.opt_b.b_2 : 0.000014s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000015s : 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 : 0.000112s : 0.07% optimize.optimize_parallel_all_gather_comm : 0.000029s : 0.02% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.003161s : 1.95% optimize.loop_unroll : 0.001629s : 1.00% optimize.opt_after_cconv.c_1 : 0.000066s : 0.04% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.01% 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 : 0.000148s : 0.09% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000081s : 0.05% optimize.tuple_transform.d_1 : 0.004605s : 2.83% optimize.tuple_transform.none_parameter_eliminate : 0.000005s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000021s : 0.01% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000129s : 0.08% optimize.cse_after_recomputation.cse : 0.000049s : 0.03% optimize.environ_conv : 0.000011s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000008s : 0.01% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000002s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000026s : 0.02% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000011s : 0.01% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 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 : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000069s : 0.04% 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 : 0.003614s : 2.22% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000054s : 0.03% optimize.symbol_engine_optimizer.elim_not_effective : 0.000038s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000026s : 0.02% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000028s : 0.02% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.001745s : 1.07% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000016s : 0.01% opt_after_jit_grad : 0.004439s : 2.73% validate : 0.000138s : 0.08% Time group info: ------[substitution.] 0.004721 39 0.19% : 0.000009s : 2: substitution.elim_not_effective 0.23% : 0.000011s : 2: substitution.fold_const_symbol 95.11% : 0.004490s : 10: substitution.graph_param_transform 3.95% : 0.000186s : 1: substitution.inline 0.12% : 0.000006s : 4: substitution.j_node_and_user_rematch 0.14% : 0.000007s : 4: substitution.remove_not_recompute_node 0.27% : 0.000013s : 16: substitution.replace_old_param ------[type_inference.] 0.093669 2 92.00% : 0.086175s : 1: type_inference.infer 8.00% : 0.007494s : 1: type_inference.specialize ------[replace.] 0.000029 1 100.00% : 0.000029s : 1: replace.inline ------[match.] 0.000184 1 100.00% : 0.000184s : 1: match.inline ------[predicate.] 0.000338 2335 0.69% : 0.000002s : 21: predicate.accumulaten_eliminater 1.58% : 0.000005s : 10: predicate.ad_related_special_op_eliminate 0.57% : 0.000002s : 20: predicate.addn_check_dump 0.63% : 0.000002s : 21: predicate.addn_zero_filter 0.58% : 0.000002s : 21: predicate.adjust_all_reduce_mul_add 1.76% : 0.000006s : 41: predicate.arithmetic_simplify 0.68% : 0.000002s : 21: predicate.cast_eliminate 0.61% : 0.000002s : 20: predicate.check_bprop_eliminate 0.57% : 0.000002s : 20: predicate.compare_switch_simplify 0.22% : 0.000001s : 10: predicate.const_output_eliminate 1.01% : 0.000003s : 20: predicate.depend_value_elim 0.69% : 0.000002s : 21: predicate.dict_get_item_const_eliminator 0.90% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.84% : 0.000003s : 21: predicate.dict_set_item_eliminator 10.54% : 0.000036s : 20: predicate.dumpgradient_eliminate 0.41% : 0.000001s : 10: predicate.elim_not_effective 0.67% : 0.000002s : 10: predicate.elim_shapecalc_of_broadcastargs 1.09% : 0.000004s : 31: predicate.environ_add_const_eliminate 0.88% : 0.000003s : 31: predicate.environ_get_add_eliminate 0.89% : 0.000003s : 31: predicate.environ_get_depend_swap 1.82% : 0.000006s : 51: predicate.environ_get_eliminate 0.90% : 0.000003s : 31: predicate.environ_get_set_eliminate 0.64% : 0.000002s : 22: predicate.exchange_switch_depend_value 1.44% : 0.000005s : 22: predicate.float_depend_g_call 0.57% : 0.000002s : 20: predicate.float_environ_get_switch 0.87% : 0.000003s : 30: predicate.float_tuple_getitem_switch 0.24% : 0.000001s : 10: predicate.fold_const_symbol 0.84% : 0.000003s : 20: predicate.get_grad_eliminate 0.42% : 0.000001s : 10: predicate.graph_param_transform 0.62% : 0.000002s : 20: predicate.incorporate_call 0.49% : 0.000002s : 20: predicate.incorporate_call_switch 4.84% : 0.000016s : 103: predicate.inline 1.95% : 0.000007s : 20: predicate.inline_without_move 0.41% : 0.000001s : 20: predicate.j_node_and_user_rematch 1.15% : 0.000004s : 20: predicate.less_batch_normalization 1.90% : 0.000006s : 41: predicate.list_to_tuple_eliminator_ 1.73% : 0.000006s : 62: predicate.load_eliminater 1.22% : 0.000004s : 10: predicate.loop_unroll_after_grad 1.14% : 0.000004s : 31: predicate.loop_unroll_before_grad 1.52% : 0.000005s : 41: predicate.make_slice_get_slice_eliminator 0.59% : 0.000002s : 20: predicate.merge_addn 0.67% : 0.000002s : 20: predicate.micro_step_allgather_replace 0.61% : 0.000002s : 20: predicate.mini_step_allgather_replace 0.64% : 0.000002s : 21: predicate.minmaximum_grad 1.42% : 0.000005s : 10: predicate.mutable_eliminate 0.41% : 0.000001s : 10: predicate.opt_reshape 0.37% : 0.000001s : 10: predicate.parallel_virtual_node 0.93% : 0.000003s : 22: predicate.partial_defer_inline 0.93% : 0.000003s : 31: predicate.partial_eliminate 0.74% : 0.000002s : 21: predicate.print_const_string_wrapper 0.73% : 0.000002s : 20: predicate.reduce_all_const_elim 1.09% : 0.000004s : 21: predicate.reduce_eliminate 1.85% : 0.000006s : 62: predicate.redundant_stop_gradient_eliminater 0.82% : 0.000003s : 20: predicate.remove_not_recompute_node 1.81% : 0.000006s : 41: predicate.replace_applicator 0.62% : 0.000002s : 20: predicate.replace_old_param 0.44% : 0.000001s : 10: predicate.reset_defer_inline 0.75% : 0.000003s : 21: predicate.reshape_eliminate 0.76% : 0.000003s : 20: predicate.row_tensor_add_zeros_like 0.41% : 0.000001s : 10: predicate.row_tensor_eliminate 0.82% : 0.000003s : 20: predicate.same_eliminate 0.67% : 0.000002s : 20: predicate.set_cell_output_no_recompute 1.16% : 0.000004s : 20: predicate.shard_identity_eliminate 0.74% : 0.000003s : 20: predicate.special_op_eliminate 0.73% : 0.000002s : 20: predicate.specialize_transform 0.98% : 0.000003s : 20: predicate.split_environ_get_set_with_tuple_value 1.28% : 0.000004s : 20: predicate.stack_unstack_eliminate 0.38% : 0.000001s : 10: predicate.switch_call_monad_eliminater 0.67% : 0.000002s : 22: predicate.switch_defer_inline 1.33% : 0.000005s : 42: predicate.switch_layer_defer_inline 3.87% : 0.000013s : 83: predicate.switch_simplify 0.66% : 0.000002s : 21: predicate.tile_eliminate 0.64% : 0.000002s : 21: predicate.transpose_eliminate 1.42% : 0.000005s : 41: predicate.tuple_list_convert_item_index_to_positive 1.32% : 0.000004s : 41: predicate.tuple_list_get_item_const_eliminator 1.26% : 0.000004s : 41: predicate.tuple_list_get_item_depend_reorder 2.95% : 0.000010s : 61: predicate.tuple_list_get_item_eliminator 1.42% : 0.000005s : 41: predicate.tuple_list_get_set_item_eliminator 2.10% : 0.000007s : 61: predicate.tuple_list_set_item_eliminator 1.33% : 0.000004s : 41: predicate.tuple_to_list_eliminator_ 1.69% : 0.000006s : 62: predicate.updatestate_pure_node_eliminater 2.32% : 0.000008s : 82: predicate.updatestate_useless_node_eliminater 0.38% : 0.000001s : 10: predicate.value_based_eliminate 0.77% : 0.000003s : 20: predicate.virtual_dataset_eliminate 0.73% : 0.000002s : 20: predicate.virtual_output_eliminate 0.31% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.98% : 0.000003s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.018176 6 75.88% : 0.013792s : 3: func_graph_cloner_run.FuncGraphClonerGraph 24.12% : 0.004384s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.338762 192 0.00% : 0.000004s : 1: ForceFp32Comm 12.84% : 0.043482s : 1: add_attr 12.82% : 0.043439s : 1: add_attr_with_inline 0.00% : 0.000011s : 1: add_comm_op_reuse_tag 0.04% : 0.000136s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.03% : 0.000117s : 1: auto_monad 0.52% : 0.001764s : 1: auto_monad_reorder 0.00% : 0.000008s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 1.64% : 0.005548s : 1: bootstrap 0.94% : 0.003180s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.01% : 0.000030s : 1: control_data_broadcast_order 0.00% : 0.000014s : 1: convert_after_rewriter 0.02% : 0.000073s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.01% : 0.000017s : 1: environ_conv 0.01% : 0.000026s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000008s : 1: get_jit_bprop_graph 0.00% : 0.000009s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000012s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000009s : 1: label_fine_grained_interleaved_index 0.00% : 0.000011s : 1: label_micro_interleaved_index 0.49% : 0.001644s : 1: loop_unroll 0.00% : 0.000008s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 2.64% : 0.008954s : 1: mutable_eliminate 0.00% : 0.000015s : 1: offloading_packed_experts 0.01% : 0.000032s : 1: opt.transform.loop_unroll_optimizer 1.07% : 0.003613s : 1: opt.transform.mutable_eliminate 4.03% : 0.013666s : 78: opt.transform.opt_a 0.02% : 0.000065s : 1: opt.transform.opt_after_cconv 0.03% : 0.000099s : 1: opt.transform.opt_after_jit_grad 0.08% : 0.000266s : 28: opt.transform.opt_b 1.36% : 0.004620s : 2: opt.transform.opt_trans_graph 0.04% : 0.000137s : 4: opt.transform.symbol_engine_opt 8.35% : 0.028302s : 1: opt_a 0.10% : 0.000340s : 1: opt_after_cconv 1.32% : 0.004464s : 1: opt_after_jit_grad 0.16% : 0.000527s : 1: opt_b 16.83% : 0.057010s : 1: optimize 0.01% : 0.000033s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.02% : 0.000077s : 1: overlap_grad_flash_sp 0.00% : 0.000007s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000009s : 1: overlap_grad_ring_attention 0.01% : 0.000034s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000007s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000011s : 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% : 0.000007s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.01% : 0.000047s : 1: pre_auto_parallel 0.01% : 0.000044s : 1: py_interpret_to_execute 0.01% : 0.000029s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.03% : 0.000086s : 1: remove_dup_value 1.02% : 0.003441s : 1: renormalize.infer 1.34% : 0.004541s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000020s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000137s : 1: rewriter_after_opt_a 1.31% : 0.004449s : 1: rewriter_before_opt_a 0.01% : 0.000018s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000009s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000016s : 1: swap_dp_allreduce_reducescatter 1.14% : 0.003864s : 1: symbol_engine_optimizer 1.38% : 0.004692s : 1: tuple_transform 28.16% : 0.095387s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_jiutian[QuantMethod.INT_CUBE-1] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_jiutian[QuantMethod.INT_CUBE-1],max_mem:728.0M =============================== 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 446.39s (0:07:26) ==================