==================================================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_003/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(167181:281473318440752,MainProcess):2026-01-29-17:37:44.794.924 [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 = 0.226525, [21] [bootstrap]: 0.00078838 [type_inference]: 0.0553901 [event_method]: 1.988e-05 [auto_monad]: 0.00010485 [graph_reusing]: 5.56998e-06 [inline]: 3.66001e-06 [add_attr]: 0.0965884, [1] [add_attr_with_inline]: 0.096573, [1] [Cycle 1]: 0.00011041, [2] [tag_attr]: 2.312e-05 [meta_addattr_fg_expand]: 4.06001e-06 [parallel-infer-symbol]: 4.08999e-06 [pre_auto_parallel]: 4.943e-05 [insert-virtual-dataset]: 2.74999e-06 [parallel-infer-symbol-second]: 9.09989e-07 [dataset_repeat_opt]: 2.41e-06 [pipeline_split]: 2.16e-06 [optimize]: 0.072399, [53] [py_interpret_to_execute]: 2.917e-05 [rewriter_before_opt_a]: 8.274e-05 [opt_a]: 0.00372492, [2] [Cycle 1]: 0.00251017, [45] [expand_dump_flag]: 3.33998e-06 [switch_simplify]: 3.652e-05 [loop_unroll]: 2.154e-05 [a_1]: 0.00050531 [with_stream_mark]: 2.624e-05 [recompute_prepare]: 1.609e-05 [updatestate_depend_eliminate]: 6.59001e-06 [updatestate_assign_eliminate]: 4.90001e-06 [updatestate_loads_eliminate]: 4.94e-06 [parameter_eliminate]: 2.01003e-06 [a_2]: 0.0001643 [accelerated_algorithm]: 1.365e-05 [shard]: 2.36e-06 [meta_shard_fg_expand]: 2.69999e-06 [shard_inline]: 1.232e-05 [merge_send_recv]: 1.202e-05 [auto_parallel]: 1.132e-05 [parallel]: 4.781e-05 [flash_sp]: 1.176e-05 [merge_comm]: 6.21e-06 [allreduce_fusion]: 5.17e-06 [matmul_add_comm_reduction]: 1.293e-05 [allreduce_slice_to_reducescatter]: 6.79982e-07 [virtual_shard_identity]: 1.587e-05 [virtual_dataset]: 1.219e-05 [get_grad_eliminate_]: 1.17e-05 [virtual_output]: 1.19e-05 [merge_forward]: 5.72001e-06 [cell_reuse_recompute_pass]: 1.79998e-06 [offload_activation]: 1.307e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.251e-05 [merge_recompute_call_nodes]: 1.93002e-06 [before_grad]: 1.633e-05 [set_forward_comm_id_for_comm_node_pass]: 5.62999e-06 [meta_fg_expand]: 3.93999e-06 [flash_sp_send_recv_attached]: 3.01001e-06 [receive_attached]: 1.279e-05 [after_resolve]: 2.759e-05 [a_after_grad]: 2.011e-05 [renormalize]: 0.00090315 [add_forward_monad_depend]: 9.07999e-06 [auto_monad_grad]: 2.73e-06 [auto_monad_eliminator]: 2.104e-05 [cse]: 8.588e-05 [a_3]: 9.342e-05 [Cycle 2]: 0.00120133, [45] [expand_dump_flag]: 2.89001e-06 [switch_simplify]: 1.568e-05 [loop_unroll]: 1.264e-05 [a_1]: 0.00032168 [with_stream_mark]: 2.308e-05 [recompute_prepare]: 1.326e-05 [updatestate_depend_eliminate]: 6.48998e-06 [updatestate_assign_eliminate]: 4.58001e-06 [updatestate_loads_eliminate]: 4.65001e-06 [parameter_eliminate]: 2.39999e-06 [a_2]: 0.00015304 [accelerated_algorithm]: 1.35e-05 [shard]: 2.09999e-06 [meta_shard_fg_expand]: 2.53998e-06 [shard_inline]: 1.48e-05 [merge_send_recv]: 1.238e-05 [auto_parallel]: 1.164e-05 [parallel]: 7.82e-06 [flash_sp]: 3.98001e-06 [merge_comm]: 5.74999e-06 [allreduce_fusion]: 4.93001e-06 [matmul_add_comm_reduction]: 1.211e-05 [allreduce_slice_to_reducescatter]: 6.09987e-07 [virtual_shard_identity]: 1.612e-05 [virtual_dataset]: 1.134e-05 [get_grad_eliminate_]: 1.153e-05 [virtual_output]: 1.136e-05 [merge_forward]: 7.23999e-06 [cell_reuse_recompute_pass]: 2.08002e-06 [offload_activation]: 1.18e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.462e-05 [merge_recompute_call_nodes]: 1.60999e-06 [before_grad]: 1.62e-05 [set_forward_comm_id_for_comm_node_pass]: 5.66e-06 [meta_fg_expand]: 3.73999e-06 [flash_sp_send_recv_attached]: 1.82001e-06 [receive_attached]: 2.70002e-06 [after_resolve]: 2.61e-05 [a_after_grad]: 1.884e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 3.38999e-06 [auto_monad_grad]: 1.85001e-06 [auto_monad_eliminator]: 1.492e-05 [cse]: 4.059e-05 [a_3]: 7.907e-05 [py_interpret_to_execute_after_opt_a]: 2.359e-05 [slice_cell_reuse_recomputed_activation]: 2.83e-06 [rewriter_after_opt_a]: 9.994e-05 [convert_after_rewriter]: 1.297e-05 [order_py_execute_after_rewriter]: 8.21002e-06 [mutable_eliminate]: 0.00080283 [opt_b]: 0.00040993, [1] [Cycle 1]: 0.0003979, [7] [b_1]: 0.00025291 [b_2]: 1.625e-05 [updatestate_depend_eliminate]: 1.439e-05 [updatestate_assign_eliminate]: 4.97e-06 [updatestate_loads_eliminate]: 4.76002e-06 [renormalize]: 9.20001e-07 [cse]: 5.732e-05 [optimize_parallel_all_gather_comm]: 2.841e-05 [overlap_param_gather]: 3.25e-06 [cconv]: 4.073e-05 [loop_unroll]: 0.00057476 [opt_after_cconv]: 0.0654682, [1] [Cycle 1]: 0.0654558, [7] [c_1]: 0.0652366 [parameter_eliminate]: 8.80001e-06 [updatestate_depend_eliminate]: 2.445e-05 [updatestate_assign_eliminate]: 5.36998e-06 [updatestate_loads_eliminate]: 5.09e-06 [cse]: 7.719e-05 [renormalize]: 1.11002e-06 [remove_dup_value]: 7.805e-05 [tuple_transform]: 0.00016021, [1] [Cycle 1]: 0.00014829, [4] [d_1]: 0.00011201 [none_parameter_eliminate]: 1.63002e-06 [renormalize]: 1.8999e-07 [switch_simplify]: 1.346e-05 [partial_unused_args_eliminate]: 2.85002e-06 [add_recomputation]: 8.237e-05 [cse_after_recomputation]: 3.621e-05, [1] [Cycle 1]: 3.133e-05, [1] [cse]: 2.436e-05 [environ_conv]: 2.503e-05 [swap_dp_allreduce_reducescatter]: 8.18001e-06 [bias_add_comm_swap]: 3.55e-06 [label_micro_interleaved_index]: 8.70999e-06 [label_fine_grained_interleaved_index]: 3.4e-06 [merge_cast_opt]: 1.52999e-06 [slice_recompute_activation]: 2.24999e-06 [micro_interleaved_order_control]: 2.83e-06 [assign_add_opt]: 1.61002e-06 [ForceFp32Comm]: 9.99979e-07 [remove_cast_before_assign_add]: 1.19e-06 [full_micro_interleaved_order_control]: 2.87002e-06 [reorder_send_recv_between_fp_bp]: 3.04999e-06 [comm_op_add_attrs]: 1.35001e-06 [add_comm_op_reuse_tag]: 1.20001e-06 [interleave_split_concat_branches]: 1.49e-06 [interleave_parallel_branches]: 1.49e-06 [overlap_opt_shard_in_pipeline]: 2.914e-05 [overlap_opt_shard_grad_in_pipeline]: 2.17001e-06 [control_data_broadcast_order]: 2.226e-05 [grouped_pairwise_exchange_alltoall]: 1.94999e-06 [offloading_packed_experts]: 6.23e-06 [overlap_recompute_and_grad_model_parallel]: 6.68e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.61998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.57999e-06 [overlap_recompute_comm]: 2.59001e-06 [overlap_grad_ring_attention]: 5.49998e-06 [overlap_grad_flash_sp]: 4.248e-05 [begin_end_overlap_inline]: 6.69999e-07 [split_matmul_comm_elemetwise]: 2.26e-06 [split_layernorm_comm]: 2.41e-06 [handle_group_info]: 1.12e-06 [symbol_engine_optimizer]: 0.00024579, [1] [Cycle 1]: 0.00023955, [6] [build]: 0.00011223 [elim_shapecalc]: 1.994e-05 [elim_not_effective]: 3.081e-05 [opt_reshape]: 1.409e-05 [fold_const_symbol]: 2.341e-05 [renormalize]: 1.8999e-07 [detach_backward]: 2.90002e-06 [pipeline_parallel_scheduler]: 1.83002e-06 [auto_monad_reorder]: 3.36e-05 [get_jit_bprop_graph]: 2.06e-06 [rewriter_after_jit_bprop_graph]: 5.97001e-06 [opt_after_jit_grad]: 0.00082095 [validate]: 8.312e-05 Sums bootstrap : 0.000788s : 0.61% type_inference : 0.055390s : 43.04% event_method : 0.000020s : 0.02% auto_monad : 0.000105s : 0.08% graph_reusing : 0.000006s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000023s : 0.02% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000049s : 0.04% 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 : 0.000029s : 0.02% optimize.rewriter_before_opt_a : 0.000083s : 0.06% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000052s : 0.04% optimize.opt_a.loop_unroll : 0.000034s : 0.03% optimize.opt_a.a_1 : 0.000827s : 0.64% optimize.opt_a.with_stream_mark : 0.000049s : 0.04% optimize.opt_a.recompute_prepare : 0.000029s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000013s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000009s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000010s : 0.01% optimize.opt_a.parameter_eliminate : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000317s : 0.25% optimize.opt_a.accelerated_algorithm : 0.000027s : 0.02% optimize.opt_a.shard : 0.000004s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000005s : 0.00% optimize.opt_a.shard_inline : 0.000027s : 0.02% optimize.opt_a.merge_send_recv : 0.000024s : 0.02% optimize.opt_a.auto_parallel : 0.000023s : 0.02% optimize.opt_a.parallel : 0.000056s : 0.04% optimize.opt_a.flash_sp : 0.000016s : 0.01% optimize.opt_a.merge_comm : 0.000012s : 0.01% optimize.opt_a.allreduce_fusion : 0.000010s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000025s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000032s : 0.02% optimize.opt_a.virtual_dataset : 0.000024s : 0.02% optimize.opt_a.get_grad_eliminate_ : 0.000023s : 0.02% optimize.opt_a.virtual_output : 0.000023s : 0.02% optimize.opt_a.merge_forward : 0.000013s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.00% optimize.opt_a.offload_activation : 0.000025s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000047s : 0.04% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000033s : 0.03% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000011s : 0.01% optimize.opt_a.meta_fg_expand : 0.000008s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000005s : 0.00% optimize.opt_a.receive_attached : 0.000015s : 0.01% optimize.opt_a.after_resolve : 0.000054s : 0.04% optimize.opt_a.a_after_grad : 0.000039s : 0.03% optimize.opt_a.renormalize : 0.000903s : 0.70% optimize.opt_a.add_forward_monad_depend : 0.000012s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000036s : 0.03% optimize.opt_a.cse : 0.000126s : 0.10% optimize.opt_a.a_3 : 0.000172s : 0.13% optimize.py_interpret_to_execute_after_opt_a : 0.000024s : 0.02% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000100s : 0.08% optimize.convert_after_rewriter : 0.000013s : 0.01% optimize.order_py_execute_after_rewriter : 0.000008s : 0.01% optimize.mutable_eliminate : 0.000803s : 0.62% optimize.opt_b.b_1 : 0.000253s : 0.20% optimize.opt_b.b_2 : 0.000016s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 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 : 0.000057s : 0.04% optimize.optimize_parallel_all_gather_comm : 0.000028s : 0.02% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000041s : 0.03% optimize.loop_unroll : 0.000575s : 0.45% optimize.opt_after_cconv.c_1 : 0.065237s : 50.70% optimize.opt_after_cconv.parameter_eliminate : 0.000009s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000024s : 0.02% 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 : 0.000077s : 0.06% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000078s : 0.06% optimize.tuple_transform.d_1 : 0.000112s : 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 : 0.000013s : 0.01% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000082s : 0.06% optimize.cse_after_recomputation.cse : 0.000024s : 0.02% optimize.environ_conv : 0.000025s : 0.02% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.01% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000009s : 0.01% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 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 : 0.00% 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 : 0.000029s : 0.02% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000022s : 0.02% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.01% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000042s : 0.03% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000112s : 0.09% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000020s : 0.02% optimize.symbol_engine_optimizer.elim_not_effective : 0.000031s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000014s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000023s : 0.02% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000034s : 0.03% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000821s : 0.64% validate : 0.000083s : 0.06% Time group info: ------[substitution.] 0.000168 39 7.05% : 0.000012s : 2: substitution.elim_not_effective 5.06% : 0.000009s : 2: substitution.fold_const_symbol 6.63% : 0.000011s : 10: substitution.graph_param_transform 65.95% : 0.000111s : 1: substitution.inline 2.77% : 0.000005s : 4: substitution.j_node_and_user_rematch 4.79% : 0.000008s : 4: substitution.remove_not_recompute_node 7.75% : 0.000013s : 16: substitution.replace_old_param ------[type_inference.] 0.055273 2 98.85% : 0.054636s : 1: type_inference.infer 1.15% : 0.000636s : 1: type_inference.specialize ------[replace.] 0.000019 1 100.00% : 0.000019s : 1: replace.inline ------[match.] 0.000110 1 100.00% : 0.000110s : 1: match.inline ------[predicate.] 0.000316 2335 0.77% : 0.000002s : 21: predicate.accumulaten_eliminater 1.06% : 0.000003s : 10: predicate.ad_related_special_op_eliminate 0.74% : 0.000002s : 20: predicate.addn_check_dump 0.82% : 0.000003s : 21: predicate.addn_zero_filter 0.76% : 0.000002s : 21: predicate.adjust_all_reduce_mul_add 1.83% : 0.000006s : 41: predicate.arithmetic_simplify 0.79% : 0.000003s : 21: predicate.cast_eliminate 0.78% : 0.000002s : 20: predicate.check_bprop_eliminate 0.70% : 0.000002s : 20: predicate.compare_switch_simplify 0.30% : 0.000001s : 10: predicate.const_output_eliminate 0.74% : 0.000002s : 20: predicate.depend_value_elim 0.83% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.96% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.81% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.54% : 0.000005s : 20: predicate.dumpgradient_eliminate 0.32% : 0.000001s : 10: predicate.elim_not_effective 0.63% : 0.000002s : 10: predicate.elim_shapecalc_of_broadcastargs 1.19% : 0.000004s : 31: predicate.environ_add_const_eliminate 1.09% : 0.000003s : 31: predicate.environ_get_add_eliminate 1.13% : 0.000004s : 31: predicate.environ_get_depend_swap 1.92% : 0.000006s : 51: predicate.environ_get_eliminate 1.13% : 0.000004s : 31: predicate.environ_get_set_eliminate 0.89% : 0.000003s : 22: predicate.exchange_switch_depend_value 1.34% : 0.000004s : 22: predicate.float_depend_g_call 0.70% : 0.000002s : 20: predicate.float_environ_get_switch 1.23% : 0.000004s : 30: predicate.float_tuple_getitem_switch 0.31% : 0.000001s : 10: predicate.fold_const_symbol 0.81% : 0.000003s : 20: predicate.get_grad_eliminate 0.50% : 0.000002s : 10: predicate.graph_param_transform 0.72% : 0.000002s : 20: predicate.incorporate_call 0.66% : 0.000002s : 20: predicate.incorporate_call_switch 6.43% : 0.000020s : 103: predicate.inline 0.98% : 0.000003s : 20: predicate.inline_without_move 0.55% : 0.000002s : 20: predicate.j_node_and_user_rematch 1.02% : 0.000003s : 20: predicate.less_batch_normalization 1.74% : 0.000006s : 41: predicate.list_to_tuple_eliminator_ 2.29% : 0.000007s : 62: predicate.load_eliminater 0.98% : 0.000003s : 10: predicate.loop_unroll_after_grad 1.30% : 0.000004s : 31: predicate.loop_unroll_before_grad 1.96% : 0.000006s : 41: predicate.make_slice_get_slice_eliminator 0.79% : 0.000003s : 20: predicate.merge_addn 0.73% : 0.000002s : 20: predicate.micro_step_allgather_replace 0.81% : 0.000003s : 20: predicate.mini_step_allgather_replace 0.74% : 0.000002s : 21: predicate.minmaximum_grad 1.38% : 0.000004s : 10: predicate.mutable_eliminate 0.42% : 0.000001s : 10: predicate.opt_reshape 0.37% : 0.000001s : 10: predicate.parallel_virtual_node 1.16% : 0.000004s : 22: predicate.partial_defer_inline 1.23% : 0.000004s : 31: predicate.partial_eliminate 0.80% : 0.000003s : 21: predicate.print_const_string_wrapper 0.73% : 0.000002s : 20: predicate.reduce_all_const_elim 0.91% : 0.000003s : 21: predicate.reduce_eliminate 2.31% : 0.000007s : 62: predicate.redundant_stop_gradient_eliminater 0.73% : 0.000002s : 20: predicate.remove_not_recompute_node 1.53% : 0.000005s : 41: predicate.replace_applicator 0.75% : 0.000002s : 20: predicate.replace_old_param 0.41% : 0.000001s : 10: predicate.reset_defer_inline 0.82% : 0.000003s : 21: predicate.reshape_eliminate 0.88% : 0.000003s : 20: predicate.row_tensor_add_zeros_like 0.58% : 0.000002s : 10: predicate.row_tensor_eliminate 1.03% : 0.000003s : 20: predicate.same_eliminate 0.64% : 0.000002s : 20: predicate.set_cell_output_no_recompute 1.14% : 0.000004s : 20: predicate.shard_identity_eliminate 0.80% : 0.000003s : 20: predicate.special_op_eliminate 0.89% : 0.000003s : 20: predicate.specialize_transform 1.16% : 0.000004s : 20: predicate.split_environ_get_set_with_tuple_value 1.01% : 0.000003s : 20: predicate.stack_unstack_eliminate 0.55% : 0.000002s : 10: predicate.switch_call_monad_eliminater 0.84% : 0.000003s : 22: predicate.switch_defer_inline 1.68% : 0.000005s : 42: predicate.switch_layer_defer_inline 3.60% : 0.000011s : 83: predicate.switch_simplify 0.82% : 0.000003s : 21: predicate.tile_eliminate 0.79% : 0.000002s : 21: predicate.transpose_eliminate 1.44% : 0.000005s : 41: predicate.tuple_list_convert_item_index_to_positive 1.52% : 0.000005s : 41: predicate.tuple_list_get_item_const_eliminator 1.41% : 0.000004s : 41: predicate.tuple_list_get_item_depend_reorder 3.08% : 0.000010s : 61: predicate.tuple_list_get_item_eliminator 1.46% : 0.000005s : 41: predicate.tuple_list_get_set_item_eliminator 2.28% : 0.000007s : 61: predicate.tuple_list_set_item_eliminator 1.67% : 0.000005s : 41: predicate.tuple_to_list_eliminator_ 2.26% : 0.000007s : 62: predicate.updatestate_pure_node_eliminater 3.66% : 0.000012s : 82: predicate.updatestate_useless_node_eliminater 0.37% : 0.000001s : 10: predicate.value_based_eliminate 0.82% : 0.000003s : 20: predicate.virtual_dataset_eliminate 0.86% : 0.000003s : 20: predicate.virtual_output_eliminate 0.36% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.52% : 0.000002s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000600 6 50.78% : 0.000305s : 3: func_graph_cloner_run.FuncGraphClonerGraph 49.22% : 0.000295s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.463656 192 0.00% : 0.000004s : 1: ForceFp32Comm 20.83% : 0.096595s : 1: add_attr 20.83% : 0.096578s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000088s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.02% : 0.000113s : 1: auto_monad 0.01% : 0.000039s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.18% : 0.000842s : 1: bootstrap 0.01% : 0.000045s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000026s : 1: control_data_broadcast_order 0.00% : 0.000018s : 1: convert_after_rewriter 0.01% : 0.000039s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.01% : 0.000029s : 1: environ_conv 0.01% : 0.000027s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000010s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000012s : 1: label_micro_interleaved_index 0.13% : 0.000590s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.18% : 0.000823s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.01% : 0.000029s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000034s : 1: opt.transform.mutable_eliminate 0.36% : 0.001658s : 78: opt.transform.opt_a 14.07% : 0.065231s : 1: opt.transform.opt_after_cconv 0.01% : 0.000053s : 1: opt.transform.opt_after_jit_grad 0.05% : 0.000238s : 28: opt.transform.opt_b 0.03% : 0.000121s : 2: opt.transform.opt_trans_graph 0.02% : 0.000083s : 4: opt.transform.symbol_engine_opt 0.80% : 0.003729s : 1: opt_a 14.12% : 0.065474s : 1: opt_after_cconv 0.18% : 0.000836s : 1: opt_after_jit_grad 0.09% : 0.000415s : 1: opt_b 15.62% : 0.072404s : 1: optimize 0.01% : 0.000033s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000012s : 1: order_py_execute_after_rewriter 0.01% : 0.000047s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000009s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.01% : 0.000033s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 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% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000054s : 1: pre_auto_parallel 0.01% : 0.000034s : 1: py_interpret_to_execute 0.01% : 0.000028s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000083s : 1: remove_dup_value 0.10% : 0.000469s : 1: renormalize.infer 0.09% : 0.000421s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000009s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000109s : 1: rewriter_after_opt_a 0.02% : 0.000088s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000012s : 1: swap_dp_allreduce_reducescatter 0.05% : 0.000249s : 1: symbol_engine_optimizer 0.04% : 0.000163s : 1: tuple_transform 11.95% : 0.055421s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_with_anti_shape[QuantMethod.FP16_VEC-0] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_with_anti_shape[QuantMethod.FP16_VEC-0],max_mem:684.0M [WARNING] ME(167181:281473318440752,MainProcess):2026-01-29-17:38:46.636.766 [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 = 0.206379, [21] [bootstrap]: 0.00073259 [type_inference]: 0.00640615 [event_method]: 1.938e-05 [auto_monad]: 6.849e-05 [graph_reusing]: 5.32999e-06 [inline]: 2.94001e-06 [add_attr]: 0.189558, [1] [add_attr_with_inline]: 0.189539, [1] [Cycle 1]: 8.123e-05, [2] [tag_attr]: 2.598e-05 [meta_addattr_fg_expand]: 4.62998e-06 [parallel-infer-symbol]: 3.78001e-06 [pre_auto_parallel]: 4.008e-05 [insert-virtual-dataset]: 2.79001e-06 [parallel-infer-symbol-second]: 1.10001e-06 [dataset_repeat_opt]: 2.98e-06 [pipeline_split]: 1.72999e-06 [optimize]: 0.00831527, [53] [py_interpret_to_execute]: 3.432e-05 [rewriter_before_opt_a]: 8.782e-05 [opt_a]: 0.0044669, [2] [Cycle 1]: 0.00299514, [45] [expand_dump_flag]: 3.38e-06 [switch_simplify]: 3.715e-05 [loop_unroll]: 2.589e-05 [a_1]: 0.000593 [with_stream_mark]: 3.243e-05 [recompute_prepare]: 2.219e-05 [updatestate_depend_eliminate]: 6.86001e-06 [updatestate_assign_eliminate]: 5.81e-06 [updatestate_loads_eliminate]: 5.62999e-06 [parameter_eliminate]: 2.46e-06 [a_2]: 0.00016956 [accelerated_algorithm]: 1.633e-05 [shard]: 3.35998e-06 [meta_shard_fg_expand]: 2.81e-06 [shard_inline]: 1.414e-05 [merge_send_recv]: 1.344e-05 [auto_parallel]: 1.426e-05 [parallel]: 3.676e-05 [flash_sp]: 1.332e-05 [merge_comm]: 6.93e-06 [allreduce_fusion]: 5.64e-06 [matmul_add_comm_reduction]: 1.413e-05 [allreduce_slice_to_reducescatter]: 9.29984e-07 [virtual_shard_identity]: 2.104e-05 [virtual_dataset]: 1.336e-05 [get_grad_eliminate_]: 1.237e-05 [virtual_output]: 1.307e-05 [merge_forward]: 8.99998e-06 [cell_reuse_recompute_pass]: 2.38998e-06 [offload_activation]: 1.546e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.848e-05 [merge_recompute_call_nodes]: 2.62001e-06 [before_grad]: 1.93e-05 [set_forward_comm_id_for_comm_node_pass]: 6.45002e-06 [meta_fg_expand]: 4.25e-06 [flash_sp_send_recv_attached]: 5.14e-06 [receive_attached]: 2.71e-06 [after_resolve]: 3.186e-05 [a_after_grad]: 2.071e-05 [renormalize]: 0.00114331 [add_forward_monad_depend]: 1.061e-05 [auto_monad_grad]: 3.39001e-06 [auto_monad_eliminator]: 3.619e-05 [cse]: 8.332e-05 [a_3]: 0.00010437 [Cycle 2]: 0.00145436, [45] [expand_dump_flag]: 3.91001e-06 [switch_simplify]: 1.671e-05 [loop_unroll]: 1.267e-05 [a_1]: 0.00036651 [with_stream_mark]: 3.241e-05 [recompute_prepare]: 1.865e-05 [updatestate_depend_eliminate]: 6.54999e-06 [updatestate_assign_eliminate]: 5.84999e-06 [updatestate_loads_eliminate]: 6.39999e-06 [parameter_eliminate]: 2.26e-06 [a_2]: 0.00015933 [accelerated_algorithm]: 1.602e-05 [shard]: 2.71e-06 [meta_shard_fg_expand]: 4.03001e-06 [shard_inline]: 1.37e-05 [merge_send_recv]: 1.196e-05 [auto_parallel]: 1.611e-05 [parallel]: 1.05e-05 [flash_sp]: 4.10998e-06 [merge_comm]: 7.48e-06 [allreduce_fusion]: 5.67001e-06 [matmul_add_comm_reduction]: 1.426e-05 [allreduce_slice_to_reducescatter]: 1.60999e-06 [virtual_shard_identity]: 1.82e-05 [virtual_dataset]: 1.239e-05 [get_grad_eliminate_]: 1.279e-05 [virtual_output]: 1.231e-05 [merge_forward]: 7.36999e-06 [cell_reuse_recompute_pass]: 2.49999e-06 [offload_activation]: 1.422e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.932e-05 [merge_recompute_call_nodes]: 1.38002e-06 [before_grad]: 1.846e-05 [set_forward_comm_id_for_comm_node_pass]: 7.71999e-06 [meta_fg_expand]: 4.48001e-06 [flash_sp_send_recv_attached]: 2.25002e-06 [receive_attached]: 3.07002e-06 [after_resolve]: 2.983e-05 [a_after_grad]: 2.264e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 4.89003e-06 [auto_monad_grad]: 2.75002e-06 [auto_monad_eliminator]: 4.358e-05 [cse]: 6.559e-05 [a_3]: 8.87e-05 [py_interpret_to_execute_after_opt_a]: 2.672e-05 [slice_cell_reuse_recomputed_activation]: 2.60002e-06 [rewriter_after_opt_a]: 7.192e-05 [convert_after_rewriter]: 1.179e-05 [order_py_execute_after_rewriter]: 9.30001e-06 [mutable_eliminate]: 0.0009373 [opt_b]: 0.00045584, [1] [Cycle 1]: 0.00044227, [7] [b_1]: 0.00025861 [b_2]: 1.672e-05 [updatestate_depend_eliminate]: 1.576e-05 [updatestate_assign_eliminate]: 5.24e-06 [updatestate_loads_eliminate]: 5.06002e-06 [renormalize]: 6.79982e-07 [cse]: 6.871e-05 [optimize_parallel_all_gather_comm]: 3.301e-05 [overlap_param_gather]: 2.83e-06 [cconv]: 4.254e-05 [loop_unroll]: 0.00071546 [opt_after_cconv]: 0.00022002, [1] [Cycle 1]: 0.00021035, [7] [c_1]: 6.924e-05 [parameter_eliminate]: 6.23e-06 [updatestate_depend_eliminate]: 1.231e-05 [updatestate_assign_eliminate]: 4.85001e-06 [updatestate_loads_eliminate]: 4.56002e-06 [cse]: 5.913e-05 [renormalize]: 7.79983e-07 [remove_dup_value]: 7.504e-05 [tuple_transform]: 0.00016961, [1] [Cycle 1]: 0.00015548, [4] [d_1]: 0.00010903 [none_parameter_eliminate]: 1.93002e-06 [renormalize]: 1.60013e-07 [switch_simplify]: 1.556e-05 [partial_unused_args_eliminate]: 2.44001e-06 [add_recomputation]: 0.00011469 [cse_after_recomputation]: 5.294e-05, [1] [Cycle 1]: 4.717e-05, [1] [cse]: 3.69e-05 [environ_conv]: 1.042e-05 [swap_dp_allreduce_reducescatter]: 1.218e-05 [bias_add_comm_swap]: 4.3e-06 [label_micro_interleaved_index]: 7.6e-06 [label_fine_grained_interleaved_index]: 3.40998e-06 [merge_cast_opt]: 1.66e-06 [slice_recompute_activation]: 2.71e-06 [micro_interleaved_order_control]: 3.33e-06 [assign_add_opt]: 1.60999e-06 [ForceFp32Comm]: 1.01002e-06 [remove_cast_before_assign_add]: 1.29e-06 [full_micro_interleaved_order_control]: 3.53e-06 [reorder_send_recv_between_fp_bp]: 3.41999e-06 [comm_op_add_attrs]: 1.43002e-06 [add_comm_op_reuse_tag]: 1.67999e-06 [interleave_split_concat_branches]: 1.45999e-06 [interleave_parallel_branches]: 1.47001e-06 [overlap_opt_shard_in_pipeline]: 1.49e-06 [overlap_opt_shard_grad_in_pipeline]: 2.72001e-06 [control_data_broadcast_order]: 2.96e-05 [grouped_pairwise_exchange_alltoall]: 2.04e-06 [offloading_packed_experts]: 5.76e-06 [overlap_recompute_and_grad_model_parallel]: 7.67002e-06 [overlap_grad_matmul_and_grad_allreduce]: 2.14e-06 [overlap_recompute_allgather_and_fa_grad]: 1.71998e-06 [overlap_recompute_comm]: 2.68e-06 [overlap_grad_ring_attention]: 6.64999e-06 [overlap_grad_flash_sp]: 2.973e-05 [begin_end_overlap_inline]: 8.70001e-07 [split_matmul_comm_elemetwise]: 2.71e-06 [split_layernorm_comm]: 2.36e-06 [handle_group_info]: 1.35001e-06 [symbol_engine_optimizer]: 0.00026452, [1] [Cycle 1]: 0.00025501, [6] [build]: 0.00010634 [elim_shapecalc]: 2.723e-05 [elim_not_effective]: 2.747e-05 [opt_reshape]: 1.452e-05 [fold_const_symbol]: 2.545e-05 [renormalize]: 4.99975e-07 [detach_backward]: 3.04001e-06 [pipeline_parallel_scheduler]: 1.82999e-06 [auto_monad_reorder]: 3.424e-05 [get_jit_bprop_graph]: 2.88998e-06 [rewriter_after_jit_bprop_graph]: 6.88e-06 [opt_after_jit_grad]: 0.0008661 [validate]: 8.06e-05 Sums bootstrap : 0.000733s : 4.78% type_inference : 0.006406s : 41.83% event_method : 0.000019s : 0.13% auto_monad : 0.000068s : 0.45% graph_reusing : 0.000005s : 0.03% inline : 0.000003s : 0.02% add_attr.add_attr_with_inline.tag_attr : 0.000026s : 0.17% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.03% parallel-infer-symbol : 0.000004s : 0.02% pre_auto_parallel : 0.000040s : 0.26% insert-virtual-dataset : 0.000003s : 0.02% parallel-infer-symbol-second : 0.000001s : 0.01% dataset_repeat_opt : 0.000003s : 0.02% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000034s : 0.22% optimize.rewriter_before_opt_a : 0.000088s : 0.57% optimize.opt_a.expand_dump_flag : 0.000007s : 0.05% optimize.opt_a.switch_simplify : 0.000054s : 0.35% optimize.opt_a.loop_unroll : 0.000039s : 0.25% optimize.opt_a.a_1 : 0.000960s : 6.26% optimize.opt_a.with_stream_mark : 0.000065s : 0.42% optimize.opt_a.recompute_prepare : 0.000041s : 0.27% optimize.opt_a.updatestate_depend_eliminate : 0.000013s : 0.09% optimize.opt_a.updatestate_assign_eliminate : 0.000012s : 0.08% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.08% optimize.opt_a.parameter_eliminate : 0.000005s : 0.03% optimize.opt_a.a_2 : 0.000329s : 2.15% optimize.opt_a.accelerated_algorithm : 0.000032s : 0.21% optimize.opt_a.shard : 0.000006s : 0.04% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.04% optimize.opt_a.shard_inline : 0.000028s : 0.18% optimize.opt_a.merge_send_recv : 0.000025s : 0.17% optimize.opt_a.auto_parallel : 0.000030s : 0.20% optimize.opt_a.parallel : 0.000047s : 0.31% optimize.opt_a.flash_sp : 0.000017s : 0.11% optimize.opt_a.merge_comm : 0.000014s : 0.09% optimize.opt_a.allreduce_fusion : 0.000011s : 0.07% optimize.opt_a.matmul_add_comm_reduction : 0.000028s : 0.19% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000003s : 0.02% optimize.opt_a.virtual_shard_identity : 0.000039s : 0.26% optimize.opt_a.virtual_dataset : 0.000026s : 0.17% optimize.opt_a.get_grad_eliminate_ : 0.000025s : 0.16% optimize.opt_a.virtual_output : 0.000025s : 0.17% optimize.opt_a.merge_forward : 0.000016s : 0.11% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.03% optimize.opt_a.offload_activation : 0.000030s : 0.19% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000058s : 0.38% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.03% optimize.opt_a.before_grad : 0.000038s : 0.25% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.09% optimize.opt_a.meta_fg_expand : 0.000009s : 0.06% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.05% optimize.opt_a.receive_attached : 0.000006s : 0.04% optimize.opt_a.after_resolve : 0.000062s : 0.40% optimize.opt_a.a_after_grad : 0.000043s : 0.28% optimize.opt_a.renormalize : 0.001143s : 7.47% optimize.opt_a.add_forward_monad_depend : 0.000016s : 0.10% optimize.opt_a.auto_monad_grad : 0.000006s : 0.04% optimize.opt_a.auto_monad_eliminator : 0.000080s : 0.52% optimize.opt_a.cse : 0.000149s : 0.97% optimize.opt_a.a_3 : 0.000193s : 1.26% optimize.py_interpret_to_execute_after_opt_a : 0.000027s : 0.17% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.02% optimize.rewriter_after_opt_a : 0.000072s : 0.47% optimize.convert_after_rewriter : 0.000012s : 0.08% optimize.order_py_execute_after_rewriter : 0.000009s : 0.06% optimize.mutable_eliminate : 0.000937s : 6.12% optimize.opt_b.b_1 : 0.000259s : 1.69% optimize.opt_b.b_2 : 0.000017s : 0.11% optimize.opt_b.updatestate_depend_eliminate : 0.000016s : 0.10% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.03% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.03% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000069s : 0.45% optimize.optimize_parallel_all_gather_comm : 0.000033s : 0.22% optimize.overlap_param_gather : 0.000003s : 0.02% optimize.cconv : 0.000043s : 0.28% optimize.loop_unroll : 0.000715s : 4.67% optimize.opt_after_cconv.c_1 : 0.000069s : 0.45% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.04% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.08% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.03% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.03% optimize.opt_after_cconv.cse : 0.000059s : 0.39% optimize.opt_after_cconv.renormalize : 0.000001s : 0.01% optimize.remove_dup_value : 0.000075s : 0.49% optimize.tuple_transform.d_1 : 0.000109s : 0.71% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000016s : 0.10% optimize.partial_unused_args_eliminate : 0.000002s : 0.02% optimize.add_recomputation : 0.000115s : 0.75% optimize.cse_after_recomputation.cse : 0.000037s : 0.24% optimize.environ_conv : 0.000010s : 0.07% optimize.swap_dp_allreduce_reducescatter : 0.000012s : 0.08% optimize.bias_add_comm_swap : 0.000004s : 0.03% optimize.label_micro_interleaved_index : 0.000008s : 0.05% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.02% optimize.merge_cast_opt : 0.000002s : 0.01% optimize.slice_recompute_activation : 0.000003s : 0.02% optimize.micro_interleaved_order_control : 0.000003s : 0.02% optimize.assign_add_opt : 0.000002s : 0.01% optimize.ForceFp32Comm : 0.000001s : 0.01% optimize.remove_cast_before_assign_add : 0.000001s : 0.01% optimize.full_micro_interleaved_order_control : 0.000004s : 0.02% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.02% optimize.comm_op_add_attrs : 0.000001s : 0.01% optimize.add_comm_op_reuse_tag : 0.000002s : 0.01% optimize.interleave_split_concat_branches : 0.000001s : 0.01% optimize.interleave_parallel_branches : 0.000001s : 0.01% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000003s : 0.02% optimize.control_data_broadcast_order : 0.000030s : 0.19% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000006s : 0.04% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.05% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.01% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.01% optimize.overlap_recompute_comm : 0.000003s : 0.02% optimize.overlap_grad_ring_attention : 0.000007s : 0.04% optimize.overlap_grad_flash_sp : 0.000030s : 0.19% optimize.begin_end_overlap_inline : 0.000001s : 0.01% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.02% optimize.split_layernorm_comm : 0.000002s : 0.02% optimize.handle_group_info : 0.000001s : 0.01% optimize.symbol_engine_optimizer.build : 0.000106s : 0.69% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000027s : 0.18% optimize.symbol_engine_optimizer.elim_not_effective : 0.000027s : 0.18% optimize.symbol_engine_optimizer.opt_reshape : 0.000015s : 0.09% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000025s : 0.17% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.02% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000034s : 0.22% get_jit_bprop_graph : 0.000003s : 0.02% rewriter_after_jit_bprop_graph : 0.000007s : 0.04% opt_after_jit_grad : 0.000866s : 5.65% validate : 0.000081s : 0.53% Time group info: ------[substitution.] 0.000200 39 2.58% : 0.000005s : 2: substitution.elim_not_effective 4.68% : 0.000009s : 2: substitution.fold_const_symbol 5.16% : 0.000010s : 10: substitution.graph_param_transform 73.41% : 0.000147s : 1: substitution.inline 2.85% : 0.000006s : 4: substitution.j_node_and_user_rematch 3.61% : 0.000007s : 4: substitution.remove_not_recompute_node 7.71% : 0.000015s : 16: substitution.replace_old_param ------[type_inference.] 0.006285 2 88.21% : 0.005544s : 1: type_inference.infer 11.79% : 0.000741s : 1: type_inference.specialize ------[replace.] 0.000026 1 100.00% : 0.000026s : 1: replace.inline ------[match.] 0.000144 1 100.00% : 0.000144s : 1: match.inline ------[predicate.] 0.000352 2335 0.83% : 0.000003s : 21: predicate.accumulaten_eliminater 1.14% : 0.000004s : 10: predicate.ad_related_special_op_eliminate 0.72% : 0.000003s : 20: predicate.addn_check_dump 0.87% : 0.000003s : 21: predicate.addn_zero_filter 0.74% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 1.75% : 0.000006s : 41: predicate.arithmetic_simplify 0.79% : 0.000003s : 21: predicate.cast_eliminate 0.73% : 0.000003s : 20: predicate.check_bprop_eliminate 0.70% : 0.000002s : 20: predicate.compare_switch_simplify 0.27% : 0.000001s : 10: predicate.const_output_eliminate 0.79% : 0.000003s : 20: predicate.depend_value_elim 0.95% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.81% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.93% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.49% : 0.000005s : 20: predicate.dumpgradient_eliminate 0.40% : 0.000001s : 10: predicate.elim_not_effective 0.63% : 0.000002s : 10: predicate.elim_shapecalc_of_broadcastargs 1.23% : 0.000004s : 31: predicate.environ_add_const_eliminate 1.17% : 0.000004s : 31: predicate.environ_get_add_eliminate 1.24% : 0.000004s : 31: predicate.environ_get_depend_swap 1.94% : 0.000007s : 51: predicate.environ_get_eliminate 1.07% : 0.000004s : 31: predicate.environ_get_set_eliminate 0.91% : 0.000003s : 22: predicate.exchange_switch_depend_value 1.38% : 0.000005s : 22: predicate.float_depend_g_call 0.72% : 0.000003s : 20: predicate.float_environ_get_switch 1.15% : 0.000004s : 30: predicate.float_tuple_getitem_switch 0.28% : 0.000001s : 10: predicate.fold_const_symbol 0.92% : 0.000003s : 20: predicate.get_grad_eliminate 0.42% : 0.000001s : 10: predicate.graph_param_transform 0.80% : 0.000003s : 20: predicate.incorporate_call 0.63% : 0.000002s : 20: predicate.incorporate_call_switch 5.45% : 0.000019s : 103: predicate.inline 1.04% : 0.000004s : 20: predicate.inline_without_move 0.51% : 0.000002s : 20: predicate.j_node_and_user_rematch 1.12% : 0.000004s : 20: predicate.less_batch_normalization 1.80% : 0.000006s : 41: predicate.list_to_tuple_eliminator_ 2.25% : 0.000008s : 62: predicate.load_eliminater 1.22% : 0.000004s : 10: predicate.loop_unroll_after_grad 1.36% : 0.000005s : 31: predicate.loop_unroll_before_grad 1.75% : 0.000006s : 41: predicate.make_slice_get_slice_eliminator 0.88% : 0.000003s : 20: predicate.merge_addn 0.81% : 0.000003s : 20: predicate.micro_step_allgather_replace 0.72% : 0.000003s : 20: predicate.mini_step_allgather_replace 0.82% : 0.000003s : 21: predicate.minmaximum_grad 1.62% : 0.000006s : 10: predicate.mutable_eliminate 0.49% : 0.000002s : 10: predicate.opt_reshape 0.42% : 0.000001s : 10: predicate.parallel_virtual_node 1.14% : 0.000004s : 22: predicate.partial_defer_inline 1.18% : 0.000004s : 31: predicate.partial_eliminate 0.88% : 0.000003s : 21: predicate.print_const_string_wrapper 0.81% : 0.000003s : 20: predicate.reduce_all_const_elim 1.07% : 0.000004s : 21: predicate.reduce_eliminate 2.16% : 0.000008s : 62: predicate.redundant_stop_gradient_eliminater 0.68% : 0.000002s : 20: predicate.remove_not_recompute_node 1.51% : 0.000005s : 41: predicate.replace_applicator 0.63% : 0.000002s : 20: predicate.replace_old_param 0.46% : 0.000002s : 10: predicate.reset_defer_inline 0.84% : 0.000003s : 21: predicate.reshape_eliminate 0.95% : 0.000003s : 20: predicate.row_tensor_add_zeros_like 0.62% : 0.000002s : 10: predicate.row_tensor_eliminate 1.10% : 0.000004s : 20: predicate.same_eliminate 0.76% : 0.000003s : 20: predicate.set_cell_output_no_recompute 1.28% : 0.000005s : 20: predicate.shard_identity_eliminate 0.97% : 0.000003s : 20: predicate.special_op_eliminate 0.76% : 0.000003s : 20: predicate.specialize_transform 1.20% : 0.000004s : 20: predicate.split_environ_get_set_with_tuple_value 1.08% : 0.000004s : 20: predicate.stack_unstack_eliminate 0.42% : 0.000001s : 10: predicate.switch_call_monad_eliminater 1.13% : 0.000004s : 22: predicate.switch_defer_inline 1.46% : 0.000005s : 42: predicate.switch_layer_defer_inline 3.53% : 0.000012s : 83: predicate.switch_simplify 0.88% : 0.000003s : 21: predicate.tile_eliminate 0.75% : 0.000003s : 21: predicate.transpose_eliminate 1.57% : 0.000006s : 41: predicate.tuple_list_convert_item_index_to_positive 1.65% : 0.000006s : 41: predicate.tuple_list_get_item_const_eliminator 1.64% : 0.000006s : 41: predicate.tuple_list_get_item_depend_reorder 2.72% : 0.000010s : 61: predicate.tuple_list_get_item_eliminator 1.37% : 0.000005s : 41: predicate.tuple_list_get_set_item_eliminator 2.13% : 0.000008s : 61: predicate.tuple_list_set_item_eliminator 1.84% : 0.000006s : 41: predicate.tuple_to_list_eliminator_ 2.04% : 0.000007s : 62: predicate.updatestate_pure_node_eliminater 3.05% : 0.000011s : 82: predicate.updatestate_useless_node_eliminater 0.41% : 0.000001s : 10: predicate.value_based_eliminate 0.81% : 0.000003s : 20: predicate.virtual_dataset_eliminate 0.96% : 0.000003s : 20: predicate.virtual_output_eliminate 0.46% : 0.000002s : 10: predicate.virtual_view_grad_eliminate 0.45% : 0.000002s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000832 6 50.32% : 0.000419s : 3: func_graph_cloner_run.FuncGraphClonerGraph 49.68% : 0.000413s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.407665 192 0.00% : 0.000004s : 1: ForceFp32Comm 46.50% : 0.189566s : 1: add_attr 46.50% : 0.189544s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.03% : 0.000124s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000075s : 1: auto_monad 0.01% : 0.000041s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.19% : 0.000775s : 1: bootstrap 0.01% : 0.000048s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.01% : 0.000035s : 1: control_data_broadcast_order 0.01% : 0.000029s : 1: convert_after_rewriter 0.01% : 0.000057s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000015s : 1: environ_conv 0.01% : 0.000027s : 1: event_method 0.00% : 0.000007s : 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% : 0.000005s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000008s : 1: label_fine_grained_interleaved_index 0.00% : 0.000011s : 1: label_micro_interleaved_index 0.18% : 0.000734s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000007s : 1: micro_interleaved_order_control 0.23% : 0.000956s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.01% : 0.000031s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000034s : 1: opt.transform.mutable_eliminate 0.46% : 0.001867s : 78: opt.transform.opt_a 0.02% : 0.000067s : 1: opt.transform.opt_after_cconv 0.01% : 0.000058s : 1: opt.transform.opt_after_jit_grad 0.06% : 0.000243s : 28: opt.transform.opt_b 0.03% : 0.000120s : 2: opt.transform.opt_trans_graph 0.02% : 0.000088s : 4: opt.transform.symbol_engine_opt 1.10% : 0.004472s : 1: opt_a 0.06% : 0.000225s : 1: opt_after_cconv 0.22% : 0.000889s : 1: opt_after_jit_grad 0.11% : 0.000461s : 1: opt_b 2.04% : 0.008322s : 1: optimize 0.01% : 0.000039s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000014s : 1: order_py_execute_after_rewriter 0.01% : 0.000035s : 1: overlap_grad_flash_sp 0.00% : 0.000010s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000016s : 1: overlap_grad_ring_attention 0.00% : 0.000008s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000005s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000008s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000005s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000045s : 1: pre_auto_parallel 0.01% : 0.000039s : 1: py_interpret_to_execute 0.01% : 0.000032s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.02% : 0.000080s : 1: remove_dup_value 0.15% : 0.000595s : 1: renormalize.infer 0.13% : 0.000530s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000082s : 1: rewriter_after_opt_a 0.02% : 0.000093s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000009s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000017s : 1: swap_dp_allreduce_reducescatter 0.07% : 0.000268s : 1: symbol_engine_optimizer 0.04% : 0.000173s : 1: tuple_transform 1.58% : 0.006430s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_with_anti_shape[QuantMethod.FP16_VEC-1] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_with_anti_shape[QuantMethod.FP16_VEC-1],max_mem:684.0M [WARNING] ME(167181:281473318440752,MainProcess):2026-01-29-17:39:50.609.7 [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 = 0.264252, [21] [bootstrap]: 0.00068877 [type_inference]: 0.00614725 [event_method]: 2.02e-05 [auto_monad]: 6.299e-05 [graph_reusing]: 6.12001e-06 [inline]: 4.12e-06 [add_attr]: 0.00511473, [1] [add_attr_with_inline]: 0.00509723, [1] [Cycle 1]: 7.895e-05, [2] [tag_attr]: 2.322e-05 [meta_addattr_fg_expand]: 4.57e-06 [parallel-infer-symbol]: 3.85e-06 [pre_auto_parallel]: 4.469e-05 [insert-virtual-dataset]: 3.50003e-06 [parallel-infer-symbol-second]: 8.09989e-07 [dataset_repeat_opt]: 2.98998e-06 [pipeline_split]: 1.99e-06 [optimize]: 0.251266, [53] [py_interpret_to_execute]: 3.449e-05 [rewriter_before_opt_a]: 8.359e-05 [opt_a]: 0.247828, [2] [Cycle 1]: 0.246501, [45] [expand_dump_flag]: 3.23998e-06 [switch_simplify]: 3.785e-05 [loop_unroll]: 2.345e-05 [a_1]: 0.00054809 [with_stream_mark]: 3.021e-05 [recompute_prepare]: 1.873e-05 [updatestate_depend_eliminate]: 7.52002e-06 [updatestate_assign_eliminate]: 5.57999e-06 [updatestate_loads_eliminate]: 4.85001e-06 [parameter_eliminate]: 2.68e-06 [a_2]: 0.00018105 [accelerated_algorithm]: 1.436e-05 [shard]: 3.53999e-06 [meta_shard_fg_expand]: 2.39001e-06 [shard_inline]: 1.248e-05 [merge_send_recv]: 1.173e-05 [auto_parallel]: 1.029e-05 [parallel]: 3.74e-05 [flash_sp]: 1.197e-05 [merge_comm]: 6.05002e-06 [allreduce_fusion]: 5.54e-06 [matmul_add_comm_reduction]: 1.433e-05 [allreduce_slice_to_reducescatter]: 9.70002e-07 [virtual_shard_identity]: 1.721e-05 [virtual_dataset]: 1.254e-05 [get_grad_eliminate_]: 1.201e-05 [virtual_output]: 1.24e-05 [merge_forward]: 6.93e-06 [cell_reuse_recompute_pass]: 1.90001e-06 [offload_activation]: 1.4e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.479e-05 [merge_recompute_call_nodes]: 1.62999e-06 [before_grad]: 1.853e-05 [set_forward_comm_id_for_comm_node_pass]: 7.1e-06 [meta_fg_expand]: 3.92998e-06 [flash_sp_send_recv_attached]: 3.30003e-06 [receive_attached]: 2.56e-06 [after_resolve]: 2.946e-05 [a_after_grad]: 1.9e-05 [renormalize]: 0.244727 [add_forward_monad_depend]: 1.529e-05 [auto_monad_grad]: 2.95002e-06 [auto_monad_eliminator]: 2.883e-05 [cse]: 8.548e-05 [a_3]: 0.00011517 [Cycle 2]: 0.0013122, [45] [expand_dump_flag]: 2.56998e-06 [switch_simplify]: 1.727e-05 [loop_unroll]: 1.372e-05 [a_1]: 0.00033828 [with_stream_mark]: 2.709e-05 [recompute_prepare]: 1.515e-05 [updatestate_depend_eliminate]: 6.77002e-06 [updatestate_assign_eliminate]: 5.29e-06 [updatestate_loads_eliminate]: 6.33e-06 [parameter_eliminate]: 2.04e-06 [a_2]: 0.00016104 [accelerated_algorithm]: 1.381e-05 [shard]: 3.55e-06 [meta_shard_fg_expand]: 3.63e-06 [shard_inline]: 1.176e-05 [merge_send_recv]: 1.316e-05 [auto_parallel]: 1.251e-05 [parallel]: 1.059e-05 [flash_sp]: 4.37e-06 [merge_comm]: 5.46002e-06 [allreduce_fusion]: 5.84e-06 [matmul_add_comm_reduction]: 1.255e-05 [allreduce_slice_to_reducescatter]: 1.00999e-06 [virtual_shard_identity]: 1.518e-05 [virtual_dataset]: 1.306e-05 [get_grad_eliminate_]: 1.196e-05 [virtual_output]: 1.279e-05 [merge_forward]: 7.33e-06 [cell_reuse_recompute_pass]: 4.17e-06 [offload_activation]: 1.559e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.694e-05 [merge_recompute_call_nodes]: 2.06e-06 [before_grad]: 1.838e-05 [set_forward_comm_id_for_comm_node_pass]: 5.77999e-06 [meta_fg_expand]: 4.47e-06 [flash_sp_send_recv_attached]: 2.34999e-06 [receive_attached]: 3.11999e-06 [after_resolve]: 3.055e-05 [a_after_grad]: 2.034e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 2.56998e-06 [auto_monad_grad]: 2.09e-06 [auto_monad_eliminator]: 1.299e-05 [cse]: 5.558e-05 [a_3]: 8.449e-05 [py_interpret_to_execute_after_opt_a]: 2.935e-05 [slice_cell_reuse_recomputed_activation]: 3.04999e-06 [rewriter_after_opt_a]: 6.852e-05 [convert_after_rewriter]: 1.154e-05 [order_py_execute_after_rewriter]: 7.45003e-06 [mutable_eliminate]: 0.00090005 [opt_b]: 0.00042851, [1] [Cycle 1]: 0.00041897, [7] [b_1]: 0.00026445 [b_2]: 1.417e-05 [updatestate_depend_eliminate]: 1.275e-05 [updatestate_assign_eliminate]: 5.40001e-06 [updatestate_loads_eliminate]: 4.82e-06 [renormalize]: 8.70001e-07 [cse]: 7.012e-05 [optimize_parallel_all_gather_comm]: 2.87e-05 [overlap_param_gather]: 6.20002e-06 [cconv]: 4.167e-05 [loop_unroll]: 0.00061934 [opt_after_cconv]: 0.00020277, [1] [Cycle 1]: 0.00019375, [7] [c_1]: 6.934e-05 [parameter_eliminate]: 6.96001e-06 [updatestate_depend_eliminate]: 9.93998e-06 [updatestate_assign_eliminate]: 4.68999e-06 [updatestate_loads_eliminate]: 4.52e-06 [cse]: 5.616e-05 [renormalize]: 9.39996e-07 [remove_dup_value]: 7.693e-05 [tuple_transform]: 0.00014565, [1] [Cycle 1]: 0.00013902, [4] [d_1]: 0.00010021 [none_parameter_eliminate]: 2.17999e-06 [renormalize]: 2.29978e-07 [switch_simplify]: 1.387e-05 [partial_unused_args_eliminate]: 2.26e-06 [add_recomputation]: 7.369e-05 [cse_after_recomputation]: 3.819e-05, [1] [Cycle 1]: 3.262e-05, [1] [cse]: 2.538e-05 [environ_conv]: 9.74999e-06 [swap_dp_allreduce_reducescatter]: 8.03001e-06 [bias_add_comm_swap]: 4.24002e-06 [label_micro_interleaved_index]: 7.11001e-06 [label_fine_grained_interleaved_index]: 3.36999e-06 [merge_cast_opt]: 1.76e-06 [slice_recompute_activation]: 2.37001e-06 [micro_interleaved_order_control]: 3.39001e-06 [assign_add_opt]: 1.36002e-06 [ForceFp32Comm]: 9.20001e-07 [remove_cast_before_assign_add]: 1.19e-06 [full_micro_interleaved_order_control]: 2.53e-06 [reorder_send_recv_between_fp_bp]: 3.58999e-06 [comm_op_add_attrs]: 1.15999e-06 [add_comm_op_reuse_tag]: 1.87999e-06 [interleave_split_concat_branches]: 1.60999e-06 [interleave_parallel_branches]: 1.34998e-06 [overlap_opt_shard_in_pipeline]: 4.92e-06 [overlap_opt_shard_grad_in_pipeline]: 2.54001e-06 [control_data_broadcast_order]: 1.924e-05 [grouped_pairwise_exchange_alltoall]: 1.77999e-06 [offloading_packed_experts]: 5.16002e-06 [overlap_recompute_and_grad_model_parallel]: 6.43e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.39998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.63002e-06 [overlap_recompute_comm]: 3.06999e-06 [overlap_grad_ring_attention]: 5.74e-06 [overlap_grad_flash_sp]: 2.726e-05 [begin_end_overlap_inline]: 6.09987e-07 [split_matmul_comm_elemetwise]: 2.38002e-06 [split_layernorm_comm]: 1.82001e-06 [handle_group_info]: 1.13001e-06 [symbol_engine_optimizer]: 0.00021841, [1] [Cycle 1]: 0.00021343, [6] [build]: 9.626e-05 [elim_shapecalc]: 1.876e-05 [elim_not_effective]: 2.251e-05 [opt_reshape]: 1.272e-05 [fold_const_symbol]: 2.473e-05 [renormalize]: 2.19996e-07 [detach_backward]: 2.88e-06 [pipeline_parallel_scheduler]: 2.13002e-06 [auto_monad_reorder]: 2.651e-05 [get_jit_bprop_graph]: 2.58e-06 [rewriter_after_jit_bprop_graph]: 6.58998e-06 [opt_after_jit_grad]: 0.00060062 [validate]: 6.007e-05 Sums bootstrap : 0.000689s : 0.27% type_inference : 0.006147s : 2.38% event_method : 0.000020s : 0.01% auto_monad : 0.000063s : 0.02% graph_reusing : 0.000006s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000023s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000045s : 0.02% insert-virtual-dataset : 0.000004s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000034s : 0.01% optimize.rewriter_before_opt_a : 0.000084s : 0.03% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000055s : 0.02% optimize.opt_a.loop_unroll : 0.000037s : 0.01% optimize.opt_a.a_1 : 0.000886s : 0.34% optimize.opt_a.with_stream_mark : 0.000057s : 0.02% optimize.opt_a.recompute_prepare : 0.000034s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000014s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000011s : 0.00% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000342s : 0.13% optimize.opt_a.accelerated_algorithm : 0.000028s : 0.01% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000006s : 0.00% optimize.opt_a.shard_inline : 0.000024s : 0.01% optimize.opt_a.merge_send_recv : 0.000025s : 0.01% optimize.opt_a.auto_parallel : 0.000023s : 0.01% optimize.opt_a.parallel : 0.000048s : 0.02% optimize.opt_a.flash_sp : 0.000016s : 0.01% optimize.opt_a.merge_comm : 0.000012s : 0.00% optimize.opt_a.allreduce_fusion : 0.000011s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000027s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000032s : 0.01% optimize.opt_a.virtual_dataset : 0.000026s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000024s : 0.01% optimize.opt_a.virtual_output : 0.000025s : 0.01% optimize.opt_a.merge_forward : 0.000014s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000030s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000052s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000037s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000013s : 0.00% optimize.opt_a.meta_fg_expand : 0.000008s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.00% optimize.opt_a.receive_attached : 0.000006s : 0.00% optimize.opt_a.after_resolve : 0.000060s : 0.02% optimize.opt_a.a_after_grad : 0.000039s : 0.02% optimize.opt_a.renormalize : 0.244727s : 94.90% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000042s : 0.02% optimize.opt_a.cse : 0.000141s : 0.05% optimize.opt_a.a_3 : 0.000200s : 0.08% optimize.py_interpret_to_execute_after_opt_a : 0.000029s : 0.01% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000069s : 0.03% optimize.convert_after_rewriter : 0.000012s : 0.00% optimize.order_py_execute_after_rewriter : 0.000007s : 0.00% optimize.mutable_eliminate : 0.000900s : 0.35% optimize.opt_b.b_1 : 0.000264s : 0.10% optimize.opt_b.b_2 : 0.000014s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.00% 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 : 0.000070s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000029s : 0.01% optimize.overlap_param_gather : 0.000006s : 0.00% optimize.cconv : 0.000042s : 0.02% optimize.loop_unroll : 0.000619s : 0.24% optimize.opt_after_cconv.c_1 : 0.000069s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000056s : 0.02% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000077s : 0.03% optimize.tuple_transform.d_1 : 0.000100s : 0.04% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000014s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000074s : 0.03% optimize.cse_after_recomputation.cse : 0.000025s : 0.01% optimize.environ_conv : 0.000010s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000007s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000004s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000002s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000005s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000003s : 0.00% optimize.control_data_broadcast_order : 0.000019s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000005s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 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 : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000027s : 0.01% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000096s : 0.04% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000019s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000023s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000013s : 0.00% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000025s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000027s : 0.01% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000007s : 0.00% opt_after_jit_grad : 0.000601s : 0.23% validate : 0.000060s : 0.02% Time group info: ------[substitution.] 0.000180 39 2.54% : 0.000005s : 2: substitution.elim_not_effective 5.17% : 0.000009s : 2: substitution.fold_const_symbol 5.50% : 0.000010s : 10: substitution.graph_param_transform 72.50% : 0.000130s : 1: substitution.inline 2.79% : 0.000005s : 4: substitution.j_node_and_user_rematch 3.40% : 0.000006s : 4: substitution.remove_not_recompute_node 8.11% : 0.000015s : 16: substitution.replace_old_param ------[type_inference.] 0.006036 2 88.79% : 0.005359s : 1: type_inference.infer 11.21% : 0.000677s : 1: type_inference.specialize ------[replace.] 0.000023 1 100.00% : 0.000023s : 1: replace.inline ------[match.] 0.000129 1 100.00% : 0.000129s : 1: match.inline ------[predicate.] 0.000321 2335 0.86% : 0.000003s : 21: predicate.accumulaten_eliminater 0.78% : 0.000003s : 10: predicate.ad_related_special_op_eliminate 0.76% : 0.000002s : 20: predicate.addn_check_dump 0.91% : 0.000003s : 21: predicate.addn_zero_filter 0.76% : 0.000002s : 21: predicate.adjust_all_reduce_mul_add 1.86% : 0.000006s : 41: predicate.arithmetic_simplify 0.85% : 0.000003s : 21: predicate.cast_eliminate 0.98% : 0.000003s : 20: predicate.check_bprop_eliminate 0.73% : 0.000002s : 20: predicate.compare_switch_simplify 0.30% : 0.000001s : 10: predicate.const_output_eliminate 0.76% : 0.000002s : 20: predicate.depend_value_elim 0.83% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.89% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.81% : 0.000003s : 21: predicate.dict_set_item_eliminator 0.98% : 0.000003s : 20: predicate.dumpgradient_eliminate 0.35% : 0.000001s : 10: predicate.elim_not_effective 0.53% : 0.000002s : 10: predicate.elim_shapecalc_of_broadcastargs 1.24% : 0.000004s : 31: predicate.environ_add_const_eliminate 1.22% : 0.000004s : 31: predicate.environ_get_add_eliminate 1.11% : 0.000004s : 31: predicate.environ_get_depend_swap 1.97% : 0.000006s : 51: predicate.environ_get_eliminate 1.18% : 0.000004s : 31: predicate.environ_get_set_eliminate 0.83% : 0.000003s : 22: predicate.exchange_switch_depend_value 1.56% : 0.000005s : 22: predicate.float_depend_g_call 0.73% : 0.000002s : 20: predicate.float_environ_get_switch 1.20% : 0.000004s : 30: predicate.float_tuple_getitem_switch 0.31% : 0.000001s : 10: predicate.fold_const_symbol 0.87% : 0.000003s : 20: predicate.get_grad_eliminate 0.52% : 0.000002s : 10: predicate.graph_param_transform 0.73% : 0.000002s : 20: predicate.incorporate_call 0.67% : 0.000002s : 20: predicate.incorporate_call_switch 5.38% : 0.000017s : 103: predicate.inline 0.98% : 0.000003s : 20: predicate.inline_without_move 0.57% : 0.000002s : 20: predicate.j_node_and_user_rematch 1.02% : 0.000003s : 20: predicate.less_batch_normalization 1.92% : 0.000006s : 41: predicate.list_to_tuple_eliminator_ 2.43% : 0.000008s : 62: predicate.load_eliminater 0.96% : 0.000003s : 10: predicate.loop_unroll_after_grad 1.35% : 0.000004s : 31: predicate.loop_unroll_before_grad 1.74% : 0.000006s : 41: predicate.make_slice_get_slice_eliminator 0.79% : 0.000003s : 20: predicate.merge_addn 0.79% : 0.000003s : 20: predicate.micro_step_allgather_replace 0.88% : 0.000003s : 20: predicate.mini_step_allgather_replace 0.74% : 0.000002s : 21: predicate.minmaximum_grad 1.15% : 0.000004s : 10: predicate.mutable_eliminate 0.44% : 0.000001s : 10: predicate.opt_reshape 0.41% : 0.000001s : 10: predicate.parallel_virtual_node 0.98% : 0.000003s : 22: predicate.partial_defer_inline 1.27% : 0.000004s : 31: predicate.partial_eliminate 0.86% : 0.000003s : 21: predicate.print_const_string_wrapper 0.83% : 0.000003s : 20: predicate.reduce_all_const_elim 1.01% : 0.000003s : 21: predicate.reduce_eliminate 2.33% : 0.000007s : 62: predicate.redundant_stop_gradient_eliminater 0.83% : 0.000003s : 20: predicate.remove_not_recompute_node 1.88% : 0.000006s : 41: predicate.replace_applicator 0.81% : 0.000003s : 20: predicate.replace_old_param 0.34% : 0.000001s : 10: predicate.reset_defer_inline 0.84% : 0.000003s : 21: predicate.reshape_eliminate 0.84% : 0.000003s : 20: predicate.row_tensor_add_zeros_like 0.52% : 0.000002s : 10: predicate.row_tensor_eliminate 1.05% : 0.000003s : 20: predicate.same_eliminate 0.67% : 0.000002s : 20: predicate.set_cell_output_no_recompute 0.94% : 0.000003s : 20: predicate.shard_identity_eliminate 0.85% : 0.000003s : 20: predicate.special_op_eliminate 0.82% : 0.000003s : 20: predicate.specialize_transform 1.22% : 0.000004s : 20: predicate.split_environ_get_set_with_tuple_value 0.94% : 0.000003s : 20: predicate.stack_unstack_eliminate 0.48% : 0.000002s : 10: predicate.switch_call_monad_eliminater 0.87% : 0.000003s : 22: predicate.switch_defer_inline 1.76% : 0.000006s : 42: predicate.switch_layer_defer_inline 3.78% : 0.000012s : 83: predicate.switch_simplify 0.84% : 0.000003s : 21: predicate.tile_eliminate 0.84% : 0.000003s : 21: predicate.transpose_eliminate 1.46% : 0.000005s : 41: predicate.tuple_list_convert_item_index_to_positive 1.54% : 0.000005s : 41: predicate.tuple_list_get_item_const_eliminator 1.44% : 0.000005s : 41: predicate.tuple_list_get_item_depend_reorder 3.03% : 0.000010s : 61: predicate.tuple_list_get_item_eliminator 1.56% : 0.000005s : 41: predicate.tuple_list_get_set_item_eliminator 2.55% : 0.000008s : 61: predicate.tuple_list_set_item_eliminator 1.93% : 0.000006s : 41: predicate.tuple_to_list_eliminator_ 2.23% : 0.000007s : 62: predicate.updatestate_pure_node_eliminater 3.20% : 0.000010s : 82: predicate.updatestate_useless_node_eliminater 0.43% : 0.000001s : 10: predicate.value_based_eliminate 0.89% : 0.000003s : 20: predicate.virtual_dataset_eliminate 0.87% : 0.000003s : 20: predicate.virtual_output_eliminate 0.35% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.49% : 0.000002s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000767 6 43.36% : 0.000332s : 3: func_graph_cloner_run.FuncGraphClonerGraph 56.64% : 0.000434s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.767560 192 0.00% : 0.000004s : 1: ForceFp32Comm 0.67% : 0.005121s : 1: add_attr 0.66% : 0.005102s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.01% : 0.000079s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000069s : 1: auto_monad 0.00% : 0.000031s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.09% : 0.000724s : 1: bootstrap 0.01% : 0.000046s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.00% : 0.000023s : 1: control_data_broadcast_order 0.00% : 0.000016s : 1: convert_after_rewriter 0.01% : 0.000041s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000013s : 1: environ_conv 0.00% : 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% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000008s : 1: label_fine_grained_interleaved_index 0.00% : 0.000010s : 1: label_micro_interleaved_index 0.08% : 0.000632s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000007s : 1: micro_interleaved_order_control 0.12% : 0.000916s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.00% : 0.000025s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000032s : 1: opt.transform.mutable_eliminate 0.23% : 0.001783s : 78: opt.transform.opt_a 0.01% : 0.000068s : 1: opt.transform.opt_after_cconv 0.01% : 0.000044s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000245s : 28: opt.transform.opt_b 0.01% : 0.000112s : 2: opt.transform.opt_trans_graph 0.01% : 0.000075s : 4: opt.transform.symbol_engine_opt 32.29% : 0.247833s : 1: opt_a 0.03% : 0.000207s : 1: opt_after_cconv 0.08% : 0.000614s : 1: opt_after_jit_grad 0.06% : 0.000433s : 1: opt_b 32.74% : 0.251272s : 1: optimize 0.00% : 0.000033s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.00% : 0.000031s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 1: overlap_grad_ring_attention 0.00% : 0.000013s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000008s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000010s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000007s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.01% : 0.000049s : 1: pre_auto_parallel 0.01% : 0.000039s : 1: py_interpret_to_execute 0.00% : 0.000034s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000083s : 1: remove_dup_value 31.80% : 0.244070s : 1: renormalize.infer 0.08% : 0.000635s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.01% : 0.000075s : 1: rewriter_after_opt_a 0.01% : 0.000090s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000005s : 1: split_matmul_comm_elemetwise 0.00% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.03% : 0.000221s : 1: symbol_engine_optimizer 0.02% : 0.000149s : 1: tuple_transform 0.80% : 0.006173s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_with_anti_shape[QuantMethod.INT_CUBE-0] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_with_anti_shape[QuantMethod.INT_CUBE-0],max_mem:684.0M [WARNING] ME(167181:281473318440752,MainProcess):2026-01-29-17:40:53.491.872 [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 = 0.171428, [21] [bootstrap]: 0.00076788 [type_inference]: 0.0065241 [event_method]: 1.581e-05 [auto_monad]: 6.123e-05 [graph_reusing]: 5.20001e-06 [inline]: 2.69999e-06 [add_attr]: 0.00521653, [1] [add_attr_with_inline]: 0.00519914, [1] [Cycle 1]: 7.259e-05, [2] [tag_attr]: 2.521e-05 [meta_addattr_fg_expand]: 4.12e-06 [parallel-infer-symbol]: 3.51001e-06 [pre_auto_parallel]: 4.68e-05 [insert-virtual-dataset]: 3.13e-06 [parallel-infer-symbol-second]: 7.89994e-07 [dataset_repeat_opt]: 2.54001e-06 [pipeline_split]: 1.84998e-06 [optimize]: 0.157491, [53] [py_interpret_to_execute]: 3.489e-05 [rewriter_before_opt_a]: 8.044e-05 [opt_a]: 0.00410561, [2] [Cycle 1]: 0.00284227, [45] [expand_dump_flag]: 3.25e-06 [switch_simplify]: 3.635e-05 [loop_unroll]: 2.283e-05 [a_1]: 0.00056203 [with_stream_mark]: 2.997e-05 [recompute_prepare]: 1.464e-05 [updatestate_depend_eliminate]: 5.99e-06 [updatestate_assign_eliminate]: 5.23002e-06 [updatestate_loads_eliminate]: 5.04e-06 [parameter_eliminate]: 2.11e-06 [a_2]: 0.00016461 [accelerated_algorithm]: 1.358e-05 [shard]: 3.10998e-06 [meta_shard_fg_expand]: 2.77002e-06 [shard_inline]: 1.212e-05 [merge_send_recv]: 1.215e-05 [auto_parallel]: 9.69e-06 [parallel]: 3.598e-05 [flash_sp]: 1.292e-05 [merge_comm]: 6.94999e-06 [allreduce_fusion]: 5.94e-06 [matmul_add_comm_reduction]: 1.232e-05 [allreduce_slice_to_reducescatter]: 6.80011e-07 [virtual_shard_identity]: 1.585e-05 [virtual_dataset]: 1.303e-05 [get_grad_eliminate_]: 1.19e-05 [virtual_output]: 1.23e-05 [merge_forward]: 6.01e-06 [cell_reuse_recompute_pass]: 1.64e-06 [offload_activation]: 1.305e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.254e-05 [merge_recompute_call_nodes]: 1.67001e-06 [before_grad]: 1.71e-05 [set_forward_comm_id_for_comm_node_pass]: 5.89e-06 [meta_fg_expand]: 4.08001e-06 [flash_sp_send_recv_attached]: 2.94001e-06 [receive_attached]: 3.06999e-06 [after_resolve]: 2.847e-05 [a_after_grad]: 1.936e-05 [renormalize]: 0.00116662 [add_forward_monad_depend]: 8.04002e-06 [auto_monad_grad]: 3.09001e-06 [auto_monad_eliminator]: 2.194e-05 [cse]: 7.89e-05 [a_3]: 9.946e-05 [Cycle 2]: 0.00124858, [45] [expand_dump_flag]: 2.10002e-06 [switch_simplify]: 1.616e-05 [loop_unroll]: 1.318e-05 [a_1]: 0.00032777 [with_stream_mark]: 2.283e-05 [recompute_prepare]: 1.397e-05 [updatestate_depend_eliminate]: 6.78e-06 [updatestate_assign_eliminate]: 5.29e-06 [updatestate_loads_eliminate]: 5.99999e-06 [parameter_eliminate]: 1.54998e-06 [a_2]: 0.000159 [accelerated_algorithm]: 1.288e-05 [shard]: 2.28002e-06 [meta_shard_fg_expand]: 3.24001e-06 [shard_inline]: 1.205e-05 [merge_send_recv]: 1.083e-05 [auto_parallel]: 1.107e-05 [parallel]: 8.75001e-06 [flash_sp]: 4.30999e-06 [merge_comm]: 5.67999e-06 [allreduce_fusion]: 5.56e-06 [matmul_add_comm_reduction]: 1.169e-05 [allreduce_slice_to_reducescatter]: 1.00001e-06 [virtual_shard_identity]: 1.484e-05 [virtual_dataset]: 1.262e-05 [get_grad_eliminate_]: 1.223e-05 [virtual_output]: 1.218e-05 [merge_forward]: 5.79e-06 [cell_reuse_recompute_pass]: 2.64999e-06 [offload_activation]: 1.309e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.505e-05 [merge_recompute_call_nodes]: 1.21002e-06 [before_grad]: 1.697e-05 [set_forward_comm_id_for_comm_node_pass]: 6.03998e-06 [meta_fg_expand]: 3.92998e-06 [flash_sp_send_recv_attached]: 1.52001e-06 [receive_attached]: 2.62001e-06 [after_resolve]: 2.816e-05 [a_after_grad]: 2.034e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 2.01e-06 [auto_monad_grad]: 2.42001e-06 [auto_monad_eliminator]: 1.37e-05 [cse]: 5.706e-05 [a_3]: 7.825e-05 [py_interpret_to_execute_after_opt_a]: 2.635e-05 [slice_cell_reuse_recomputed_activation]: 2.81e-06 [rewriter_after_opt_a]: 7.315e-05 [convert_after_rewriter]: 1.153e-05 [order_py_execute_after_rewriter]: 7.96001e-06 [mutable_eliminate]: 0.00083526 [opt_b]: 0.0004349, [1] [Cycle 1]: 0.00042391, [7] [b_1]: 0.00026681 [b_2]: 1.488e-05 [updatestate_depend_eliminate]: 1.356e-05 [updatestate_assign_eliminate]: 5.14e-06 [updatestate_loads_eliminate]: 4.68001e-06 [renormalize]: 9.09989e-07 [cse]: 7.172e-05 [optimize_parallel_all_gather_comm]: 3.069e-05 [overlap_param_gather]: 2.22999e-06 [cconv]: 4.21e-05 [loop_unroll]: 0.00068067 [opt_after_cconv]: 0.150008, [1] [Cycle 1]: 0.149997, [7] [c_1]: 0.00012932 [parameter_eliminate]: 8.57998e-06 [updatestate_depend_eliminate]: 2.003e-05 [updatestate_assign_eliminate]: 5.67001e-06 [updatestate_loads_eliminate]: 5.09998e-06 [cse]: 9.85e-05 [renormalize]: 1.05999e-06 [remove_dup_value]: 0.00010165 [tuple_transform]: 0.00018974, [1] [Cycle 1]: 0.00017666, [4] [d_1]: 0.0001227 [none_parameter_eliminate]: 2.67001e-06 [renormalize]: 2.59985e-07 [switch_simplify]: 1.533e-05 [partial_unused_args_eliminate]: 2.54001e-06 [add_recomputation]: 9.997e-05 [cse_after_recomputation]: 4.897e-05, [1] [Cycle 1]: 4.245e-05, [1] [cse]: 3.055e-05 [environ_conv]: 1.143e-05 [swap_dp_allreduce_reducescatter]: 8.94e-06 [bias_add_comm_swap]: 3.74002e-06 [label_micro_interleaved_index]: 9.96e-06 [label_fine_grained_interleaved_index]: 3.65e-06 [merge_cast_opt]: 1.59e-06 [slice_recompute_activation]: 2.52001e-06 [micro_interleaved_order_control]: 3.18998e-06 [assign_add_opt]: 1.60001e-06 [ForceFp32Comm]: 9.20001e-07 [remove_cast_before_assign_add]: 1.76003e-06 [full_micro_interleaved_order_control]: 2.71999e-06 [reorder_send_recv_between_fp_bp]: 3.75998e-06 [comm_op_add_attrs]: 1.17e-06 [add_comm_op_reuse_tag]: 1.19e-06 [interleave_split_concat_branches]: 1.59998e-06 [interleave_parallel_branches]: 1.25001e-06 [overlap_opt_shard_in_pipeline]: 1.45001e-06 [overlap_opt_shard_grad_in_pipeline]: 2.17001e-06 [control_data_broadcast_order]: 2.26e-05 [grouped_pairwise_exchange_alltoall]: 1.77001e-06 [offloading_packed_experts]: 5.90002e-06 [overlap_recompute_and_grad_model_parallel]: 6.54001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.43002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.57999e-06 [overlap_recompute_comm]: 2.71e-06 [overlap_grad_ring_attention]: 5.84e-06 [overlap_grad_flash_sp]: 2.957e-05 [begin_end_overlap_inline]: 6.29982e-07 [split_matmul_comm_elemetwise]: 2.68e-06 [split_layernorm_comm]: 1.76e-06 [handle_group_info]: 1.12e-06 [symbol_engine_optimizer]: 0.00023658, [1] [Cycle 1]: 0.00022948, [6] [build]: 0.00010228 [elim_shapecalc]: 2.183e-05 [elim_not_effective]: 2.328e-05 [opt_reshape]: 1.357e-05 [fold_const_symbol]: 2.374e-05 [renormalize]: 5.40022e-07 [detach_backward]: 2.60002e-06 [pipeline_parallel_scheduler]: 1.92001e-06 [auto_monad_reorder]: 2.821e-05 [get_jit_bprop_graph]: 1.95001e-06 [rewriter_after_jit_bprop_graph]: 7.71999e-06 [opt_after_jit_grad]: 0.00097023 [validate]: 7.587e-05 Sums bootstrap : 0.000768s : 5.03% type_inference : 0.006524s : 42.72% event_method : 0.000016s : 0.10% auto_monad : 0.000061s : 0.40% graph_reusing : 0.000005s : 0.03% inline : 0.000003s : 0.02% add_attr.add_attr_with_inline.tag_attr : 0.000025s : 0.17% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.03% parallel-infer-symbol : 0.000004s : 0.02% pre_auto_parallel : 0.000047s : 0.31% insert-virtual-dataset : 0.000003s : 0.02% parallel-infer-symbol-second : 0.000001s : 0.01% dataset_repeat_opt : 0.000003s : 0.02% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000035s : 0.23% optimize.rewriter_before_opt_a : 0.000080s : 0.53% optimize.opt_a.expand_dump_flag : 0.000005s : 0.04% optimize.opt_a.switch_simplify : 0.000053s : 0.34% optimize.opt_a.loop_unroll : 0.000036s : 0.24% optimize.opt_a.a_1 : 0.000890s : 5.83% optimize.opt_a.with_stream_mark : 0.000053s : 0.35% optimize.opt_a.recompute_prepare : 0.000029s : 0.19% optimize.opt_a.updatestate_depend_eliminate : 0.000013s : 0.08% optimize.opt_a.updatestate_assign_eliminate : 0.000011s : 0.07% optimize.opt_a.updatestate_loads_eliminate : 0.000011s : 0.07% optimize.opt_a.parameter_eliminate : 0.000004s : 0.02% optimize.opt_a.a_2 : 0.000324s : 2.12% optimize.opt_a.accelerated_algorithm : 0.000026s : 0.17% optimize.opt_a.shard : 0.000005s : 0.04% optimize.opt_a.meta_shard_fg_expand : 0.000006s : 0.04% optimize.opt_a.shard_inline : 0.000024s : 0.16% optimize.opt_a.merge_send_recv : 0.000023s : 0.15% optimize.opt_a.auto_parallel : 0.000021s : 0.14% optimize.opt_a.parallel : 0.000045s : 0.29% optimize.opt_a.flash_sp : 0.000017s : 0.11% optimize.opt_a.merge_comm : 0.000013s : 0.08% optimize.opt_a.allreduce_fusion : 0.000012s : 0.08% optimize.opt_a.matmul_add_comm_reduction : 0.000024s : 0.16% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000031s : 0.20% optimize.opt_a.virtual_dataset : 0.000026s : 0.17% optimize.opt_a.get_grad_eliminate_ : 0.000024s : 0.16% optimize.opt_a.virtual_output : 0.000024s : 0.16% optimize.opt_a.merge_forward : 0.000012s : 0.08% optimize.opt_a.cell_reuse_recompute_pass : 0.000004s : 0.03% optimize.opt_a.offload_activation : 0.000026s : 0.17% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000048s : 0.31% optimize.opt_a.merge_recompute_call_nodes : 0.000003s : 0.02% optimize.opt_a.before_grad : 0.000034s : 0.22% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000012s : 0.08% optimize.opt_a.meta_fg_expand : 0.000008s : 0.05% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.03% optimize.opt_a.receive_attached : 0.000006s : 0.04% optimize.opt_a.after_resolve : 0.000057s : 0.37% optimize.opt_a.a_after_grad : 0.000040s : 0.26% optimize.opt_a.renormalize : 0.001167s : 7.64% optimize.opt_a.add_forward_monad_depend : 0.000010s : 0.07% optimize.opt_a.auto_monad_grad : 0.000006s : 0.04% optimize.opt_a.auto_monad_eliminator : 0.000036s : 0.23% optimize.opt_a.cse : 0.000136s : 0.89% optimize.opt_a.a_3 : 0.000178s : 1.16% optimize.py_interpret_to_execute_after_opt_a : 0.000026s : 0.17% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.02% optimize.rewriter_after_opt_a : 0.000073s : 0.48% optimize.convert_after_rewriter : 0.000012s : 0.08% optimize.order_py_execute_after_rewriter : 0.000008s : 0.05% optimize.mutable_eliminate : 0.000835s : 5.47% optimize.opt_b.b_1 : 0.000267s : 1.75% optimize.opt_b.b_2 : 0.000015s : 0.10% optimize.opt_b.updatestate_depend_eliminate : 0.000014s : 0.09% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.03% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.03% optimize.opt_b.renormalize : 0.000001s : 0.01% optimize.opt_b.cse : 0.000072s : 0.47% optimize.optimize_parallel_all_gather_comm : 0.000031s : 0.20% optimize.overlap_param_gather : 0.000002s : 0.01% optimize.cconv : 0.000042s : 0.28% optimize.loop_unroll : 0.000681s : 4.46% optimize.opt_after_cconv.c_1 : 0.000129s : 0.85% optimize.opt_after_cconv.parameter_eliminate : 0.000009s : 0.06% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000020s : 0.13% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000006s : 0.04% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.03% optimize.opt_after_cconv.cse : 0.000098s : 0.65% optimize.opt_after_cconv.renormalize : 0.000001s : 0.01% optimize.remove_dup_value : 0.000102s : 0.67% optimize.tuple_transform.d_1 : 0.000123s : 0.80% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.02% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000015s : 0.10% optimize.partial_unused_args_eliminate : 0.000003s : 0.02% optimize.add_recomputation : 0.000100s : 0.65% optimize.cse_after_recomputation.cse : 0.000031s : 0.20% optimize.environ_conv : 0.000011s : 0.07% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 0.06% optimize.bias_add_comm_swap : 0.000004s : 0.02% optimize.label_micro_interleaved_index : 0.000010s : 0.07% optimize.label_fine_grained_interleaved_index : 0.000004s : 0.02% optimize.merge_cast_opt : 0.000002s : 0.01% optimize.slice_recompute_activation : 0.000003s : 0.02% optimize.micro_interleaved_order_control : 0.000003s : 0.02% optimize.assign_add_opt : 0.000002s : 0.01% optimize.ForceFp32Comm : 0.000001s : 0.01% optimize.remove_cast_before_assign_add : 0.000002s : 0.01% optimize.full_micro_interleaved_order_control : 0.000003s : 0.02% optimize.reorder_send_recv_between_fp_bp : 0.000004s : 0.02% optimize.comm_op_add_attrs : 0.000001s : 0.01% optimize.add_comm_op_reuse_tag : 0.000001s : 0.01% optimize.interleave_split_concat_branches : 0.000002s : 0.01% optimize.interleave_parallel_branches : 0.000001s : 0.01% optimize.overlap_opt_shard_in_pipeline : 0.000001s : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000023s : 0.15% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000006s : 0.04% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.04% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.01% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.01% optimize.overlap_recompute_comm : 0.000003s : 0.02% optimize.overlap_grad_ring_attention : 0.000006s : 0.04% optimize.overlap_grad_flash_sp : 0.000030s : 0.19% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.02% optimize.split_layernorm_comm : 0.000002s : 0.01% optimize.handle_group_info : 0.000001s : 0.01% optimize.symbol_engine_optimizer.build : 0.000102s : 0.67% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000022s : 0.14% optimize.symbol_engine_optimizer.elim_not_effective : 0.000023s : 0.15% optimize.symbol_engine_optimizer.opt_reshape : 0.000014s : 0.09% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000024s : 0.16% optimize.symbol_engine_optimizer.renormalize : 0.000001s : 0.00% detach_backward : 0.000003s : 0.02% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000028s : 0.18% get_jit_bprop_graph : 0.000002s : 0.01% rewriter_after_jit_bprop_graph : 0.000008s : 0.05% opt_after_jit_grad : 0.000970s : 6.35% validate : 0.000076s : 0.50% Time group info: ------[substitution.] 0.000189 39 2.22% : 0.000004s : 2: substitution.elim_not_effective 4.23% : 0.000008s : 2: substitution.fold_const_symbol 6.08% : 0.000011s : 10: substitution.graph_param_transform 74.79% : 0.000141s : 1: substitution.inline 2.28% : 0.000004s : 4: substitution.j_node_and_user_rematch 3.61% : 0.000007s : 4: substitution.remove_not_recompute_node 6.80% : 0.000013s : 16: substitution.replace_old_param ------[type_inference.] 0.006406 2 88.81% : 0.005689s : 1: type_inference.infer 11.19% : 0.000717s : 1: type_inference.specialize ------[replace.] 0.000022 1 100.00% : 0.000022s : 1: replace.inline ------[match.] 0.000140 1 100.00% : 0.000140s : 1: match.inline ------[predicate.] 0.000335 2335 0.80% : 0.000003s : 21: predicate.accumulaten_eliminater 0.99% : 0.000003s : 10: predicate.ad_related_special_op_eliminate 0.72% : 0.000002s : 20: predicate.addn_check_dump 0.78% : 0.000003s : 21: predicate.addn_zero_filter 0.78% : 0.000003s : 21: predicate.adjust_all_reduce_mul_add 1.76% : 0.000006s : 41: predicate.arithmetic_simplify 1.48% : 0.000005s : 21: predicate.cast_eliminate 0.75% : 0.000002s : 20: predicate.check_bprop_eliminate 0.72% : 0.000002s : 20: predicate.compare_switch_simplify 0.27% : 0.000001s : 10: predicate.const_output_eliminate 0.73% : 0.000002s : 20: predicate.depend_value_elim 0.79% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 0.89% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.81% : 0.000003s : 21: predicate.dict_set_item_eliminator 1.38% : 0.000005s : 20: predicate.dumpgradient_eliminate 0.39% : 0.000001s : 10: predicate.elim_not_effective 0.44% : 0.000001s : 10: predicate.elim_shapecalc_of_broadcastargs 1.13% : 0.000004s : 31: predicate.environ_add_const_eliminate 1.21% : 0.000004s : 31: predicate.environ_get_add_eliminate 1.08% : 0.000004s : 31: predicate.environ_get_depend_swap 1.81% : 0.000006s : 51: predicate.environ_get_eliminate 1.11% : 0.000004s : 31: predicate.environ_get_set_eliminate 0.82% : 0.000003s : 22: predicate.exchange_switch_depend_value 1.56% : 0.000005s : 22: predicate.float_depend_g_call 0.76% : 0.000003s : 20: predicate.float_environ_get_switch 1.18% : 0.000004s : 30: predicate.float_tuple_getitem_switch 0.28% : 0.000001s : 10: predicate.fold_const_symbol 0.86% : 0.000003s : 20: predicate.get_grad_eliminate 0.41% : 0.000001s : 10: predicate.graph_param_transform 0.77% : 0.000003s : 20: predicate.incorporate_call 0.65% : 0.000002s : 20: predicate.incorporate_call_switch 6.80% : 0.000023s : 103: predicate.inline 0.91% : 0.000003s : 20: predicate.inline_without_move 0.52% : 0.000002s : 20: predicate.j_node_and_user_rematch 1.02% : 0.000003s : 20: predicate.less_batch_normalization 1.71% : 0.000006s : 41: predicate.list_to_tuple_eliminator_ 2.31% : 0.000008s : 62: predicate.load_eliminater 1.10% : 0.000004s : 10: predicate.loop_unroll_after_grad 1.23% : 0.000004s : 31: predicate.loop_unroll_before_grad 1.92% : 0.000006s : 41: predicate.make_slice_get_slice_eliminator 0.75% : 0.000003s : 20: predicate.merge_addn 0.77% : 0.000003s : 20: predicate.micro_step_allgather_replace 0.74% : 0.000002s : 20: predicate.mini_step_allgather_replace 0.77% : 0.000003s : 21: predicate.minmaximum_grad 1.57% : 0.000005s : 10: predicate.mutable_eliminate 0.48% : 0.000002s : 10: predicate.opt_reshape 0.43% : 0.000001s : 10: predicate.parallel_virtual_node 0.94% : 0.000003s : 22: predicate.partial_defer_inline 1.22% : 0.000004s : 31: predicate.partial_eliminate 0.76% : 0.000003s : 21: predicate.print_const_string_wrapper 0.76% : 0.000003s : 20: predicate.reduce_all_const_elim 1.12% : 0.000004s : 21: predicate.reduce_eliminate 2.49% : 0.000008s : 62: predicate.redundant_stop_gradient_eliminater 0.71% : 0.000002s : 20: predicate.remove_not_recompute_node 1.37% : 0.000005s : 41: predicate.replace_applicator 0.73% : 0.000002s : 20: predicate.replace_old_param 0.32% : 0.000001s : 10: predicate.reset_defer_inline 0.94% : 0.000003s : 21: predicate.reshape_eliminate 0.79% : 0.000003s : 20: predicate.row_tensor_add_zeros_like 0.43% : 0.000001s : 10: predicate.row_tensor_eliminate 0.93% : 0.000003s : 20: predicate.same_eliminate 0.62% : 0.000002s : 20: predicate.set_cell_output_no_recompute 0.97% : 0.000003s : 20: predicate.shard_identity_eliminate 0.80% : 0.000003s : 20: predicate.special_op_eliminate 0.79% : 0.000003s : 20: predicate.specialize_transform 1.14% : 0.000004s : 20: predicate.split_environ_get_set_with_tuple_value 0.94% : 0.000003s : 20: predicate.stack_unstack_eliminate 0.49% : 0.000002s : 10: predicate.switch_call_monad_eliminater 0.81% : 0.000003s : 22: predicate.switch_defer_inline 1.58% : 0.000005s : 42: predicate.switch_layer_defer_inline 3.43% : 0.000012s : 83: predicate.switch_simplify 0.82% : 0.000003s : 21: predicate.tile_eliminate 0.79% : 0.000003s : 21: predicate.transpose_eliminate 1.52% : 0.000005s : 41: predicate.tuple_list_convert_item_index_to_positive 1.57% : 0.000005s : 41: predicate.tuple_list_get_item_const_eliminator 1.54% : 0.000005s : 41: predicate.tuple_list_get_item_depend_reorder 2.65% : 0.000009s : 61: predicate.tuple_list_get_item_eliminator 1.64% : 0.000006s : 41: predicate.tuple_list_get_set_item_eliminator 2.34% : 0.000008s : 61: predicate.tuple_list_set_item_eliminator 1.72% : 0.000006s : 41: predicate.tuple_to_list_eliminator_ 2.20% : 0.000007s : 62: predicate.updatestate_pure_node_eliminater 3.99% : 0.000013s : 82: predicate.updatestate_useless_node_eliminater 0.38% : 0.000001s : 10: predicate.value_based_eliminate 0.84% : 0.000003s : 20: predicate.virtual_dataset_eliminate 0.90% : 0.000003s : 20: predicate.virtual_output_eliminate 0.39% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.47% : 0.000002s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000728 6 48.30% : 0.000351s : 3: func_graph_cloner_run.FuncGraphClonerGraph 51.70% : 0.000376s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.337612 192 0.00% : 0.000004s : 1: ForceFp32Comm 1.55% : 0.005223s : 1: add_attr 1.54% : 0.005205s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.03% : 0.000106s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.02% : 0.000066s : 1: auto_monad 0.01% : 0.000034s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.24% : 0.000808s : 1: bootstrap 0.01% : 0.000046s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000027s : 1: control_data_broadcast_order 0.00% : 0.000016s : 1: convert_after_rewriter 0.02% : 0.000052s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000016s : 1: environ_conv 0.01% : 0.000023s : 1: event_method 0.00% : 0.000010s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000009s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000008s : 1: label_fine_grained_interleaved_index 0.00% : 0.000013s : 1: label_micro_interleaved_index 0.21% : 0.000692s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.25% : 0.000853s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.03% : 0.000101s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000031s : 1: opt.transform.mutable_eliminate 0.51% : 0.001736s : 78: opt.transform.opt_a 0.03% : 0.000117s : 1: opt.transform.opt_after_cconv 0.02% : 0.000057s : 1: opt.transform.opt_after_jit_grad 0.07% : 0.000246s : 28: opt.transform.opt_b 0.04% : 0.000135s : 2: opt.transform.opt_trans_graph 0.02% : 0.000078s : 4: opt.transform.symbol_engine_opt 1.22% : 0.004110s : 1: opt_a 44.43% : 0.150014s : 1: opt_after_cconv 0.29% : 0.000991s : 1: opt_after_jit_grad 0.13% : 0.000439s : 1: opt_b 46.65% : 0.157499s : 1: optimize 0.01% : 0.000035s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.01% : 0.000034s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000010s : 1: overlap_grad_ring_attention 0.00% : 0.000007s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000004s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000005s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000007s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000052s : 1: pre_auto_parallel 0.01% : 0.000039s : 1: py_interpret_to_execute 0.01% : 0.000031s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.03% : 0.000113s : 1: remove_dup_value 0.15% : 0.000521s : 1: renormalize.infer 0.19% : 0.000635s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000011s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000079s : 1: rewriter_after_opt_a 0.03% : 0.000085s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000009s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.00% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.07% : 0.000240s : 1: symbol_engine_optimizer 0.06% : 0.000193s : 1: tuple_transform 1.94% : 0.006547s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_with_anti_shape[QuantMethod.INT_CUBE-1] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_with_anti_shape[QuantMethod.INT_CUBE-1],max_mem:684.0M =============================== 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 287.42s (0:04:47) ==================