==================================================Ascend ============================= test session starts ============================== platform linux -- Python 3.9.19, pytest-6.2.5, py-1.11.0, pluggy-1.5.0 rootdir: /home/jenkins/mindspore/testcases/testcases/tests/st/infer/ops/test_internal_ops, configfile: ../../../../../../../../sault/virtual_test/virtualenv_005/sault/config/pytest.ini plugins: mock-3.14.0, hydra-core-1.3.2, forked-1.6.0, anyio-4.9.0, xdist-1.32.0 collected 4 items test_asd_paged_attention.py [WARNING] ME(169973:281473287331632,MainProcess):2026-01-29-17:37:57.317.073 [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 = 0.0366227, [21] [bootstrap]: 0.0008135 [type_inference]: 0.0207388 [event_method]: 1.638e-05 [auto_monad]: 0.00010938 [graph_reusing]: 5.39e-06 [inline]: 2.83e-06 [add_attr]: 0.00843249, [1] [add_attr_with_inline]: 0.00841567, [1] [Cycle 1]: 9.99e-05, [2] [tag_attr]: 2.295e-05 [meta_addattr_fg_expand]: 3.63999e-06 [parallel-infer-symbol]: 4.80001e-06 [pre_auto_parallel]: 4.55e-05 [insert-virtual-dataset]: 2.68003e-06 [parallel-infer-symbol-second]: 7.50006e-07 [dataset_repeat_opt]: 2.10002e-06 [pipeline_split]: 1.89999e-06 [optimize]: 0.00566682, [53] [py_interpret_to_execute]: 2.642e-05 [rewriter_before_opt_a]: 8.551e-05 [opt_a]: 0.00306877, [2] [Cycle 1]: 0.00215159, [45] [expand_dump_flag]: 3.16999e-06 [switch_simplify]: 2.967e-05 [loop_unroll]: 1.662e-05 [a_1]: 0.00040612 [with_stream_mark]: 2.38e-05 [recompute_prepare]: 1.154e-05 [updatestate_depend_eliminate]: 6.16e-06 [updatestate_assign_eliminate]: 4.92999e-06 [updatestate_loads_eliminate]: 4.65001e-06 [parameter_eliminate]: 2.25002e-06 [a_2]: 0.00012535 [accelerated_algorithm]: 1.12e-05 [shard]: 2.56998e-06 [meta_shard_fg_expand]: 1.96e-06 [shard_inline]: 8.97e-06 [merge_send_recv]: 2.015e-05 [auto_parallel]: 8.27e-06 [parallel]: 5.141e-05 [flash_sp]: 1.997e-05 [merge_comm]: 6.19001e-06 [allreduce_fusion]: 4.96002e-06 [matmul_add_comm_reduction]: 1.226e-05 [allreduce_slice_to_reducescatter]: 6.39993e-07 [virtual_shard_identity]: 1.161e-05 [virtual_dataset]: 9.34e-06 [get_grad_eliminate_]: 9.04e-06 [virtual_output]: 8.99e-06 [merge_forward]: 5.62001e-06 [cell_reuse_recompute_pass]: 1.50001e-06 [offload_activation]: 1.231e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.565e-05 [merge_recompute_call_nodes]: 1.50001e-06 [before_grad]: 1.464e-05 [set_forward_comm_id_for_comm_node_pass]: 5.24e-06 [meta_fg_expand]: 3.29001e-06 [flash_sp_send_recv_attached]: 2.74999e-06 [receive_attached]: 1.085e-05 [after_resolve]: 1.796e-05 [a_after_grad]: 1.384e-05 [renormalize]: 0.00079616 [add_forward_monad_depend]: 6.44001e-06 [auto_monad_grad]: 2.81e-06 [auto_monad_eliminator]: 1.896e-05 [cse]: 8.536e-05 [a_3]: 7.021e-05 [Cycle 2]: 0.00090484, [45] [expand_dump_flag]: 2.08002e-06 [switch_simplify]: 1.139e-05 [loop_unroll]: 8.89e-06 [a_1]: 0.00020013 [with_stream_mark]: 1.71e-05 [recompute_prepare]: 9.69999e-06 [updatestate_depend_eliminate]: 5.04e-06 [updatestate_assign_eliminate]: 4.33001e-06 [updatestate_loads_eliminate]: 4.03999e-06 [parameter_eliminate]: 1.62001e-06 [a_2]: 0.00011296 [accelerated_algorithm]: 9.27001e-06 [shard]: 1.62001e-06 [meta_shard_fg_expand]: 1.47001e-06 [shard_inline]: 9.79999e-06 [merge_send_recv]: 7.51001e-06 [auto_parallel]: 9.25999e-06 [parallel]: 6.01e-06 [flash_sp]: 3.88999e-06 [merge_comm]: 4.89998e-06 [allreduce_fusion]: 4.79e-06 [matmul_add_comm_reduction]: 7.66001e-06 [allreduce_slice_to_reducescatter]: 3.10014e-07 [virtual_shard_identity]: 1.024e-05 [virtual_dataset]: 8.69998e-06 [get_grad_eliminate_]: 8.42e-06 [virtual_output]: 8.37e-06 [merge_forward]: 4.70999e-06 [cell_reuse_recompute_pass]: 1.92999e-06 [offload_activation]: 9.17001e-06 [cell_reuse_handle_not_recompute_node_pass]: 1.613e-05 [merge_recompute_call_nodes]: 9.29984e-07 [before_grad]: 1.182e-05 [set_forward_comm_id_for_comm_node_pass]: 5.05001e-06 [meta_fg_expand]: 3.16999e-06 [flash_sp_send_recv_attached]: 1.15999e-06 [receive_attached]: 1.82001e-06 [after_resolve]: 1.653e-05 [a_after_grad]: 1.38e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 1.62001e-06 [auto_monad_grad]: 1.50999e-06 [auto_monad_eliminator]: 1.01e-05 [cse]: 3.155e-05 [a_3]: 5.727e-05 [py_interpret_to_execute_after_opt_a]: 1.586e-05 [slice_cell_reuse_recomputed_activation]: 1.89999e-06 [rewriter_after_opt_a]: 6.626e-05 [convert_after_rewriter]: 2.014e-05 [order_py_execute_after_rewriter]: 6.65998e-06 [mutable_eliminate]: 0.0006797 [opt_b]: 0.00029955, [1] [Cycle 1]: 0.00029123, [7] [b_1]: 0.00018842 [b_2]: 1.074e-05 [updatestate_depend_eliminate]: 9.02e-06 [updatestate_assign_eliminate]: 4.05e-06 [updatestate_loads_eliminate]: 4.05e-06 [renormalize]: 5.59987e-07 [cse]: 3.881e-05 [optimize_parallel_all_gather_comm]: 2.122e-05 [overlap_param_gather]: 5.54e-06 [cconv]: 3.245e-05 [loop_unroll]: 0.0004455 [opt_after_cconv]: 0.00013755, [1] [Cycle 1]: 0.0001315, [7] [c_1]: 4.427e-05 [parameter_eliminate]: 3.9e-06 [updatestate_depend_eliminate]: 6.88e-06 [updatestate_assign_eliminate]: 4.10998e-06 [updatestate_loads_eliminate]: 3.76001e-06 [cse]: 3.475e-05 [renormalize]: 3.60014e-07 [remove_dup_value]: 7.412e-05 [tuple_transform]: 0.00010032, [1] [Cycle 1]: 9.462e-05, [4] [d_1]: 6.397e-05 [none_parameter_eliminate]: 1.87001e-06 [renormalize]: 1.80007e-07 [switch_simplify]: 9.82999e-06 [partial_unused_args_eliminate]: 2.13998e-06 [add_recomputation]: 6.537e-05 [cse_after_recomputation]: 3.194e-05, [1] [Cycle 1]: 2.701e-05, [1] [cse]: 2.13e-05 [environ_conv]: 1.894e-05 [swap_dp_allreduce_reducescatter]: 7.14001e-06 [bias_add_comm_swap]: 2.77002e-06 [label_micro_interleaved_index]: 4.73001e-06 [label_fine_grained_interleaved_index]: 3.10002e-06 [merge_cast_opt]: 1.39e-06 [slice_recompute_activation]: 3.14999e-06 [micro_interleaved_order_control]: 3.35998e-06 [assign_add_opt]: 1.56002e-06 [ForceFp32Comm]: 9.10019e-07 [remove_cast_before_assign_add]: 1.09998e-06 [full_micro_interleaved_order_control]: 2.48e-06 [reorder_send_recv_between_fp_bp]: 2.68e-06 [comm_op_add_attrs]: 1.09e-06 [add_comm_op_reuse_tag]: 1.02e-06 [interleave_split_concat_branches]: 1.25001e-06 [interleave_parallel_branches]: 1.15999e-06 [overlap_opt_shard_in_pipeline]: 2.382e-05 [overlap_opt_shard_grad_in_pipeline]: 2.14e-06 [control_data_broadcast_order]: 1.683e-05 [grouped_pairwise_exchange_alltoall]: 1.66e-06 [offloading_packed_experts]: 4.89e-06 [overlap_recompute_and_grad_model_parallel]: 6.48998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.24e-06 [overlap_recompute_allgather_and_fa_grad]: 1.49998e-06 [overlap_recompute_comm]: 2.65002e-06 [overlap_grad_ring_attention]: 4.79e-06 [overlap_grad_flash_sp]: 2.551e-05 [begin_end_overlap_inline]: 6.50005e-07 [split_matmul_comm_elemetwise]: 2.44001e-06 [split_layernorm_comm]: 2.12999e-06 [handle_group_info]: 1.10999e-06 [symbol_engine_optimizer]: 8.626e-05, [1] [Cycle 1]: 8.18e-05, [6] [build]: 3.48999e-06 [elim_shapecalc]: 1.324e-05 [elim_not_effective]: 1.623e-05 [opt_reshape]: 9.66e-06 [fold_const_symbol]: 1.27e-05 [renormalize]: 1.90019e-07 [detach_backward]: 2.32999e-06 [pipeline_parallel_scheduler]: 1.54e-06 [auto_monad_reorder]: 2.915e-05 [get_jit_bprop_graph]: 1.75001e-06 [rewriter_after_jit_bprop_graph]: 4.60001e-06 [opt_after_jit_grad]: 0.00049039 [validate]: 6.797e-05 Sums bootstrap : 0.000813s : 3.00% type_inference : 0.020739s : 76.38% event_method : 0.000016s : 0.06% auto_monad : 0.000109s : 0.40% graph_reusing : 0.000005s : 0.02% inline : 0.000003s : 0.01% add_attr.add_attr_with_inline.tag_attr : 0.000023s : 0.08% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.01% parallel-infer-symbol : 0.000005s : 0.02% pre_auto_parallel : 0.000045s : 0.17% insert-virtual-dataset : 0.000003s : 0.01% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.01% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000026s : 0.10% optimize.rewriter_before_opt_a : 0.000086s : 0.31% optimize.opt_a.expand_dump_flag : 0.000005s : 0.02% optimize.opt_a.switch_simplify : 0.000041s : 0.15% optimize.opt_a.loop_unroll : 0.000026s : 0.09% optimize.opt_a.a_1 : 0.000606s : 2.23% optimize.opt_a.with_stream_mark : 0.000041s : 0.15% optimize.opt_a.recompute_prepare : 0.000021s : 0.08% optimize.opt_a.updatestate_depend_eliminate : 0.000011s : 0.04% optimize.opt_a.updatestate_assign_eliminate : 0.000009s : 0.03% optimize.opt_a.updatestate_loads_eliminate : 0.000009s : 0.03% optimize.opt_a.parameter_eliminate : 0.000004s : 0.01% optimize.opt_a.a_2 : 0.000238s : 0.88% optimize.opt_a.accelerated_algorithm : 0.000020s : 0.08% optimize.opt_a.shard : 0.000004s : 0.02% optimize.opt_a.meta_shard_fg_expand : 0.000003s : 0.01% optimize.opt_a.shard_inline : 0.000019s : 0.07% optimize.opt_a.merge_send_recv : 0.000028s : 0.10% optimize.opt_a.auto_parallel : 0.000018s : 0.06% optimize.opt_a.parallel : 0.000057s : 0.21% optimize.opt_a.flash_sp : 0.000024s : 0.09% optimize.opt_a.merge_comm : 0.000011s : 0.04% optimize.opt_a.allreduce_fusion : 0.000010s : 0.04% optimize.opt_a.matmul_add_comm_reduction : 0.000020s : 0.07% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000022s : 0.08% optimize.opt_a.virtual_dataset : 0.000018s : 0.07% optimize.opt_a.get_grad_eliminate_ : 0.000017s : 0.06% optimize.opt_a.virtual_output : 0.000017s : 0.06% optimize.opt_a.merge_forward : 0.000010s : 0.04% optimize.opt_a.cell_reuse_recompute_pass : 0.000003s : 0.01% optimize.opt_a.offload_activation : 0.000021s : 0.08% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000032s : 0.12% optimize.opt_a.merge_recompute_call_nodes : 0.000002s : 0.01% optimize.opt_a.before_grad : 0.000026s : 0.10% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000010s : 0.04% optimize.opt_a.meta_fg_expand : 0.000006s : 0.02% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.01% optimize.opt_a.receive_attached : 0.000013s : 0.05% optimize.opt_a.after_resolve : 0.000034s : 0.13% optimize.opt_a.a_after_grad : 0.000028s : 0.10% optimize.opt_a.renormalize : 0.000796s : 2.93% optimize.opt_a.add_forward_monad_depend : 0.000008s : 0.03% optimize.opt_a.auto_monad_grad : 0.000004s : 0.02% optimize.opt_a.auto_monad_eliminator : 0.000029s : 0.11% optimize.opt_a.cse : 0.000117s : 0.43% optimize.opt_a.a_3 : 0.000127s : 0.47% optimize.py_interpret_to_execute_after_opt_a : 0.000016s : 0.06% optimize.slice_cell_reuse_recomputed_activation : 0.000002s : 0.01% optimize.rewriter_after_opt_a : 0.000066s : 0.24% optimize.convert_after_rewriter : 0.000020s : 0.07% optimize.order_py_execute_after_rewriter : 0.000007s : 0.02% optimize.mutable_eliminate : 0.000680s : 2.50% optimize.opt_b.b_1 : 0.000188s : 0.69% optimize.opt_b.b_2 : 0.000011s : 0.04% optimize.opt_b.updatestate_depend_eliminate : 0.000009s : 0.03% optimize.opt_b.updatestate_assign_eliminate : 0.000004s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000004s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000039s : 0.14% optimize.optimize_parallel_all_gather_comm : 0.000021s : 0.08% optimize.overlap_param_gather : 0.000006s : 0.02% optimize.cconv : 0.000032s : 0.12% optimize.loop_unroll : 0.000445s : 1.64% optimize.opt_after_cconv.c_1 : 0.000044s : 0.16% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000007s : 0.03% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000004s : 0.02% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.01% optimize.opt_after_cconv.cse : 0.000035s : 0.13% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000074s : 0.27% optimize.tuple_transform.d_1 : 0.000064s : 0.24% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000010s : 0.04% optimize.partial_unused_args_eliminate : 0.000002s : 0.01% optimize.add_recomputation : 0.000065s : 0.24% optimize.cse_after_recomputation.cse : 0.000021s : 0.08% optimize.environ_conv : 0.000019s : 0.07% optimize.swap_dp_allreduce_reducescatter : 0.000007s : 0.03% optimize.bias_add_comm_swap : 0.000003s : 0.01% optimize.label_micro_interleaved_index : 0.000005s : 0.02% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.01% optimize.merge_cast_opt : 0.000001s : 0.01% optimize.slice_recompute_activation : 0.000003s : 0.01% optimize.micro_interleaved_order_control : 0.000003s : 0.01% optimize.assign_add_opt : 0.000002s : 0.01% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.01% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.01% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000024s : 0.09% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000017s : 0.06% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000005s : 0.02% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 0.02% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.01% optimize.overlap_recompute_comm : 0.000003s : 0.01% optimize.overlap_grad_ring_attention : 0.000005s : 0.02% optimize.overlap_grad_flash_sp : 0.000026s : 0.09% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.01% optimize.split_layernorm_comm : 0.000002s : 0.01% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000003s : 0.01% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000013s : 0.05% optimize.symbol_engine_optimizer.elim_not_effective : 0.000016s : 0.06% optimize.symbol_engine_optimizer.opt_reshape : 0.000010s : 0.04% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000013s : 0.05% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.01% pipeline_parallel_scheduler : 0.000002s : 0.01% auto_monad_reorder : 0.000029s : 0.11% get_jit_bprop_graph : 0.000002s : 0.01% rewriter_after_jit_bprop_graph : 0.000005s : 0.02% opt_after_jit_grad : 0.000490s : 1.81% validate : 0.000068s : 0.25% Time group info: ------[substitution.] 0.000145 30 1.23% : 0.000002s : 2: substitution.elim_not_effective 0.92% : 0.000001s : 2: substitution.fold_const_symbol 4.92% : 0.000007s : 7: substitution.graph_param_transform 81.28% : 0.000118s : 1: substitution.inline 2.93% : 0.000004s : 4: substitution.j_node_and_user_rematch 3.35% : 0.000005s : 4: substitution.remove_not_recompute_node 5.37% : 0.000008s : 10: substitution.replace_old_param ------[type_inference.] 0.020641 2 97.02% : 0.020025s : 1: type_inference.infer 2.98% : 0.000616s : 1: type_inference.specialize ------[replace.] 0.000022 1 100.00% : 0.000022s : 1: replace.inline ------[match.] 0.000116 1 100.00% : 0.000116s : 1: match.inline ------[predicate.] 0.000198 1651 0.76% : 0.000002s : 15: predicate.accumulaten_eliminater 0.94% : 0.000002s : 7: predicate.ad_related_special_op_eliminate 0.75% : 0.000001s : 14: predicate.addn_check_dump 0.78% : 0.000002s : 15: predicate.addn_zero_filter 0.73% : 0.000001s : 15: predicate.adjust_all_reduce_mul_add 1.94% : 0.000004s : 29: predicate.arithmetic_simplify 0.76% : 0.000002s : 15: predicate.cast_eliminate 0.76% : 0.000002s : 14: predicate.check_bprop_eliminate 0.70% : 0.000001s : 14: predicate.compare_switch_simplify 0.27% : 0.000001s : 7: predicate.const_output_eliminate 0.77% : 0.000002s : 14: predicate.depend_value_elim 0.84% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 1.09% : 0.000002s : 15: predicate.dict_get_item_eliminator 0.79% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.39% : 0.000003s : 14: predicate.dumpgradient_eliminate 0.38% : 0.000001s : 7: predicate.elim_not_effective 0.49% : 0.000001s : 7: predicate.elim_shapecalc_of_broadcastargs 1.16% : 0.000002s : 22: predicate.environ_add_const_eliminate 1.10% : 0.000002s : 22: predicate.environ_get_add_eliminate 1.11% : 0.000002s : 22: predicate.environ_get_depend_swap 1.87% : 0.000004s : 36: predicate.environ_get_eliminate 1.06% : 0.000002s : 22: predicate.environ_get_set_eliminate 0.84% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.55% : 0.000003s : 16: predicate.float_depend_g_call 0.76% : 0.000002s : 14: predicate.float_environ_get_switch 1.07% : 0.000002s : 21: predicate.float_tuple_getitem_switch 0.29% : 0.000001s : 7: predicate.fold_const_symbol 0.88% : 0.000002s : 14: predicate.get_grad_eliminate 0.40% : 0.000001s : 7: predicate.graph_param_transform 0.75% : 0.000001s : 14: predicate.incorporate_call 0.67% : 0.000001s : 14: predicate.incorporate_call_switch 5.81% : 0.000012s : 73: predicate.inline 1.24% : 0.000002s : 14: predicate.inline_without_move 0.52% : 0.000001s : 14: predicate.j_node_and_user_rematch 1.15% : 0.000002s : 14: predicate.less_batch_normalization 1.56% : 0.000003s : 29: predicate.list_to_tuple_eliminator_ 2.22% : 0.000004s : 44: predicate.load_eliminater 1.13% : 0.000002s : 7: predicate.loop_unroll_after_grad 1.35% : 0.000003s : 22: predicate.loop_unroll_before_grad 1.82% : 0.000004s : 29: predicate.make_slice_get_slice_eliminator 0.79% : 0.000002s : 14: predicate.merge_addn 0.83% : 0.000002s : 14: predicate.micro_step_allgather_replace 0.76% : 0.000002s : 14: predicate.mini_step_allgather_replace 0.72% : 0.000001s : 15: predicate.minmaximum_grad 1.65% : 0.000003s : 7: predicate.mutable_eliminate 0.47% : 0.000001s : 7: predicate.opt_reshape 0.57% : 0.000001s : 7: predicate.parallel_virtual_node 0.97% : 0.000002s : 16: predicate.partial_defer_inline 1.34% : 0.000003s : 22: predicate.partial_eliminate 0.77% : 0.000002s : 15: predicate.print_const_string_wrapper 0.76% : 0.000002s : 14: predicate.reduce_all_const_elim 0.98% : 0.000002s : 15: predicate.reduce_eliminate 2.29% : 0.000005s : 44: predicate.redundant_stop_gradient_eliminater 0.86% : 0.000002s : 14: predicate.remove_not_recompute_node 1.39% : 0.000003s : 29: predicate.replace_applicator 0.86% : 0.000002s : 14: predicate.replace_old_param 0.47% : 0.000001s : 7: predicate.reset_defer_inline 0.85% : 0.000002s : 15: predicate.reshape_eliminate 0.79% : 0.000002s : 14: predicate.row_tensor_add_zeros_like 0.51% : 0.000001s : 7: predicate.row_tensor_eliminate 1.05% : 0.000002s : 14: predicate.same_eliminate 0.70% : 0.000001s : 14: predicate.set_cell_output_no_recompute 0.88% : 0.000002s : 14: predicate.shard_identity_eliminate 0.81% : 0.000002s : 14: predicate.special_op_eliminate 0.87% : 0.000002s : 14: predicate.specialize_transform 1.10% : 0.000002s : 14: predicate.split_environ_get_set_with_tuple_value 0.95% : 0.000002s : 14: predicate.stack_unstack_eliminate 0.48% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.90% : 0.000002s : 16: predicate.switch_defer_inline 1.81% : 0.000004s : 30: predicate.switch_layer_defer_inline 3.79% : 0.000008s : 59: predicate.switch_simplify 0.79% : 0.000002s : 15: predicate.tile_eliminate 1.41% : 0.000003s : 15: predicate.transpose_eliminate 1.58% : 0.000003s : 29: predicate.tuple_list_convert_item_index_to_positive 1.56% : 0.000003s : 29: predicate.tuple_list_get_item_const_eliminator 1.49% : 0.000003s : 29: predicate.tuple_list_get_item_depend_reorder 2.98% : 0.000006s : 43: predicate.tuple_list_get_item_eliminator 1.49% : 0.000003s : 29: predicate.tuple_list_get_set_item_eliminator 2.49% : 0.000005s : 43: predicate.tuple_list_set_item_eliminator 1.65% : 0.000003s : 29: predicate.tuple_to_list_eliminator_ 2.17% : 0.000004s : 44: predicate.updatestate_pure_node_eliminater 3.05% : 0.000006s : 58: predicate.updatestate_useless_node_eliminater 0.39% : 0.000001s : 7: predicate.value_based_eliminate 0.84% : 0.000002s : 14: predicate.virtual_dataset_eliminate 0.79% : 0.000002s : 14: predicate.virtual_output_eliminate 0.35% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.53% : 0.000001s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000535 6 56.59% : 0.000303s : 3: func_graph_cloner_run.FuncGraphClonerGraph 43.41% : 0.000232s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.052957 192 0.01% : 0.000004s : 1: ForceFp32Comm 15.94% : 0.008439s : 1: add_attr 15.90% : 0.008420s : 1: add_attr_with_inline 0.01% : 0.000004s : 1: add_comm_op_reuse_tag 0.13% : 0.000070s : 1: add_recomputation 0.01% : 0.000004s : 1: assign_add_opt 0.22% : 0.000116s : 1: auto_monad 0.06% : 0.000034s : 1: auto_monad_reorder 0.01% : 0.000004s : 1: begin_end_overlap_inline 0.01% : 0.000006s : 1: bias_add_comm_swap 1.61% : 0.000854s : 1: bootstrap 0.07% : 0.000036s : 1: cconv 0.01% : 0.000004s : 1: comm_op_add_attrs 0.04% : 0.000020s : 1: control_data_broadcast_order 0.04% : 0.000024s : 1: convert_after_rewriter 0.07% : 0.000035s : 1: cse_after_recomputation 0.01% : 0.000005s : 1: dataset_repeat_opt 0.01% : 0.000006s : 1: detach_backward 0.04% : 0.000023s : 1: environ_conv 0.05% : 0.000025s : 1: event_method 0.01% : 0.000005s : 1: full_micro_interleaved_order_control 0.01% : 0.000005s : 1: get_jit_bprop_graph 0.02% : 0.000009s : 1: graph_reusing 0.01% : 0.000004s : 1: grouped_pairwise_exchange_alltoall 0.01% : 0.000004s : 1: handle_group_info 0.01% : 0.000006s : 1: inline 0.01% : 0.000006s : 1: insert-virtual-dataset 0.01% : 0.000004s : 1: interleave_parallel_branches 0.01% : 0.000004s : 1: interleave_split_concat_branches 0.01% : 0.000006s : 1: label_fine_grained_interleaved_index 0.02% : 0.000008s : 1: label_micro_interleaved_index 0.86% : 0.000455s : 1: loop_unroll 0.01% : 0.000004s : 1: merge_cast_opt 0.01% : 0.000006s : 1: micro_interleaved_order_control 1.30% : 0.000691s : 1: mutable_eliminate 0.01% : 0.000008s : 1: offloading_packed_experts 0.03% : 0.000017s : 1: opt.transform.loop_unroll_optimizer 0.04% : 0.000022s : 1: opt.transform.mutable_eliminate 2.28% : 0.001210s : 78: opt.transform.opt_a 0.08% : 0.000043s : 1: opt.transform.opt_after_cconv 0.06% : 0.000034s : 1: opt.transform.opt_after_jit_grad 0.32% : 0.000172s : 28: opt.transform.opt_b 0.14% : 0.000072s : 2: opt.transform.opt_trans_graph 0.09% : 0.000049s : 4: opt.transform.symbol_engine_opt 5.80% : 0.003073s : 1: opt_a 0.27% : 0.000141s : 1: opt_after_cconv 0.95% : 0.000502s : 1: opt_after_jit_grad 0.57% : 0.000303s : 1: opt_b 10.71% : 0.005672s : 1: optimize 0.05% : 0.000025s : 1: optimize_parallel_all_gather_comm 0.02% : 0.000010s : 1: order_py_execute_after_rewriter 0.05% : 0.000029s : 1: overlap_grad_flash_sp 0.01% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.02% : 0.000008s : 1: overlap_grad_ring_attention 0.01% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.05% : 0.000028s : 1: overlap_opt_shard_in_pipeline 0.02% : 0.000009s : 1: overlap_param_gather 0.01% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.02% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.01% : 0.000005s : 1: overlap_recompute_comm 0.02% : 0.000008s : 1: parallel-infer-symbol 0.01% : 0.000004s : 1: parallel-infer-symbol-second 0.01% : 0.000005s : 1: partial_unused_args_eliminate 0.01% : 0.000005s : 1: pipeline_parallel_scheduler 0.01% : 0.000005s : 1: pipeline_split 0.09% : 0.000050s : 1: pre_auto_parallel 0.06% : 0.000031s : 1: py_interpret_to_execute 0.04% : 0.000020s : 1: py_interpret_to_execute_after_opt_a 0.01% : 0.000004s : 1: remove_cast_before_assign_add 0.15% : 0.000078s : 1: remove_dup_value 0.80% : 0.000426s : 1: renormalize.infer 0.68% : 0.000360s : 1: renormalize.specialize 0.01% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.02% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.13% : 0.000071s : 1: rewriter_after_opt_a 0.17% : 0.000090s : 1: rewriter_before_opt_a 0.01% : 0.000005s : 1: slice_cell_reuse_recomputed_activation 0.01% : 0.000006s : 1: slice_recompute_activation 0.01% : 0.000005s : 1: split_layernorm_comm 0.01% : 0.000005s : 1: split_matmul_comm_elemetwise 0.02% : 0.000010s : 1: swap_dp_allreduce_reducescatter 0.17% : 0.000089s : 1: symbol_engine_optimizer 0.19% : 0.000103s : 1: tuple_transform 39.21% : 0.020765s : 1: type_inference mki_log delete old file:/home/jenkins/ascend/log/atb/atb_74945_20260129172203.log . [hook] pytest_runtest_teardown:test_internel_asd_paged_attention[False-ms_dtype0] tests/st/infer/ops/test_internal_ops/test_asd_paged_attention.py::test_internel_asd_paged_attention[False-ms_dtype0],max_mem:350.0M [WARNING] ME(169973:281473287331632,MainProcess):2026-01-29-17:39:36.318.682 [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 = 0.102359, [21] [bootstrap]: 0.00086565 [type_inference]: 0.00761917 [event_method]: 2.093e-05 [auto_monad]: 7.825e-05 [graph_reusing]: 5.96e-06 [inline]: 3.35e-06 [add_attr]: 0.0838319, [1] [add_attr_with_inline]: 0.0838089, [1] [Cycle 1]: 9.387e-05, [2] [tag_attr]: 2.926e-05 [meta_addattr_fg_expand]: 4.43999e-06 [parallel-infer-symbol]: 4.04002e-06 [pre_auto_parallel]: 4.072e-05 [insert-virtual-dataset]: 2.75002e-06 [parallel-infer-symbol-second]: 6.59988e-07 [dataset_repeat_opt]: 1.78997e-06 [pipeline_split]: 1.55999e-06 [optimize]: 0.00871755, [53] [py_interpret_to_execute]: 6.458e-05 [rewriter_before_opt_a]: 0.00011483 [opt_a]: 0.00510746, [2] [Cycle 1]: 0.0034704, [45] [expand_dump_flag]: 6.26e-06 [switch_simplify]: 3.516e-05 [loop_unroll]: 1.755e-05 [a_1]: 0.00049868 [with_stream_mark]: 2.894e-05 [recompute_prepare]: 1.398e-05 [updatestate_depend_eliminate]: 6.73e-06 [updatestate_assign_eliminate]: 5.97999e-06 [updatestate_loads_eliminate]: 5.74999e-06 [parameter_eliminate]: 2.54001e-06 [a_2]: 0.00013132 [accelerated_algorithm]: 1.446e-05 [shard]: 2.52001e-06 [meta_shard_fg_expand]: 4.33001e-06 [shard_inline]: 1.19e-05 [merge_send_recv]: 1.185e-05 [auto_parallel]: 1.002e-05 [parallel]: 3.43e-05 [flash_sp]: 1.239e-05 [merge_comm]: 9.64999e-06 [allreduce_fusion]: 5.92999e-06 [matmul_add_comm_reduction]: 1.301e-05 [allreduce_slice_to_reducescatter]: 8.70001e-07 [virtual_shard_identity]: 1.616e-05 [virtual_dataset]: 1.073e-05 [get_grad_eliminate_]: 9.79999e-06 [virtual_output]: 1.07e-05 [merge_forward]: 6.81999e-06 [cell_reuse_recompute_pass]: 1.54998e-06 [offload_activation]: 1.626e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.285e-05 [merge_recompute_call_nodes]: 1.77001e-06 [before_grad]: 1.698e-05 [set_forward_comm_id_for_comm_node_pass]: 1.289e-05 [meta_fg_expand]: 5.49e-06 [flash_sp_send_recv_attached]: 4.81002e-06 [receive_attached]: 2.91e-06 [after_resolve]: 3.766e-05 [a_after_grad]: 1.748e-05 [renormalize]: 0.00147146 [add_forward_monad_depend]: 1.465e-05 [auto_monad_grad]: 2.68e-06 [auto_monad_eliminator]: 2.26e-05 [cse]: 0.00010229 [a_3]: 9.324e-05 [Cycle 2]: 0.00161402, [45] [expand_dump_flag]: 4.17e-06 [switch_simplify]: 1.414e-05 [loop_unroll]: 1.013e-05 [a_1]: 0.00030244 [with_stream_mark]: 2.949e-05 [recompute_prepare]: 1.336e-05 [updatestate_depend_eliminate]: 7.2e-06 [updatestate_assign_eliminate]: 6.68e-06 [updatestate_loads_eliminate]: 7.01999e-06 [parameter_eliminate]: 2.39001e-06 [a_2]: 0.00012592 [accelerated_algorithm]: 1.297e-05 [shard]: 3.48e-06 [meta_shard_fg_expand]: 3.8e-06 [shard_inline]: 9.85002e-06 [merge_send_recv]: 1.047e-05 [auto_parallel]: 1.216e-05 [parallel]: 1.098e-05 [flash_sp]: 5.04e-06 [merge_comm]: 6.36998e-06 [allreduce_fusion]: 5.87001e-06 [matmul_add_comm_reduction]: 1.479e-05 [allreduce_slice_to_reducescatter]: 8.10018e-07 [virtual_shard_identity]: 1.364e-05 [virtual_dataset]: 1.13e-05 [get_grad_eliminate_]: 1.15e-05 [virtual_output]: 1.136e-05 [merge_forward]: 7.23e-06 [cell_reuse_recompute_pass]: 3.19001e-06 [offload_activation]: 2.024e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.859e-05 [merge_recompute_call_nodes]: 1.87001e-06 [before_grad]: 0.00017639 [set_forward_comm_id_for_comm_node_pass]: 1.128e-05 [meta_fg_expand]: 5.78002e-06 [flash_sp_send_recv_attached]: 2.01e-06 [receive_attached]: 2.63998e-06 [after_resolve]: 2.959e-05 [a_after_grad]: 1.709e-05 [renormalize]: 7.00238e-08 [add_forward_monad_depend]: 3.02002e-06 [auto_monad_grad]: 1.81e-06 [auto_monad_eliminator]: 1.482e-05 [cse]: 8.349e-05 [a_3]: 6.548e-05 [py_interpret_to_execute_after_opt_a]: 2.777e-05 [slice_cell_reuse_recomputed_activation]: 2.51998e-06 [rewriter_after_opt_a]: 7.361e-05 [convert_after_rewriter]: 9.86e-06 [order_py_execute_after_rewriter]: 7.05e-06 [mutable_eliminate]: 0.00097568 [opt_b]: 0.00039105, [1] [Cycle 1]: 0.0003782, [7] [b_1]: 0.00020875 [b_2]: 1.246e-05 [updatestate_depend_eliminate]: 1.066e-05 [updatestate_assign_eliminate]: 5.10001e-06 [updatestate_loads_eliminate]: 7.97998e-06 [renormalize]: 7.10017e-07 [cse]: 7.282e-05 [optimize_parallel_all_gather_comm]: 2.783e-05 [overlap_param_gather]: 2.93e-06 [cconv]: 4.668e-05 [loop_unroll]: 0.00062004 [opt_after_cconv]: 0.00023837, [1] [Cycle 1]: 0.00022914, [7] [c_1]: 4.753e-05 [parameter_eliminate]: 4.925e-05 [updatestate_depend_eliminate]: 9.54999e-06 [updatestate_assign_eliminate]: 4.50001e-06 [updatestate_loads_eliminate]: 4.50999e-06 [cse]: 6.454e-05 [renormalize]: 4.80009e-07 [remove_dup_value]: 8.797e-05 [tuple_transform]: 0.00012846, [1] [Cycle 1]: 0.00012117, [4] [d_1]: 7.994e-05 [none_parameter_eliminate]: 2.26e-06 [renormalize]: 1.30007e-07 [switch_simplify]: 1.135e-05 [partial_unused_args_eliminate]: 2.35002e-06 [add_recomputation]: 0.0001131 [cse_after_recomputation]: 5.112e-05, [1] [Cycle 1]: 4.349e-05, [1] [cse]: 3.333e-05 [environ_conv]: 9.29998e-06 [swap_dp_allreduce_reducescatter]: 8.78001e-06 [bias_add_comm_swap]: 3.43e-06 [label_micro_interleaved_index]: 7.61999e-06 [label_fine_grained_interleaved_index]: 3.16001e-06 [merge_cast_opt]: 1.67999e-06 [slice_recompute_activation]: 2.32001e-06 [micro_interleaved_order_control]: 3.65e-06 [assign_add_opt]: 1.30999e-06 [ForceFp32Comm]: 1.02998e-06 [remove_cast_before_assign_add]: 1.11002e-06 [full_micro_interleaved_order_control]: 2.68e-06 [reorder_send_recv_between_fp_bp]: 3.31001e-06 [comm_op_add_attrs]: 1.10999e-06 [add_comm_op_reuse_tag]: 1.07e-06 [interleave_split_concat_branches]: 1.71e-06 [interleave_parallel_branches]: 1.42999e-06 [overlap_opt_shard_in_pipeline]: 2.59999e-06 [overlap_opt_shard_grad_in_pipeline]: 1.61998e-06 [control_data_broadcast_order]: 1.88e-05 [grouped_pairwise_exchange_alltoall]: 1.69998e-06 [offloading_packed_experts]: 5.64e-06 [overlap_recompute_and_grad_model_parallel]: 6.66999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.70001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.69998e-06 [overlap_recompute_comm]: 2.59001e-06 [overlap_grad_ring_attention]: 6.60002e-06 [overlap_grad_flash_sp]: 2.908e-05 [begin_end_overlap_inline]: 5.39992e-07 [split_matmul_comm_elemetwise]: 2.53e-06 [split_layernorm_comm]: 2.06e-06 [handle_group_info]: 1.14003e-06 [symbol_engine_optimizer]: 0.00013311, [1] [Cycle 1]: 0.0001259, [6] [build]: 4.88001e-06 [elim_shapecalc]: 2.398e-05 [elim_not_effective]: 2.068e-05 [opt_reshape]: 1.281e-05 [fold_const_symbol]: 1.48e-05 [renormalize]: 2.00002e-07 [detach_backward]: 2.31998e-06 [pipeline_parallel_scheduler]: 1.44998e-06 [auto_monad_reorder]: 3.853e-05 [get_jit_bprop_graph]: 2.24001e-06 [rewriter_after_jit_bprop_graph]: 6.88e-06 [opt_after_jit_grad]: 0.00079368 [validate]: 7.158e-05 Sums bootstrap : 0.000866s : 5.23% type_inference : 0.007619s : 46.06% event_method : 0.000021s : 0.13% auto_monad : 0.000078s : 0.47% graph_reusing : 0.000006s : 0.04% inline : 0.000003s : 0.02% add_attr.add_attr_with_inline.tag_attr : 0.000029s : 0.18% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.03% parallel-infer-symbol : 0.000004s : 0.02% pre_auto_parallel : 0.000041s : 0.25% insert-virtual-dataset : 0.000003s : 0.02% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.01% pipeline_split : 0.000002s : 0.01% optimize.py_interpret_to_execute : 0.000065s : 0.39% optimize.rewriter_before_opt_a : 0.000115s : 0.69% optimize.opt_a.expand_dump_flag : 0.000010s : 0.06% optimize.opt_a.switch_simplify : 0.000049s : 0.30% optimize.opt_a.loop_unroll : 0.000028s : 0.17% optimize.opt_a.a_1 : 0.000801s : 4.84% optimize.opt_a.with_stream_mark : 0.000058s : 0.35% optimize.opt_a.recompute_prepare : 0.000027s : 0.17% optimize.opt_a.updatestate_depend_eliminate : 0.000014s : 0.08% optimize.opt_a.updatestate_assign_eliminate : 0.000013s : 0.08% optimize.opt_a.updatestate_loads_eliminate : 0.000013s : 0.08% optimize.opt_a.parameter_eliminate : 0.000005s : 0.03% optimize.opt_a.a_2 : 0.000257s : 1.56% optimize.opt_a.accelerated_algorithm : 0.000027s : 0.17% optimize.opt_a.shard : 0.000006s : 0.04% optimize.opt_a.meta_shard_fg_expand : 0.000008s : 0.05% optimize.opt_a.shard_inline : 0.000022s : 0.13% optimize.opt_a.merge_send_recv : 0.000022s : 0.13% optimize.opt_a.auto_parallel : 0.000022s : 0.13% optimize.opt_a.parallel : 0.000045s : 0.27% optimize.opt_a.flash_sp : 0.000017s : 0.11% optimize.opt_a.merge_comm : 0.000016s : 0.10% optimize.opt_a.allreduce_fusion : 0.000012s : 0.07% optimize.opt_a.matmul_add_comm_reduction : 0.000028s : 0.17% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.01% optimize.opt_a.virtual_shard_identity : 0.000030s : 0.18% optimize.opt_a.virtual_dataset : 0.000022s : 0.13% optimize.opt_a.get_grad_eliminate_ : 0.000021s : 0.13% optimize.opt_a.virtual_output : 0.000022s : 0.13% optimize.opt_a.merge_forward : 0.000014s : 0.08% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.03% optimize.opt_a.offload_activation : 0.000036s : 0.22% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000051s : 0.31% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.02% optimize.opt_a.before_grad : 0.000193s : 1.17% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000024s : 0.15% optimize.opt_a.meta_fg_expand : 0.000011s : 0.07% optimize.opt_a.flash_sp_send_recv_attached : 0.000007s : 0.04% optimize.opt_a.receive_attached : 0.000006s : 0.03% optimize.opt_a.after_resolve : 0.000067s : 0.41% optimize.opt_a.a_after_grad : 0.000035s : 0.21% optimize.opt_a.renormalize : 0.001472s : 8.90% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.11% optimize.opt_a.auto_monad_grad : 0.000004s : 0.03% optimize.opt_a.auto_monad_eliminator : 0.000037s : 0.23% optimize.opt_a.cse : 0.000186s : 1.12% optimize.opt_a.a_3 : 0.000159s : 0.96% optimize.py_interpret_to_execute_after_opt_a : 0.000028s : 0.17% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.02% optimize.rewriter_after_opt_a : 0.000074s : 0.44% optimize.convert_after_rewriter : 0.000010s : 0.06% optimize.order_py_execute_after_rewriter : 0.000007s : 0.04% optimize.mutable_eliminate : 0.000976s : 5.90% optimize.opt_b.b_1 : 0.000209s : 1.26% optimize.opt_b.b_2 : 0.000012s : 0.08% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.06% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.03% optimize.opt_b.updatestate_loads_eliminate : 0.000008s : 0.05% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000073s : 0.44% optimize.optimize_parallel_all_gather_comm : 0.000028s : 0.17% optimize.overlap_param_gather : 0.000003s : 0.02% optimize.cconv : 0.000047s : 0.28% optimize.loop_unroll : 0.000620s : 3.75% optimize.opt_after_cconv.c_1 : 0.000048s : 0.29% optimize.opt_after_cconv.parameter_eliminate : 0.000049s : 0.30% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.06% 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 : 0.000065s : 0.39% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000088s : 0.53% optimize.tuple_transform.d_1 : 0.000080s : 0.48% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000011s : 0.07% optimize.partial_unused_args_eliminate : 0.000002s : 0.01% optimize.add_recomputation : 0.000113s : 0.68% optimize.cse_after_recomputation.cse : 0.000033s : 0.20% optimize.environ_conv : 0.000009s : 0.06% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 0.05% optimize.bias_add_comm_swap : 0.000003s : 0.02% 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 : 0.000002s : 0.01% optimize.micro_interleaved_order_control : 0.000004s : 0.02% optimize.assign_add_opt : 0.000001s : 0.01% optimize.ForceFp32Comm : 0.000001s : 0.01% optimize.remove_cast_before_assign_add : 0.000001s : 0.01% optimize.full_micro_interleaved_order_control : 0.000003s : 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 : 0.000001s : 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 : 0.000003s : 0.02% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.01% optimize.control_data_broadcast_order : 0.000019s : 0.11% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.01% optimize.offloading_packed_experts : 0.000006s : 0.03% optimize.overlap_recompute_and_grad_model_parallel : 0.000007s : 0.04% 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 : 0.000029s : 0.18% 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 : 0.000005s : 0.03% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000024s : 0.14% optimize.symbol_engine_optimizer.elim_not_effective : 0.000021s : 0.13% optimize.symbol_engine_optimizer.opt_reshape : 0.000013s : 0.08% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000015s : 0.09% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.01% pipeline_parallel_scheduler : 0.000001s : 0.01% auto_monad_reorder : 0.000039s : 0.23% get_jit_bprop_graph : 0.000002s : 0.01% rewriter_after_jit_bprop_graph : 0.000007s : 0.04% opt_after_jit_grad : 0.000794s : 4.80% validate : 0.000072s : 0.43% Time group info: ------[substitution.] 0.000201 30 1.05% : 0.000002s : 2: substitution.elim_not_effective 0.57% : 0.000001s : 2: substitution.fold_const_symbol 4.08% : 0.000008s : 7: substitution.graph_param_transform 83.05% : 0.000167s : 1: substitution.inline 2.91% : 0.000006s : 4: substitution.j_node_and_user_rematch 3.20% : 0.000006s : 4: substitution.remove_not_recompute_node 5.15% : 0.000010s : 10: substitution.replace_old_param ------[type_inference.] 0.007480 2 84.95% : 0.006354s : 1: type_inference.infer 15.05% : 0.001126s : 1: type_inference.specialize ------[replace.] 0.000031 1 100.00% : 0.000031s : 1: replace.inline ------[match.] 0.000165 1 100.00% : 0.000165s : 1: match.inline ------[predicate.] 0.000237 1651 0.93% : 0.000002s : 15: predicate.accumulaten_eliminater 1.23% : 0.000003s : 7: predicate.ad_related_special_op_eliminate 0.67% : 0.000002s : 14: predicate.addn_check_dump 0.74% : 0.000002s : 15: predicate.addn_zero_filter 0.62% : 0.000001s : 15: predicate.adjust_all_reduce_mul_add 2.48% : 0.000006s : 29: predicate.arithmetic_simplify 0.76% : 0.000002s : 15: predicate.cast_eliminate 0.71% : 0.000002s : 14: predicate.check_bprop_eliminate 0.65% : 0.000002s : 14: predicate.compare_switch_simplify 0.25% : 0.000001s : 7: predicate.const_output_eliminate 0.89% : 0.000002s : 14: predicate.depend_value_elim 0.83% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 1.00% : 0.000002s : 15: predicate.dict_get_item_eliminator 0.79% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.37% : 0.000003s : 14: predicate.dumpgradient_eliminate 0.34% : 0.000001s : 7: predicate.elim_not_effective 0.73% : 0.000002s : 7: predicate.elim_shapecalc_of_broadcastargs 1.19% : 0.000003s : 22: predicate.environ_add_const_eliminate 1.01% : 0.000002s : 22: predicate.environ_get_add_eliminate 1.00% : 0.000002s : 22: predicate.environ_get_depend_swap 1.84% : 0.000004s : 36: predicate.environ_get_eliminate 1.20% : 0.000003s : 22: predicate.environ_get_set_eliminate 0.79% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.75% : 0.000004s : 16: predicate.float_depend_g_call 0.64% : 0.000002s : 14: predicate.float_environ_get_switch 1.00% : 0.000002s : 21: predicate.float_tuple_getitem_switch 0.25% : 0.000001s : 7: predicate.fold_const_symbol 0.96% : 0.000002s : 14: predicate.get_grad_eliminate 0.33% : 0.000001s : 7: predicate.graph_param_transform 0.64% : 0.000002s : 14: predicate.incorporate_call 0.57% : 0.000001s : 14: predicate.incorporate_call_switch 5.34% : 0.000013s : 73: predicate.inline 1.02% : 0.000002s : 14: predicate.inline_without_move 0.50% : 0.000001s : 14: predicate.j_node_and_user_rematch 2.08% : 0.000005s : 14: predicate.less_batch_normalization 2.07% : 0.000005s : 29: predicate.list_to_tuple_eliminator_ 2.05% : 0.000005s : 44: predicate.load_eliminater 1.22% : 0.000003s : 7: predicate.loop_unroll_after_grad 1.16% : 0.000003s : 22: predicate.loop_unroll_before_grad 1.91% : 0.000005s : 29: predicate.make_slice_get_slice_eliminator 0.71% : 0.000002s : 14: predicate.merge_addn 0.67% : 0.000002s : 14: predicate.micro_step_allgather_replace 0.71% : 0.000002s : 14: predicate.mini_step_allgather_replace 0.82% : 0.000002s : 15: predicate.minmaximum_grad 1.49% : 0.000004s : 7: predicate.mutable_eliminate 0.47% : 0.000001s : 7: predicate.opt_reshape 0.42% : 0.000001s : 7: predicate.parallel_virtual_node 0.98% : 0.000002s : 16: predicate.partial_defer_inline 1.14% : 0.000003s : 22: predicate.partial_eliminate 0.78% : 0.000002s : 15: predicate.print_const_string_wrapper 0.72% : 0.000002s : 14: predicate.reduce_all_const_elim 1.47% : 0.000003s : 15: predicate.reduce_eliminate 2.14% : 0.000005s : 44: predicate.redundant_stop_gradient_eliminater 0.71% : 0.000002s : 14: predicate.remove_not_recompute_node 1.23% : 0.000003s : 29: predicate.replace_applicator 0.77% : 0.000002s : 14: predicate.replace_old_param 0.35% : 0.000001s : 7: predicate.reset_defer_inline 0.95% : 0.000002s : 15: predicate.reshape_eliminate 0.83% : 0.000002s : 14: predicate.row_tensor_add_zeros_like 0.48% : 0.000001s : 7: predicate.row_tensor_eliminate 0.95% : 0.000002s : 14: predicate.same_eliminate 0.58% : 0.000001s : 14: predicate.set_cell_output_no_recompute 1.16% : 0.000003s : 14: predicate.shard_identity_eliminate 1.03% : 0.000002s : 14: predicate.special_op_eliminate 0.76% : 0.000002s : 14: predicate.specialize_transform 1.31% : 0.000003s : 14: predicate.split_environ_get_set_with_tuple_value 0.96% : 0.000002s : 14: predicate.stack_unstack_eliminate 0.39% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.83% : 0.000002s : 16: predicate.switch_defer_inline 1.56% : 0.000004s : 30: predicate.switch_layer_defer_inline 3.72% : 0.000009s : 59: predicate.switch_simplify 0.85% : 0.000002s : 15: predicate.tile_eliminate 1.14% : 0.000003s : 15: predicate.transpose_eliminate 1.57% : 0.000004s : 29: predicate.tuple_list_convert_item_index_to_positive 1.85% : 0.000004s : 29: predicate.tuple_list_get_item_const_eliminator 1.42% : 0.000003s : 29: predicate.tuple_list_get_item_depend_reorder 3.12% : 0.000007s : 43: predicate.tuple_list_get_item_eliminator 1.41% : 0.000003s : 29: predicate.tuple_list_get_set_item_eliminator 2.76% : 0.000007s : 43: predicate.tuple_list_set_item_eliminator 1.47% : 0.000003s : 29: predicate.tuple_to_list_eliminator_ 1.90% : 0.000004s : 44: predicate.updatestate_pure_node_eliminater 2.70% : 0.000006s : 58: predicate.updatestate_useless_node_eliminater 0.52% : 0.000001s : 7: predicate.value_based_eliminate 0.89% : 0.000002s : 14: predicate.virtual_dataset_eliminate 0.88% : 0.000002s : 14: predicate.virtual_output_eliminate 0.41% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.51% : 0.000001s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.001149 6 47.29% : 0.000543s : 3: func_graph_cloner_run.FuncGraphClonerGraph 52.71% : 0.000606s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.198353 192 0.00% : 0.000005s : 1: ForceFp32Comm 42.27% : 0.083840s : 1: add_attr 42.25% : 0.083814s : 1: add_attr_with_inline 0.00% : 0.000007s : 1: add_comm_op_reuse_tag 0.06% : 0.000121s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.04% : 0.000089s : 1: auto_monad 0.02% : 0.000043s : 1: auto_monad_reorder 0.00% : 0.000006s : 1: begin_end_overlap_inline 0.00% : 0.000008s : 1: bias_add_comm_swap 0.46% : 0.000909s : 1: bootstrap 0.03% : 0.000053s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.01% : 0.000023s : 1: control_data_broadcast_order 0.01% : 0.000014s : 1: convert_after_rewriter 0.03% : 0.000056s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000014s : 1: environ_conv 0.02% : 0.000030s : 1: event_method 0.00% : 0.000007s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.01% : 0.000011s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.01% : 0.000016s : 1: inline 0.01% : 0.000010s : 1: insert-virtual-dataset 0.00% : 0.000005s : 1: interleave_parallel_branches 0.00% : 0.000006s : 1: interleave_split_concat_branches 0.00% : 0.000009s : 1: label_fine_grained_interleaved_index 0.01% : 0.000012s : 1: label_micro_interleaved_index 0.32% : 0.000633s : 1: loop_unroll 0.00% : 0.000006s : 1: merge_cast_opt 0.00% : 0.000008s : 1: micro_interleaved_order_control 0.50% : 0.000990s : 1: mutable_eliminate 0.00% : 0.000010s : 1: offloading_packed_experts 0.01% : 0.000023s : 1: opt.transform.loop_unroll_optimizer 0.02% : 0.000030s : 1: opt.transform.mutable_eliminate 0.85% : 0.001695s : 78: opt.transform.opt_a 0.02% : 0.000046s : 1: opt.transform.opt_after_cconv 0.04% : 0.000072s : 1: opt.transform.opt_after_jit_grad 0.09% : 0.000188s : 28: opt.transform.opt_b 0.04% : 0.000088s : 2: opt.transform.opt_trans_graph 0.03% : 0.000068s : 4: opt.transform.symbol_engine_opt 2.58% : 0.005114s : 1: opt_a 0.12% : 0.000242s : 1: opt_after_cconv 0.41% : 0.000810s : 1: opt_after_jit_grad 0.20% : 0.000397s : 1: opt_b 4.40% : 0.008726s : 1: optimize 0.02% : 0.000033s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000011s : 1: order_py_execute_after_rewriter 0.02% : 0.000034s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000006s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000007s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000011s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000007s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000007s : 1: partial_unused_args_eliminate 0.00% : 0.000005s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000046s : 1: pre_auto_parallel 0.04% : 0.000074s : 1: py_interpret_to_execute 0.02% : 0.000032s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000005s : 1: remove_cast_before_assign_add 0.05% : 0.000093s : 1: remove_dup_value 0.31% : 0.000607s : 1: renormalize.infer 0.43% : 0.000851s : 1: renormalize.specialize 0.00% : 0.000009s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000014s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000078s : 1: rewriter_after_opt_a 0.06% : 0.000126s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000007s : 1: split_matmul_comm_elemetwise 0.01% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.07% : 0.000137s : 1: symbol_engine_optimizer 0.07% : 0.000132s : 1: tuple_transform 3.86% : 0.007653s : 1: type_inference . [hook] pytest_runtest_teardown:test_internel_asd_paged_attention[False-ms_dtype1] tests/st/infer/ops/test_internal_ops/test_asd_paged_attention.py::test_internel_asd_paged_attention[False-ms_dtype1],max_mem:350.0M [WARNING] ME(169973:281473287331632,MainProcess):2026-01-29-17:41:21.697.232 [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 = 0.619856, [21] [bootstrap]: 0.00336904 [type_inference]: 0.222248 [event_method]: 2.32e-05 [auto_monad]: 0.00012638 [graph_reusing]: 5.05999e-06 [inline]: 3.47002e-06 [add_attr]: 0.1918, [1] [add_attr_with_inline]: 0.191781, [1] [Cycle 1]: 0.00019401, [2] [tag_attr]: 5.161e-05 [meta_addattr_fg_expand]: 4.28999e-06 [parallel-infer-symbol]: 4.29002e-06 [pre_auto_parallel]: 3.801e-05 [insert-virtual-dataset]: 2.62001e-06 [parallel-infer-symbol-second]: 7.39994e-07 [dataset_repeat_opt]: 1.92999e-06 [pipeline_split]: 1.67001e-06 [optimize]: 0.200464, [53] [py_interpret_to_execute]: 0.00014081 [rewriter_before_opt_a]: 0.00016798 [opt_a]: 0.00766694, [2] [Cycle 1]: 0.00597278, [45] [expand_dump_flag]: 3.05998e-06 [switch_simplify]: 3.189e-05 [loop_unroll]: 1.782e-05 [a_1]: 0.00057459 [with_stream_mark]: 2.333e-05 [recompute_prepare]: 1.263e-05 [updatestate_depend_eliminate]: 3.378e-05 [updatestate_assign_eliminate]: 5.59998e-06 [updatestate_loads_eliminate]: 5.91e-06 [parameter_eliminate]: 2.37999e-06 [a_2]: 0.00016543 [accelerated_algorithm]: 5.419e-05 [shard]: 2.65002e-06 [meta_shard_fg_expand]: 2.93998e-06 [shard_inline]: 1.227e-05 [merge_send_recv]: 1.177e-05 [auto_parallel]: 1.103e-05 [parallel]: 0.00010427 [flash_sp]: 1.314e-05 [merge_comm]: 6.38e-06 [allreduce_fusion]: 5.26002e-06 [matmul_add_comm_reduction]: 2.837e-05 [allreduce_slice_to_reducescatter]: 7.29982e-07 [virtual_shard_identity]: 1.475e-05 [virtual_dataset]: 1.109e-05 [get_grad_eliminate_]: 1.032e-05 [virtual_output]: 4.401e-05 [merge_forward]: 7.22002e-06 [cell_reuse_recompute_pass]: 1.89e-06 [offload_activation]: 4.893e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.557e-05 [merge_recompute_call_nodes]: 1.82999e-06 [before_grad]: 1.698e-05 [set_forward_comm_id_for_comm_node_pass]: 7.04001e-06 [meta_fg_expand]: 4.60999e-06 [flash_sp_send_recv_attached]: 4e-06 [receive_attached]: 3.47997e-06 [after_resolve]: 8.733e-05 [a_after_grad]: 9.722e-05 [renormalize]: 0.00283644 [add_forward_monad_depend]: 3.557e-05 [auto_monad_grad]: 3.04999e-06 [auto_monad_eliminator]: 2.588e-05 [cse]: 0.00014195 [a_3]: 8.98e-05 [Cycle 2]: 0.0016584, [45] [expand_dump_flag]: 3.02002e-06 [switch_simplify]: 1.36e-05 [loop_unroll]: 1.203e-05 [a_1]: 0.00022685 [with_stream_mark]: 2.35e-05 [recompute_prepare]: 1.05e-05 [updatestate_depend_eliminate]: 6.16e-06 [updatestate_assign_eliminate]: 5.30999e-06 [updatestate_loads_eliminate]: 5.34998e-06 [parameter_eliminate]: 2.07999e-06 [a_2]: 0.00019148 [accelerated_algorithm]: 1.182e-05 [shard]: 2.95998e-06 [meta_shard_fg_expand]: 4.31002e-06 [shard_inline]: 9.70002e-06 [merge_send_recv]: 1.186e-05 [auto_parallel]: 1.384e-05 [parallel]: 1.087e-05 [flash_sp]: 5.14e-06 [merge_comm]: 6.63e-06 [allreduce_fusion]: 5.20999e-06 [matmul_add_comm_reduction]: 1.265e-05 [allreduce_slice_to_reducescatter]: 5.90022e-07 [virtual_shard_identity]: 1.455e-05 [virtual_dataset]: 1.09e-05 [get_grad_eliminate_]: 9.54e-06 [virtual_output]: 9.91e-06 [merge_forward]: 7.5e-06 [cell_reuse_recompute_pass]: 3.76999e-06 [offload_activation]: 1.427e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.46e-05 [merge_recompute_call_nodes]: 1.71e-06 [before_grad]: 1.586e-05 [set_forward_comm_id_for_comm_node_pass]: 6.86001e-06 [meta_fg_expand]: 4.95999e-06 [flash_sp_send_recv_attached]: 1.94e-06 [receive_attached]: 3.28e-06 [after_resolve]: 5.174e-05 [a_after_grad]: 1.574e-05 [renormalize]: 1.00001e-07 [add_forward_monad_depend]: 4.37e-06 [auto_monad_grad]: 2.39999e-06 [auto_monad_eliminator]: 1.638e-05 [cse]: 0.00012039 [a_3]: 6.876e-05 [py_interpret_to_execute_after_opt_a]: 2.874e-05 [slice_cell_reuse_recomputed_activation]: 2.75002e-06 [rewriter_after_opt_a]: 0.00034395 [convert_after_rewriter]: 1.419e-05 [order_py_execute_after_rewriter]: 7.10998e-06 [mutable_eliminate]: 0.00107816 [opt_b]: 0.0004886, [1] [Cycle 1]: 0.00042885, [7] [b_1]: 0.00021681 [b_2]: 1.321e-05 [updatestate_depend_eliminate]: 1.067e-05 [updatestate_assign_eliminate]: 5.10001e-06 [updatestate_loads_eliminate]: 5.29e-06 [renormalize]: 9.60019e-07 [cse]: 7.296e-05 [optimize_parallel_all_gather_comm]: 2.954e-05 [overlap_param_gather]: 2.805e-05 [cconv]: 3.856e-05 [loop_unroll]: 0.0138141 [opt_after_cconv]: 0.174406, [1] [Cycle 1]: 0.174332, [7] [c_1]: 9.039e-05 [parameter_eliminate]: 7.42002e-06 [updatestate_depend_eliminate]: 1.858e-05 [updatestate_assign_eliminate]: 5.72001e-06 [updatestate_loads_eliminate]: 6.39001e-06 [cse]: 0.17392 [renormalize]: 1.83002e-06 [remove_dup_value]: 0.00010511 [tuple_transform]: 0.00028551, [1] [Cycle 1]: 0.00027217, [4] [d_1]: 0.0001937 [none_parameter_eliminate]: 6.63e-06 [renormalize]: 2.69996e-07 [switch_simplify]: 1.489e-05 [partial_unused_args_eliminate]: 2.39001e-06 [add_recomputation]: 0.00016648 [cse_after_recomputation]: 0.000104, [1] [Cycle 1]: 9.765e-05, [1] [cse]: 8.776e-05 [environ_conv]: 0.00011433 [swap_dp_allreduce_reducescatter]: 1.036e-05 [bias_add_comm_swap]: 4.15999e-06 [label_micro_interleaved_index]: 9.65002e-06 [label_fine_grained_interleaved_index]: 3.38e-06 [merge_cast_opt]: 1.49e-06 [slice_recompute_activation]: 2.22999e-06 [micro_interleaved_order_control]: 2.51998e-06 [assign_add_opt]: 1.57001e-06 [ForceFp32Comm]: 1.50999e-06 [remove_cast_before_assign_add]: 1.29e-06 [full_micro_interleaved_order_control]: 2.66999e-06 [reorder_send_recv_between_fp_bp]: 2.414e-05 [comm_op_add_attrs]: 1.05999e-06 [add_comm_op_reuse_tag]: 9.39996e-07 [interleave_split_concat_branches]: 1.84e-06 [interleave_parallel_branches]: 1.20001e-06 [overlap_opt_shard_in_pipeline]: 2.742e-05 [overlap_opt_shard_grad_in_pipeline]: 1.96e-06 [control_data_broadcast_order]: 2.403e-05 [grouped_pairwise_exchange_alltoall]: 1.62001e-06 [offloading_packed_experts]: 6.09999e-06 [overlap_recompute_and_grad_model_parallel]: 7.75e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.57001e-06 [overlap_recompute_allgather_and_fa_grad]: 1.56998e-06 [overlap_recompute_comm]: 2.73e-06 [overlap_grad_ring_attention]: 6.18998e-06 [overlap_grad_flash_sp]: 5.195e-05 [begin_end_overlap_inline]: 5.19998e-07 [split_matmul_comm_elemetwise]: 2.18002e-06 [split_layernorm_comm]: 2.05002e-06 [handle_group_info]: 9.89996e-07 [symbol_engine_optimizer]: 0.0005484, [1] [Cycle 1]: 0.00053944, [6] [build]: 0.00015324 [elim_shapecalc]: 5.356e-05 [elim_not_effective]: 6.208e-05 [opt_reshape]: 6.557e-05 [fold_const_symbol]: 4.765e-05 [renormalize]: 2.50002e-07 [detach_backward]: 3.13998e-06 [pipeline_parallel_scheduler]: 1.99999e-06 [auto_monad_reorder]: 4.022e-05 [get_jit_bprop_graph]: 3.11999e-06 [rewriter_after_jit_bprop_graph]: 3.522e-05 [opt_after_jit_grad]: 0.00125957 [validate]: 0.00011591 Sums bootstrap : 0.003369s : 0.79% type_inference : 0.222248s : 52.37% event_method : 0.000023s : 0.01% auto_monad : 0.000126s : 0.03% graph_reusing : 0.000005s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000052s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000038s : 0.01% 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 : 0.000141s : 0.03% optimize.rewriter_before_opt_a : 0.000168s : 0.04% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000045s : 0.01% optimize.opt_a.loop_unroll : 0.000030s : 0.01% optimize.opt_a.a_1 : 0.000801s : 0.19% optimize.opt_a.with_stream_mark : 0.000047s : 0.01% optimize.opt_a.recompute_prepare : 0.000023s : 0.01% optimize.opt_a.updatestate_depend_eliminate : 0.000040s : 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 : 0.000004s : 0.00% optimize.opt_a.a_2 : 0.000357s : 0.08% optimize.opt_a.accelerated_algorithm : 0.000066s : 0.02% optimize.opt_a.shard : 0.000006s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000007s : 0.00% optimize.opt_a.shard_inline : 0.000022s : 0.01% optimize.opt_a.merge_send_recv : 0.000024s : 0.01% optimize.opt_a.auto_parallel : 0.000025s : 0.01% optimize.opt_a.parallel : 0.000115s : 0.03% optimize.opt_a.flash_sp : 0.000018s : 0.00% optimize.opt_a.merge_comm : 0.000013s : 0.00% optimize.opt_a.allreduce_fusion : 0.000010s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000041s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000001s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000029s : 0.01% optimize.opt_a.virtual_dataset : 0.000022s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000020s : 0.00% optimize.opt_a.virtual_output : 0.000054s : 0.01% optimize.opt_a.merge_forward : 0.000015s : 0.00% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000063s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000070s : 0.02% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000033s : 0.01% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.00% optimize.opt_a.meta_fg_expand : 0.000010s : 0.00% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.00% optimize.opt_a.receive_attached : 0.000007s : 0.00% optimize.opt_a.after_resolve : 0.000139s : 0.03% optimize.opt_a.a_after_grad : 0.000113s : 0.03% optimize.opt_a.renormalize : 0.002837s : 0.67% optimize.opt_a.add_forward_monad_depend : 0.000040s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000042s : 0.01% optimize.opt_a.cse : 0.000262s : 0.06% optimize.opt_a.a_3 : 0.000159s : 0.04% 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 : 0.000344s : 0.08% optimize.convert_after_rewriter : 0.000014s : 0.00% optimize.order_py_execute_after_rewriter : 0.000007s : 0.00% optimize.mutable_eliminate : 0.001078s : 0.25% optimize.opt_b.b_1 : 0.000217s : 0.05% optimize.opt_b.b_2 : 0.000013s : 0.00% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 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 : 0.000073s : 0.02% optimize.optimize_parallel_all_gather_comm : 0.000030s : 0.01% optimize.overlap_param_gather : 0.000028s : 0.01% optimize.cconv : 0.000039s : 0.01% optimize.loop_unroll : 0.013814s : 3.26% optimize.opt_after_cconv.c_1 : 0.000090s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.000007s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000019s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.cse : 0.173920s : 40.98% optimize.opt_after_cconv.renormalize : 0.000002s : 0.00% optimize.remove_dup_value : 0.000105s : 0.02% optimize.tuple_transform.d_1 : 0.000194s : 0.05% optimize.tuple_transform.none_parameter_eliminate : 0.000007s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000015s : 0.00% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000166s : 0.04% optimize.cse_after_recomputation.cse : 0.000088s : 0.02% optimize.environ_conv : 0.000114s : 0.03% optimize.swap_dp_allreduce_reducescatter : 0.000010s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000010s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000002s : 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 : 0.000024s : 0.01% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000002s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000027s : 0.01% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000024s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000006s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000008s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000002s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000003s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000052s : 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 : 0.000153s : 0.04% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000054s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000062s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000066s : 0.02% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000048s : 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 : 0.000040s : 0.01% get_jit_bprop_graph : 0.000003s : 0.00% rewriter_after_jit_bprop_graph : 0.000035s : 0.01% opt_after_jit_grad : 0.001260s : 0.30% validate : 0.000116s : 0.03% Time group info: ------[substitution.] 0.000343 30 11.39% : 0.000039s : 2: substitution.elim_not_effective 3.12% : 0.000011s : 2: substitution.fold_const_symbol 3.08% : 0.000011s : 7: substitution.graph_param_transform 75.95% : 0.000261s : 1: substitution.inline 1.43% : 0.000005s : 4: substitution.j_node_and_user_rematch 1.80% : 0.000006s : 4: substitution.remove_not_recompute_node 3.23% : 0.000011s : 10: substitution.replace_old_param ------[type_inference.] 0.222036 2 98.01% : 0.217609s : 1: type_inference.infer 1.99% : 0.004427s : 1: type_inference.specialize ------[replace.] 0.000024 1 100.00% : 0.000024s : 1: replace.inline ------[match.] 0.000260 1 100.00% : 0.000260s : 1: match.inline ------[predicate.] 0.000325 1651 0.55% : 0.000002s : 15: predicate.accumulaten_eliminater 1.19% : 0.000004s : 7: predicate.ad_related_special_op_eliminate 0.53% : 0.000002s : 14: predicate.addn_check_dump 0.58% : 0.000002s : 15: predicate.addn_zero_filter 0.48% : 0.000002s : 15: predicate.adjust_all_reduce_mul_add 1.36% : 0.000004s : 29: predicate.arithmetic_simplify 0.73% : 0.000002s : 15: predicate.cast_eliminate 0.52% : 0.000002s : 14: predicate.check_bprop_eliminate 0.59% : 0.000002s : 14: predicate.compare_switch_simplify 0.17% : 0.000001s : 7: predicate.const_output_eliminate 0.58% : 0.000002s : 14: predicate.depend_value_elim 0.49% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.66% : 0.000002s : 15: predicate.dict_get_item_eliminator 0.60% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.13% : 0.000004s : 14: predicate.dumpgradient_eliminate 0.31% : 0.000001s : 7: predicate.elim_not_effective 0.43% : 0.000001s : 7: predicate.elim_shapecalc_of_broadcastargs 0.79% : 0.000003s : 22: predicate.environ_add_const_eliminate 0.69% : 0.000002s : 22: predicate.environ_get_add_eliminate 0.71% : 0.000002s : 22: predicate.environ_get_depend_swap 1.28% : 0.000004s : 36: predicate.environ_get_eliminate 0.72% : 0.000002s : 22: predicate.environ_get_set_eliminate 0.54% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.10% : 0.000004s : 16: predicate.float_depend_g_call 0.46% : 0.000001s : 14: predicate.float_environ_get_switch 0.79% : 0.000003s : 21: predicate.float_tuple_getitem_switch 0.26% : 0.000001s : 7: predicate.fold_const_symbol 0.60% : 0.000002s : 14: predicate.get_grad_eliminate 0.38% : 0.000001s : 7: predicate.graph_param_transform 0.49% : 0.000002s : 14: predicate.incorporate_call 0.41% : 0.000001s : 14: predicate.incorporate_call_switch 4.50% : 0.000015s : 73: predicate.inline 0.75% : 0.000002s : 14: predicate.inline_without_move 0.34% : 0.000001s : 14: predicate.j_node_and_user_rematch 7.50% : 0.000024s : 14: predicate.less_batch_normalization 1.48% : 0.000005s : 29: predicate.list_to_tuple_eliminator_ 1.64% : 0.000005s : 44: predicate.load_eliminater 2.39% : 0.000008s : 7: predicate.loop_unroll_after_grad 0.98% : 0.000003s : 22: predicate.loop_unroll_before_grad 1.49% : 0.000005s : 29: predicate.make_slice_get_slice_eliminator 0.64% : 0.000002s : 14: predicate.merge_addn 0.59% : 0.000002s : 14: predicate.micro_step_allgather_replace 0.54% : 0.000002s : 14: predicate.mini_step_allgather_replace 0.45% : 0.000001s : 15: predicate.minmaximum_grad 1.33% : 0.000004s : 7: predicate.mutable_eliminate 0.30% : 0.000001s : 7: predicate.opt_reshape 0.31% : 0.000001s : 7: predicate.parallel_virtual_node 0.68% : 0.000002s : 16: predicate.partial_defer_inline 0.87% : 0.000003s : 22: predicate.partial_eliminate 0.53% : 0.000002s : 15: predicate.print_const_string_wrapper 0.54% : 0.000002s : 14: predicate.reduce_all_const_elim 0.87% : 0.000003s : 15: predicate.reduce_eliminate 1.59% : 0.000005s : 44: predicate.redundant_stop_gradient_eliminater 0.54% : 0.000002s : 14: predicate.remove_not_recompute_node 1.02% : 0.000003s : 29: predicate.replace_applicator 0.65% : 0.000002s : 14: predicate.replace_old_param 0.34% : 0.000001s : 7: predicate.reset_defer_inline 0.55% : 0.000002s : 15: predicate.reshape_eliminate 0.55% : 0.000002s : 14: predicate.row_tensor_add_zeros_like 0.41% : 0.000001s : 7: predicate.row_tensor_eliminate 0.87% : 0.000003s : 14: predicate.same_eliminate 0.47% : 0.000002s : 14: predicate.set_cell_output_no_recompute 0.84% : 0.000003s : 14: predicate.shard_identity_eliminate 0.67% : 0.000002s : 14: predicate.special_op_eliminate 18.05% : 0.000059s : 14: predicate.specialize_transform 1.06% : 0.000003s : 14: predicate.split_environ_get_set_with_tuple_value 0.97% : 0.000003s : 14: predicate.stack_unstack_eliminate 0.33% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.55% : 0.000002s : 16: predicate.switch_defer_inline 1.06% : 0.000003s : 30: predicate.switch_layer_defer_inline 2.88% : 0.000009s : 59: predicate.switch_simplify 0.60% : 0.000002s : 15: predicate.tile_eliminate 0.88% : 0.000003s : 15: predicate.transpose_eliminate 1.36% : 0.000004s : 29: predicate.tuple_list_convert_item_index_to_positive 1.23% : 0.000004s : 29: predicate.tuple_list_get_item_const_eliminator 1.02% : 0.000003s : 29: predicate.tuple_list_get_item_depend_reorder 2.73% : 0.000009s : 43: predicate.tuple_list_get_item_eliminator 1.13% : 0.000004s : 29: predicate.tuple_list_get_set_item_eliminator 1.94% : 0.000006s : 43: predicate.tuple_list_set_item_eliminator 1.18% : 0.000004s : 29: predicate.tuple_to_list_eliminator_ 1.37% : 0.000004s : 44: predicate.updatestate_pure_node_eliminater 2.18% : 0.000007s : 58: predicate.updatestate_useless_node_eliminater 0.30% : 0.000001s : 7: predicate.value_based_eliminate 0.62% : 0.000002s : 14: predicate.virtual_dataset_eliminate 0.63% : 0.000002s : 14: predicate.virtual_output_eliminate 0.25% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.35% : 0.000001s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.004945 6 59.93% : 0.002963s : 3: func_graph_cloner_run.FuncGraphClonerGraph 40.07% : 0.001982s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 1.017405 192 0.00% : 0.000006s : 1: ForceFp32Comm 18.85% : 0.191808s : 1: add_attr 18.85% : 0.191785s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000173s : 1: add_recomputation 0.01% : 0.000085s : 1: assign_add_opt 0.01% : 0.000134s : 1: auto_monad 0.00% : 0.000045s : 1: auto_monad_reorder 0.00% : 0.000003s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.34% : 0.003498s : 1: bootstrap 0.00% : 0.000043s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.00% : 0.000029s : 1: control_data_broadcast_order 0.00% : 0.000018s : 1: convert_after_rewriter 0.01% : 0.000108s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000008s : 1: detach_backward 0.01% : 0.000119s : 1: environ_conv 0.00% : 0.000031s : 1: event_method 0.00% : 0.000045s : 1: full_micro_interleaved_order_control 0.00% : 0.000007s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 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% : 0.000006s : 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% : 0.000013s : 1: label_micro_interleaved_index 1.36% : 0.013846s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.11% : 0.001092s : 1: mutable_eliminate 0.00% : 0.000036s : 1: offloading_packed_experts 0.01% : 0.000056s : 1: opt.transform.loop_unroll_optimizer 0.00% : 0.000028s : 1: opt.transform.mutable_eliminate 0.18% : 0.001833s : 78: opt.transform.opt_a 0.01% : 0.000088s : 1: opt.transform.opt_after_cconv 0.01% : 0.000127s : 1: opt.transform.opt_after_jit_grad 0.02% : 0.000194s : 28: opt.transform.opt_b 0.02% : 0.000200s : 2: opt.transform.opt_trans_graph 0.02% : 0.000221s : 4: opt.transform.symbol_engine_opt 0.76% : 0.007688s : 1: opt_a 17.14% : 0.174415s : 1: opt_after_cconv 0.13% : 0.001280s : 1: opt_after_jit_grad 0.05% : 0.000494s : 1: opt_b 19.70% : 0.200473s : 1: optimize 0.00% : 0.000035s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.01% : 0.000057s : 1: overlap_grad_flash_sp 0.00% : 0.000006s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000032s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000032s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000033s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000033s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000006s : 1: overlap_recompute_comm 0.00% : 0.000010s : 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% : 0.000004s : 1: pipeline_split 0.00% : 0.000042s : 1: pre_auto_parallel 0.01% : 0.000146s : 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% : 0.000151s : 1: remove_dup_value 0.13% : 0.001336s : 1: renormalize.infer 0.14% : 0.001468s : 1: renormalize.specialize 0.00% : 0.000050s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000040s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000358s : 1: rewriter_after_opt_a 0.02% : 0.000173s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000029s : 1: split_matmul_comm_elemetwise 0.00% : 0.000014s : 1: swap_dp_allreduce_reducescatter 0.06% : 0.000576s : 1: symbol_engine_optimizer 0.03% : 0.000289s : 1: tuple_transform 21.85% : 0.222279s : 1: type_inference . [hook] pytest_runtest_teardown:test_internel_asd_paged_attention[True-ms_dtype0] tests/st/infer/ops/test_internal_ops/test_asd_paged_attention.py::test_internel_asd_paged_attention[True-ms_dtype0],max_mem:386.0M [WARNING] ME(169973:281473287331632,MainProcess):2026-01-29-17:44:33.273.854 [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 = 0.109531, [21] [bootstrap]: 0.00104668 [type_inference]: 0.0556248 [event_method]: 1.929e-05 [auto_monad]: 8.967e-05 [graph_reusing]: 4.97999e-06 [inline]: 2.71e-06 [add_attr]: 0.00617868, [1] [add_attr_with_inline]: 0.0061355, [1] [Cycle 1]: 9.746e-05, [2] [tag_attr]: 2.372e-05 [meta_addattr_fg_expand]: 4.48999e-06 [parallel-infer-symbol]: 3.95998e-06 [pre_auto_parallel]: 4.117e-05 [insert-virtual-dataset]: 2.66999e-06 [parallel-infer-symbol-second]: 7.09988e-07 [dataset_repeat_opt]: 2.02999e-06 [pipeline_split]: 1.79998e-06 [optimize]: 0.0456029, [53] [py_interpret_to_execute]: 5.519e-05 [rewriter_before_opt_a]: 0.0001026 [opt_a]: 0.0418826, [2] [Cycle 1]: 0.00270936, [45] [expand_dump_flag]: 3.35e-06 [switch_simplify]: 3.01e-05 [loop_unroll]: 2.386e-05 [a_1]: 0.00048071 [with_stream_mark]: 2.678e-05 [recompute_prepare]: 1.44e-05 [updatestate_depend_eliminate]: 6.46e-06 [updatestate_assign_eliminate]: 5.84999e-06 [updatestate_loads_eliminate]: 5.52001e-06 [parameter_eliminate]: 2.86e-06 [a_2]: 0.00013108 [accelerated_algorithm]: 1.301e-05 [shard]: 2.53e-06 [meta_shard_fg_expand]: 2.55997e-06 [shard_inline]: 1.024e-05 [merge_send_recv]: 1.185e-05 [auto_parallel]: 1.032e-05 [parallel]: 7.365e-05 [flash_sp]: 1.347e-05 [merge_comm]: 8.05999e-06 [allreduce_fusion]: 5.35999e-06 [matmul_add_comm_reduction]: 1.286e-05 [allreduce_slice_to_reducescatter]: 8.60018e-07 [virtual_shard_identity]: 1.445e-05 [virtual_dataset]: 1.211e-05 [get_grad_eliminate_]: 1.141e-05 [virtual_output]: 1.082e-05 [merge_forward]: 6.68e-06 [cell_reuse_recompute_pass]: 2.21998e-06 [offload_activation]: 1.38e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.531e-05 [merge_recompute_call_nodes]: 2.32999e-06 [before_grad]: 1.667e-05 [set_forward_comm_id_for_comm_node_pass]: 6.44999e-06 [meta_fg_expand]: 4.15e-06 [flash_sp_send_recv_attached]: 3.56001e-06 [receive_attached]: 2.84999e-06 [after_resolve]: 2.272e-05 [a_after_grad]: 1.876e-05 [renormalize]: 0.00105419 [add_forward_monad_depend]: 9.04998e-06 [auto_monad_grad]: 2.59001e-06 [auto_monad_eliminator]: 2.455e-05 [cse]: 9.109e-05 [a_3]: 9.063e-05 [Cycle 2]: 0.0391563, [45] [expand_dump_flag]: 2.91e-06 [switch_simplify]: 1.363e-05 [loop_unroll]: 1.081e-05 [a_1]: 0.037973 [with_stream_mark]: 4.438e-05 [recompute_prepare]: 2.182e-05 [updatestate_depend_eliminate]: 7.21001e-06 [updatestate_assign_eliminate]: 5.43002e-06 [updatestate_loads_eliminate]: 6.90998e-06 [parameter_eliminate]: 2.61e-06 [a_2]: 0.00014075 [accelerated_algorithm]: 1.293e-05 [shard]: 3.61999e-06 [meta_shard_fg_expand]: 6.63998e-06 [shard_inline]: 9.87999e-06 [merge_send_recv]: 1.303e-05 [auto_parallel]: 1.292e-05 [parallel]: 1.178e-05 [flash_sp]: 4.4e-06 [merge_comm]: 5.56e-06 [allreduce_fusion]: 5.76998e-06 [matmul_add_comm_reduction]: 1.364e-05 [allreduce_slice_to_reducescatter]: 9.40025e-07 [virtual_shard_identity]: 1.788e-05 [virtual_dataset]: 1.081e-05 [get_grad_eliminate_]: 1.071e-05 [virtual_output]: 9.69999e-06 [merge_forward]: 7.92003e-06 [cell_reuse_recompute_pass]: 3.18e-06 [offload_activation]: 1.441e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.12e-05 [merge_recompute_call_nodes]: 1.49e-06 [before_grad]: 1.566e-05 [set_forward_comm_id_for_comm_node_pass]: 7.19001e-06 [meta_fg_expand]: 4.86997e-06 [flash_sp_send_recv_attached]: 2.50002e-06 [receive_attached]: 3.48e-06 [after_resolve]: 2.21e-05 [a_after_grad]: 1.747e-05 [renormalize]: 6.99947e-08 [add_forward_monad_depend]: 4.54002e-06 [auto_monad_grad]: 3.63999e-06 [auto_monad_eliminator]: 3.512e-05 [cse]: 9.074e-05 [a_3]: 7.166e-05 [py_interpret_to_execute_after_opt_a]: 3.284e-05 [slice_cell_reuse_recomputed_activation]: 2.59999e-06 [rewriter_after_opt_a]: 7.775e-05 [convert_after_rewriter]: 1.004e-05 [order_py_execute_after_rewriter]: 6.82002e-06 [mutable_eliminate]: 0.00087321 [opt_b]: 0.00046585, [1] [Cycle 1]: 0.00043714, [7] [b_1]: 0.00021486 [b_2]: 1.399e-05 [updatestate_depend_eliminate]: 1.135e-05 [updatestate_assign_eliminate]: 4.92999e-06 [updatestate_loads_eliminate]: 5.56e-06 [renormalize]: 5.99975e-07 [cse]: 0.00012607 [optimize_parallel_all_gather_comm]: 4.631e-05 [overlap_param_gather]: 3.05002e-06 [cconv]: 3.932e-05 [loop_unroll]: 0.0005929 [opt_after_cconv]: 0.00018408, [1] [Cycle 1]: 0.0001754, [7] [c_1]: 4.865e-05 [parameter_eliminate]: 5.22999e-06 [updatestate_depend_eliminate]: 8.93002e-06 [updatestate_assign_eliminate]: 4.4e-06 [updatestate_loads_eliminate]: 4.13999e-06 [cse]: 5.404e-05 [renormalize]: 5.39992e-07 [remove_dup_value]: 8.086e-05 [tuple_transform]: 0.00012078, [1] [Cycle 1]: 0.00011441, [4] [d_1]: 7.583e-05 [none_parameter_eliminate]: 2.19999e-06 [renormalize]: 1.30007e-07 [switch_simplify]: 1.158e-05 [partial_unused_args_eliminate]: 1.74e-06 [add_recomputation]: 0.00010082 [cse_after_recomputation]: 4.5e-05, [1] [Cycle 1]: 3.965e-05, [1] [cse]: 3.037e-05 [environ_conv]: 8.08001e-06 [swap_dp_allreduce_reducescatter]: 7.49002e-06 [bias_add_comm_swap]: 2.74999e-06 [label_micro_interleaved_index]: 5.53002e-06 [label_fine_grained_interleaved_index]: 2.78998e-06 [merge_cast_opt]: 1.45999e-06 [slice_recompute_activation]: 2.03002e-06 [micro_interleaved_order_control]: 2.54001e-06 [assign_add_opt]: 1.39e-06 [ForceFp32Comm]: 8.79983e-07 [remove_cast_before_assign_add]: 1.18001e-06 [full_micro_interleaved_order_control]: 2.14e-06 [reorder_send_recv_between_fp_bp]: 3.38e-06 [comm_op_add_attrs]: 1.00999e-06 [add_comm_op_reuse_tag]: 9.20001e-07 [interleave_split_concat_branches]: 1.39e-06 [interleave_parallel_branches]: 1.25001e-06 [overlap_opt_shard_in_pipeline]: 2.64001e-06 [overlap_opt_shard_grad_in_pipeline]: 2.10002e-06 [control_data_broadcast_order]: 1.975e-05 [grouped_pairwise_exchange_alltoall]: 1.55999e-06 [offloading_packed_experts]: 5.42001e-06 [overlap_recompute_and_grad_model_parallel]: 6.48e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.41998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.57999e-06 [overlap_recompute_comm]: 2.29001e-06 [overlap_grad_ring_attention]: 5.22999e-06 [overlap_grad_flash_sp]: 4.158e-05 [begin_end_overlap_inline]: 6.69999e-07 [split_matmul_comm_elemetwise]: 2.39999e-06 [split_layernorm_comm]: 2.49001e-06 [handle_group_info]: 9.80013e-07 [symbol_engine_optimizer]: 0.00033178, [1] [Cycle 1]: 0.0003259, [6] [build]: 0.00017723 [elim_shapecalc]: 2.163e-05 [elim_not_effective]: 4.193e-05 [opt_reshape]: 1.263e-05 [fold_const_symbol]: 2.124e-05 [renormalize]: 1.69995e-07 [detach_backward]: 2.99999e-06 [pipeline_parallel_scheduler]: 1.80001e-06 [auto_monad_reorder]: 3.493e-05 [get_jit_bprop_graph]: 2.02001e-06 [rewriter_after_jit_bprop_graph]: 5.17e-06 [opt_after_jit_grad]: 0.00060561 [validate]: 5.833e-05 Sums bootstrap : 0.001047s : 1.03% type_inference : 0.055625s : 54.69% event_method : 0.000019s : 0.02% auto_monad : 0.000090s : 0.09% graph_reusing : 0.000005s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000024s : 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 : 0.000041s : 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 : 0.000055s : 0.05% optimize.rewriter_before_opt_a : 0.000103s : 0.10% optimize.opt_a.expand_dump_flag : 0.000006s : 0.01% optimize.opt_a.switch_simplify : 0.000044s : 0.04% optimize.opt_a.loop_unroll : 0.000035s : 0.03% optimize.opt_a.a_1 : 0.038454s : 37.81% optimize.opt_a.with_stream_mark : 0.000071s : 0.07% optimize.opt_a.recompute_prepare : 0.000036s : 0.04% optimize.opt_a.updatestate_depend_eliminate : 0.000014s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000011s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.01% optimize.opt_a.parameter_eliminate : 0.000005s : 0.01% optimize.opt_a.a_2 : 0.000272s : 0.27% optimize.opt_a.accelerated_algorithm : 0.000026s : 0.03% optimize.opt_a.shard : 0.000006s : 0.01% optimize.opt_a.meta_shard_fg_expand : 0.000009s : 0.01% optimize.opt_a.shard_inline : 0.000020s : 0.02% optimize.opt_a.merge_send_recv : 0.000025s : 0.02% optimize.opt_a.auto_parallel : 0.000023s : 0.02% optimize.opt_a.parallel : 0.000085s : 0.08% optimize.opt_a.flash_sp : 0.000018s : 0.02% optimize.opt_a.merge_comm : 0.000014s : 0.01% optimize.opt_a.allreduce_fusion : 0.000011s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000026s : 0.03% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000032s : 0.03% optimize.opt_a.virtual_dataset : 0.000023s : 0.02% optimize.opt_a.get_grad_eliminate_ : 0.000022s : 0.02% optimize.opt_a.virtual_output : 0.000021s : 0.02% optimize.opt_a.merge_forward : 0.000015s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.01% optimize.opt_a.offload_activation : 0.000028s : 0.03% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000057s : 0.06% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000032s : 0.03% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000014s : 0.01% optimize.opt_a.meta_fg_expand : 0.000009s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000006s : 0.01% optimize.opt_a.receive_attached : 0.000006s : 0.01% optimize.opt_a.after_resolve : 0.000045s : 0.04% optimize.opt_a.a_after_grad : 0.000036s : 0.04% optimize.opt_a.renormalize : 0.001054s : 1.04% optimize.opt_a.add_forward_monad_depend : 0.000014s : 0.01% optimize.opt_a.auto_monad_grad : 0.000006s : 0.01% optimize.opt_a.auto_monad_eliminator : 0.000060s : 0.06% optimize.opt_a.cse : 0.000182s : 0.18% optimize.opt_a.a_3 : 0.000162s : 0.16% optimize.py_interpret_to_execute_after_opt_a : 0.000033s : 0.03% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000078s : 0.08% optimize.convert_after_rewriter : 0.000010s : 0.01% optimize.order_py_execute_after_rewriter : 0.000007s : 0.01% optimize.mutable_eliminate : 0.000873s : 0.86% optimize.opt_b.b_1 : 0.000215s : 0.21% optimize.opt_b.b_2 : 0.000014s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000011s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000006s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000126s : 0.12% optimize.optimize_parallel_all_gather_comm : 0.000046s : 0.05% optimize.overlap_param_gather : 0.000003s : 0.00% optimize.cconv : 0.000039s : 0.04% optimize.loop_unroll : 0.000593s : 0.58% optimize.opt_after_cconv.c_1 : 0.000049s : 0.05% optimize.opt_after_cconv.parameter_eliminate : 0.000005s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000009s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.cse : 0.000054s : 0.05% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000081s : 0.08% optimize.tuple_transform.d_1 : 0.000076s : 0.07% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000012s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000101s : 0.10% optimize.cse_after_recomputation.cse : 0.000030s : 0.03% optimize.environ_conv : 0.000008s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000007s : 0.01% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.01% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000020s : 0.02% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000005s : 0.01% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 0.01% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000005s : 0.01% optimize.overlap_grad_flash_sp : 0.000042s : 0.04% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000177s : 0.17% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000022s : 0.02% optimize.symbol_engine_optimizer.elim_not_effective : 0.000042s : 0.04% optimize.symbol_engine_optimizer.opt_reshape : 0.000013s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000021s : 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 : 0.000035s : 0.03% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000005s : 0.01% opt_after_jit_grad : 0.000606s : 0.60% validate : 0.000058s : 0.06% Time group info: ------[substitution.] 0.000204 30 11.78% : 0.000024s : 2: substitution.elim_not_effective 3.98% : 0.000008s : 2: substitution.fold_const_symbol 3.83% : 0.000008s : 7: substitution.graph_param_transform 70.05% : 0.000143s : 1: substitution.inline 2.61% : 0.000005s : 4: substitution.j_node_and_user_rematch 3.24% : 0.000007s : 4: substitution.remove_not_recompute_node 4.51% : 0.000009s : 10: substitution.replace_old_param ------[type_inference.] 0.055495 2 98.41% : 0.054611s : 1: type_inference.infer 1.59% : 0.000884s : 1: type_inference.specialize ------[replace.] 0.000026 1 100.00% : 0.000026s : 1: replace.inline ------[match.] 0.000141 1 100.00% : 0.000141s : 1: match.inline ------[predicate.] 0.000262 1651 0.78% : 0.000002s : 15: predicate.accumulaten_eliminater 0.93% : 0.000002s : 7: predicate.ad_related_special_op_eliminate 0.61% : 0.000002s : 14: predicate.addn_check_dump 0.60% : 0.000002s : 15: predicate.addn_zero_filter 0.57% : 0.000001s : 15: predicate.adjust_all_reduce_mul_add 2.34% : 0.000006s : 29: predicate.arithmetic_simplify 0.70% : 0.000002s : 15: predicate.cast_eliminate 0.84% : 0.000002s : 14: predicate.check_bprop_eliminate 0.60% : 0.000002s : 14: predicate.compare_switch_simplify 0.20% : 0.000001s : 7: predicate.const_output_eliminate 0.76% : 0.000002s : 14: predicate.depend_value_elim 0.74% : 0.000002s : 15: predicate.dict_get_item_const_eliminator 0.80% : 0.000002s : 15: predicate.dict_get_item_eliminator 0.73% : 0.000002s : 15: predicate.dict_set_item_eliminator 1.14% : 0.000003s : 14: predicate.dumpgradient_eliminate 0.35% : 0.000001s : 7: predicate.elim_not_effective 0.65% : 0.000002s : 7: predicate.elim_shapecalc_of_broadcastargs 1.09% : 0.000003s : 22: predicate.environ_add_const_eliminate 0.86% : 0.000002s : 22: predicate.environ_get_add_eliminate 0.86% : 0.000002s : 22: predicate.environ_get_depend_swap 1.60% : 0.000004s : 36: predicate.environ_get_eliminate 0.87% : 0.000002s : 22: predicate.environ_get_set_eliminate 0.77% : 0.000002s : 16: predicate.exchange_switch_depend_value 1.41% : 0.000004s : 16: predicate.float_depend_g_call 0.63% : 0.000002s : 14: predicate.float_environ_get_switch 0.89% : 0.000002s : 21: predicate.float_tuple_getitem_switch 0.24% : 0.000001s : 7: predicate.fold_const_symbol 0.94% : 0.000002s : 14: predicate.get_grad_eliminate 0.36% : 0.000001s : 7: predicate.graph_param_transform 0.66% : 0.000002s : 14: predicate.incorporate_call 0.51% : 0.000001s : 14: predicate.incorporate_call_switch 4.77% : 0.000012s : 73: predicate.inline 1.03% : 0.000003s : 14: predicate.inline_without_move 0.40% : 0.000001s : 14: predicate.j_node_and_user_rematch 1.85% : 0.000005s : 14: predicate.less_batch_normalization 1.46% : 0.000004s : 29: predicate.list_to_tuple_eliminator_ 1.94% : 0.000005s : 44: predicate.load_eliminater 1.05% : 0.000003s : 7: predicate.loop_unroll_after_grad 1.05% : 0.000003s : 22: predicate.loop_unroll_before_grad 1.56% : 0.000004s : 29: predicate.make_slice_get_slice_eliminator 0.71% : 0.000002s : 14: predicate.merge_addn 0.68% : 0.000002s : 14: predicate.micro_step_allgather_replace 1.09% : 0.000003s : 14: predicate.mini_step_allgather_replace 0.65% : 0.000002s : 15: predicate.minmaximum_grad 1.48% : 0.000004s : 7: predicate.mutable_eliminate 0.40% : 0.000001s : 7: predicate.opt_reshape 0.38% : 0.000001s : 7: predicate.parallel_virtual_node 0.89% : 0.000002s : 16: predicate.partial_defer_inline 1.40% : 0.000004s : 22: predicate.partial_eliminate 0.63% : 0.000002s : 15: predicate.print_const_string_wrapper 0.70% : 0.000002s : 14: predicate.reduce_all_const_elim 0.99% : 0.000003s : 15: predicate.reduce_eliminate 1.83% : 0.000005s : 44: predicate.redundant_stop_gradient_eliminater 0.77% : 0.000002s : 14: predicate.remove_not_recompute_node 1.53% : 0.000004s : 29: predicate.replace_applicator 0.60% : 0.000002s : 14: predicate.replace_old_param 0.49% : 0.000001s : 7: predicate.reset_defer_inline 0.74% : 0.000002s : 15: predicate.reshape_eliminate 0.90% : 0.000002s : 14: predicate.row_tensor_add_zeros_like 0.49% : 0.000001s : 7: predicate.row_tensor_eliminate 1.03% : 0.000003s : 14: predicate.same_eliminate 0.58% : 0.000002s : 14: predicate.set_cell_output_no_recompute 1.07% : 0.000003s : 14: predicate.shard_identity_eliminate 0.84% : 0.000002s : 14: predicate.special_op_eliminate 0.82% : 0.000002s : 14: predicate.specialize_transform 1.27% : 0.000003s : 14: predicate.split_environ_get_set_with_tuple_value 1.01% : 0.000003s : 14: predicate.stack_unstack_eliminate 0.40% : 0.000001s : 7: predicate.switch_call_monad_eliminater 0.75% : 0.000002s : 16: predicate.switch_defer_inline 1.42% : 0.000004s : 30: predicate.switch_layer_defer_inline 3.23% : 0.000008s : 59: predicate.switch_simplify 0.67% : 0.000002s : 15: predicate.tile_eliminate 9.30% : 0.000024s : 15: predicate.transpose_eliminate 1.46% : 0.000004s : 29: predicate.tuple_list_convert_item_index_to_positive 1.36% : 0.000004s : 29: predicate.tuple_list_get_item_const_eliminator 1.32% : 0.000003s : 29: predicate.tuple_list_get_item_depend_reorder 2.88% : 0.000008s : 43: predicate.tuple_list_get_item_eliminator 1.58% : 0.000004s : 29: predicate.tuple_list_get_set_item_eliminator 2.47% : 0.000006s : 43: predicate.tuple_list_set_item_eliminator 1.39% : 0.000004s : 29: predicate.tuple_to_list_eliminator_ 1.72% : 0.000005s : 44: predicate.updatestate_pure_node_eliminater 3.23% : 0.000008s : 58: predicate.updatestate_useless_node_eliminater 0.39% : 0.000001s : 7: predicate.value_based_eliminate 0.75% : 0.000002s : 14: predicate.virtual_dataset_eliminate 0.72% : 0.000002s : 14: predicate.virtual_output_eliminate 0.31% : 0.000001s : 7: predicate.virtual_view_grad_eliminate 0.51% : 0.000001s : 7: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000894 6 51.12% : 0.000457s : 3: func_graph_cloner_run.FuncGraphClonerGraph 48.88% : 0.000437s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.201837 192 0.00% : 0.000004s : 1: ForceFp32Comm 3.07% : 0.006191s : 1: add_attr 3.04% : 0.006145s : 1: add_attr_with_inline 0.00% : 0.000005s : 1: add_comm_op_reuse_tag 0.05% : 0.000107s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.05% : 0.000096s : 1: auto_monad 0.02% : 0.000040s : 1: auto_monad_reorder 0.00% : 0.000005s : 1: begin_end_overlap_inline 0.00% : 0.000006s : 1: bias_add_comm_swap 0.54% : 0.001087s : 1: bootstrap 0.02% : 0.000047s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.01% : 0.000024s : 1: control_data_broadcast_order 0.01% : 0.000014s : 1: convert_after_rewriter 0.02% : 0.000049s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.01% : 0.000014s : 1: environ_conv 0.01% : 0.000027s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000009s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000006s : 1: inline 0.00% : 0.000006s : 1: insert-virtual-dataset 0.00% : 0.000004s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.01% : 0.000010s : 1: label_micro_interleaved_index 0.30% : 0.000604s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.44% : 0.000890s : 1: mutable_eliminate 0.00% : 0.000009s : 1: offloading_packed_experts 0.01% : 0.000025s : 1: opt.transform.loop_unroll_optimizer 0.02% : 0.000032s : 1: opt.transform.mutable_eliminate 19.42% : 0.039194s : 78: opt.transform.opt_a 0.02% : 0.000047s : 1: opt.transform.opt_after_cconv 0.02% : 0.000043s : 1: opt.transform.opt_after_jit_grad 0.10% : 0.000193s : 28: opt.transform.opt_b 0.04% : 0.000084s : 2: opt.transform.opt_trans_graph 0.05% : 0.000092s : 4: opt.transform.symbol_engine_opt 20.75% : 0.041891s : 1: opt_a 0.09% : 0.000190s : 1: opt_after_cconv 0.31% : 0.000618s : 1: opt_after_jit_grad 0.24% : 0.000477s : 1: opt_b 22.60% : 0.045610s : 1: optimize 0.03% : 0.000052s : 1: optimize_parallel_all_gather_comm 0.01% : 0.000011s : 1: order_py_execute_after_rewriter 0.02% : 0.000047s : 1: overlap_grad_flash_sp 0.00% : 0.000005s : 1: overlap_grad_matmul_and_grad_allreduce 0.02% : 0.000032s : 1: overlap_grad_ring_attention 0.02% : 0.000035s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000008s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000012s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000005s : 1: partial_unused_args_eliminate 0.00% : 0.000006s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000046s : 1: pre_auto_parallel 0.03% : 0.000062s : 1: py_interpret_to_execute 0.02% : 0.000037s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.04% : 0.000087s : 1: remove_dup_value 0.24% : 0.000483s : 1: renormalize.infer 0.28% : 0.000557s : 1: renormalize.specialize 0.00% : 0.000007s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000008s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000087s : 1: rewriter_after_opt_a 0.05% : 0.000108s : 1: rewriter_before_opt_a 0.00% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000006s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000006s : 1: split_matmul_comm_elemetwise 0.01% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.17% : 0.000336s : 1: symbol_engine_optimizer 0.06% : 0.000124s : 1: tuple_transform 27.57% : 0.055651s : 1: type_inference . [hook] pytest_runtest_teardown:test_internel_asd_paged_attention[True-ms_dtype1] tests/st/infer/ops/test_internal_ops/test_asd_paged_attention.py::test_internel_asd_paged_attention[True-ms_dtype1],max_mem:386.0M =============================== 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 567.14s (0:09:27) ==================