==================================================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_002/sault/config/pytest.ini plugins: mock-3.14.0, hydra-core-1.3.2, forked-1.6.0, anyio-4.9.0, xdist-1.32.0 collected 4 items test_paged_attention.py [WARNING] ME(163399:281473684254512,MainProcess):2026-01-29-17:37:29.920.664 [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 = 0.0457645, [21] [bootstrap]: 0.00083427 [type_inference]: 0.0282663 [event_method]: 1.655e-05 [auto_monad]: 8.565e-05 [graph_reusing]: 4.92999e-06 [inline]: 2.71e-06 [add_attr]: 0.00820546, [1] [add_attr_with_inline]: 0.00819156, [1] [Cycle 1]: 9.873e-05, [2] [tag_attr]: 2.115e-05 [meta_addattr_fg_expand]: 4.03999e-06 [parallel-infer-symbol]: 3.87002e-06 [pre_auto_parallel]: 4.628e-05 [insert-virtual-dataset]: 2.53e-06 [parallel-infer-symbol-second]: 6.50005e-07 [dataset_repeat_opt]: 2.16e-06 [pipeline_split]: 1.72001e-06 [optimize]: 0.00749985, [53] [py_interpret_to_execute]: 2.775e-05 [rewriter_before_opt_a]: 7.617e-05 [opt_a]: 0.00458359, [2] [Cycle 1]: 0.00219363, [45] [expand_dump_flag]: 3.09001e-06 [switch_simplify]: 3.308e-05 [loop_unroll]: 1.947e-05 [a_1]: 0.00045638 [with_stream_mark]: 2.443e-05 [recompute_prepare]: 1.278e-05 [updatestate_depend_eliminate]: 5.49e-06 [updatestate_assign_eliminate]: 4.85999e-06 [updatestate_loads_eliminate]: 4.67998e-06 [parameter_eliminate]: 2.09999e-06 [a_2]: 0.00015006 [accelerated_algorithm]: 1.15e-05 [shard]: 2.56e-06 [meta_shard_fg_expand]: 2.29001e-06 [shard_inline]: 1.089e-05 [merge_send_recv]: 1.002e-05 [auto_parallel]: 8.74e-06 [parallel]: 5.283e-05 [flash_sp]: 1.144e-05 [merge_comm]: 5.59e-06 [allreduce_fusion]: 4.73001e-06 [matmul_add_comm_reduction]: 1.11e-05 [allreduce_slice_to_reducescatter]: 9.79984e-07 [virtual_shard_identity]: 1.238e-05 [virtual_dataset]: 1.08e-05 [get_grad_eliminate_]: 1.041e-05 [virtual_output]: 1.042e-05 [merge_forward]: 5.59e-06 [cell_reuse_recompute_pass]: 1.60999e-06 [offload_activation]: 1.237e-05 [cell_reuse_handle_not_recompute_node_pass]: 1.881e-05 [merge_recompute_call_nodes]: 1.37e-06 [before_grad]: 1.526e-05 [set_forward_comm_id_for_comm_node_pass]: 5.46998e-06 [meta_fg_expand]: 3.32002e-06 [flash_sp_send_recv_attached]: 2.74999e-06 [receive_attached]: 1.265e-05 [after_resolve]: 2.235e-05 [a_after_grad]: 1.773e-05 [renormalize]: 0.00075435 [add_forward_monad_depend]: 5.92001e-06 [auto_monad_grad]: 2.79001e-06 [auto_monad_eliminator]: 1.725e-05 [cse]: 8.16e-05 [a_3]: 8.053e-05 [Cycle 2]: 0.00237765, [45] [expand_dump_flag]: 1.41998e-06 [switch_simplify]: 1.375e-05 [loop_unroll]: 1.103e-05 [a_1]: 0.00027357 [with_stream_mark]: 1.737e-05 [recompute_prepare]: 1.106e-05 [updatestate_depend_eliminate]: 5.37999e-06 [updatestate_assign_eliminate]: 4.37998e-06 [updatestate_loads_eliminate]: 4.15e-06 [parameter_eliminate]: 1.44e-06 [a_2]: 0.00141367 [accelerated_algorithm]: 1.53e-05 [shard]: 2.94999e-06 [meta_shard_fg_expand]: 3.54002e-06 [shard_inline]: 1.148e-05 [merge_send_recv]: 1.351e-05 [auto_parallel]: 1.279e-05 [parallel]: 7.93001e-06 [flash_sp]: 5.08002e-06 [merge_comm]: 5.22e-06 [allreduce_fusion]: 4.94e-06 [matmul_add_comm_reduction]: 1.248e-05 [allreduce_slice_to_reducescatter]: 7.59988e-07 [virtual_shard_identity]: 1.273e-05 [virtual_dataset]: 1.061e-05 [get_grad_eliminate_]: 1.069e-05 [virtual_output]: 1.063e-05 [merge_forward]: 5.56e-06 [cell_reuse_recompute_pass]: 3.06001e-06 [offload_activation]: 1.317e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.311e-05 [merge_recompute_call_nodes]: 1.09003e-06 [before_grad]: 1.497e-05 [set_forward_comm_id_for_comm_node_pass]: 5.43002e-06 [meta_fg_expand]: 4.06001e-06 [flash_sp_send_recv_attached]: 1.32999e-06 [receive_attached]: 1.97999e-06 [after_resolve]: 2.327e-05 [a_after_grad]: 1.716e-05 [renormalize]: 8.00064e-08 [add_forward_monad_depend]: 4.51002e-06 [auto_monad_grad]: 2.22999e-06 [auto_monad_eliminator]: 1.542e-05 [cse]: 4.984e-05 [a_3]: 7.02e-05 [py_interpret_to_execute_after_opt_a]: 2.116e-05 [slice_cell_reuse_recomputed_activation]: 2.64999e-06 [rewriter_after_opt_a]: 9.358e-05 [convert_after_rewriter]: 1.04e-05 [order_py_execute_after_rewriter]: 6.82002e-06 [mutable_eliminate]: 0.00069946 [opt_b]: 0.00033938, [1] [Cycle 1]: 0.00032925, [7] [b_1]: 0.0002214 [b_2]: 1.284e-05 [updatestate_depend_eliminate]: 9.83998e-06 [updatestate_assign_eliminate]: 4.58001e-06 [updatestate_loads_eliminate]: 4.92999e-06 [renormalize]: 6.30011e-07 [cse]: 4.035e-05 [optimize_parallel_all_gather_comm]: 1.984e-05 [overlap_param_gather]: 5.37999e-06 [cconv]: 3.286e-05 [loop_unroll]: 0.00045422 [opt_after_cconv]: 0.00015316, [1] [Cycle 1]: 0.00014525, [7] [c_1]: 5.664e-05 [parameter_eliminate]: 4.48999e-06 [updatestate_depend_eliminate]: 7.78999e-06 [updatestate_assign_eliminate]: 4.12998e-06 [updatestate_loads_eliminate]: 4.15e-06 [cse]: 3.444e-05 [renormalize]: 2.89991e-07 [remove_dup_value]: 6.376e-05 [tuple_transform]: 0.00020338, [1] [Cycle 1]: 0.00019733, [4] [d_1]: 0.00016155 [none_parameter_eliminate]: 2.21e-06 [renormalize]: 2.59985e-07 [switch_simplify]: 1.222e-05 [partial_unused_args_eliminate]: 1.86e-06 [add_recomputation]: 6.534e-05 [cse_after_recomputation]: 3.551e-05, [1] [Cycle 1]: 3.009e-05, [1] [cse]: 2.429e-05 [environ_conv]: 1.912e-05 [swap_dp_allreduce_reducescatter]: 7.38e-06 [bias_add_comm_swap]: 3.45e-06 [label_micro_interleaved_index]: 5.00999e-06 [label_fine_grained_interleaved_index]: 2.68998e-06 [merge_cast_opt]: 1.39e-06 [slice_recompute_activation]: 2.59999e-06 [micro_interleaved_order_control]: 2.11e-06 [assign_add_opt]: 1.28002e-06 [ForceFp32Comm]: 9.20001e-07 [remove_cast_before_assign_add]: 9.09989e-07 [full_micro_interleaved_order_control]: 2.04e-06 [reorder_send_recv_between_fp_bp]: 2.84001e-06 [comm_op_add_attrs]: 1.09e-06 [add_comm_op_reuse_tag]: 9.20001e-07 [interleave_split_concat_branches]: 1.10001e-06 [interleave_parallel_branches]: 1.07e-06 [overlap_opt_shard_in_pipeline]: 2.333e-05 [overlap_opt_shard_grad_in_pipeline]: 1.61998e-06 [control_data_broadcast_order]: 1.852e-05 [grouped_pairwise_exchange_alltoall]: 1.73002e-06 [offloading_packed_experts]: 5.05999e-06 [overlap_recompute_and_grad_model_parallel]: 6.31998e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.19998e-06 [overlap_recompute_allgather_and_fa_grad]: 1.61998e-06 [overlap_recompute_comm]: 2.17001e-06 [overlap_grad_ring_attention]: 5.15001e-06 [overlap_grad_flash_sp]: 3.711e-05 [begin_end_overlap_inline]: 5.10016e-07 [split_matmul_comm_elemetwise]: 2.32999e-06 [split_layernorm_comm]: 1.66e-06 [handle_group_info]: 1.00999e-06 [symbol_engine_optimizer]: 0.00020111, [1] [Cycle 1]: 0.00019538, [6] [build]: 8.644e-05 [elim_shapecalc]: 1.717e-05 [elim_not_effective]: 2.766e-05 [opt_reshape]: 1.099e-05 [fold_const_symbol]: 2.051e-05 [renormalize]: 3.50003e-07 [detach_backward]: 2.63e-06 [pipeline_parallel_scheduler]: 1.41998e-06 [auto_monad_reorder]: 2.784e-05 [get_jit_bprop_graph]: 1.57001e-06 [rewriter_after_jit_bprop_graph]: 4.25e-06 [opt_after_jit_grad]: 0.00052135 [validate]: 6.722e-05 Sums bootstrap : 0.000834s : 2.28% type_inference : 0.028266s : 77.35% event_method : 0.000017s : 0.05% auto_monad : 0.000086s : 0.23% graph_reusing : 0.000005s : 0.01% inline : 0.000003s : 0.01% add_attr.add_attr_with_inline.tag_attr : 0.000021s : 0.06% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000004s : 0.01% parallel-infer-symbol : 0.000004s : 0.01% pre_auto_parallel : 0.000046s : 0.13% 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 : 0.00% optimize.py_interpret_to_execute : 0.000028s : 0.08% optimize.rewriter_before_opt_a : 0.000076s : 0.21% optimize.opt_a.expand_dump_flag : 0.000005s : 0.01% optimize.opt_a.switch_simplify : 0.000047s : 0.13% optimize.opt_a.loop_unroll : 0.000030s : 0.08% optimize.opt_a.a_1 : 0.000730s : 2.00% optimize.opt_a.with_stream_mark : 0.000042s : 0.11% optimize.opt_a.recompute_prepare : 0.000024s : 0.07% optimize.opt_a.updatestate_depend_eliminate : 0.000011s : 0.03% optimize.opt_a.updatestate_assign_eliminate : 0.000009s : 0.03% optimize.opt_a.updatestate_loads_eliminate : 0.000009s : 0.02% optimize.opt_a.parameter_eliminate : 0.000004s : 0.01% optimize.opt_a.a_2 : 0.001564s : 4.28% optimize.opt_a.accelerated_algorithm : 0.000027s : 0.07% optimize.opt_a.shard : 0.000006s : 0.02% optimize.opt_a.meta_shard_fg_expand : 0.000006s : 0.02% optimize.opt_a.shard_inline : 0.000022s : 0.06% optimize.opt_a.merge_send_recv : 0.000024s : 0.06% optimize.opt_a.auto_parallel : 0.000022s : 0.06% optimize.opt_a.parallel : 0.000061s : 0.17% optimize.opt_a.flash_sp : 0.000017s : 0.05% optimize.opt_a.merge_comm : 0.000011s : 0.03% optimize.opt_a.allreduce_fusion : 0.000010s : 0.03% optimize.opt_a.matmul_add_comm_reduction : 0.000024s : 0.06% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000025s : 0.07% optimize.opt_a.virtual_dataset : 0.000021s : 0.06% optimize.opt_a.get_grad_eliminate_ : 0.000021s : 0.06% optimize.opt_a.virtual_output : 0.000021s : 0.06% optimize.opt_a.merge_forward : 0.000011s : 0.03% optimize.opt_a.cell_reuse_recompute_pass : 0.000005s : 0.01% optimize.opt_a.offload_activation : 0.000026s : 0.07% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000042s : 0.11% optimize.opt_a.merge_recompute_call_nodes : 0.000002s : 0.01% optimize.opt_a.before_grad : 0.000030s : 0.08% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000011s : 0.03% optimize.opt_a.meta_fg_expand : 0.000007s : 0.02% optimize.opt_a.flash_sp_send_recv_attached : 0.000004s : 0.01% optimize.opt_a.receive_attached : 0.000015s : 0.04% optimize.opt_a.after_resolve : 0.000046s : 0.12% optimize.opt_a.a_after_grad : 0.000035s : 0.10% optimize.opt_a.renormalize : 0.000754s : 2.06% optimize.opt_a.add_forward_monad_depend : 0.000010s : 0.03% optimize.opt_a.auto_monad_grad : 0.000005s : 0.01% optimize.opt_a.auto_monad_eliminator : 0.000033s : 0.09% optimize.opt_a.cse : 0.000131s : 0.36% optimize.opt_a.a_3 : 0.000151s : 0.41% optimize.py_interpret_to_execute_after_opt_a : 0.000021s : 0.06% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.01% optimize.rewriter_after_opt_a : 0.000094s : 0.26% optimize.convert_after_rewriter : 0.000010s : 0.03% optimize.order_py_execute_after_rewriter : 0.000007s : 0.02% optimize.mutable_eliminate : 0.000699s : 1.91% optimize.opt_b.b_1 : 0.000221s : 0.61% optimize.opt_b.b_2 : 0.000013s : 0.04% optimize.opt_b.updatestate_depend_eliminate : 0.000010s : 0.03% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.01% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.01% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000040s : 0.11% optimize.optimize_parallel_all_gather_comm : 0.000020s : 0.05% optimize.overlap_param_gather : 0.000005s : 0.01% optimize.cconv : 0.000033s : 0.09% optimize.loop_unroll : 0.000454s : 1.24% optimize.opt_after_cconv.c_1 : 0.000057s : 0.15% optimize.opt_after_cconv.parameter_eliminate : 0.000004s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000008s : 0.02% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000004s : 0.01% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.01% optimize.opt_after_cconv.cse : 0.000034s : 0.09% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000064s : 0.17% optimize.tuple_transform.d_1 : 0.000162s : 0.44% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.01% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000012s : 0.03% optimize.partial_unused_args_eliminate : 0.000002s : 0.01% optimize.add_recomputation : 0.000065s : 0.18% optimize.cse_after_recomputation.cse : 0.000024s : 0.07% optimize.environ_conv : 0.000019s : 0.05% optimize.swap_dp_allreduce_reducescatter : 0.000007s : 0.02% optimize.bias_add_comm_swap : 0.000003s : 0.01% optimize.label_micro_interleaved_index : 0.000005s : 0.01% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.01% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000003s : 0.01% optimize.micro_interleaved_order_control : 0.000002s : 0.01% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.01% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 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 : 0.000023s : 0.06% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000019s : 0.05% 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 : 0.02% 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 : 0.01% optimize.overlap_grad_ring_attention : 0.000005s : 0.01% optimize.overlap_grad_flash_sp : 0.000037s : 0.10% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000002s : 0.01% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000086s : 0.24% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000017s : 0.05% optimize.symbol_engine_optimizer.elim_not_effective : 0.000028s : 0.08% optimize.symbol_engine_optimizer.opt_reshape : 0.000011s : 0.03% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000021s : 0.06% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000003s : 0.01% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000028s : 0.08% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000004s : 0.01% opt_after_jit_grad : 0.000521s : 1.43% validate : 0.000067s : 0.18% Time group info: ------[substitution.] 0.000161 39 6.20% : 0.000010s : 2: substitution.elim_not_effective 4.92% : 0.000008s : 2: substitution.fold_const_symbol 12.69% : 0.000020s : 10: substitution.graph_param_transform 62.97% : 0.000102s : 1: substitution.inline 2.82% : 0.000005s : 4: substitution.j_node_and_user_rematch 3.72% : 0.000006s : 4: substitution.remove_not_recompute_node 6.68% : 0.000011s : 16: substitution.replace_old_param ------[type_inference.] 0.028162 2 98.00% : 0.027597s : 1: type_inference.infer 2.00% : 0.000564s : 1: type_inference.specialize ------[replace.] 0.000019 1 100.00% : 0.000019s : 1: replace.inline ------[match.] 0.000101 1 100.00% : 0.000101s : 1: match.inline ------[predicate.] 0.000253 2335 0.78% : 0.000002s : 21: predicate.accumulaten_eliminater 0.82% : 0.000002s : 10: predicate.ad_related_special_op_eliminate 0.70% : 0.000002s : 20: predicate.addn_check_dump 0.82% : 0.000002s : 21: predicate.addn_zero_filter 0.73% : 0.000002s : 21: predicate.adjust_all_reduce_mul_add 2.03% : 0.000005s : 41: predicate.arithmetic_simplify 0.82% : 0.000002s : 21: predicate.cast_eliminate 0.83% : 0.000002s : 20: predicate.check_bprop_eliminate 0.72% : 0.000002s : 20: predicate.compare_switch_simplify 0.29% : 0.000001s : 10: predicate.const_output_eliminate 0.98% : 0.000002s : 20: predicate.depend_value_elim 0.86% : 0.000002s : 21: predicate.dict_get_item_const_eliminator 0.92% : 0.000002s : 21: predicate.dict_get_item_eliminator 0.78% : 0.000002s : 21: predicate.dict_set_item_eliminator 1.14% : 0.000003s : 20: predicate.dumpgradient_eliminate 0.44% : 0.000001s : 10: predicate.elim_not_effective 0.50% : 0.000001s : 10: predicate.elim_shapecalc_of_broadcastargs 1.14% : 0.000003s : 31: predicate.environ_add_const_eliminate 1.07% : 0.000003s : 31: predicate.environ_get_add_eliminate 1.09% : 0.000003s : 31: predicate.environ_get_depend_swap 2.64% : 0.000007s : 51: predicate.environ_get_eliminate 1.08% : 0.000003s : 31: predicate.environ_get_set_eliminate 0.79% : 0.000002s : 22: predicate.exchange_switch_depend_value 1.40% : 0.000004s : 22: predicate.float_depend_g_call 0.69% : 0.000002s : 20: predicate.float_environ_get_switch 1.11% : 0.000003s : 30: predicate.float_tuple_getitem_switch 0.30% : 0.000001s : 10: predicate.fold_const_symbol 0.90% : 0.000002s : 20: predicate.get_grad_eliminate 0.41% : 0.000001s : 10: predicate.graph_param_transform 0.83% : 0.000002s : 20: predicate.incorporate_call 1.13% : 0.000003s : 20: predicate.incorporate_call_switch 5.66% : 0.000014s : 103: predicate.inline 1.12% : 0.000003s : 20: predicate.inline_without_move 0.56% : 0.000001s : 20: predicate.j_node_and_user_rematch 1.01% : 0.000003s : 20: predicate.less_batch_normalization 1.65% : 0.000004s : 41: predicate.list_to_tuple_eliminator_ 2.25% : 0.000006s : 62: predicate.load_eliminater 1.02% : 0.000003s : 10: predicate.loop_unroll_after_grad 1.28% : 0.000003s : 31: predicate.loop_unroll_before_grad 1.81% : 0.000005s : 41: predicate.make_slice_get_slice_eliminator 0.75% : 0.000002s : 20: predicate.merge_addn 0.78% : 0.000002s : 20: predicate.micro_step_allgather_replace 0.78% : 0.000002s : 20: predicate.mini_step_allgather_replace 0.72% : 0.000002s : 21: predicate.minmaximum_grad 1.31% : 0.000003s : 10: predicate.mutable_eliminate 0.41% : 0.000001s : 10: predicate.opt_reshape 0.41% : 0.000001s : 10: predicate.parallel_virtual_node 1.03% : 0.000003s : 22: predicate.partial_defer_inline 1.33% : 0.000003s : 31: predicate.partial_eliminate 0.80% : 0.000002s : 21: predicate.print_const_string_wrapper 0.75% : 0.000002s : 20: predicate.reduce_all_const_elim 0.95% : 0.000002s : 21: predicate.reduce_eliminate 2.25% : 0.000006s : 62: predicate.redundant_stop_gradient_eliminater 0.92% : 0.000002s : 20: predicate.remove_not_recompute_node 1.52% : 0.000004s : 41: predicate.replace_applicator 0.82% : 0.000002s : 20: predicate.replace_old_param 0.43% : 0.000001s : 10: predicate.reset_defer_inline 0.77% : 0.000002s : 21: predicate.reshape_eliminate 0.91% : 0.000002s : 20: predicate.row_tensor_add_zeros_like 0.50% : 0.000001s : 10: predicate.row_tensor_eliminate 1.01% : 0.000003s : 20: predicate.same_eliminate 0.63% : 0.000002s : 20: predicate.set_cell_output_no_recompute 0.99% : 0.000003s : 20: predicate.shard_identity_eliminate 0.99% : 0.000003s : 20: predicate.special_op_eliminate 0.84% : 0.000002s : 20: predicate.specialize_transform 1.27% : 0.000003s : 20: predicate.split_environ_get_set_with_tuple_value 1.01% : 0.000003s : 20: predicate.stack_unstack_eliminate 0.43% : 0.000001s : 10: predicate.switch_call_monad_eliminater 0.89% : 0.000002s : 22: predicate.switch_defer_inline 1.67% : 0.000004s : 42: predicate.switch_layer_defer_inline 3.60% : 0.000009s : 83: predicate.switch_simplify 0.76% : 0.000002s : 21: predicate.tile_eliminate 0.91% : 0.000002s : 21: predicate.transpose_eliminate 1.58% : 0.000004s : 41: predicate.tuple_list_convert_item_index_to_positive 1.60% : 0.000004s : 41: predicate.tuple_list_get_item_const_eliminator 1.44% : 0.000004s : 41: predicate.tuple_list_get_item_depend_reorder 2.98% : 0.000008s : 61: predicate.tuple_list_get_item_eliminator 1.46% : 0.000004s : 41: predicate.tuple_list_get_set_item_eliminator 2.37% : 0.000006s : 61: predicate.tuple_list_set_item_eliminator 1.62% : 0.000004s : 41: predicate.tuple_to_list_eliminator_ 2.20% : 0.000006s : 62: predicate.updatestate_pure_node_eliminater 3.26% : 0.000008s : 82: predicate.updatestate_useless_node_eliminater 0.54% : 0.000001s : 10: predicate.value_based_eliminate 0.88% : 0.000002s : 20: predicate.virtual_dataset_eliminate 0.96% : 0.000002s : 20: predicate.virtual_output_eliminate 0.37% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.51% : 0.000001s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.000527 6 54.09% : 0.000285s : 3: func_graph_cloner_run.FuncGraphClonerGraph 45.91% : 0.000242s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.065378 192 0.01% : 0.000004s : 1: ForceFp32Comm 12.56% : 0.008211s : 1: add_attr 12.54% : 0.008196s : 1: add_attr_with_inline 0.01% : 0.000004s : 1: add_comm_op_reuse_tag 0.11% : 0.000070s : 1: add_recomputation 0.01% : 0.000004s : 1: assign_add_opt 0.14% : 0.000091s : 1: auto_monad 0.05% : 0.000032s : 1: auto_monad_reorder 0.01% : 0.000004s : 1: begin_end_overlap_inline 0.01% : 0.000006s : 1: bias_add_comm_swap 1.33% : 0.000868s : 1: bootstrap 0.06% : 0.000037s : 1: cconv 0.01% : 0.000004s : 1: comm_op_add_attrs 0.03% : 0.000022s : 1: control_data_broadcast_order 0.02% : 0.000014s : 1: convert_after_rewriter 0.06% : 0.000038s : 1: cse_after_recomputation 0.01% : 0.000005s : 1: dataset_repeat_opt 0.01% : 0.000006s : 1: detach_backward 0.03% : 0.000023s : 1: environ_conv 0.03% : 0.000023s : 1: event_method 0.01% : 0.000005s : 1: full_micro_interleaved_order_control 0.01% : 0.000005s : 1: get_jit_bprop_graph 0.01% : 0.000008s : 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 0.01% : 0.000008s : 1: label_micro_interleaved_index 0.71% : 0.000463s : 1: loop_unroll 0.01% : 0.000004s : 1: merge_cast_opt 0.01% : 0.000005s : 1: micro_interleaved_order_control 1.09% : 0.000711s : 1: mutable_eliminate 0.01% : 0.000008s : 1: offloading_packed_experts 0.03% : 0.000019s : 1: opt.transform.loop_unroll_optimizer 0.04% : 0.000025s : 1: opt.transform.mutable_eliminate 4.18% : 0.002732s : 78: opt.transform.opt_a 0.08% : 0.000055s : 1: opt.transform.opt_after_cconv 0.06% : 0.000040s : 1: opt.transform.opt_after_jit_grad 0.32% : 0.000208s : 28: opt.transform.opt_b 0.26% : 0.000171s : 2: opt.transform.opt_trans_graph 0.11% : 0.000072s : 4: opt.transform.symbol_engine_opt 7.02% : 0.004588s : 1: opt_a 0.24% : 0.000157s : 1: opt_after_cconv 0.82% : 0.000533s : 1: opt_after_jit_grad 0.52% : 0.000343s : 1: opt_b 11.48% : 0.007506s : 1: optimize 0.04% : 0.000023s : 1: optimize_parallel_all_gather_comm 0.02% : 0.000010s : 1: order_py_execute_after_rewriter 0.06% : 0.000041s : 1: overlap_grad_flash_sp 0.01% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000009s : 1: overlap_grad_ring_attention 0.01% : 0.000005s : 1: overlap_opt_shard_grad_in_pipeline 0.04% : 0.000027s : 1: overlap_opt_shard_in_pipeline 0.01% : 0.000009s : 1: overlap_param_gather 0.01% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.01% : 0.000009s : 1: overlap_recompute_and_grad_model_parallel 0.01% : 0.000005s : 1: overlap_recompute_comm 0.01% : 0.000007s : 1: parallel-infer-symbol 0.01% : 0.000004s : 1: parallel-infer-symbol-second 0.01% : 0.000005s : 1: partial_unused_args_eliminate 0.01% : 0.000005s : 1: pipeline_parallel_scheduler 0.01% : 0.000005s : 1: pipeline_split 0.08% : 0.000051s : 1: pre_auto_parallel 0.05% : 0.000032s : 1: py_interpret_to_execute 0.04% : 0.000025s : 1: py_interpret_to_execute_after_opt_a 0.01% : 0.000004s : 1: remove_cast_before_assign_add 0.11% : 0.000069s : 1: remove_dup_value 0.60% : 0.000394s : 1: renormalize.infer 0.54% : 0.000351s : 1: renormalize.specialize 0.01% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.01% : 0.000007s : 1: rewriter_after_jit_bprop_graph 0.15% : 0.000099s : 1: rewriter_after_opt_a 0.12% : 0.000080s : 1: rewriter_before_opt_a 0.01% : 0.000006s : 1: slice_cell_reuse_recomputed_activation 0.01% : 0.000005s : 1: slice_recompute_activation 0.01% : 0.000004s : 1: split_layernorm_comm 0.01% : 0.000005s : 1: split_matmul_comm_elemetwise 0.02% : 0.000010s : 1: swap_dp_allreduce_reducescatter 0.31% : 0.000204s : 1: symbol_engine_optimizer 0.32% : 0.000206s : 1: tuple_transform 43.27% : 0.028288s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_bsh[QuantMethod.FP16_VEC-0] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_bsh[QuantMethod.FP16_VEC-0],max_mem:454.0M [WARNING] ME(163399:281473684254512,MainProcess):2026-01-29-17:38:06.724.71 [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 = 0.219442, [21] [bootstrap]: 0.00083112 [type_inference]: 0.080151 [event_method]: 2.16e-05 [auto_monad]: 0.00011278 [graph_reusing]: 5.94999e-06 [inline]: 3.09001e-06 [add_attr]: 0.00881843, [1] [add_attr_with_inline]: 0.00879377, [1] [Cycle 1]: 0.00010363, [2] [tag_attr]: 2.748e-05 [meta_addattr_fg_expand]: 5.64e-06 [parallel-infer-symbol]: 3.79002e-06 [pre_auto_parallel]: 5.636e-05 [insert-virtual-dataset]: 2.98998e-06 [parallel-infer-symbol-second]: 8.2e-07 [dataset_repeat_opt]: 1.76e-06 [pipeline_split]: 1.58002e-06 [optimize]: 0.128252, [53] [py_interpret_to_execute]: 0.00010682 [rewriter_before_opt_a]: 0.0001492 [opt_a]: 0.124151, [2] [Cycle 1]: 0.122755, [45] [expand_dump_flag]: 3.38999e-06 [switch_simplify]: 3.702e-05 [loop_unroll]: 2.026e-05 [a_1]: 0.00064141 [with_stream_mark]: 2.433e-05 [recompute_prepare]: 1.645e-05 [updatestate_depend_eliminate]: 6.71e-06 [updatestate_assign_eliminate]: 5.42999e-06 [updatestate_loads_eliminate]: 5.39e-06 [parameter_eliminate]: 2.16003e-06 [a_2]: 0.00015372 [accelerated_algorithm]: 2.159e-05 [shard]: 2.93e-06 [meta_shard_fg_expand]: 3.51999e-06 [shard_inline]: 1.575e-05 [merge_send_recv]: 1.118e-05 [auto_parallel]: 1.2e-05 [parallel]: 4.934e-05 [flash_sp]: 1.234e-05 [merge_comm]: 5.98002e-06 [allreduce_fusion]: 5.33002e-06 [matmul_add_comm_reduction]: 1.436e-05 [allreduce_slice_to_reducescatter]: 8.89995e-07 [virtual_shard_identity]: 1.911e-05 [virtual_dataset]: 1.765e-05 [get_grad_eliminate_]: 6.235e-05 [virtual_output]: 2.191e-05 [merge_forward]: 1.456e-05 [cell_reuse_recompute_pass]: 4.30999e-06 [offload_activation]: 2.371e-05 [cell_reuse_handle_not_recompute_node_pass]: 4.157e-05 [merge_recompute_call_nodes]: 3.28e-06 [before_grad]: 2.351e-05 [set_forward_comm_id_for_comm_node_pass]: 1.118e-05 [meta_fg_expand]: 1.179e-05 [flash_sp_send_recv_attached]: 8.59e-06 [receive_attached]: 3.33e-06 [after_resolve]: 4.41e-05 [a_after_grad]: 3.187e-05 [renormalize]: 0.114589 [add_forward_monad_depend]: 1.047e-05 [auto_monad_grad]: 3.01999e-06 [auto_monad_eliminator]: 2.438e-05 [cse]: 0.00010083 [a_3]: 0.00011399 [Cycle 2]: 0.00137541, [45] [expand_dump_flag]: 2.94999e-06 [switch_simplify]: 1.678e-05 [loop_unroll]: 1.341e-05 [a_1]: 0.00032941 [with_stream_mark]: 2.593e-05 [recompute_prepare]: 1.485e-05 [updatestate_depend_eliminate]: 7.56999e-06 [updatestate_assign_eliminate]: 5.61003e-06 [updatestate_loads_eliminate]: 5.86e-06 [parameter_eliminate]: 2.86999e-06 [a_2]: 0.00014564 [accelerated_algorithm]: 1.426e-05 [shard]: 3.09001e-06 [meta_shard_fg_expand]: 3.76999e-06 [shard_inline]: 1.123e-05 [merge_send_recv]: 1.057e-05 [auto_parallel]: 1.277e-05 [parallel]: 1.044e-05 [flash_sp]: 4.43999e-06 [merge_comm]: 6.31e-06 [allreduce_fusion]: 4.95001e-06 [matmul_add_comm_reduction]: 1.296e-05 [allreduce_slice_to_reducescatter]: 6.19999e-07 [virtual_shard_identity]: 1.599e-05 [virtual_dataset]: 1.275e-05 [get_grad_eliminate_]: 1.224e-05 [virtual_output]: 1.228e-05 [merge_forward]: 9.37001e-06 [cell_reuse_recompute_pass]: 3.93001e-06 [offload_activation]: 1.506e-05 [cell_reuse_handle_not_recompute_node_pass]: 2.759e-05 [merge_recompute_call_nodes]: 1.77999e-06 [before_grad]: 1.795e-05 [set_forward_comm_id_for_comm_node_pass]: 6.42001e-06 [meta_fg_expand]: 5.15999e-06 [flash_sp_send_recv_attached]: 2.05002e-06 [receive_attached]: 3.46001e-06 [after_resolve]: 3.588e-05 [a_after_grad]: 1.866e-05 [renormalize]: 1.19995e-07 [add_forward_monad_depend]: 2.88998e-06 [auto_monad_grad]: 2.06998e-06 [auto_monad_eliminator]: 1.616e-05 [cse]: 7.196e-05 [a_3]: 7.798e-05 [py_interpret_to_execute_after_opt_a]: 3.09e-05 [slice_cell_reuse_recomputed_activation]: 2.79999e-06 [rewriter_after_opt_a]: 7.567e-05 [convert_after_rewriter]: 1.192e-05 [order_py_execute_after_rewriter]: 7.98001e-06 [mutable_eliminate]: 0.00097908 [opt_b]: 0.00047229, [1] [Cycle 1]: 0.00045817, [7] [b_1]: 0.00025245 [b_2]: 1.517e-05 [updatestate_depend_eliminate]: 1.471e-05 [updatestate_assign_eliminate]: 7.90998e-06 [updatestate_loads_eliminate]: 4.78001e-06 [renormalize]: 7.50006e-07 [cse]: 9.853e-05 [optimize_parallel_all_gather_comm]: 3.535e-05 [overlap_param_gather]: 2.29999e-06 [cconv]: 4.999e-05 [loop_unroll]: 0.00077457 [opt_after_cconv]: 0.00023346, [1] [Cycle 1]: 0.00022329, [7] [c_1]: 6.772e-05 [parameter_eliminate]: 6.36e-06 [updatestate_depend_eliminate]: 1.212e-05 [updatestate_assign_eliminate]: 4.65001e-06 [updatestate_loads_eliminate]: 4.47e-06 [cse]: 7.782e-05 [renormalize]: 6.89994e-07 [remove_dup_value]: 7.531e-05 [tuple_transform]: 0.00016428, [1] [Cycle 1]: 0.0001553, [4] [d_1]: 0.00010545 [none_parameter_eliminate]: 3.46999e-06 [renormalize]: 1.90019e-07 [switch_simplify]: 1.473e-05 [partial_unused_args_eliminate]: 2.27999e-06 [add_recomputation]: 8.504e-05 [cse_after_recomputation]: 4.583e-05, [1] [Cycle 1]: 4.02e-05, [1] [cse]: 3.192e-05 [environ_conv]: 1.197e-05 [swap_dp_allreduce_reducescatter]: 9.00999e-06 [bias_add_comm_swap]: 3.14999e-06 [label_micro_interleaved_index]: 8.75001e-06 [label_fine_grained_interleaved_index]: 2.54999e-06 [merge_cast_opt]: 1.52001e-06 [slice_recompute_activation]: 2.29001e-06 [micro_interleaved_order_control]: 2.86999e-06 [assign_add_opt]: 1.27e-06 [ForceFp32Comm]: 1.07e-06 [remove_cast_before_assign_add]: 1.07998e-06 [full_micro_interleaved_order_control]: 2.25002e-06 [reorder_send_recv_between_fp_bp]: 2.99001e-06 [comm_op_add_attrs]: 1.10999e-06 [add_comm_op_reuse_tag]: 9.89996e-07 [interleave_split_concat_branches]: 1.25999e-06 [interleave_parallel_branches]: 3.80998e-06 [overlap_opt_shard_in_pipeline]: 2.94001e-06 [overlap_opt_shard_grad_in_pipeline]: 2.21e-06 [control_data_broadcast_order]: 2.231e-05 [grouped_pairwise_exchange_alltoall]: 1.65001e-06 [offloading_packed_experts]: 8.43999e-06 [overlap_recompute_and_grad_model_parallel]: 9.05001e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.36002e-06 [overlap_recompute_allgather_and_fa_grad]: 1.82001e-06 [overlap_recompute_comm]: 2.40002e-06 [overlap_grad_ring_attention]: 5.22e-06 [overlap_grad_flash_sp]: 2.76e-05 [begin_end_overlap_inline]: 5.19998e-07 [split_matmul_comm_elemetwise]: 2.57001e-06 [split_layernorm_comm]: 2.11998e-06 [handle_group_info]: 1.09003e-06 [symbol_engine_optimizer]: 0.00025314, [1] [Cycle 1]: 0.00024613, [6] [build]: 0.00010406 [elim_shapecalc]: 2.558e-05 [elim_not_effective]: 2.772e-05 [opt_reshape]: 1.648e-05 [fold_const_symbol]: 2.397e-05 [renormalize]: 2.30008e-07 [detach_backward]: 2.48e-06 [pipeline_parallel_scheduler]: 1.40999e-06 [auto_monad_reorder]: 4.02e-05 [get_jit_bprop_graph]: 1.99e-06 [rewriter_after_jit_bprop_graph]: 6.46999e-06 [opt_after_jit_grad]: 0.00081432 [validate]: 7.907e-05 Sums bootstrap : 0.000831s : 0.41% type_inference : 0.080151s : 39.50% event_method : 0.000022s : 0.01% auto_monad : 0.000113s : 0.06% graph_reusing : 0.000006s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000027s : 0.01% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000006s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000056s : 0.03% 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 : 0.000107s : 0.05% optimize.rewriter_before_opt_a : 0.000149s : 0.07% optimize.opt_a.expand_dump_flag : 0.000006s : 0.00% optimize.opt_a.switch_simplify : 0.000054s : 0.03% optimize.opt_a.loop_unroll : 0.000034s : 0.02% optimize.opt_a.a_1 : 0.000971s : 0.48% optimize.opt_a.with_stream_mark : 0.000050s : 0.02% optimize.opt_a.recompute_prepare : 0.000031s : 0.02% 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 : 0.000011s : 0.01% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000299s : 0.15% optimize.opt_a.accelerated_algorithm : 0.000036s : 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 : 0.000027s : 0.01% optimize.opt_a.merge_send_recv : 0.000022s : 0.01% optimize.opt_a.auto_parallel : 0.000025s : 0.01% optimize.opt_a.parallel : 0.000060s : 0.03% optimize.opt_a.flash_sp : 0.000017s : 0.01% optimize.opt_a.merge_comm : 0.000012s : 0.01% optimize.opt_a.allreduce_fusion : 0.000010s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000027s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000035s : 0.02% optimize.opt_a.virtual_dataset : 0.000030s : 0.01% optimize.opt_a.get_grad_eliminate_ : 0.000075s : 0.04% optimize.opt_a.virtual_output : 0.000034s : 0.02% optimize.opt_a.merge_forward : 0.000024s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000008s : 0.00% optimize.opt_a.offload_activation : 0.000039s : 0.02% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000069s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000005s : 0.00% optimize.opt_a.before_grad : 0.000041s : 0.02% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000018s : 0.01% optimize.opt_a.meta_fg_expand : 0.000017s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000011s : 0.01% optimize.opt_a.receive_attached : 0.000007s : 0.00% optimize.opt_a.after_resolve : 0.000080s : 0.04% optimize.opt_a.a_after_grad : 0.000051s : 0.02% optimize.opt_a.renormalize : 0.114589s : 56.47% optimize.opt_a.add_forward_monad_depend : 0.000013s : 0.01% optimize.opt_a.auto_monad_grad : 0.000005s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000041s : 0.02% optimize.opt_a.cse : 0.000173s : 0.09% optimize.opt_a.a_3 : 0.000192s : 0.09% optimize.py_interpret_to_execute_after_opt_a : 0.000031s : 0.02% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000076s : 0.04% optimize.convert_after_rewriter : 0.000012s : 0.01% optimize.order_py_execute_after_rewriter : 0.000008s : 0.00% optimize.mutable_eliminate : 0.000979s : 0.48% optimize.opt_b.b_1 : 0.000252s : 0.12% optimize.opt_b.b_2 : 0.000015s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000015s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000008s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000099s : 0.05% optimize.optimize_parallel_all_gather_comm : 0.000035s : 0.02% optimize.overlap_param_gather : 0.000002s : 0.00% optimize.cconv : 0.000050s : 0.02% optimize.loop_unroll : 0.000775s : 0.38% optimize.opt_after_cconv.c_1 : 0.000068s : 0.03% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000012s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000004s : 0.00% optimize.opt_after_cconv.cse : 0.000078s : 0.04% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000075s : 0.04% optimize.tuple_transform.d_1 : 0.000105s : 0.05% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000015s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000085s : 0.04% optimize.cse_after_recomputation.cse : 0.000032s : 0.02% optimize.environ_conv : 0.000012s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 0.00% optimize.bias_add_comm_swap : 0.000003s : 0.00% optimize.label_micro_interleaved_index : 0.000009s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000002s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 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 : 0.000004s : 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 : 0.000022s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000008s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000009s : 0.00% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000002s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000005s : 0.00% optimize.overlap_grad_flash_sp : 0.000028s : 0.01% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000104s : 0.05% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000026s : 0.01% optimize.symbol_engine_optimizer.elim_not_effective : 0.000028s : 0.01% optimize.symbol_engine_optimizer.opt_reshape : 0.000016s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000024s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000002s : 0.00% pipeline_parallel_scheduler : 0.000001s : 0.00% auto_monad_reorder : 0.000040s : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000006s : 0.00% opt_after_jit_grad : 0.000814s : 0.40% validate : 0.000079s : 0.04% Time group info: ------[substitution.] 0.000236 39 2.51% : 0.000006s : 2: substitution.elim_not_effective 3.85% : 0.000009s : 2: substitution.fold_const_symbol 3.84% : 0.000009s : 10: substitution.graph_param_transform 78.35% : 0.000185s : 1: substitution.inline 2.14% : 0.000005s : 4: substitution.j_node_and_user_rematch 2.72% : 0.000006s : 4: substitution.remove_not_recompute_node 6.59% : 0.000016s : 16: substitution.replace_old_param ------[type_inference.] 0.079989 2 98.38% : 0.078695s : 1: type_inference.infer 1.62% : 0.001294s : 1: type_inference.specialize ------[replace.] 0.000028 1 100.00% : 0.000028s : 1: replace.inline ------[match.] 0.000183 1 100.00% : 0.000183s : 1: match.inline ------[predicate.] 0.000293 2335 0.86% : 0.000003s : 21: predicate.accumulaten_eliminater 1.04% : 0.000003s : 10: predicate.ad_related_special_op_eliminate 0.66% : 0.000002s : 20: predicate.addn_check_dump 0.77% : 0.000002s : 21: predicate.addn_zero_filter 0.70% : 0.000002s : 21: predicate.adjust_all_reduce_mul_add 2.35% : 0.000007s : 41: predicate.arithmetic_simplify 0.83% : 0.000002s : 21: predicate.cast_eliminate 0.81% : 0.000002s : 20: predicate.check_bprop_eliminate 0.69% : 0.000002s : 20: predicate.compare_switch_simplify 0.25% : 0.000001s : 10: predicate.const_output_eliminate 0.79% : 0.000002s : 20: predicate.depend_value_elim 0.77% : 0.000002s : 21: predicate.dict_get_item_const_eliminator 1.09% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.80% : 0.000002s : 21: predicate.dict_set_item_eliminator 1.10% : 0.000003s : 20: predicate.dumpgradient_eliminate 0.27% : 0.000001s : 10: predicate.elim_not_effective 0.52% : 0.000002s : 10: predicate.elim_shapecalc_of_broadcastargs 1.27% : 0.000004s : 31: predicate.environ_add_const_eliminate 0.98% : 0.000003s : 31: predicate.environ_get_add_eliminate 1.13% : 0.000003s : 31: predicate.environ_get_depend_swap 1.70% : 0.000005s : 51: predicate.environ_get_eliminate 1.00% : 0.000003s : 31: predicate.environ_get_set_eliminate 0.75% : 0.000002s : 22: predicate.exchange_switch_depend_value 1.40% : 0.000004s : 22: predicate.float_depend_g_call 0.62% : 0.000002s : 20: predicate.float_environ_get_switch 1.02% : 0.000003s : 30: predicate.float_tuple_getitem_switch 0.25% : 0.000001s : 10: predicate.fold_const_symbol 2.16% : 0.000006s : 20: predicate.get_grad_eliminate 0.37% : 0.000001s : 10: predicate.graph_param_transform 0.69% : 0.000002s : 20: predicate.incorporate_call 0.58% : 0.000002s : 20: predicate.incorporate_call_switch 5.25% : 0.000015s : 103: predicate.inline 1.09% : 0.000003s : 20: predicate.inline_without_move 0.48% : 0.000001s : 20: predicate.j_node_and_user_rematch 1.25% : 0.000004s : 20: predicate.less_batch_normalization 1.83% : 0.000005s : 41: predicate.list_to_tuple_eliminator_ 2.14% : 0.000006s : 62: predicate.load_eliminater 1.53% : 0.000004s : 10: predicate.loop_unroll_after_grad 1.19% : 0.000003s : 31: predicate.loop_unroll_before_grad 1.70% : 0.000005s : 41: predicate.make_slice_get_slice_eliminator 0.70% : 0.000002s : 20: predicate.merge_addn 0.68% : 0.000002s : 20: predicate.micro_step_allgather_replace 0.80% : 0.000002s : 20: predicate.mini_step_allgather_replace 0.71% : 0.000002s : 21: predicate.minmaximum_grad 1.91% : 0.000006s : 10: predicate.mutable_eliminate 0.41% : 0.000001s : 10: predicate.opt_reshape 0.49% : 0.000001s : 10: predicate.parallel_virtual_node 0.92% : 0.000003s : 22: predicate.partial_defer_inline 1.17% : 0.000003s : 31: predicate.partial_eliminate 0.75% : 0.000002s : 21: predicate.print_const_string_wrapper 0.72% : 0.000002s : 20: predicate.reduce_all_const_elim 1.20% : 0.000004s : 21: predicate.reduce_eliminate 2.16% : 0.000006s : 62: predicate.redundant_stop_gradient_eliminater 0.80% : 0.000002s : 20: predicate.remove_not_recompute_node 1.49% : 0.000004s : 41: predicate.replace_applicator 0.72% : 0.000002s : 20: predicate.replace_old_param 0.47% : 0.000001s : 10: predicate.reset_defer_inline 0.91% : 0.000003s : 21: predicate.reshape_eliminate 0.78% : 0.000002s : 20: predicate.row_tensor_add_zeros_like 0.46% : 0.000001s : 10: predicate.row_tensor_eliminate 0.95% : 0.000003s : 20: predicate.same_eliminate 0.63% : 0.000002s : 20: predicate.set_cell_output_no_recompute 0.95% : 0.000003s : 20: predicate.shard_identity_eliminate 0.87% : 0.000003s : 20: predicate.special_op_eliminate 0.76% : 0.000002s : 20: predicate.specialize_transform 1.24% : 0.000004s : 20: predicate.split_environ_get_set_with_tuple_value 1.03% : 0.000003s : 20: predicate.stack_unstack_eliminate 0.45% : 0.000001s : 10: predicate.switch_call_monad_eliminater 0.76% : 0.000002s : 22: predicate.switch_defer_inline 1.56% : 0.000005s : 42: predicate.switch_layer_defer_inline 3.55% : 0.000010s : 83: predicate.switch_simplify 0.87% : 0.000003s : 21: predicate.tile_eliminate 0.74% : 0.000002s : 21: predicate.transpose_eliminate 2.25% : 0.000007s : 41: predicate.tuple_list_convert_item_index_to_positive 1.82% : 0.000005s : 41: predicate.tuple_list_get_item_const_eliminator 1.66% : 0.000005s : 41: predicate.tuple_list_get_item_depend_reorder 3.31% : 0.000010s : 61: predicate.tuple_list_get_item_eliminator 1.51% : 0.000004s : 41: predicate.tuple_list_get_set_item_eliminator 2.52% : 0.000007s : 61: predicate.tuple_list_set_item_eliminator 1.52% : 0.000004s : 41: predicate.tuple_to_list_eliminator_ 2.02% : 0.000006s : 62: predicate.updatestate_pure_node_eliminater 2.88% : 0.000008s : 82: predicate.updatestate_useless_node_eliminater 0.43% : 0.000001s : 10: predicate.value_based_eliminate 0.82% : 0.000002s : 20: predicate.virtual_dataset_eliminate 0.88% : 0.000003s : 20: predicate.virtual_output_eliminate 0.40% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.65% : 0.000002s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.001418 6 39.97% : 0.000567s : 3: func_graph_cloner_run.FuncGraphClonerGraph 60.03% : 0.000851s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.473414 192 0.00% : 0.000004s : 1: ForceFp32Comm 1.86% : 0.008826s : 1: add_attr 1.86% : 0.008799s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000093s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.03% : 0.000129s : 1: auto_monad 0.01% : 0.000045s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000009s : 1: bias_add_comm_swap 0.18% : 0.000866s : 1: bootstrap 0.01% : 0.000057s : 1: cconv 0.00% : 0.000005s : 1: comm_op_add_attrs 0.01% : 0.000029s : 1: control_data_broadcast_order 0.00% : 0.000017s : 1: convert_after_rewriter 0.01% : 0.000049s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000006s : 1: detach_backward 0.00% : 0.000016s : 1: environ_conv 0.01% : 0.000035s : 1: event_method 0.00% : 0.000006s : 1: full_micro_interleaved_order_control 0.00% : 0.000005s : 1: get_jit_bprop_graph 0.00% : 0.000012s : 1: graph_reusing 0.00% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000005s : 1: handle_group_info 0.00% : 0.000012s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000007s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000013s : 1: label_micro_interleaved_index 0.17% : 0.000791s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000007s : 1: micro_interleaved_order_control 0.21% : 0.001000s : 1: mutable_eliminate 0.00% : 0.000012s : 1: offloading_packed_experts 0.01% : 0.000034s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000042s : 1: opt.transform.mutable_eliminate 0.41% : 0.001924s : 78: opt.transform.opt_a 0.01% : 0.000065s : 1: opt.transform.opt_after_cconv 0.01% : 0.000068s : 1: opt.transform.opt_after_jit_grad 0.05% : 0.000232s : 28: opt.transform.opt_b 0.02% : 0.000117s : 2: opt.transform.opt_trans_graph 0.02% : 0.000089s : 4: opt.transform.symbol_engine_opt 26.23% : 0.124164s : 1: opt_a 0.05% : 0.000238s : 1: opt_after_cconv 0.18% : 0.000829s : 1: opt_after_jit_grad 0.10% : 0.000482s : 1: opt_b 27.09% : 0.128260s : 1: optimize 0.01% : 0.000041s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000013s : 1: order_py_execute_after_rewriter 0.01% : 0.000032s : 1: overlap_grad_flash_sp 0.00% : 0.000007s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000017s : 1: overlap_grad_ring_attention 0.00% : 0.000007s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000007s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000006s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000013s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000011s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000007s : 1: pipeline_parallel_scheduler 0.00% : 0.000011s : 1: pipeline_split 0.01% : 0.000061s : 1: pre_auto_parallel 0.03% : 0.000124s : 1: py_interpret_to_execute 0.01% : 0.000036s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000082s : 1: remove_dup_value 24.00% : 0.113623s : 1: renormalize.infer 0.20% : 0.000938s : 1: renormalize.specialize 0.00% : 0.000008s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000010s : 1: rewriter_after_jit_bprop_graph 0.02% : 0.000083s : 1: rewriter_after_opt_a 0.03% : 0.000162s : 1: rewriter_before_opt_a 0.00% : 0.000007s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000009s : 1: split_matmul_comm_elemetwise 0.00% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.05% : 0.000259s : 1: symbol_engine_optimizer 0.04% : 0.000168s : 1: tuple_transform 16.94% : 0.080177s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_bsh[QuantMethod.FP16_VEC-1] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_bsh[QuantMethod.FP16_VEC-1],max_mem:454.0M [WARNING] ME(163399:281473684254512,MainProcess):2026-01-29-17:38:21.267.471 [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 = 0.348322, [21] [bootstrap]: 0.00092897 [type_inference]: 0.14718 [event_method]: 2.378e-05 [auto_monad]: 0.00012502 [graph_reusing]: 5.67999e-06 [inline]: 3.58999e-06 [add_attr]: 0.0872618, [1] [add_attr_with_inline]: 0.0872385, [1] [Cycle 1]: 0.00016486, [2] [tag_attr]: 6.884e-05 [meta_addattr_fg_expand]: 5.25001e-06 [parallel-infer-symbol]: 4.47e-06 [pre_auto_parallel]: 0.00010443 [insert-virtual-dataset]: 3.14001e-06 [parallel-infer-symbol-second]: 9.50007e-07 [dataset_repeat_opt]: 2.64001e-06 [pipeline_split]: 2.01e-06 [optimize]: 0.11151, [53] [py_interpret_to_execute]: 0.00014409 [rewriter_before_opt_a]: 0.00022296 [opt_a]: 0.0100627, [2] [Cycle 1]: 0.00721911, [45] [expand_dump_flag]: 4.28999e-06 [switch_simplify]: 3.902e-05 [loop_unroll]: 5.045e-05 [a_1]: 0.00102638 [with_stream_mark]: 4.119e-05 [recompute_prepare]: 2.328e-05 [updatestate_depend_eliminate]: 3.086e-05 [updatestate_assign_eliminate]: 6.35002e-06 [updatestate_loads_eliminate]: 5.51e-06 [parameter_eliminate]: 3.32002e-06 [a_2]: 0.00017663 [accelerated_algorithm]: 4.786e-05 [shard]: 3.47997e-06 [meta_shard_fg_expand]: 4.70999e-06 [shard_inline]: 1.36e-05 [merge_send_recv]: 1.325e-05 [auto_parallel]: 1.553e-05 [parallel]: 7.067e-05 [flash_sp]: 1.451e-05 [merge_comm]: 6.36998e-06 [allreduce_fusion]: 5.46e-06 [matmul_add_comm_reduction]: 1.367e-05 [allreduce_slice_to_reducescatter]: 9.50007e-07 [virtual_shard_identity]: 1.907e-05 [virtual_dataset]: 1.306e-05 [get_grad_eliminate_]: 1.342e-05 [virtual_output]: 1.519e-05 [merge_forward]: 8.57e-06 [cell_reuse_recompute_pass]: 3.14999e-06 [offload_activation]: 1.725e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.551e-05 [merge_recompute_call_nodes]: 1.75001e-06 [before_grad]: 2.095e-05 [set_forward_comm_id_for_comm_node_pass]: 8.54e-06 [meta_fg_expand]: 6.47001e-06 [flash_sp_send_recv_attached]: 4.59002e-06 [receive_attached]: 2.75002e-06 [after_resolve]: 6.563e-05 [a_after_grad]: 5.423e-05 [renormalize]: 0.00352409 [add_forward_monad_depend]: 1.284e-05 [auto_monad_grad]: 2.94001e-06 [auto_monad_eliminator]: 3.071e-05 [cse]: 0.00016238 [a_3]: 0.00010676 [Cycle 2]: 0.00279179, [45] [expand_dump_flag]: 3.00998e-06 [switch_simplify]: 1.576e-05 [loop_unroll]: 1.361e-05 [a_1]: 0.00031149 [with_stream_mark]: 2.958e-05 [recompute_prepare]: 1.408e-05 [updatestate_depend_eliminate]: 8.21002e-06 [updatestate_assign_eliminate]: 6.48e-06 [updatestate_loads_eliminate]: 6.86001e-06 [parameter_eliminate]: 3.20002e-06 [a_2]: 0.00015478 [accelerated_algorithm]: 4.363e-05 [shard]: 2.945e-05 [meta_shard_fg_expand]: 6.64001e-06 [shard_inline]: 1.22e-05 [merge_send_recv]: 5.305e-05 [auto_parallel]: 1.556e-05 [parallel]: 1.16e-05 [flash_sp]: 5.94999e-06 [merge_comm]: 6.89999e-06 [allreduce_fusion]: 5.71998e-06 [matmul_add_comm_reduction]: 1.544e-05 [allreduce_slice_to_reducescatter]: 8.39995e-07 [virtual_shard_identity]: 1.811e-05 [virtual_dataset]: 4.163e-05 [get_grad_eliminate_]: 1.223e-05 [virtual_output]: 1.285e-05 [merge_forward]: 9.54999e-06 [cell_reuse_recompute_pass]: 3.76999e-06 [offload_activation]: 8.026e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.721e-05 [merge_recompute_call_nodes]: 2.31e-06 [before_grad]: 4.9e-05 [set_forward_comm_id_for_comm_node_pass]: 9.07999e-06 [meta_fg_expand]: 6.46e-06 [flash_sp_send_recv_attached]: 2.98e-06 [receive_attached]: 2.63998e-06 [after_resolve]: 8.435e-05 [a_after_grad]: 5.174e-05 [renormalize]: 6.00121e-08 [add_forward_monad_depend]: 5.54e-06 [auto_monad_grad]: 3.19001e-06 [auto_monad_eliminator]: 2.425e-05 [cse]: 0.00012492 [a_3]: 9.132e-05 [py_interpret_to_execute_after_opt_a]: 0.00011389 [slice_cell_reuse_recomputed_activation]: 3.38e-06 [rewriter_after_opt_a]: 0.00013928 [convert_after_rewriter]: 1.376e-05 [order_py_execute_after_rewriter]: 7.67998e-06 [mutable_eliminate]: 0.00122356 [opt_b]: 0.0969073, [1] [Cycle 1]: 0.0968906, [7] [b_1]: 0.00028877 [b_2]: 1.45e-05 [updatestate_depend_eliminate]: 1.688e-05 [updatestate_assign_eliminate]: 6.13002e-06 [updatestate_loads_eliminate]: 5.28002e-06 [renormalize]: 3.59985e-07 [cse]: 0.0001523 [optimize_parallel_all_gather_comm]: 4.385e-05 [overlap_param_gather]: 3.66999e-06 [cconv]: 4.681e-05 [loop_unroll]: 0.00098737 [opt_after_cconv]: 0.00028497, [1] [Cycle 1]: 0.00027155, [7] [c_1]: 7.416e-05 [parameter_eliminate]: 8.32e-06 [updatestate_depend_eliminate]: 1.453e-05 [updatestate_assign_eliminate]: 6.06e-06 [updatestate_loads_eliminate]: 5.23002e-06 [cse]: 7.633e-05 [renormalize]: 1.18001e-06 [remove_dup_value]: 8.501e-05 [tuple_transform]: 0.00018392, [1] [Cycle 1]: 0.00016872, [4] [d_1]: 0.00011335 [none_parameter_eliminate]: 2.74001e-06 [renormalize]: 2.59985e-07 [switch_simplify]: 1.754e-05 [partial_unused_args_eliminate]: 2.48e-06 [add_recomputation]: 9.194e-05 [cse_after_recomputation]: 5.35e-05, [1] [Cycle 1]: 4.742e-05, [1] [cse]: 3.824e-05 [environ_conv]: 1.037e-05 [swap_dp_allreduce_reducescatter]: 9.17999e-06 [bias_add_comm_swap]: 3.6e-06 [label_micro_interleaved_index]: 6.27001e-06 [label_fine_grained_interleaved_index]: 3.06001e-06 [merge_cast_opt]: 1.46002e-06 [slice_recompute_activation]: 2.23002e-06 [micro_interleaved_order_control]: 3.11001e-06 [assign_add_opt]: 1.71e-06 [ForceFp32Comm]: 9.60019e-07 [remove_cast_before_assign_add]: 1.36002e-06 [full_micro_interleaved_order_control]: 2.53e-06 [reorder_send_recv_between_fp_bp]: 2.93e-06 [comm_op_add_attrs]: 1.10001e-06 [add_comm_op_reuse_tag]: 1.05001e-06 [interleave_split_concat_branches]: 1.37999e-06 [interleave_parallel_branches]: 1.19e-06 [overlap_opt_shard_in_pipeline]: 2.68e-06 [overlap_opt_shard_grad_in_pipeline]: 2.15002e-06 [control_data_broadcast_order]: 2.25e-05 [grouped_pairwise_exchange_alltoall]: 1.91998e-06 [offloading_packed_experts]: 6.99001e-06 [overlap_recompute_and_grad_model_parallel]: 6.34999e-06 [overlap_grad_matmul_and_grad_allreduce]: 1.52999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.62999e-06 [overlap_recompute_comm]: 5.76998e-06 [overlap_grad_ring_attention]: 5.77999e-06 [overlap_grad_flash_sp]: 3.042e-05 [begin_end_overlap_inline]: 5.50004e-07 [split_matmul_comm_elemetwise]: 2.54001e-06 [split_layernorm_comm]: 2.13998e-06 [handle_group_info]: 1.48002e-06 [symbol_engine_optimizer]: 0.00029949, [1] [Cycle 1]: 0.00028658, [6] [build]: 0.00010909 [elim_shapecalc]: 3.018e-05 [elim_not_effective]: 2.883e-05 [opt_reshape]: 1.555e-05 [fold_const_symbol]: 2.945e-05 [renormalize]: 2.19996e-07 [detach_backward]: 3.38e-06 [pipeline_parallel_scheduler]: 2.05002e-06 [auto_monad_reorder]: 3.479e-05 [get_jit_bprop_graph]: 2.25002e-06 [rewriter_after_jit_bprop_graph]: 1.144e-05 [opt_after_jit_grad]: 0.00081633 [validate]: 8.232e-05 Sums bootstrap : 0.000929s : 0.58% type_inference : 0.147180s : 91.44% event_method : 0.000024s : 0.01% auto_monad : 0.000125s : 0.08% graph_reusing : 0.000006s : 0.00% inline : 0.000004s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000069s : 0.04% add_attr.add_attr_with_inline.meta_addattr_fg_expand : 0.000005s : 0.00% parallel-infer-symbol : 0.000004s : 0.00% pre_auto_parallel : 0.000104s : 0.06% insert-virtual-dataset : 0.000003s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000003s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000144s : 0.09% optimize.rewriter_before_opt_a : 0.000223s : 0.14% optimize.opt_a.expand_dump_flag : 0.000007s : 0.00% optimize.opt_a.switch_simplify : 0.000055s : 0.03% optimize.opt_a.loop_unroll : 0.000064s : 0.04% optimize.opt_a.a_1 : 0.001338s : 0.83% optimize.opt_a.with_stream_mark : 0.000071s : 0.04% optimize.opt_a.recompute_prepare : 0.000037s : 0.02% optimize.opt_a.updatestate_depend_eliminate : 0.000039s : 0.02% optimize.opt_a.updatestate_assign_eliminate : 0.000013s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.01% optimize.opt_a.parameter_eliminate : 0.000007s : 0.00% optimize.opt_a.a_2 : 0.000331s : 0.21% optimize.opt_a.accelerated_algorithm : 0.000091s : 0.06% optimize.opt_a.shard : 0.000033s : 0.02% optimize.opt_a.meta_shard_fg_expand : 0.000011s : 0.01% optimize.opt_a.shard_inline : 0.000026s : 0.02% optimize.opt_a.merge_send_recv : 0.000066s : 0.04% optimize.opt_a.auto_parallel : 0.000031s : 0.02% optimize.opt_a.parallel : 0.000082s : 0.05% optimize.opt_a.flash_sp : 0.000020s : 0.01% optimize.opt_a.merge_comm : 0.000013s : 0.01% optimize.opt_a.allreduce_fusion : 0.000011s : 0.01% optimize.opt_a.matmul_add_comm_reduction : 0.000029s : 0.02% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000037s : 0.02% optimize.opt_a.virtual_dataset : 0.000055s : 0.03% optimize.opt_a.get_grad_eliminate_ : 0.000026s : 0.02% optimize.opt_a.virtual_output : 0.000028s : 0.02% optimize.opt_a.merge_forward : 0.000018s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000007s : 0.00% optimize.opt_a.offload_activation : 0.000098s : 0.06% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000093s : 0.06% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000070s : 0.04% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000018s : 0.01% optimize.opt_a.meta_fg_expand : 0.000013s : 0.01% optimize.opt_a.flash_sp_send_recv_attached : 0.000008s : 0.00% optimize.opt_a.receive_attached : 0.000005s : 0.00% optimize.opt_a.after_resolve : 0.000150s : 0.09% optimize.opt_a.a_after_grad : 0.000106s : 0.07% optimize.opt_a.renormalize : 0.003524s : 2.19% optimize.opt_a.add_forward_monad_depend : 0.000018s : 0.01% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000055s : 0.03% optimize.opt_a.cse : 0.000287s : 0.18% optimize.opt_a.a_3 : 0.000198s : 0.12% optimize.py_interpret_to_execute_after_opt_a : 0.000114s : 0.07% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000139s : 0.09% optimize.convert_after_rewriter : 0.000014s : 0.01% optimize.order_py_execute_after_rewriter : 0.000008s : 0.00% optimize.mutable_eliminate : 0.001224s : 0.76% optimize.opt_b.b_1 : 0.000289s : 0.18% optimize.opt_b.b_2 : 0.000014s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000017s : 0.01% optimize.opt_b.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000000s : 0.00% optimize.opt_b.cse : 0.000152s : 0.09% optimize.optimize_parallel_all_gather_comm : 0.000044s : 0.03% optimize.overlap_param_gather : 0.000004s : 0.00% optimize.cconv : 0.000047s : 0.03% optimize.loop_unroll : 0.000987s : 0.61% optimize.opt_after_cconv.c_1 : 0.000074s : 0.05% optimize.opt_after_cconv.parameter_eliminate : 0.000008s : 0.01% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000015s : 0.01% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000076s : 0.05% optimize.opt_after_cconv.renormalize : 0.000001s : 0.00% optimize.remove_dup_value : 0.000085s : 0.05% optimize.tuple_transform.d_1 : 0.000113s : 0.07% optimize.tuple_transform.none_parameter_eliminate : 0.000003s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000018s : 0.01% optimize.partial_unused_args_eliminate : 0.000002s : 0.00% optimize.add_recomputation : 0.000092s : 0.06% optimize.cse_after_recomputation.cse : 0.000038s : 0.02% optimize.environ_conv : 0.000010s : 0.01% optimize.swap_dp_allreduce_reducescatter : 0.000009s : 0.01% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000002s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000003s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 0.00% optimize.comm_op_add_attrs : 0.000001s : 0.00% optimize.add_comm_op_reuse_tag : 0.000001s : 0.00% optimize.interleave_split_concat_branches : 0.000001s : 0.00% optimize.interleave_parallel_branches : 0.000001s : 0.00% optimize.overlap_opt_shard_in_pipeline : 0.000003s : 0.00% optimize.overlap_opt_shard_grad_in_pipeline : 0.000002s : 0.00% optimize.control_data_broadcast_order : 0.000022s : 0.01% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000007s : 0.00% optimize.overlap_recompute_and_grad_model_parallel : 0.000006s : 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 : 0.000006s : 0.00% optimize.overlap_grad_ring_attention : 0.000006s : 0.00% optimize.overlap_grad_flash_sp : 0.000030s : 0.02% optimize.begin_end_overlap_inline : 0.000001s : 0.00% optimize.split_matmul_comm_elemetwise : 0.000003s : 0.00% optimize.split_layernorm_comm : 0.000002s : 0.00% optimize.handle_group_info : 0.000001s : 0.00% optimize.symbol_engine_optimizer.build : 0.000109s : 0.07% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000030s : 0.02% optimize.symbol_engine_optimizer.elim_not_effective : 0.000029s : 0.02% optimize.symbol_engine_optimizer.opt_reshape : 0.000016s : 0.01% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000029s : 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 : 0.02% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000011s : 0.01% opt_after_jit_grad : 0.000816s : 0.51% validate : 0.000082s : 0.05% Time group info: ------[substitution.] 0.000547 39 1.29% : 0.000007s : 2: substitution.elim_not_effective 1.84% : 0.000010s : 2: substitution.fold_const_symbol 1.73% : 0.000009s : 10: substitution.graph_param_transform 90.02% : 0.000492s : 1: substitution.inline 1.07% : 0.000006s : 4: substitution.j_node_and_user_rematch 1.44% : 0.000008s : 4: substitution.remove_not_recompute_node 2.61% : 0.000014s : 16: substitution.replace_old_param ------[type_inference.] 0.147007 2 5.03% : 0.007400s : 1: type_inference.infer 94.97% : 0.139606s : 1: type_inference.specialize ------[replace.] 0.000056 1 100.00% : 0.000056s : 1: replace.inline ------[match.] 0.000490 1 100.00% : 0.000490s : 1: match.inline ------[predicate.] 0.000310 2335 0.85% : 0.000003s : 21: predicate.accumulaten_eliminater 1.31% : 0.000004s : 10: predicate.ad_related_special_op_eliminate 0.65% : 0.000002s : 20: predicate.addn_check_dump 0.70% : 0.000002s : 21: predicate.addn_zero_filter 0.62% : 0.000002s : 21: predicate.adjust_all_reduce_mul_add 2.27% : 0.000007s : 41: predicate.arithmetic_simplify 0.85% : 0.000003s : 21: predicate.cast_eliminate 0.82% : 0.000003s : 20: predicate.check_bprop_eliminate 0.65% : 0.000002s : 20: predicate.compare_switch_simplify 0.25% : 0.000001s : 10: predicate.const_output_eliminate 0.75% : 0.000002s : 20: predicate.depend_value_elim 0.76% : 0.000002s : 21: predicate.dict_get_item_const_eliminator 0.95% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.79% : 0.000002s : 21: predicate.dict_set_item_eliminator 1.41% : 0.000004s : 20: predicate.dumpgradient_eliminate 0.39% : 0.000001s : 10: predicate.elim_not_effective 0.56% : 0.000002s : 10: predicate.elim_shapecalc_of_broadcastargs 1.05% : 0.000003s : 31: predicate.environ_add_const_eliminate 0.95% : 0.000003s : 31: predicate.environ_get_add_eliminate 1.03% : 0.000003s : 31: predicate.environ_get_depend_swap 1.78% : 0.000006s : 51: predicate.environ_get_eliminate 1.01% : 0.000003s : 31: predicate.environ_get_set_eliminate 0.72% : 0.000002s : 22: predicate.exchange_switch_depend_value 1.53% : 0.000005s : 22: predicate.float_depend_g_call 0.65% : 0.000002s : 20: predicate.float_environ_get_switch 0.92% : 0.000003s : 30: predicate.float_tuple_getitem_switch 0.25% : 0.000001s : 10: predicate.fold_const_symbol 1.04% : 0.000003s : 20: predicate.get_grad_eliminate 0.33% : 0.000001s : 10: predicate.graph_param_transform 0.68% : 0.000002s : 20: predicate.incorporate_call 0.58% : 0.000002s : 20: predicate.incorporate_call_switch 5.32% : 0.000016s : 103: predicate.inline 1.36% : 0.000004s : 20: predicate.inline_without_move 0.55% : 0.000002s : 20: predicate.j_node_and_user_rematch 0.99% : 0.000003s : 20: predicate.less_batch_normalization 1.76% : 0.000005s : 41: predicate.list_to_tuple_eliminator_ 2.23% : 0.000007s : 62: predicate.load_eliminater 1.80% : 0.000006s : 10: predicate.loop_unroll_after_grad 1.36% : 0.000004s : 31: predicate.loop_unroll_before_grad 2.13% : 0.000007s : 41: predicate.make_slice_get_slice_eliminator 0.74% : 0.000002s : 20: predicate.merge_addn 0.88% : 0.000003s : 20: predicate.micro_step_allgather_replace 0.71% : 0.000002s : 20: predicate.mini_step_allgather_replace 0.64% : 0.000002s : 21: predicate.minmaximum_grad 1.68% : 0.000005s : 10: predicate.mutable_eliminate 0.49% : 0.000002s : 10: predicate.opt_reshape 0.48% : 0.000001s : 10: predicate.parallel_virtual_node 1.40% : 0.000004s : 22: predicate.partial_defer_inline 1.08% : 0.000003s : 31: predicate.partial_eliminate 0.75% : 0.000002s : 21: predicate.print_const_string_wrapper 0.70% : 0.000002s : 20: predicate.reduce_all_const_elim 1.24% : 0.000004s : 21: predicate.reduce_eliminate 2.11% : 0.000007s : 62: predicate.redundant_stop_gradient_eliminater 0.84% : 0.000003s : 20: predicate.remove_not_recompute_node 1.33% : 0.000004s : 41: predicate.replace_applicator 0.73% : 0.000002s : 20: predicate.replace_old_param 0.38% : 0.000001s : 10: predicate.reset_defer_inline 0.80% : 0.000002s : 21: predicate.reshape_eliminate 0.85% : 0.000003s : 20: predicate.row_tensor_add_zeros_like 0.39% : 0.000001s : 10: predicate.row_tensor_eliminate 1.62% : 0.000005s : 20: predicate.same_eliminate 0.69% : 0.000002s : 20: predicate.set_cell_output_no_recompute 1.14% : 0.000004s : 20: predicate.shard_identity_eliminate 0.88% : 0.000003s : 20: predicate.special_op_eliminate 0.94% : 0.000003s : 20: predicate.specialize_transform 1.26% : 0.000004s : 20: predicate.split_environ_get_set_with_tuple_value 1.21% : 0.000004s : 20: predicate.stack_unstack_eliminate 0.45% : 0.000001s : 10: predicate.switch_call_monad_eliminater 0.77% : 0.000002s : 22: predicate.switch_defer_inline 1.52% : 0.000005s : 42: predicate.switch_layer_defer_inline 3.72% : 0.000012s : 83: predicate.switch_simplify 0.73% : 0.000002s : 21: predicate.tile_eliminate 0.71% : 0.000002s : 21: predicate.transpose_eliminate 1.68% : 0.000005s : 41: predicate.tuple_list_convert_item_index_to_positive 1.56% : 0.000005s : 41: predicate.tuple_list_get_item_const_eliminator 1.50% : 0.000005s : 41: predicate.tuple_list_get_item_depend_reorder 3.03% : 0.000009s : 61: predicate.tuple_list_get_item_eliminator 1.56% : 0.000005s : 41: predicate.tuple_list_get_set_item_eliminator 2.78% : 0.000009s : 61: predicate.tuple_list_set_item_eliminator 1.45% : 0.000004s : 41: predicate.tuple_to_list_eliminator_ 1.98% : 0.000006s : 62: predicate.updatestate_pure_node_eliminater 2.77% : 0.000009s : 82: predicate.updatestate_useless_node_eliminater 0.45% : 0.000001s : 10: predicate.value_based_eliminate 0.83% : 0.000003s : 20: predicate.virtual_dataset_eliminate 0.98% : 0.000003s : 20: predicate.virtual_output_eliminate 0.35% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.65% : 0.000002s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.002272 6 29.73% : 0.000675s : 3: func_graph_cloner_run.FuncGraphClonerGraph 70.27% : 0.001596s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.553598 192 0.00% : 0.000004s : 1: ForceFp32Comm 15.76% : 0.087270s : 1: add_attr 15.76% : 0.087244s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000099s : 1: add_recomputation 0.00% : 0.000005s : 1: assign_add_opt 0.02% : 0.000133s : 1: auto_monad 0.01% : 0.000040s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000007s : 1: bias_add_comm_swap 0.17% : 0.000967s : 1: bootstrap 0.01% : 0.000055s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000031s : 1: control_data_broadcast_order 0.00% : 0.000018s : 1: convert_after_rewriter 0.01% : 0.000057s : 1: cse_after_recomputation 0.00% : 0.000006s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000018s : 1: environ_conv 0.01% : 0.000032s : 1: event_method 0.00% : 0.000009s : 1: full_micro_interleaved_order_control 0.00% : 0.000006s : 1: get_jit_bprop_graph 0.00% : 0.000011s : 1: graph_reusing 0.00% : 0.000006s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000008s : 1: interleave_parallel_branches 0.00% : 0.000005s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000014s : 1: label_micro_interleaved_index 0.18% : 0.001007s : 1: loop_unroll 0.00% : 0.000004s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.22% : 0.001240s : 1: mutable_eliminate 0.00% : 0.000011s : 1: offloading_packed_experts 0.01% : 0.000041s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000036s : 1: opt.transform.mutable_eliminate 0.46% : 0.002545s : 78: opt.transform.opt_a 0.01% : 0.000072s : 1: opt.transform.opt_after_cconv 0.01% : 0.000062s : 1: opt.transform.opt_after_jit_grad 0.04% : 0.000231s : 28: opt.transform.opt_b 0.02% : 0.000128s : 2: opt.transform.opt_trans_graph 0.02% : 0.000097s : 4: opt.transform.symbol_engine_opt 1.82% : 0.010090s : 1: opt_a 0.05% : 0.000290s : 1: opt_after_cconv 0.15% : 0.000836s : 1: opt_after_jit_grad 17.51% : 0.096915s : 1: opt_b 20.14% : 0.111517s : 1: optimize 0.01% : 0.000049s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000011s : 1: order_py_execute_after_rewriter 0.01% : 0.000036s : 1: overlap_grad_flash_sp 0.00% : 0.000009s : 1: overlap_grad_matmul_and_grad_allreduce 0.00% : 0.000011s : 1: overlap_grad_ring_attention 0.00% : 0.000014s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000005s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000010s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000009s : 1: overlap_recompute_comm 0.00% : 0.000009s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000011s : 1: pipeline_parallel_scheduler 0.00% : 0.000005s : 1: pipeline_split 0.02% : 0.000110s : 1: pre_auto_parallel 0.03% : 0.000152s : 1: py_interpret_to_execute 0.02% : 0.000121s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.02% : 0.000091s : 1: remove_dup_value 0.19% : 0.001024s : 1: renormalize.infer 0.45% : 0.002481s : 1: renormalize.specialize 0.00% : 0.000006s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000015s : 1: rewriter_after_jit_bprop_graph 0.03% : 0.000175s : 1: rewriter_after_opt_a 0.04% : 0.000230s : 1: rewriter_before_opt_a 0.01% : 0.000036s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000006s : 1: split_layernorm_comm 0.00% : 0.000009s : 1: split_matmul_comm_elemetwise 0.00% : 0.000013s : 1: swap_dp_allreduce_reducescatter 0.05% : 0.000303s : 1: symbol_engine_optimizer 0.03% : 0.000190s : 1: tuple_transform 26.59% : 0.147205s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_bsh[QuantMethod.INT_CUBE-0] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_bsh[QuantMethod.INT_CUBE-0],max_mem:454.0M [WARNING] ME(163399:281473684254512,MainProcess):2026-01-29-17:38:34.968.090 [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 = 0.55821, [21] [bootstrap]: 0.00187358 [type_inference]: 0.276982 [event_method]: 1.963e-05 [auto_monad]: 6.717e-05 [graph_reusing]: 5.27001e-06 [inline]: 3.4e-06 [add_attr]: 0.26079, [1] [add_attr_with_inline]: 0.260773, [1] [Cycle 1]: 7.465e-05, [2] [tag_attr]: 2.181e-05 [meta_addattr_fg_expand]: 4.25e-06 [parallel-infer-symbol]: 3.53e-06 [pre_auto_parallel]: 6.473e-05 [insert-virtual-dataset]: 2.46e-06 [parallel-infer-symbol-second]: 7.00005e-07 [dataset_repeat_opt]: 1.72999e-06 [pipeline_split]: 1.57001e-06 [optimize]: 0.0164121, [53] [py_interpret_to_execute]: 6.283e-05 [rewriter_before_opt_a]: 0.00028273 [opt_a]: 0.0110817, [2] [Cycle 1]: 0.00829197, [45] [expand_dump_flag]: 3.31999e-06 [switch_simplify]: 3.555e-05 [loop_unroll]: 2.273e-05 [a_1]: 0.00193245 [with_stream_mark]: 3.015e-05 [recompute_prepare]: 7.898e-05 [updatestate_depend_eliminate]: 8.10999e-06 [updatestate_assign_eliminate]: 5.35999e-06 [updatestate_loads_eliminate]: 5.33002e-06 [parameter_eliminate]: 2.27001e-06 [a_2]: 0.00040964 [accelerated_algorithm]: 4.673e-05 [shard]: 3.03e-06 [meta_shard_fg_expand]: 4.54002e-06 [shard_inline]: 1.213e-05 [merge_send_recv]: 1.273e-05 [auto_parallel]: 1.212e-05 [parallel]: 3.429e-05 [flash_sp]: 1.387e-05 [merge_comm]: 6.36e-06 [allreduce_fusion]: 5.12999e-06 [matmul_add_comm_reduction]: 1.39e-05 [allreduce_slice_to_reducescatter]: 7.40023e-07 [virtual_shard_identity]: 4.608e-05 [virtual_dataset]: 7.229e-05 [get_grad_eliminate_]: 4.598e-05 [virtual_output]: 6.897e-05 [merge_forward]: 7.56999e-06 [cell_reuse_recompute_pass]: 2.83998e-06 [offload_activation]: 1.464e-05 [cell_reuse_handle_not_recompute_node_pass]: 5.494e-05 [merge_recompute_call_nodes]: 1.90001e-06 [before_grad]: 9.941e-05 [set_forward_comm_id_for_comm_node_pass]: 7.75e-06 [meta_fg_expand]: 5.05999e-06 [flash_sp_send_recv_attached]: 4.08001e-06 [receive_attached]: 1.67e-05 [after_resolve]: 8.029e-05 [a_after_grad]: 8.854e-05 [renormalize]: 0.00330719 [add_forward_monad_depend]: 1.275e-05 [auto_monad_grad]: 3.01001e-06 [auto_monad_eliminator]: 6.131e-05 [cse]: 0.000193 [a_3]: 0.00018289 [Cycle 2]: 0.00268486, [45] [expand_dump_flag]: 3.855e-05 [switch_simplify]: 7.497e-05 [loop_unroll]: 1.373e-05 [a_1]: 0.00035829 [with_stream_mark]: 3.301e-05 [recompute_prepare]: 1.609e-05 [updatestate_depend_eliminate]: 7.97e-06 [updatestate_assign_eliminate]: 3.632e-05 [updatestate_loads_eliminate]: 7.01001e-06 [parameter_eliminate]: 2.74001e-06 [a_2]: 0.00016498 [accelerated_algorithm]: 1.488e-05 [shard]: 3.83001e-06 [meta_shard_fg_expand]: 5.22e-06 [shard_inline]: 1.295e-05 [merge_send_recv]: 1.223e-05 [auto_parallel]: 1.352e-05 [parallel]: 1.069e-05 [flash_sp]: 4.56002e-06 [merge_comm]: 5.52001e-06 [allreduce_fusion]: 5.20001e-06 [matmul_add_comm_reduction]: 1.448e-05 [allreduce_slice_to_reducescatter]: 1.02e-06 [virtual_shard_identity]: 1.715e-05 [virtual_dataset]: 1.41e-05 [get_grad_eliminate_]: 1.303e-05 [virtual_output]: 1.271e-05 [merge_forward]: 7.28e-06 [cell_reuse_recompute_pass]: 3.62002e-06 [offload_activation]: 1.549e-05 [cell_reuse_handle_not_recompute_node_pass]: 3.18e-05 [merge_recompute_call_nodes]: 1.82999e-06 [before_grad]: 4.835e-05 [set_forward_comm_id_for_comm_node_pass]: 8.15e-06 [meta_fg_expand]: 5.42001e-06 [flash_sp_send_recv_attached]: 2.22001e-06 [receive_attached]: 3.36999e-06 [after_resolve]: 3.618e-05 [a_after_grad]: 2.088e-05 [renormalize]: 8.9989e-08 [add_forward_monad_depend]: 4.62e-06 [auto_monad_grad]: 2.88e-06 [auto_monad_eliminator]: 1.992e-05 [cse]: 0.00017494 [a_3]: 8.04e-05 [py_interpret_to_execute_after_opt_a]: 0.00017016 [slice_cell_reuse_recomputed_activation]: 2.99001e-06 [rewriter_after_opt_a]: 0.00030804 [convert_after_rewriter]: 1.218e-05 [order_py_execute_after_rewriter]: 3.702e-05 [mutable_eliminate]: 0.00096687 [opt_b]: 0.00045288, [1] [Cycle 1]: 0.00044105, [7] [b_1]: 0.0002517 [b_2]: 1.47e-05 [updatestate_depend_eliminate]: 1.31e-05 [updatestate_assign_eliminate]: 5.45001e-06 [updatestate_loads_eliminate]: 5.29e-06 [renormalize]: 5.50004e-07 [cse]: 0.00010053 [optimize_parallel_all_gather_comm]: 2.802e-05 [overlap_param_gather]: 4.01001e-06 [cconv]: 4.101e-05 [loop_unroll]: 0.00070752 [opt_after_cconv]: 0.00030084, [1] [Cycle 1]: 0.00029179, [7] [c_1]: 6.476e-05 [parameter_eliminate]: 5.95002e-06 [updatestate_depend_eliminate]: 9.55001e-06 [updatestate_assign_eliminate]: 4.58001e-06 [updatestate_loads_eliminate]: 4.51002e-06 [cse]: 8.132e-05 [renormalize]: 3.50003e-07 [remove_dup_value]: 6.821e-05 [tuple_transform]: 0.00019964, [1] [Cycle 1]: 0.0001928, [4] [d_1]: 0.00012728 [none_parameter_eliminate]: 2.19001e-06 [renormalize]: 2.00002e-07 [switch_simplify]: 1.408e-05 [partial_unused_args_eliminate]: 2.56e-06 [add_recomputation]: 0.00019347 [cse_after_recomputation]: 0.00010126, [1] [Cycle 1]: 9.469e-05, [1] [cse]: 8.684e-05 [environ_conv]: 1.135e-05 [swap_dp_allreduce_reducescatter]: 7.77002e-06 [bias_add_comm_swap]: 3.81999e-06 [label_micro_interleaved_index]: 6.17999e-06 [label_fine_grained_interleaved_index]: 3.13e-06 [merge_cast_opt]: 1.42999e-06 [slice_recompute_activation]: 2.46998e-06 [micro_interleaved_order_control]: 2.67001e-06 [assign_add_opt]: 1.40001e-06 [ForceFp32Comm]: 9.09989e-07 [remove_cast_before_assign_add]: 1.19e-06 [full_micro_interleaved_order_control]: 2.36998e-06 [reorder_send_recv_between_fp_bp]: 3.04999e-06 [comm_op_add_attrs]: 1.07998e-06 [add_comm_op_reuse_tag]: 1.27e-06 [interleave_split_concat_branches]: 1.29e-06 [interleave_parallel_branches]: 2.746e-05 [overlap_opt_shard_in_pipeline]: 2.54001e-06 [overlap_opt_shard_grad_in_pipeline]: 2.09e-06 [control_data_broadcast_order]: 4.964e-05 [grouped_pairwise_exchange_alltoall]: 1.85001e-06 [offloading_packed_experts]: 3.432e-05 [overlap_recompute_and_grad_model_parallel]: 3.32e-05 [overlap_grad_matmul_and_grad_allreduce]: 1.35999e-06 [overlap_recompute_allgather_and_fa_grad]: 1.49998e-06 [overlap_recompute_comm]: 2.46e-06 [overlap_grad_ring_attention]: 5.978e-05 [overlap_grad_flash_sp]: 2.554e-05 [begin_end_overlap_inline]: 8.2e-07 [split_matmul_comm_elemetwise]: 2.02999e-06 [split_layernorm_comm]: 2.01e-06 [handle_group_info]: 9.79984e-07 [symbol_engine_optimizer]: 0.00064492, [1] [Cycle 1]: 0.00060753, [6] [build]: 0.00018169 [elim_shapecalc]: 0.00010268 [elim_not_effective]: 0.00011065 [opt_reshape]: 8.838e-05 [fold_const_symbol]: 2.604e-05 [renormalize]: 2.9002e-07 [detach_backward]: 3.75e-06 [pipeline_parallel_scheduler]: 1.70001e-06 [auto_monad_reorder]: 3.998e-05 [get_jit_bprop_graph]: 1.81e-06 [rewriter_after_jit_bprop_graph]: 9.57999e-06 [opt_after_jit_grad]: 0.00152638 [validate]: 0.00010396 Sums bootstrap : 0.001874s : 0.64% type_inference : 0.276982s : 94.31% event_method : 0.000020s : 0.01% auto_monad : 0.000067s : 0.02% graph_reusing : 0.000005s : 0.00% inline : 0.000003s : 0.00% add_attr.add_attr_with_inline.tag_attr : 0.000022s : 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 : 0.000065s : 0.02% insert-virtual-dataset : 0.000002s : 0.00% parallel-infer-symbol-second : 0.000001s : 0.00% dataset_repeat_opt : 0.000002s : 0.00% pipeline_split : 0.000002s : 0.00% optimize.py_interpret_to_execute : 0.000063s : 0.02% optimize.rewriter_before_opt_a : 0.000283s : 0.10% optimize.opt_a.expand_dump_flag : 0.000042s : 0.01% optimize.opt_a.switch_simplify : 0.000111s : 0.04% optimize.opt_a.loop_unroll : 0.000036s : 0.01% optimize.opt_a.a_1 : 0.002291s : 0.78% optimize.opt_a.with_stream_mark : 0.000063s : 0.02% optimize.opt_a.recompute_prepare : 0.000095s : 0.03% optimize.opt_a.updatestate_depend_eliminate : 0.000016s : 0.01% optimize.opt_a.updatestate_assign_eliminate : 0.000042s : 0.01% optimize.opt_a.updatestate_loads_eliminate : 0.000012s : 0.00% optimize.opt_a.parameter_eliminate : 0.000005s : 0.00% optimize.opt_a.a_2 : 0.000575s : 0.20% optimize.opt_a.accelerated_algorithm : 0.000062s : 0.02% optimize.opt_a.shard : 0.000007s : 0.00% optimize.opt_a.meta_shard_fg_expand : 0.000010s : 0.00% optimize.opt_a.shard_inline : 0.000025s : 0.01% optimize.opt_a.merge_send_recv : 0.000025s : 0.01% optimize.opt_a.auto_parallel : 0.000026s : 0.01% optimize.opt_a.parallel : 0.000045s : 0.02% optimize.opt_a.flash_sp : 0.000018s : 0.01% optimize.opt_a.merge_comm : 0.000012s : 0.00% optimize.opt_a.allreduce_fusion : 0.000010s : 0.00% optimize.opt_a.matmul_add_comm_reduction : 0.000028s : 0.01% optimize.opt_a.allreduce_slice_to_reducescatter : 0.000002s : 0.00% optimize.opt_a.virtual_shard_identity : 0.000063s : 0.02% optimize.opt_a.virtual_dataset : 0.000086s : 0.03% optimize.opt_a.get_grad_eliminate_ : 0.000059s : 0.02% optimize.opt_a.virtual_output : 0.000082s : 0.03% optimize.opt_a.merge_forward : 0.000015s : 0.01% optimize.opt_a.cell_reuse_recompute_pass : 0.000006s : 0.00% optimize.opt_a.offload_activation : 0.000030s : 0.01% optimize.opt_a.cell_reuse_handle_not_recompute_node_pass : 0.000087s : 0.03% optimize.opt_a.merge_recompute_call_nodes : 0.000004s : 0.00% optimize.opt_a.before_grad : 0.000148s : 0.05% optimize.opt_a.set_forward_comm_id_for_comm_node_pass : 0.000016s : 0.01% 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 : 0.000020s : 0.01% optimize.opt_a.after_resolve : 0.000116s : 0.04% optimize.opt_a.a_after_grad : 0.000109s : 0.04% optimize.opt_a.renormalize : 0.003307s : 1.13% optimize.opt_a.add_forward_monad_depend : 0.000017s : 0.01% optimize.opt_a.auto_monad_grad : 0.000006s : 0.00% optimize.opt_a.auto_monad_eliminator : 0.000081s : 0.03% optimize.opt_a.cse : 0.000368s : 0.13% optimize.opt_a.a_3 : 0.000263s : 0.09% optimize.py_interpret_to_execute_after_opt_a : 0.000170s : 0.06% optimize.slice_cell_reuse_recomputed_activation : 0.000003s : 0.00% optimize.rewriter_after_opt_a : 0.000308s : 0.10% optimize.convert_after_rewriter : 0.000012s : 0.00% optimize.order_py_execute_after_rewriter : 0.000037s : 0.01% optimize.mutable_eliminate : 0.000967s : 0.33% optimize.opt_b.b_1 : 0.000252s : 0.09% optimize.opt_b.b_2 : 0.000015s : 0.01% optimize.opt_b.updatestate_depend_eliminate : 0.000013s : 0.00% optimize.opt_b.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_b.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_b.renormalize : 0.000001s : 0.00% optimize.opt_b.cse : 0.000101s : 0.03% optimize.optimize_parallel_all_gather_comm : 0.000028s : 0.01% optimize.overlap_param_gather : 0.000004s : 0.00% optimize.cconv : 0.000041s : 0.01% optimize.loop_unroll : 0.000708s : 0.24% optimize.opt_after_cconv.c_1 : 0.000065s : 0.02% optimize.opt_after_cconv.parameter_eliminate : 0.000006s : 0.00% optimize.opt_after_cconv.updatestate_depend_eliminate : 0.000010s : 0.00% optimize.opt_after_cconv.updatestate_assign_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.updatestate_loads_eliminate : 0.000005s : 0.00% optimize.opt_after_cconv.cse : 0.000081s : 0.03% optimize.opt_after_cconv.renormalize : 0.000000s : 0.00% optimize.remove_dup_value : 0.000068s : 0.02% optimize.tuple_transform.d_1 : 0.000127s : 0.04% optimize.tuple_transform.none_parameter_eliminate : 0.000002s : 0.00% optimize.tuple_transform.renormalize : 0.000000s : 0.00% optimize.tuple_transform.switch_simplify : 0.000014s : 0.00% optimize.partial_unused_args_eliminate : 0.000003s : 0.00% optimize.add_recomputation : 0.000193s : 0.07% optimize.cse_after_recomputation.cse : 0.000087s : 0.03% optimize.environ_conv : 0.000011s : 0.00% optimize.swap_dp_allreduce_reducescatter : 0.000008s : 0.00% optimize.bias_add_comm_swap : 0.000004s : 0.00% optimize.label_micro_interleaved_index : 0.000006s : 0.00% optimize.label_fine_grained_interleaved_index : 0.000003s : 0.00% optimize.merge_cast_opt : 0.000001s : 0.00% optimize.slice_recompute_activation : 0.000002s : 0.00% optimize.micro_interleaved_order_control : 0.000003s : 0.00% optimize.assign_add_opt : 0.000001s : 0.00% optimize.ForceFp32Comm : 0.000001s : 0.00% optimize.remove_cast_before_assign_add : 0.000001s : 0.00% optimize.full_micro_interleaved_order_control : 0.000002s : 0.00% optimize.reorder_send_recv_between_fp_bp : 0.000003s : 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 : 0.000027s : 0.01% 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 : 0.000050s : 0.02% optimize.grouped_pairwise_exchange_alltoall : 0.000002s : 0.00% optimize.offloading_packed_experts : 0.000034s : 0.01% optimize.overlap_recompute_and_grad_model_parallel : 0.000033s : 0.01% optimize.overlap_grad_matmul_and_grad_allreduce : 0.000001s : 0.00% optimize.overlap_recompute_allgather_and_fa_grad : 0.000001s : 0.00% optimize.overlap_recompute_comm : 0.000002s : 0.00% optimize.overlap_grad_ring_attention : 0.000060s : 0.02% optimize.overlap_grad_flash_sp : 0.000026s : 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 : 0.000182s : 0.06% optimize.symbol_engine_optimizer.elim_shapecalc : 0.000103s : 0.03% optimize.symbol_engine_optimizer.elim_not_effective : 0.000111s : 0.04% optimize.symbol_engine_optimizer.opt_reshape : 0.000088s : 0.03% optimize.symbol_engine_optimizer.fold_const_symbol : 0.000026s : 0.01% optimize.symbol_engine_optimizer.renormalize : 0.000000s : 0.00% detach_backward : 0.000004s : 0.00% pipeline_parallel_scheduler : 0.000002s : 0.00% auto_monad_reorder : 0.000040s : 0.01% get_jit_bprop_graph : 0.000002s : 0.00% rewriter_after_jit_bprop_graph : 0.000010s : 0.00% opt_after_jit_grad : 0.001526s : 0.52% validate : 0.000104s : 0.04% Time group info: ------[substitution.] 0.000252 39 2.54% : 0.000006s : 2: substitution.elim_not_effective 4.05% : 0.000010s : 2: substitution.fold_const_symbol 3.84% : 0.000010s : 10: substitution.graph_param_transform 79.55% : 0.000201s : 1: substitution.inline 2.15% : 0.000005s : 4: substitution.j_node_and_user_rematch 2.90% : 0.000007s : 4: substitution.remove_not_recompute_node 4.97% : 0.000013s : 16: substitution.replace_old_param ------[type_inference.] 0.276723 2 93.31% : 0.258198s : 1: type_inference.infer 6.69% : 0.018525s : 1: type_inference.specialize ------[replace.] 0.000046 1 100.00% : 0.000046s : 1: replace.inline ------[match.] 0.000199 1 100.00% : 0.000199s : 1: match.inline ------[predicate.] 0.000302 2335 0.83% : 0.000003s : 21: predicate.accumulaten_eliminater 1.29% : 0.000004s : 10: predicate.ad_related_special_op_eliminate 0.66% : 0.000002s : 20: predicate.addn_check_dump 0.72% : 0.000002s : 21: predicate.addn_zero_filter 0.71% : 0.000002s : 21: predicate.adjust_all_reduce_mul_add 2.21% : 0.000007s : 41: predicate.arithmetic_simplify 0.79% : 0.000002s : 21: predicate.cast_eliminate 0.86% : 0.000003s : 20: predicate.check_bprop_eliminate 0.67% : 0.000002s : 20: predicate.compare_switch_simplify 0.27% : 0.000001s : 10: predicate.const_output_eliminate 0.94% : 0.000003s : 20: predicate.depend_value_elim 0.84% : 0.000003s : 21: predicate.dict_get_item_const_eliminator 1.11% : 0.000003s : 21: predicate.dict_get_item_eliminator 0.74% : 0.000002s : 21: predicate.dict_set_item_eliminator 1.70% : 0.000005s : 20: predicate.dumpgradient_eliminate 0.36% : 0.000001s : 10: predicate.elim_not_effective 0.62% : 0.000002s : 10: predicate.elim_shapecalc_of_broadcastargs 1.13% : 0.000003s : 31: predicate.environ_add_const_eliminate 1.31% : 0.000004s : 31: predicate.environ_get_add_eliminate 1.15% : 0.000003s : 31: predicate.environ_get_depend_swap 2.01% : 0.000006s : 51: predicate.environ_get_eliminate 1.03% : 0.000003s : 31: predicate.environ_get_set_eliminate 0.73% : 0.000002s : 22: predicate.exchange_switch_depend_value 1.55% : 0.000005s : 22: predicate.float_depend_g_call 0.71% : 0.000002s : 20: predicate.float_environ_get_switch 1.14% : 0.000003s : 30: predicate.float_tuple_getitem_switch 0.26% : 0.000001s : 10: predicate.fold_const_symbol 0.94% : 0.000003s : 20: predicate.get_grad_eliminate 0.31% : 0.000001s : 10: predicate.graph_param_transform 0.67% : 0.000002s : 20: predicate.incorporate_call 0.55% : 0.000002s : 20: predicate.incorporate_call_switch 5.27% : 0.000016s : 103: predicate.inline 1.33% : 0.000004s : 20: predicate.inline_without_move 0.50% : 0.000002s : 20: predicate.j_node_and_user_rematch 1.03% : 0.000003s : 20: predicate.less_batch_normalization 1.72% : 0.000005s : 41: predicate.list_to_tuple_eliminator_ 2.09% : 0.000006s : 62: predicate.load_eliminater 1.17% : 0.000004s : 10: predicate.loop_unroll_after_grad 1.20% : 0.000004s : 31: predicate.loop_unroll_before_grad 1.65% : 0.000005s : 41: predicate.make_slice_get_slice_eliminator 0.75% : 0.000002s : 20: predicate.merge_addn 0.68% : 0.000002s : 20: predicate.micro_step_allgather_replace 0.77% : 0.000002s : 20: predicate.mini_step_allgather_replace 0.67% : 0.000002s : 21: predicate.minmaximum_grad 1.14% : 0.000003s : 10: predicate.mutable_eliminate 0.56% : 0.000002s : 10: predicate.opt_reshape 0.44% : 0.000001s : 10: predicate.parallel_virtual_node 1.31% : 0.000004s : 22: predicate.partial_defer_inline 1.12% : 0.000003s : 31: predicate.partial_eliminate 0.86% : 0.000003s : 21: predicate.print_const_string_wrapper 0.81% : 0.000002s : 20: predicate.reduce_all_const_elim 1.19% : 0.000004s : 21: predicate.reduce_eliminate 2.03% : 0.000006s : 62: predicate.redundant_stop_gradient_eliminater 0.75% : 0.000002s : 20: predicate.remove_not_recompute_node 1.48% : 0.000004s : 41: predicate.replace_applicator 0.68% : 0.000002s : 20: predicate.replace_old_param 0.53% : 0.000002s : 10: predicate.reset_defer_inline 0.85% : 0.000003s : 21: predicate.reshape_eliminate 0.81% : 0.000002s : 20: predicate.row_tensor_add_zeros_like 0.42% : 0.000001s : 10: predicate.row_tensor_eliminate 1.22% : 0.000004s : 20: predicate.same_eliminate 0.57% : 0.000002s : 20: predicate.set_cell_output_no_recompute 1.30% : 0.000004s : 20: predicate.shard_identity_eliminate 0.92% : 0.000003s : 20: predicate.special_op_eliminate 1.03% : 0.000003s : 20: predicate.specialize_transform 1.26% : 0.000004s : 20: predicate.split_environ_get_set_with_tuple_value 1.21% : 0.000004s : 20: predicate.stack_unstack_eliminate 0.38% : 0.000001s : 10: predicate.switch_call_monad_eliminater 0.79% : 0.000002s : 22: predicate.switch_defer_inline 1.50% : 0.000005s : 42: predicate.switch_layer_defer_inline 3.94% : 0.000012s : 83: predicate.switch_simplify 0.80% : 0.000002s : 21: predicate.tile_eliminate 0.75% : 0.000002s : 21: predicate.transpose_eliminate 1.70% : 0.000005s : 41: predicate.tuple_list_convert_item_index_to_positive 1.54% : 0.000005s : 41: predicate.tuple_list_get_item_const_eliminator 1.48% : 0.000004s : 41: predicate.tuple_list_get_item_depend_reorder 3.38% : 0.000010s : 61: predicate.tuple_list_get_item_eliminator 1.47% : 0.000004s : 41: predicate.tuple_list_get_set_item_eliminator 2.51% : 0.000008s : 61: predicate.tuple_list_set_item_eliminator 1.59% : 0.000005s : 41: predicate.tuple_to_list_eliminator_ 2.05% : 0.000006s : 62: predicate.updatestate_pure_node_eliminater 2.93% : 0.000009s : 82: predicate.updatestate_useless_node_eliminater 0.41% : 0.000001s : 10: predicate.value_based_eliminate 0.94% : 0.000003s : 20: predicate.virtual_dataset_eliminate 0.85% : 0.000003s : 20: predicate.virtual_output_eliminate 0.37% : 0.000001s : 10: predicate.virtual_view_grad_eliminate 0.47% : 0.000001s : 10: predicate.zero_like_fill_zero ------[func_graph_cloner_run.] 0.018775 6 18.55% : 0.003483s : 3: func_graph_cloner_run.FuncGraphClonerGraph 81.45% : 0.015292s : 3: func_graph_cloner_run.FuncGraphSpecializer ------[meta_graph.] 0.000000 0 ------[manager.] 0.000000 0 ------[pynative] 0.000000 0 ------[others.] 0.843489 192 0.00% : 0.000004s : 1: ForceFp32Comm 30.92% : 0.260797s : 1: add_attr 30.92% : 0.260778s : 1: add_attr_with_inline 0.00% : 0.000004s : 1: add_comm_op_reuse_tag 0.02% : 0.000199s : 1: add_recomputation 0.00% : 0.000004s : 1: assign_add_opt 0.01% : 0.000072s : 1: auto_monad 0.01% : 0.000045s : 1: auto_monad_reorder 0.00% : 0.000004s : 1: begin_end_overlap_inline 0.00% : 0.000010s : 1: bias_add_comm_swap 0.23% : 0.001971s : 1: bootstrap 0.01% : 0.000045s : 1: cconv 0.00% : 0.000004s : 1: comm_op_add_attrs 0.01% : 0.000054s : 1: control_data_broadcast_order 0.00% : 0.000017s : 1: convert_after_rewriter 0.01% : 0.000105s : 1: cse_after_recomputation 0.00% : 0.000005s : 1: dataset_repeat_opt 0.00% : 0.000007s : 1: detach_backward 0.00% : 0.000016s : 1: environ_conv 0.00% : 0.000029s : 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% : 0.000005s : 1: grouped_pairwise_exchange_alltoall 0.00% : 0.000004s : 1: handle_group_info 0.00% : 0.000007s : 1: inline 0.00% : 0.000007s : 1: insert-virtual-dataset 0.00% : 0.000031s : 1: interleave_parallel_branches 0.00% : 0.000004s : 1: interleave_split_concat_branches 0.00% : 0.000007s : 1: label_fine_grained_interleaved_index 0.00% : 0.000039s : 1: label_micro_interleaved_index 0.09% : 0.000720s : 1: loop_unroll 0.00% : 0.000005s : 1: merge_cast_opt 0.00% : 0.000006s : 1: micro_interleaved_order_control 0.12% : 0.000981s : 1: mutable_eliminate 0.01% : 0.000061s : 1: offloading_packed_experts 0.00% : 0.000026s : 1: opt.transform.loop_unroll_optimizer 0.01% : 0.000057s : 1: opt.transform.mutable_eliminate 0.48% : 0.004047s : 78: opt.transform.opt_a 0.01% : 0.000063s : 1: opt.transform.opt_after_cconv 0.02% : 0.000153s : 1: opt.transform.opt_after_jit_grad 0.03% : 0.000230s : 28: opt.transform.opt_b 0.02% : 0.000138s : 2: opt.transform.opt_trans_graph 0.04% : 0.000321s : 4: opt.transform.symbol_engine_opt 1.31% : 0.011087s : 1: opt_a 0.04% : 0.000304s : 1: opt_after_cconv 0.18% : 0.001546s : 1: opt_after_jit_grad 0.05% : 0.000458s : 1: opt_b 1.95% : 0.016420s : 1: optimize 0.00% : 0.000033s : 1: optimize_parallel_all_gather_comm 0.00% : 0.000041s : 1: order_py_execute_after_rewriter 0.00% : 0.000029s : 1: overlap_grad_flash_sp 0.00% : 0.000004s : 1: overlap_grad_matmul_and_grad_allreduce 0.01% : 0.000064s : 1: overlap_grad_ring_attention 0.00% : 0.000031s : 1: overlap_opt_shard_grad_in_pipeline 0.00% : 0.000006s : 1: overlap_opt_shard_in_pipeline 0.00% : 0.000007s : 1: overlap_param_gather 0.00% : 0.000004s : 1: overlap_recompute_allgather_and_fa_grad 0.00% : 0.000038s : 1: overlap_recompute_and_grad_model_parallel 0.00% : 0.000005s : 1: overlap_recompute_comm 0.00% : 0.000008s : 1: parallel-infer-symbol 0.00% : 0.000004s : 1: parallel-infer-symbol-second 0.00% : 0.000006s : 1: partial_unused_args_eliminate 0.00% : 0.000034s : 1: pipeline_parallel_scheduler 0.00% : 0.000004s : 1: pipeline_split 0.01% : 0.000070s : 1: pre_auto_parallel 0.01% : 0.000068s : 1: py_interpret_to_execute 0.02% : 0.000178s : 1: py_interpret_to_execute_after_opt_a 0.00% : 0.000004s : 1: remove_cast_before_assign_add 0.01% : 0.000073s : 1: remove_dup_value 0.10% : 0.000826s : 1: renormalize.infer 0.29% : 0.002438s : 1: renormalize.specialize 0.00% : 0.000032s : 1: reorder_send_recv_between_fp_bp 0.00% : 0.000013s : 1: rewriter_after_jit_bprop_graph 0.04% : 0.000339s : 1: rewriter_after_opt_a 0.03% : 0.000289s : 1: rewriter_before_opt_a 0.00% : 0.000007s : 1: slice_cell_reuse_recomputed_activation 0.00% : 0.000005s : 1: slice_recompute_activation 0.00% : 0.000005s : 1: split_layernorm_comm 0.00% : 0.000030s : 1: split_matmul_comm_elemetwise 0.00% : 0.000011s : 1: swap_dp_allreduce_reducescatter 0.08% : 0.000649s : 1: symbol_engine_optimizer 0.02% : 0.000203s : 1: tuple_transform 32.84% : 0.277013s : 1: type_inference . [hook] pytest_runtest_teardown:test_paged_attention_quant_pertoken_bsh[QuantMethod.INT_CUBE-1] tests/st/infer/ops/test_internal_ops/test_paged_attention.py::test_paged_attention_quant_pertoken_bsh[QuantMethod.INT_CUBE-1],max_mem:454.0M =============================== 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 132.40s (0:02:12) ==================